Authors: Luca Beurer-Kellner, Marc Fischer, Martin Vechev
Abstract: To ensure that text generated by large language models (LLMs) is in an expected format, constrained decoding proposes to enforce strict formal language constraints during generation. However, as we show in this work, not only do such methods incur performance overhead during generation, but many of them also significantly impair task accuracy, if they do not correctly align the underlying LLM sub-word vocabularies with external constraints. To address this, we present a novel decoding algorithm, DOMINO, that can enforce constraints in a fully subword-aligned fashion, while leveraging pre-computation and speculative decoding to achieve virtually no overhead and in some cases even almost 2$\times$ speedup over unconstrained decoding -- thereby outperforming existing approaches by a wide margin.
Authors: Ziwen Wang, Jin Wee Lee, Tanujit Chakraborty, Yilin Ning, Mingxuan Liu, Feng Xie, Marcus Eng Hock Ong, Nan Liu
Abstract: Survival analysis is essential for studying time-to-event outcomes and providing a dynamic understanding of the probability of an event occurring over time. Various survival analysis techniques, from traditional statistical models to state-of-the-art machine learning algorithms, support healthcare intervention and policy decisions. However, there remains ongoing discussion about their comparative performance. We conducted a comparative study of several survival analysis methods, including Cox proportional hazards (CoxPH), stepwise CoxPH, elastic net penalized Cox model, Random Survival Forests (RSF), Gradient Boosting machine (GBM) learning, AutoScore-Survival, DeepSurv, time-dependent Cox model based on neural network (CoxTime), and DeepHit survival neural network. We applied the concordance index (C-index) for model goodness-of-fit, and integral Brier scores (IBS) for calibration, and considered the model interpretability. As a case study, we performed a retrospective analysis of patients admitted through the emergency department of a tertiary hospital from 2017 to 2019, predicting 90-day all-cause mortality based on patient demographics, clinicopathological features, and historical data. The results of the C-index indicate that deep learning achieved comparable performance, with DeepSurv producing the best discrimination (DeepSurv: 0.893; CoxTime: 0.892; DeepHit: 0.891). The calibration of DeepSurv (IBS: 0.041) performed the best, followed by RSF (IBS: 0.042) and GBM (IBS: 0.0421), all using the full variables. Moreover, AutoScore-Survival, using a minimal variable subset, is easy to interpret, and can achieve good discrimination and calibration (C-index: 0.867; IBS: 0.044). While all models were satisfactory, DeepSurv exhibited the best discrimination and calibration. In addition, AutoScore-Survival offers a more parsimonious model and excellent interpretability.
Authors: Pierre Boyeau, Anastasios N. Angelopoulos, Nir Yosef, Jitendra Malik, Michael I. Jordan
Abstract: The evaluation of machine learning models using human-labeled validation data can be expensive and time-consuming. AI-labeled synthetic data can be used to decrease the number of human annotations required for this purpose in a process called autoevaluation. We suggest efficient and statistically principled algorithms for this purpose that improve sample efficiency while remaining unbiased. These algorithms increase the effective human-labeled sample size by up to 50% on experiments with GPT-4.
Authors: DengYu Shi
Abstract: With the widespread adoption of Non-Intrusive Load Monitoring (NILM) in building energy management, ensuring the high quality of NILM data has become imperative. However, practical applications of NILM face challenges associated with data loss, significantly impacting accuracy and reliability in energy management. This paper addresses the issue of NILM data loss by introducing an innovative tensor completion(TC) model- Proportional-Integral-Derivative (PID)-incorporated Non-negative Latent Factorization of Tensors (PNLFT) with twofold ideas: 1) To tackle the issue of slow convergence in Latent Factorization of Tensors (LFT) using Stochastic Gradient Descent (SGD), a Proportional-Integral-Derivative controller is introduced during the learning process. The PID controller utilizes historical and current information to control learning residuals. 2) Considering the characteristics of NILM data, non-negative update rules are proposed in the model's learning scheme. Experimental results on three datasets demonstrate that, compared to state-of-the-art models, the proposed model exhibits noteworthy enhancements in both convergence speed and accuracy.
Authors: Rudy Semola, Julio Hurtado, Vincenzo Lomonaco, Davide Bacciu
Abstract: Hyperparameter selection in continual learning scenarios is a challenging and underexplored aspect, especially in practical non-stationary environments. Traditional approaches, such as grid searches with held-out validation data from all tasks, are unrealistic for building accurate lifelong learning systems. This paper aims to explore the role of hyperparameter selection in continual learning and the necessity of continually and automatically tuning them according to the complexity of the task at hand. Hence, we propose leveraging the nature of sequence task learning to improve Hyperparameter Optimization efficiency. By using the functional analysis of variance-based techniques, we identify the most crucial hyperparameters that have an impact on performance. We demonstrate empirically that this approach, agnostic to continual scenarios and strategies, allows us to speed up hyperparameters optimization continually across tasks and exhibit robustness even in the face of varying sequential task orders. We believe that our findings can contribute to the advancement of continual learning methodologies towards more efficient, robust and adaptable models for real-world applications.
Authors: Liyue Chen, Jiangyi Fang, Tengfei Liu, Shaosheng Cao, Leye Wang
Abstract: Spatio-Temporal (ST) prediction is crucial for making informed decisions in urban location-based applications like ride-sharing. However, existing ST models often require region partition as a prerequisite, resulting in two main pitfalls. Firstly, location-based services necessitate ad-hoc regions for various purposes, requiring multiple ST models with varying scales and zones, which can be costly to support. Secondly, different ST models may produce conflicting outputs, resulting in confusing predictions. In this paper, we propose One4All-ST, a framework that can conduct ST prediction for arbitrary modifiable areal units using only one model. To reduce the cost of getting multi-scale predictions, we design an ST network with hierarchical spatial modeling and scale normalization modules to efficiently and equally learn multi-scale representations. To address prediction inconsistencies across scales, we propose a dynamic programming scheme to solve the formulated optimal combination problem, minimizing predicted error through theoretical analysis. Besides, we suggest using an extended quad-tree to index the optimal combinations for quick response to arbitrary modifiable areal units in practical online scenarios. Extensive experiments on two real-world datasets verify the efficiency and effectiveness of One4All-ST in ST prediction for arbitrary modifiable areal units. The source codes and data of this work are available at https://github.com/uctb/One4All-ST.
Authors: Nhat Thanh Tran, Jack Xin, Guofa Zhou
Abstract: Dengue fever is one of the most deadly mosquito-born tropical infectious diseases. Detailed long range forecast model is vital in controlling the spread of disease and making mitigation efforts. In this study, we examine methods used to forecast dengue cases for long range predictions. The dataset consists of local climate/weather in addition to global climate indicators of Singapore from 2000 to 2019. We utilize newly developed deep neural networks to learn the intricate relationship between the features. The baseline models in this study are in the class of recent transformers for long sequence forecasting tasks. We found that a Fourier mixed window attention (FWin) based transformer performed the best in terms of both the mean square error and the maximum absolute error on the long range dengue forecast up to 60 weeks.
Authors: Runze Guo, Feng Xue, Anlong Ming, Nicu Sebe
Abstract: Recently, neural networks (NN) have made great strides in combinatorial optimization. However, they face challenges when solving the capacitated arc routing problem (CARP) which is to find the minimum-cost tour covering all required edges on a graph, while within capacity constraints. In tackling CARP, NN-based approaches tend to lag behind advanced metaheuristics, since they lack directed arc modeling and efficient learning methods tailored for complex CARP. In this paper, we introduce an NN-based solver to significantly narrow the gap with advanced metaheuristics while exhibiting superior efficiency. First, we propose the direction-aware attention model (DaAM) to incorporate directionality into the embedding process, facilitating more effective one-stage decision-making. Second, we design a supervised reinforcement learning scheme that involves supervised pre-training to establish a robust initial policy for subsequent reinforcement fine-tuning. It proves particularly valuable for solving CARP that has a higher complexity than the node routing problems (NRPs). Finally, a path optimization method is proposed to adjust the depot return positions within the path generated by DaAM. Experiments illustrate that our approach surpasses heuristics and achieves decision quality comparable to state-of-the-art metaheuristics for the first time while maintaining superior efficiency.
Authors: Zihao Tang, Zheqi Lv, Shengyu Zhang, Yifan Zhou, Xinyu Duan, Fei Wu, Kun Kuang
Abstract: Due to privacy or patent concerns, a growing number of large models are released without granting access to their training data, making transferring their knowledge inefficient and problematic. In response, Data-Free Knowledge Distillation (DFKD) methods have emerged as direct solutions. However, simply adopting models derived from DFKD for real-world applications suffers significant performance degradation, due to the discrepancy between teachers' training data and real-world scenarios (student domain). The degradation stems from the portions of teachers' knowledge that are not applicable to the student domain. They are specific to the teacher domain and would undermine students' performance. Hence, selectively transferring teachers' appropriate knowledge becomes the primary challenge in DFKD. In this work, we propose a simple but effective method AuG-KD. It utilizes an uncertainty-guided and sample-specific anchor to align student-domain data with the teacher domain and leverages a generative method to progressively trade off the learning process between OOD knowledge distillation and domain-specific information learning via mixup learning. Extensive experiments in 3 datasets and 8 settings demonstrate the stability and superiority of our approach. Code available at https://github.com/IshiKura-a/AuG-KD .
Authors: Zeyang Jia, Kosuke Imai, Michael Lingzhi Li
Abstract: We introduce the "cram" method, a general and efficient approach to simultaneous learning and evaluation using a generic machine learning (ML) algorithm. In a single pass of batched data, the proposed method repeatedly trains an ML algorithm and tests its empirical performance. Because it utilizes the entire sample for both learning and evaluation, cramming is significantly more data-efficient than sample-splitting. The cram method also naturally accommodates online learning algorithms, making its implementation computationally efficient. To demonstrate the power of the cram method, we consider the standard policy learning setting where cramming is applied to the same data to both develop an individualized treatment rule (ITR) and estimate the average outcome that would result if the learned ITR were to be deployed. We show that under a minimal set of assumptions, the resulting crammed evaluation estimator is consistent and asymptotically normal. While our asymptotic results require a relatively weak stabilization condition of ML algorithm, we develop a simple, generic method that can be used with any policy learning algorithm to satisfy this condition. Our extensive simulation studies show that, when compared to sample-splitting, cramming reduces the evaluation standard error by more than 40% while improving the performance of learned policy. We also apply the cram method to a randomized clinical trial to demonstrate its applicability to real-world problems. Finally, we briefly discuss future extensions of the cram method to other learning and evaluation settings.
Authors: Qian Chen, Xingjian Dong, Zhike Peng
Abstract: Neural networks, with powerful nonlinear mapping and classification capabilities, are widely applied in mechanical fault diagnosis to ensure safety. However, being typical black-box models, their application is limited in high-reliability-required scenarios. To understand the classification logic and explain what typical fault signals look like, the prototype matching network (PMN) is proposed by combining the human-inherent prototype-matching with autoencoder (AE). The PMN matches AE-extracted feature with each prototype and selects the most similar prototype as the prediction result. It has three interpreting paths on classification logic, fault prototypes, and matching contributions. Conventional diagnosis and domain generalization experiments demonstrate its competitive diagnostic performance and distinguished advantages in representation learning. Besides, the learned typical fault signals (i.e., sample-level prototypes) showcase the ability for denoising and extracting subtle key features that experts find challenging to capture. This ability broadens human understanding and provides a promising solution from interpretability research to AI-for-Science.
Authors: Hasanul Mahmud, Peng Kang, Kevin Desai, Palden Lama, Sushil Prasad
Abstract: Reducing inference time and energy usage while maintaining prediction accuracy has become a significant concern for deep neural networks (DNN) inference on resource-constrained edge devices. To address this problem, we propose a novel approach based on "converting" autoencoder and lightweight DNNs. This improves upon recent work such as early-exiting framework and DNN partitioning. Early-exiting frameworks spend different amounts of computation power for different input data depending upon their complexity. However, they can be inefficient in real-world scenarios that deal with many hard image samples. On the other hand, DNN partitioning algorithms that utilize the computation power of both the cloud and edge devices can be affected by network delays and intermittent connections between the cloud and the edge. We present CBNet, a low-latency and energy-efficient DNN inference framework tailored for edge devices. It utilizes a "converting" autoencoder to efficiently transform hard images into easy ones, which are subsequently processed by a lightweight DNN for inference. To the best of our knowledge, such autoencoder has not been proposed earlier. Our experimental results using three popular image-classification datasets on a Raspberry Pi 4, a Google Cloud instance, and an instance with Nvidia Tesla K80 GPU show that CBNet achieves up to 4.8x speedup in inference latency and 79% reduction in energy usage compared to competing techniques while maintaining similar or higher accuracy.
Authors: Annamaria Defilippo, Pierangelo Veltri, Pietro Lio', Pietro Hiram Guzzi
Abstract: Patient triage plays a crucial role in emergency departments, ensuring timely and appropriate care based on correctly evaluating the emergency grade of patient conditions. Triage methods are generally performed by human operator based on her own experience and information that are gathered from the patient management process. Thus, it is a process that can generate errors in emergency level associations. Recently, Traditional triage methods heavily rely on human decisions, which can be subjective and prone to errors. Recently, a growing interest has been focused on leveraging artificial intelligence (AI) to develop algorithms able to maximize information gathering and minimize errors in patient triage processing. We define and implement an AI based module to manage patients emergency code assignments in emergency departments. It uses emergency department historical data to train the medical decision process. Data containing relevant patient information, such as vital signs, symptoms, and medical history, are used to accurately classify patients into triage categories. Experimental results demonstrate that the proposed algorithm achieved high accuracy outperforming traditional triage methods. By using the proposed method we claim that healthcare professionals can predict severity index to guide patient management processing and resource allocation.
Authors: Xiangguo Sun, Hong Cheng, Jia Li, Bo Liu, Jihong Guan
Abstract: This paper is an extended abstract of our original work published in KDD23, where we won the best research paper award (Xiangguo Sun, Hong Cheng, Jia Li, Bo Liu, and Jihong Guan. All in one: Multi-task prompting for graph neural networks. KDD 23) The paper introduces a novel approach to bridging the gap between pre-trained graph models and the diverse tasks they're applied to, inspired by the success of prompt learning in NLP. Recognizing the challenge of aligning pre-trained models with varied graph tasks (node level, edge level, and graph level), which can lead to negative transfer and poor performance, we propose a multi-task prompting method for graphs. This method involves unifying graph and language prompt formats, enabling NLP's prompting strategies to be adapted for graph tasks. By analyzing the task space of graph applications, we reformulate problems to fit graph-level tasks and apply meta-learning to improve prompt initialization for multiple tasks. Experiments show our method's effectiveness in enhancing model performance across different graph tasks. Beyond the original work, in this extended abstract, we further discuss the graph prompt from a bigger picture and provide some of the latest work toward this area.
Authors: Minsu Kim, Sanghyeok Choi, Jiwoo Son, Hyeonah Kim, Jinkyoo Park, Yoshua Bengio
Abstract: This paper introduces the Generative Flow Ant Colony Sampler (GFACS), a novel neural-guided meta-heuristic algorithm for combinatorial optimization. GFACS integrates generative flow networks (GFlowNets) with the ant colony optimization (ACO) methodology. GFlowNets, a generative model that learns a constructive policy in combinatorial spaces, enhance ACO by providing an informed prior distribution of decision variables conditioned on input graph instances. Furthermore, we introduce a novel combination of training tricks, including search-guided local exploration, energy normalization, and energy shaping to improve GFACS. Our experimental results demonstrate that GFACS outperforms baseline ACO algorithms in seven CO tasks and is competitive with problem-specific heuristics for vehicle routing problems. The source code is available at \url{https://github.com/ai4co/gfacs}.
Authors: Kurt Butler, Guanchao Feng, Petar M. Djuric
Abstract: The field of explainable artificial intelligence (XAI) attempts to develop methods that provide insight into how complicated machine learning methods make predictions. Many methods of explanation have focused on the concept of feature attribution, a decomposition of the model's prediction into individual contributions corresponding to each input feature. In this work, we explore the problem of feature attribution in the context of Gaussian process regression (GPR). We take a principled approach to defining attributions under model uncertainty, extending the existing literature. We show that although GPR is a highly flexible and non-parametric approach, we can derive interpretable, closed-form expressions for the feature attributions. When using integrated gradients as an attribution method, we show that the attributions of a GPR model also follow a Gaussian process distribution, which quantifies the uncertainty in attribution arising from uncertainty in the model. We demonstrate, both through theory and experimentation, the versatility and robustness of this approach. We also show that, when applicable, the exact expressions for GPR attributions are both more accurate and less computationally expensive than the approximations currently used in practice. The source code for this project is freely available under MIT license at https://github.com/KurtButler/2024_attributions_paper.
URLs: https://github.com/KurtButler/2024_attributions_paper.
Authors: Fuseinin Mumuni, Alhassan Mumuni
Abstract: We review current and emerging knowledge-informed and brain-inspired cognitive systems for realizing adversarial defenses, eXplainable Artificial Intelligence (XAI), and zero-shot or few-short learning. Data-driven deep learning models have achieved remarkable performance and demonstrated capabilities surpassing human experts in many applications. Yet, their inability to exploit domain knowledge leads to serious performance limitations in practical applications. In particular, deep learning systems are exposed to adversarial attacks, which can trick them into making glaringly incorrect decisions. Moreover, complex data-driven models typically lack interpretability or explainability, i.e., their decisions cannot be understood by human subjects. Furthermore, models are usually trained on standard datasets with a closed-world assumption. Hence, they struggle to generalize to unseen cases during inference in practical open-world environments, thus, raising the zero- or few-shot generalization problem. Although many conventional solutions exist, explicit domain knowledge, brain-inspired neural network and cognitive architectures offer powerful new dimensions towards alleviating these problems. Prior knowledge is represented in appropriate forms and incorporated in deep learning frameworks to improve performance. Brain-inspired cognition methods use computational models that mimic the human mind to enhance intelligent behavior in artificial agents and autonomous robots. Ultimately, these models achieve better explainability, higher adversarial robustness and data-efficient learning, and can, in turn, provide insights for cognitive science and neuroscience-that is, to deepen human understanding on how the brain works in general, and how it handles these problems.
Authors: Xiang Meng, Wenyu Chen, Riade Benbaki, Rahul Mazumder
Abstract: The increasing computational demands of modern neural networks present deployment challenges on resource-constrained devices. Network pruning offers a solution to reduce model size and computational cost while maintaining performance. However, most current pruning methods focus primarily on improving sparsity by reducing the number of nonzero parameters, often neglecting other deployment costs such as inference time, which are closely related to the number of floating-point operations (FLOPs). In this paper, we propose FALCON, a novel combinatorial-optimization-based framework for network pruning that jointly takes into account model accuracy (fidelity), FLOPs, and sparsity constraints. A main building block of our approach is an integer linear program (ILP) that simultaneously handles FLOP and sparsity constraints. We present a novel algorithm to approximately solve the ILP. We propose a novel first-order method for our optimization framework which makes use of our ILP solver. Using problem structure (e.g., the low-rank structure of approx. Hessian), we can address instances with millions of parameters. Our experiments demonstrate that FALCON achieves superior accuracy compared to other pruning approaches within a fixed FLOP budget. For instance, for ResNet50 with 20% of the total FLOPs retained, our approach improves the accuracy by 48% relative to state-of-the-art. Furthermore, in gradual pruning settings with re-training between pruning steps, our framework outperforms existing pruning methods, emphasizing the significance of incorporating both FLOP and sparsity constraints for effective network pruning.
Authors: Stefan Balauca, Mark Niklas M\"uller, Yuhao Mao, Maximilian Baader, Marc Fischer, Martin Vechev
Abstract: Training neural networks with high certified accuracy against adversarial examples remains an open problem despite significant efforts. While certification methods can effectively leverage tight convex relaxations for bound computation, in training, these methods perform worse than looser relaxations. Prior work hypothesized that this is caused by the discontinuity and perturbation sensitivity of the loss surface induced by these tighter relaxations. In this work, we show theoretically that Gaussian Loss Smoothing can alleviate both of these issues. We confirm this empirically by proposing a certified training method combining PGPE, an algorithm computing gradients of a smoothed loss, with different convex relaxations. When using this training method, we observe that tighter bounds indeed lead to strictly better networks that can outperform state-of-the-art methods on the same network. While scaling PGPE-based training remains challenging due to high computational cost, our results clearly demonstrate the promise of Gaussian Loss Smoothing for training certifiably robust neural networks.
Authors: Aozhong Zhang, Zi Yang, Naigang Wang, Yingyong Qin, Jack Xin, Xin Li, Penghang Yin
Abstract: Post-training quantization (PTQ) has emerged as a practical approach to compress large neural networks, making them highly efficient for deployment. However, effectively reducing these models to their low-bit counterparts without compromising the original accuracy remains a key challenge. In this paper, we propose an innovative PTQ algorithm termed COMQ, which sequentially conducts coordinate-wise minimization of the layer-wise reconstruction errors. We consider the widely used integer quantization, where every quantized weight can be decomposed into a shared floating-point scalar and an integer bit-code. Within a fixed layer, COMQ treats all the scaling factor(s) and bit-codes as the variables of the reconstruction error. Every iteration improves this error along a single coordinate while keeping all other variables constant. COMQ is easy to use and requires no hyper-parameter tuning. It instead involves only dot products and rounding operations. We update these variables in a carefully designed greedy order, significantly enhancing the accuracy. COMQ achieves remarkable results in quantizing 4-bit Vision Transformers, with a negligible loss of less than 1% in Top-1 accuracy. In 4-bit INT quantization of convolutional neural networks, COMQ maintains near-lossless accuracy with a minimal drop of merely 0.3% in Top-1 accuracy.
Authors: David Cheikhi, Daniel Russo
Abstract: Identifying the trade-offs between model-based and model-free methods is a central question in reinforcement learning. Value-based methods offer substantial computational advantages and are sometimes just as statistically efficient as model-based methods. However, focusing on the core problem of policy evaluation, we show information about the transition dynamics may be impossible to represent in the space of value functions. We explore this through a series of case studies focused on structures that arises in many important problems. In several, there is no information loss and value-based methods are as statistically efficient as model based ones. In other closely-related examples, information loss is severe and value-based methods are severely outperformed. A deeper investigation points to the limitations of the representational power as the driver of the inefficiency, as opposed to failure in algorithm design.
Authors: Bishwamittra Ghosh, Debabrota Basu, Fu Huazhu, Wang Yuan, Renuga Kanagavelu, Jiang Jin Peng, Liu Yong, Goh Siow Mong Rick, Wei Qingsong
Abstract: Federated Learning (FL) is a collaborative machine learning (ML) approach, where multiple clients participate in training an ML model without exposing the private data. Fair and accurate assessment of client contributions is an important problem in FL to facilitate incentive allocation and encouraging diverse clients to participate in a unified model training. Existing methods for assessing client contribution adopts co-operative game-theoretic concepts, such as Shapley values, but under simplified assumptions. In this paper, we propose a history-aware game-theoretic framework, called FLContrib, to assess client contributions when a subset of (potentially non-i.i.d.) clients participate in each epoch of FL training. By exploiting the FL training process and linearity of Shapley value, we develop FLContrib that yields a historical timeline of client contributions as FL training progresses over epochs. Additionally, to assess client contribution under limited computational budget, we propose a scheduling procedure that considers a two-sided fairness criteria to perform expensive Shapley value computation only in a subset of training epochs. In experiments, we demonstrate a controlled trade-off between the correctness and efficiency of client contributions assessed via FLContrib. To demonstrate the benefits of history-aware client contributions, we apply FLContrib to detect dishonest clients conducting data poisoning in FL training.
Authors: Huaisheng Zhu, Teng Xiao, Vasant G Honavar
Abstract: Generating molecules with desired properties is a critical task with broad applications in drug discovery and materials design. Inspired by recent advances in large language models, there is a growing interest in using natural language descriptions of molecules to generate molecules with the desired properties. Most existing methods focus on generating molecules that precisely match the text description. However, practical applications call for methods that generate diverse, and ideally novel, molecules with the desired properties. We propose 3M-Diffusion, a novel multi-modal molecular graph generation method, to address this challenge. 3M-Diffusion first encodes molecular graphs into a graph latent space aligned with text descriptions. It then reconstructs the molecular structure and atomic attributes based on the given text descriptions using the molecule decoder. It then learns a probabilistic mapping from the text space to the latent molecular graph space using a diffusion model. The results of our extensive experiments on several datasets demonstrate that 3M-Diffusion can generate high-quality, novel and diverse molecular graphs that semantically match the textual description provided.
Authors: Fangxin Wang, Yuqing Liu, Kay Liu, Yibo Wang, Sourav Medya, Philip S. Yu
Abstract: Graph Neural Networks (GNNs) have been extensively used in various real-world applications. However, the predictive uncertainty of GNNs stemming from diverse sources such as inherent randomness in data and model training errors can lead to unstable and erroneous predictions. Therefore, identifying, quantifying, and utilizing uncertainty are essential to enhance the performance of the model for the downstream tasks as well as the reliability of the GNN predictions. This survey aims to provide a comprehensive overview of the GNNs from the perspective of uncertainty with an emphasis on its integration in graph learning. We compare and summarize existing graph uncertainty theory and methods, alongside the corresponding downstream tasks. Thereby, we bridge the gap between theory and practice, meanwhile connecting different GNN communities. Moreover, our work provides valuable insights into promising directions in this field.
Authors: Junhong Shen, Tanya Marwah, Ameet Talwalkar
Abstract: We introduce UPS (Unified PDE Solver), an effective and data-efficient approach to solve diverse spatiotemporal PDEs defined over various domains, dimensions, and resolutions. UPS unifies different PDEs into a consistent representation space and processes diverse collections of PDE data using a unified network architecture that combines LLMs with domain-specific neural operators. We train the network via a two-stage cross-modal adaptation process, leveraging ideas of modality alignment and multi-task learning. By adapting from pretrained LLMs and exploiting text-form meta information, we are able to use considerably fewer training samples than previous methods while obtaining strong empirical results. UPS outperforms existing baselines, often by a large margin, on a wide range of 1D and 2D datasets in PDEBench, achieving state-of-the-art results on 8 of 10 tasks considered. Meanwhile, it is capable of few-shot transfer to different PDE families, coefficients, and resolutions.
Authors: Yufeng Zhang, Liyu Chen, Boyi Liu, Yingxiang Yang, Qiwen Cui, Yunzhe Tao, Hongxia Yang
Abstract: Recent advances in reinforcement learning (RL) algorithms aim to enhance the performance of language models at scale. Yet, there is a noticeable absence of a cost-effective and standardized testbed tailored to evaluating and comparing these algorithms. To bridge this gap, we present a generalized version of the 24-Puzzle: the $(N,K)$-Puzzle, which challenges language models to reach a target value $K$ with $N$ integers. We evaluate the effectiveness of established RL algorithms such as Proximal Policy Optimization (PPO), alongside novel approaches like Identity Policy Optimization (IPO) and Direct Policy Optimization (DPO).
Authors: Brandon Silva, Miguel Contreras, Sabyasachi Bandyopadhyay, Yuanfang Ren, Ziyuan Guan, Jeremy Balch, Kia Khezeli, Tezcan Ozrazgat Baslanti, Ben Shickel, Azra Bihorac, Parisa Rashidi
Abstract: Assessing acute brain dysfunction (ABD), including delirium and coma in the intensive care unit (ICU), is a critical challenge due to its prevalence and severe implications for patient outcomes. Current diagnostic methods rely on infrequent clinical observations, which can only determine a patient's ABD status after onset. Our research attempts to solve these problems by harnessing Electronic Health Records (EHR) data to develop automated methods for ABD prediction for patients in the ICU. Existing models solely predict a single state (e.g., either delirium or coma), require at least 24 hours of observation data to make predictions, do not dynamically predict fluctuating ABD conditions during ICU stay (typically a one-time prediction), and use small sample size, proprietary single-hospital datasets. Our research fills these gaps in the existing literature by dynamically predicting delirium, coma, and mortality for 12-hour intervals throughout an ICU stay and validating on two public datasets. Our research also introduces the concept of dynamically predicting critical transitions from non-ABD to ABD and between different ABD states in real time, which could be clinically more informative for the hospital staff. We compared the predictive performance of two state-of-the-art neural network models, the MAMBA selective state space model and the Longformer Transformer model. Using the MAMBA model, we achieved a mean area under the receiving operator characteristic curve (AUROC) of 0.95 on outcome prediction of ABD for 12-hour intervals. The model achieves a mean AUROC of 0.79 when predicting transitions between ABD states. Our study uses a curated dataset from the University of Florida Health Shands Hospital for internal validation and two publicly available datasets, MIMIC-IV and eICU, for external validation, demonstrating robustness across ICU stays from 203 hospitals and 140,945 patients.
Authors: Yu Xia, Fang Kong, Tong Yu, Liya Guo, Ryan A. Rossi, Sungchul Kim, Shuai Li
Abstract: Web-based applications such as chatbots, search engines and news recommendations continue to grow in scale and complexity with the recent surge in the adoption of LLMs. Online model selection has thus garnered increasing attention due to the need to choose the best model among a diverse set while balancing task reward and exploration cost. Organizations faces decisions like whether to employ a costly API-based LLM or a locally finetuned small LLM, weighing cost against performance. Traditional selection methods often evaluate every candidate model before choosing one, which are becoming impractical given the rising costs of training and finetuning LLMs. Moreover, it is undesirable to allocate excessive resources towards exploring poor-performing models. While some recent works leverage online bandit algorithm to manage such exploration-exploitation trade-off in model selection, they tend to overlook the increasing-then-converging trend in model performances as the model is iteratively finetuned, leading to less accurate predictions and suboptimal model selections. In this paper, we propose a time-increasing bandit algorithm TI-UCB, which effectively predicts the increase of model performances due to finetuning and efficiently balances exploration and exploitation in model selection. To further capture the converging points of models, we develop a change detection mechanism by comparing consecutive increase predictions. We theoretically prove that our algorithm achieves a logarithmic regret upper bound in a typical increasing bandit setting, which implies a fast convergence rate. The advantage of our method is also empirically validated through extensive experiments on classification model selection and online selection of LLMs. Our results highlight the importance of utilizing increasing-then-converging pattern for more efficient and economic model selection in the deployment of LLMs.
Authors: Zhanpeng Zeng, Michael Davies, Pranav Pulijala, Karthikeyan Sankaralingam, Vikas Singh
Abstract: While GPU clusters are the de facto choice for training large deep neural network (DNN) models today, several reasons including ease of workflow, security and cost have led to efforts investigating whether CPUs may be viable for inference in routine use in many sectors of the industry. But the imbalance between the compute capabilities of GPUs and CPUs is huge. Motivated by these considerations, we study a module which is a workhorse within modern DNN architectures, GEMM based Feed Forward Networks (FFNs), and assess the extent to which it can be made compute- (or FLOP-) lite. Specifically, we propose an alternative formulation (we call it LookupFFN) to GEMM based FFNs inspired by the recent studies of using Locality Sensitive Hashing (LSH) to approximate FFNs. Our formulation recasts most essential operations as a memory look-up, leveraging the trade-off between the two resources on any platform: compute and memory (since CPUs offer it in abundance). For RoBERTa language model pretraining, our formulation achieves similar performance compared to GEMM based FFNs, while dramatically reducing the required FLOP. Our development is complemented with a detailed hardware profiling of strategies that will maximize efficiency -- not just on contemporary hardware but on products that will be offered in the near/medium term future. Code is avaiable at \url{https://github.com/mlpen/LookupFFN}.
Authors: Zhanyu Liu, Ke Hao, Guanjie Zheng, Yanwei Yu
Abstract: Time series data has been demonstrated to be crucial in various research fields. The management of large quantities of time series data presents challenges in terms of deep learning tasks, particularly for training a deep neural network. Recently, a technique named \textit{Dataset Condensation} has emerged as a solution to this problem. This technique generates a smaller synthetic dataset that has comparable performance to the full real dataset in downstream tasks such as classification. However, previous methods are primarily designed for image and graph datasets, and directly adapting them to the time series dataset leads to suboptimal performance due to their inability to effectively leverage the rich information inherent in time series data, particularly in the frequency domain. In this paper, we propose a novel framework named Dataset \textit{\textbf{Cond}}ensation for \textit{\textbf{T}}ime \textit{\textbf{S}}eries \textit{\textbf{C}}lassification via Dual Domain Matching (\textbf{CondTSC}) which focuses on the time series classification dataset condensation task. Different from previous methods, our proposed framework aims to generate a condensed dataset that matches the surrogate objectives in both the time and frequency domains. Specifically, CondTSC incorporates multi-view data augmentation, dual domain training, and dual surrogate objectives to enhance the dataset condensation process in the time and frequency domains. Through extensive experiments, we demonstrate the effectiveness of our proposed framework, which outperforms other baselines and learns a condensed synthetic dataset that exhibits desirable characteristics such as conforming to the distribution of the original data.
Authors: Chengxing Jia, Fuxiang Zhang, Yi-Chen Li, Chen-Xiao Gao, Xu-Hui Liu, Lei Yuan, Zongzhang Zhang, Yang Yu
Abstract: Offline meta-reinforcement learning (OMRL) proficiently allows an agent to tackle novel tasks while solely relying on a static dataset. For precise and efficient task identification, existing OMRL research suggests learning separate task representations that be incorporated with policy input, thus forming a context-based meta-policy. A major approach to train task representations is to adopt contrastive learning using multi-task offline data. The dataset typically encompasses interactions from various policies (i.e., the behavior policies), thus providing a plethora of contextual information regarding different tasks. Nonetheless, amassing data from a substantial number of policies is not only impractical but also often unattainable in realistic settings. Instead, we resort to a more constrained yet practical scenario, where multi-task data collection occurs with a limited number of policies. We observed that learned task representations from previous OMRL methods tend to correlate spuriously with the behavior policy instead of reflecting the essential characteristics of the task, resulting in unfavorable out-of-distribution generalization. To alleviate this issue, we introduce a novel algorithm to disentangle the impact of behavior policy from task representation learning through a process called adversarial data augmentation. Specifically, the objective of adversarial data augmentation is not merely to generate data analogous to offline data distribution; instead, it aims to create adversarial examples designed to confound learned task representations and lead to incorrect task identification. Our experiments show that learning from such adversarial samples significantly enhances the robustness and effectiveness of the task identification process and realizes satisfactory out-of-distribution generalization.
Authors: Yunpeng Qing, Shunyu liu, Jingyuan Cong, Kaixuan Chen, Yihe Zhou, Mingli Song
Abstract: Offline Reinforcement Learning (RL) endeavors to leverage offline datasets to craft effective agent policy without online interaction, which imposes proper conservative constraints with the support of behavior policies to tackle the Out-Of-Distribution (OOD) problem. However, existing works often suffer from the constraint conflict issue when offline datasets are collected from multiple behavior policies, i.e., different behavior policies may exhibit inconsistent actions with distinct returns across the state space. To remedy this issue, recent Advantage-Weighted (AW) methods prioritize samples with high advantage values for agent training while inevitably leading to overfitting on these samples. In this paper, we introduce a novel Advantage-Aware Policy Optimization (A2PO) method to explicitly construct advantage-aware policy constraints for offline learning under mixed-quality datasets. Specifically, A2PO employs a Conditional Variational Auto-Encoder (CVAE) to disentangle the action distributions of intertwined behavior policies by modeling the advantage values of all training data as conditional variables. Then the agent can follow such disentangled action distribution constraints to optimize the advantage-aware policy towards high advantage values. Extensive experiments conducted on both the single-quality and mixed-quality datasets of the D4RL benchmark demonstrate that A2PO yields results superior to state-of-the-art counterparts. Our code will be made publicly available.
Authors: Hyungi Lee, Giung Nam, Edwin Fong, Juho Lee
Abstract: Transfer learning has recently shown significant performance across various tasks involving deep neural networks. In these transfer learning scenarios, the prior distribution for downstream data becomes crucial in Bayesian model averaging (BMA). While previous works proposed the prior over the neural network parameters centered around the pre-trained solution, such strategies have limitations when dealing with distribution shifts between upstream and downstream data. This paper introduces nonparametric transfer learning (NPTL), a flexible posterior sampling method to address the distribution shift issue within the context of nonparametric learning. The nonparametric learning (NPL) method is a recent approach that employs a nonparametric prior for posterior sampling, efficiently accounting for model misspecification scenarios, which is suitable for transfer learning scenarios that may involve the distribution shift between upstream and downstream tasks. Through extensive empirical validations, we demonstrate that our approach surpasses other baselines in BMA performance.
Authors: Zhanyu Liu, Chaolv Zeng, Guanjie Zheng
Abstract: With the increasing demands of training graph neural networks (GNNs) on large-scale graphs, graph data condensation has emerged as a critical technique to relieve the storage and time costs during the training phase. It aims to condense the original large-scale graph to a much smaller synthetic graph while preserving the essential information necessary for efficiently training a downstream GNN. However, existing methods concentrate either on optimizing node features exclusively or endeavor to independently learn node features and the graph structure generator. They could not explicitly leverage the information of the original graph structure and failed to construct an interpretable graph structure for the synthetic dataset. To address these issues, we introduce a novel framework named \textbf{G}raph Data \textbf{C}ondensation via \textbf{S}elf-expressive Graph Structure \textbf{R}econstruction (\textbf{GCSR}). Our method stands out by (1) explicitly incorporating the original graph structure into the condensing process and (2) capturing the nuanced interdependencies between the condensed nodes by reconstructing an interpretable self-expressive graph structure. Extensive experiments and comprehensive analysis validate the efficacy of the proposed method across diverse GNN models and datasets. Our code is available at https://www.dropbox.com/scl/fi/2aonyp5ln5gisdqtjimu8/GCSR.zip?rlkey=11cuwfpsf54wxiiktu0klud0x&dl=0
URLs: https://www.dropbox.com/scl/fi/2aonyp5ln5gisdqtjimu8/GCSR.zip?rlkey=11cuwfpsf54wxiiktu0klud0x&dl=0
Authors: Peiyuan Liu, Hang Guo, Tao Dai, Naiqi Li, Jigang Bao, Xudong Ren, Yong Jiang, Shu-Tao Xia
Abstract: Multivariate time series forecasting has recently gained great success with the rapid growth of deep learning models. However, existing approaches usually train models from scratch using limited temporal data, preventing their generalization. Recently, with the surge of the Large Language Models (LLMs), several works have attempted to introduce LLMs into time series forecasting. Despite promising results, these methods directly take time series as the input to LLMs, ignoring the inherent modality gap between temporal and text data. In this work, we propose a novel Large Language Models and time series alignment framework, dubbed LLaTA, to fully unleash the potentials of LLMs in the time series forecasting challenge. Based on cross-modal knowledge distillation, the proposed method exploits both input-agnostic static knowledge and input-dependent dynamic knowledge in pre-trained LLMs. In this way, it empowers the forecasting model with favorable performance as well as strong generalization abilities. Extensive experiments demonstrate the proposed method establishes a new state of the art for both long- and short-term forecasting. Code is available at \url{https://github.com/Hank0626/LLaTA}.
Authors: Shaoru Chen, Lekan Molu, Mahyar Fazlyab
Abstract: Barrier functions are a general framework for establishing a safety guarantee for a system. However, there is no general method for finding these functions. To address this shortcoming, recent approaches use self-supervised learning techniques to learn these functions using training data that are periodically generated by a verification procedure, leading to a verification-aided learning framework. Despite its immense potential in automating barrier function synthesis, the verification-aided learning framework does not have termination guarantees and may suffer from a low success rate of finding a valid barrier function in practice. In this paper, we propose a holistic approach to address these drawbacks. With a convex formulation of the barrier function synthesis, we propose to first learn an empirically well-behaved NN basis function and then apply a fine-tuning algorithm that exploits the convexity and counterexamples from the verification failure to find a valid barrier function with finite-step termination guarantees: if there exist valid barrier functions, the fine-tuning algorithm is guaranteed to find one in a finite number of iterations. We demonstrate that our fine-tuning method can significantly boost the performance of the verification-aided learning framework on examples of different scales and using various neural network verifiers.
Authors: Dipesh Tamboli, Jiayu Chen, Kiran Pranesh Jotheeswaran, Denny Yu, Vaneet Aggarwal
Abstract: Sepsis, a life-threatening condition triggered by the body's exaggerated response to infection, demands urgent intervention to prevent severe complications. Existing machine learning methods for managing sepsis struggle in offline scenarios, exhibiting suboptimal performance with survival rates below 50%. This paper introduces the POSNEGDM -- ``Reinforcement Learning with Positive and Negative Demonstrations for Sequential Decision-Making" framework utilizing an innovative transformer-based model and a feedback reinforcer to replicate expert actions while considering individual patient characteristics. A mortality classifier with 96.7\% accuracy guides treatment decisions towards positive outcomes. The POSNEGDM framework significantly improves patient survival, saving 97.39% of patients, outperforming established machine learning algorithms (Decision Transformer and Behavioral Cloning) with survival rates of 33.4% and 43.5%, respectively. Additionally, ablation studies underscore the critical role of the transformer-based decision maker and the integration of a mortality classifier in enhancing overall survival rates. In summary, our proposed approach presents a promising avenue for enhancing sepsis treatment outcomes, contributing to improved patient care and reduced healthcare costs.
Authors: Seungjae Shin, HeeSun Bae, Byeonghu Na, Yoon-Yeong Kim, Il-Chul Moon
Abstract: The objective of domain generalization (DG) is to enhance the transferability of the model learned from a source domain to unobserved domains. To prevent overfitting to a specific domain, Sharpness-Aware Minimization (SAM) reduces source domain's loss sharpness. Although SAM variants have delivered significant improvements in DG, we highlight that there's still potential for improvement in generalizing to unknown domains through the exploration on data space. This paper introduces an objective rooted in both parameter and data perturbed regions for domain generalization, coined Unknown Domain Inconsistency Minimization (UDIM). UDIM reduces the loss landscape inconsistency between source domain and unknown domains. As unknown domains are inaccessible, these domains are empirically crafted by perturbing instances from the source domain dataset. In particular, by aligning the loss landscape acquired in the source domain to the loss landscape of perturbed domains, we expect to achieve generalization grounded on these flat minima for the unknown domains. Theoretically, we validate that merging SAM optimization with the UDIM objective establishes an upper bound for the true objective of the DG task. In an empirical aspect, UDIM consistently outperforms SAM variants across multiple DG benchmark datasets. Notably, UDIM shows statistically significant improvements in scenarios with more restrictive domain information, underscoring UDIM's generalization capability in unseen domains. Our code is available at \url{https://github.com/SJShin-AI/UDIM}.
Authors: Zhanpeng Zeng, Karthikeyan Sankaralingam, Vikas Singh
Abstract: GEneral Matrix Multiply (GEMM) is a central operation in deep learning and corresponds to the largest chunk of the compute footprint. Therefore, improving its efficiency is an active topic of ongoing research. A popular strategy is the use of low bit-width integers to approximate the original entries in a matrix. This allows efficiency gains, but often requires sophisticated techniques to control the rounding error incurred. In this work, we first verify/check that when the low bit-width restriction is removed, for a variety of Transformer-based models, whether integers are sufficient for all GEMMs need -- for {\em both} training and inference stages, and can achieve parity with floating point counterparts. No sophisticated techniques are needed. We find that while a large majority of entries in matrices (encountered in such models) can be easily represented by {\em low} bit-width integers, the existence of a few heavy hitter entries make it difficult to achieve efficiency gains via the exclusive use of low bit-width GEMMs alone. To address this issue, we develop a simple algorithm, Integer Matrix Unpacking (IM-Unpack), to {\em unpack} a matrix with large integer entries into a larger matrix whose entries all lie within the representable range of arbitrarily low bit-width integers. This allows {\em equivalence} with the original GEMM, i.e., the exact result can be obtained using purely low bit-width integer GEMMs. This comes at the cost of additional operations -- we show that for many popular models, this overhead is quite small.
Authors: Jiahao Zhang, Lin Wang, Shijie Wang, Wenqi Fan
Abstract: Graph Neural Networks (GNNs) have achieved remarkable success in various real-world applications. However, GNNs may be trained on undesirable graph data, which can degrade their performance and reliability. To enable trained GNNs to efficiently unlearn unwanted data, a desirable solution is retraining-based graph unlearning, which partitions the training graph into subgraphs and trains sub-models on them, allowing fast unlearning through partial retraining. However, the graph partition process causes information loss in the training graph, resulting in the low model utility of sub-GNN models. In this paper, we propose GraphRevoker, a novel graph unlearning framework that better maintains the model utility of unlearnable GNNs. Specifically, we preserve the graph property with graph property-aware sharding and effectively aggregate the sub-GNN models for prediction with graph contrastive sub-model aggregation. We conduct extensive experiments to demonstrate the superiority of our proposed approach.
Authors: Chongyu Fan, Jiancheng Liu, Alfred Hero, Sijia Liu
Abstract: The trustworthy machine learning (ML) community is increasingly recognizing the crucial need for models capable of selectively 'unlearning' data points after training. This leads to the problem of machine unlearning (MU), aiming to eliminate the influence of chosen data points on model performance, while still maintaining the model's utility post-unlearning. Despite various MU methods for data influence erasure, evaluations have largely focused on random data forgetting, ignoring the vital inquiry into which subset should be chosen to truly gauge the authenticity of unlearning performance. To tackle this issue, we introduce a new evaluative angle for MU from an adversarial viewpoint. We propose identifying the data subset that presents the most significant challenge for influence erasure, i.e., pinpointing the worst-case forget set. Utilizing a bi-level optimization principle, we amplify unlearning challenges at the upper optimization level to emulate worst-case scenarios, while simultaneously engaging in standard training and unlearning at the lower level, achieving a balance between data influence erasure and model utility. Our proposal offers a worst-case evaluation of MU's resilience and effectiveness. Through extensive experiments across different datasets (including CIFAR-10, 100, CelebA, Tiny ImageNet, and ImageNet) and models (including both image classifiers and generative models), we expose critical pros and cons in existing (approximate) unlearning strategies. Our results illuminate the complex challenges of MU in practice, guiding the future development of more accurate and robust unlearning algorithms. The code is available at https://github.com/OPTML-Group/Unlearn-WorstCase.
Authors: Sidak Pal Singh, Bobby He, Thomas Hofmann, Bernhard Sch\"olkopf
Abstract: We propose a fresh take on understanding the mechanisms of neural networks by analyzing the rich structure of parameters contained within their optimization trajectories. Towards this end, we introduce some natural notions of the complexity of optimization trajectories, both qualitative and quantitative, which reveal the inherent nuance and interplay involved between various optimization choices, such as momentum, weight decay, and batch size. We use them to provide key hallmarks about the nature of optimization in deep neural networks: when it goes right, and when it finds itself in a dead end. Further, thanks to our trajectory perspective, we uncover an intertwined behaviour of momentum and weight decay that promotes directional exploration, as well as a directional regularization behaviour of some others. We perform experiments over large-scale vision and language settings, including large language models (LLMs) with up to 12 billion parameters, to demonstrate the value of our approach.
Authors: Filip Szatkowski, Fei Yang, Bart{\l}omiej Twardowski, Tomasz Trzci\'nski, Joost van de Weijer
Abstract: Driven by the demand for energy-efficient employment of deep neural networks, early-exit methods have experienced a notable increase in research attention. These strategies allow for swift predictions by making decisions early in the network, thereby conserving computation time and resources. However, so far the early-exit networks have only been developed for stationary data distributions, which restricts their application in real-world scenarios with continuous non-stationary data. This study aims to explore the continual learning of the early-exit networks. We adapt existing continual learning methods to fit with early-exit architectures and investigate their behavior in the continual setting. We notice that early network layers exhibit reduced forgetting and can outperform standard networks even when using significantly fewer resources. Furthermore, we analyze the impact of task-recency bias on early-exit inference and propose Task-wise Logits Correction (TLC), a simple method that equalizes this bias and improves the network performance for every given compute budget in the class-incremental setting. We assess the accuracy and computational cost of various continual learning techniques enhanced with early-exits and TLC across standard class-incremental learning benchmarks such as 10 split CIFAR100 and ImageNetSubset and show that TLC can achieve the accuracy of the standard methods using less than 70\% of their computations. Moreover, at full computational budget, our method outperforms the accuracy of the standard counterparts by up to 15 percentage points. Our research underscores the inherent synergy between early-exit networks and continual learning, emphasizing their practical utility in resource-constrained environments.
Authors: Marek Elias, Haim Kaplan, Yishay Mansour, Shay Moran
Abstract: Recent advances in algorithmic design show how to utilize predictions obtained by machine learning models from past and present data. These approaches have demonstrated an enhancement in performance when the predictions are accurate, while also ensuring robustness by providing worst-case guarantees when predictions fail. In this paper we focus on online problems; prior research in this context was focused on a paradigm where the predictor is pre-trained on past data and then used as a black box (to get the predictions it was trained for). In contrast, in this work, we unpack the predictor and integrate the learning problem it gives rise for within the algorithmic challenge. In particular we allow the predictor to learn as it receives larger parts of the input, with the ultimate goal of designing online learning algorithms specifically tailored for the algorithmic task at hand. Adopting this perspective, we focus on a number of fundamental problems, including caching and scheduling, which have been well-studied in the black-box setting. For each of the problems we consider, we introduce new algorithms that take advantage of explicit learning algorithms which we carefully design towards optimizing the overall performance. We demonstrate the potential of our approach by deriving performance bounds which improve over those established in previous work.
Authors: Katherine Tsai, Stephen R. Pfohl, Olawale Salaudeen, Nicole Chiou, Matt J. Kusner, Alexander D'Amour, Sanmi Koyejo, Arthur Gretton
Abstract: We study the problem of domain adaptation under distribution shift, where the shift is due to a change in the distribution of an unobserved, latent variable that confounds both the covariates and the labels. In this setting, neither the covariate shift nor the label shift assumptions apply. Our approach to adaptation employs proximal causal learning, a technique for estimating causal effects in settings where proxies of unobserved confounders are available. We demonstrate that proxy variables allow for adaptation to distribution shift without explicitly recovering or modeling latent variables. We consider two settings, (i) Concept Bottleneck: an additional ''concept'' variable is observed that mediates the relationship between the covariates and labels; (ii) Multi-domain: training data from multiple source domains is available, where each source domain exhibits a different distribution over the latent confounder. We develop a two-stage kernel estimation approach to adapt to complex distribution shifts in both settings. In our experiments, we show that our approach outperforms other methods, notably those which explicitly recover the latent confounder.
Authors: Ana Lawry Aguila, Andre Altmann
Abstract: There has been a growing interest in recent years in modelling multiple modalities (or views) of data to for example, understand the relationship between modalities or to generate missing data. Multi-view autoencoders have gained significant traction for their adaptability and versatility in modelling multi-modal data, demonstrating an ability to tailor their approach to suit the characteristics of the data at hand. However, most multi-view autoencoders have inconsistent notation and are often implemented using different coding frameworks. To address this, we present a unified mathematical framework for multi-view autoencoders, consolidating their formulations. Moreover, we offer insights into the motivation and theoretical advantages of each model. To facilitate accessibility and practical use, we extend the documentation and functionality of the previously introduced \texttt{multi-view-AE} library. This library offers Python implementations of numerous multi-view autoencoder models, presented within a user-friendly framework. Through benchmarking experiments, we evaluate our implementations against previous ones, demonstrating comparable or superior performance. This work aims to establish a cohesive foundation for multi-modal modelling, serving as a valuable educational resource in the field.
Authors: Camila Fernandez (LPSM), Chung Shue Chen, Chen Pierre Gaillard, Alonso Silva
Abstract: Time-to-event analysis is a branch of statistics that has increased in popularity during the last decades due to its many application fields, such as predictive maintenance, customer churn prediction and population lifetime estimation. In this paper, we review and compare the performance of several prediction models for time-to-event analysis. These consist of semi-parametric and parametric statistical models, in addition to machine learning approaches. Our study is carried out on three datasets and evaluated in two different scores (the integrated Brier score and concordance index). Moreover, we show how ensemble methods, which surprisingly have not yet been much studied in time-to-event analysis, can improve the prediction accuracy and enhance the robustness of the prediction performance. We conclude the analysis with a simulation experiment in which we evaluate the factors influencing the performance ranking of the methods using both scores.
Authors: Robin Zbinden, Nina van Tiel, Marc Ru{\ss}wurm, Devis Tuia
Abstract: In the face of significant biodiversity decline, species distribution models (SDMs) are essential for understanding the impact of climate change on species habitats by connecting environmental conditions to species occurrences. Traditionally limited by a scarcity of species observations, these models have significantly improved in performance through the integration of larger datasets provided by citizen science initiatives. However, they still suffer from the strong class imbalance between species within these datasets, often resulting in the penalization of rare species--those most critical for conservation efforts. To tackle this issue, this study assesses the effectiveness of training deep learning models using a balanced presence-only loss function on large citizen science-based datasets. We demonstrate that this imbalance-aware loss function outperforms traditional loss functions across various datasets and tasks, particularly in accurately modeling rare species with limited observations.
Authors: Zeyu Zhang, Khandaker Asif Ahmed, Md Rakibul Hasan, Tom Gedeon, Md Zakir Hossain
Abstract: Diabetes, resulting from inadequate insulin production or utilization, causes extensive harm to the body. Existing diagnostic methods are often invasive and come with drawbacks, such as cost constraints. Although there are machine learning models like Classwise k Nearest Neighbor (CkNN) and General Regression Neural Network (GRNN), they struggle with imbalanced data and result in under-performance. Leveraging advancements in sensor technology and machine learning, we propose a non-invasive diabetes diagnosis using a Back Propagation Neural Network (BPNN) with batch normalization, incorporating data re-sampling and normalization for class balancing. Our method addresses existing challenges such as limited performance associated with traditional machine learning. Experimental results on three datasets show significant improvements in overall accuracy, sensitivity, and specificity compared to traditional methods. Notably, we achieve accuracies of 89.81% in Pima diabetes dataset, 75.49% in CDC BRFSS2015 dataset, and 95.28% in Mesra Diabetes dataset. This underscores the potential of deep learning models for robust diabetes diagnosis. See project website https://steve-zeyu-zhang.github.io/DiabetesDiagnosis/
Authors: Simon Letzgus, Klaus-Robert M\"uller, Gr\'egoire Montavon
Abstract: In recent years, Explainable AI (XAI) methods have facilitated profound validation and knowledge extraction from ML models. While extensively studied for classification, few XAI solutions have addressed the challenges specific to regression models. In regression, explanations need to be precisely formulated to address specific user queries (e.g.\ distinguishing between `Why is the output above 0?' and `Why is the output above 50?'). They should furthermore reflect the model's behavior on the relevant data sub-manifold. In this paper, we introduce XpertAI, a framework that disentangles the prediction strategy into multiple range-specific sub-strategies and allows the formulation of precise queries about the model (the `explanandum') as a linear combination of those sub-strategies. XpertAI is formulated generally to work alongside popular XAI attribution techniques, based on occlusion, gradient integration, or reverse propagation. Qualitative and quantitative results, demonstrate the benefits of our approach.
Authors: Oshando Johnson, Goran Piskachev, Ranjith Krishnamurthy, Eric Bodden
Abstract: To detect security vulnerabilities, static analysis tools need to be configured with security-relevant methods. Current approaches can automatically identify such methods using binary relevance machine learning approaches. However, they ignore dependencies among security-relevant methods, over-generalize and perform poorly in practice. Additionally, users have to nevertheless manually configure static analysis tools using the detected methods. Based on feedback from users and our observations, the excessive manual steps can often be tedious, error-prone and counter-intuitive. In this paper, we present Dev-Assist, an IntelliJ IDEA plugin that detects security-relevant methods using a multi-label machine learning approach that considers dependencies among labels. The plugin can automatically generate configurations for static analysis tools, run the static analysis, and show the results in IntelliJ IDEA. Our experiments reveal that Dev-Assist's machine learning approach has a higher F1-Measure than related approaches. Moreover, the plugin reduces and simplifies the manual effort required when configuring and using static analysis tools.
Authors: Shuchang Yan
Abstract: Hybrid electric vehicles (HEVs) are becoming increasingly popular because they can better combine the working characteristics of internal combustion engines and electric motors. However, the minimum fuel consumption of an HEV for a battery electrical balance case under a specific assembly condition and a specific speed curve still needs to be clarified in academia and industry. Regarding this problem, this work provides the mathematical expression of constrained optimal fuel consumption (COFC) from the perspective of constrained reinforcement learning (CRL) for the first time globally. Also, two mainstream approaches of CRL, constrained variational policy optimization (CVPO) and Lagrangian-based approaches, are utilized for the first time to obtain the vehicle's minimum fuel consumption under the battery electrical balance condition. We conduct case studies on the well-known Prius TOYOTA hybrid system (THS) under the NEDC condition; we give vital steps to implement CRL approaches and compare the performance between the CVPO and Lagrangian-based approaches. Our case study found that CVPO and Lagrangian-based approaches can obtain the lowest fuel consumption while maintaining the SOC balance constraint. The CVPO approach converges stable, but the Lagrangian-based approach can obtain the lowest fuel consumption at 3.95 L/100km, though with more significant oscillations. This result verifies the effectiveness of our proposed CRL approaches to the COFC problem.
Authors: Saksham Checker, Nikhil Churamani, Hatice Gunes
Abstract: As social robots become increasingly integrated into daily life, ensuring their behaviours align with social norms is crucial. For their widespread open-world application, it is important to explore Federated Learning (FL) settings where individual robots can learn about their unique environments while also learning from each others' experiences. In this paper, we present a novel FL benchmark that evaluates different strategies, using multi-label regression objectives, where each client individually learns to predict the social appropriateness of different robot actions while also sharing their learning with others. Furthermore, splitting the training data by different contexts such that each client incrementally learns across contexts, we present a novel Federated Continual Learning (FCL) benchmark that adapts FL-based methods to use state-of-the-art Continual Learning (CL) methods to continually learn socially appropriate agent behaviours under different contextual settings. Federated Averaging (FedAvg) of weights emerges as a robust FL strategy while rehearsal-based FCL enables incrementally learning the social appropriateness of robot actions, across contextual splits.
Authors: Kristian Schwethelm, Johannes Kaiser, Moritz Knolle, Daniel Rueckert, Georgios Kaissis, Alexander Ziller
Abstract: Image reconstruction attacks on machine learning models pose a significant risk to privacy by potentially leaking sensitive information. Although defending against such attacks using differential privacy (DP) has proven effective, determining appropriate DP parameters remains challenging. Current formal guarantees on data reconstruction success suffer from overly theoretical assumptions regarding adversary knowledge about the target data, particularly in the image domain. In this work, we empirically investigate this discrepancy and find that the practicality of these assumptions strongly depends on the domain shift between the data prior and the reconstruction target. We propose a reconstruction attack based on diffusion models (DMs) that assumes adversary access to real-world image priors and assess its implications on privacy leakage under DP-SGD. We show that (1) real-world data priors significantly influence reconstruction success, (2) current reconstruction bounds do not model the risk posed by data priors well, and (3) DMs can serve as effective auditing tools for visualizing privacy leakage.
Authors: Zhenfeng He, Yao Shu, Zhongxiang Dai, Bryan Kian Hsiang Low
Abstract: Neural architecture search (NAS) has become a key component of AutoML and a standard tool to automate the design of deep neural networks. Recently, training-free NAS as an emerging paradigm has successfully reduced the search costs of standard training-based NAS by estimating the true architecture performance with only training-free metrics. Nevertheless, the estimation ability of these metrics typically varies across different tasks, making it challenging to achieve robust and consistently good search performance on diverse tasks with only a single training-free metric. Meanwhile, the estimation gap between training-free metrics and the true architecture performances limits training-free NAS to achieve superior performance. To address these challenges, we propose the robustifying and boosting training-free NAS (RoBoT) algorithm which (a) employs the optimized combination of existing training-free metrics explored from Bayesian optimization to develop a robust and consistently better-performing metric on diverse tasks, and (b) applies greedy search, i.e., the exploitation, on the newly developed metric to bridge the aforementioned gap and consequently to boost the search performance of standard training-free NAS further. Remarkably, the expected performance of our RoBoT can be theoretically guaranteed, which improves over the existing training-free NAS under mild conditions with additional interesting insights. Our extensive experiments on various NAS benchmark tasks yield substantial empirical evidence to support our theoretical results.
Authors: {\L}ukasz Struski, Adam Pardyl, Jacek Tabor, Bartosz Zieli\'nski
Abstract: Partial Multi-label Learning (PML) is a type of weakly supervised learning where each training instance corresponds to a set of candidate labels, among which only some are true. In this paper, we introduce \our{}, a novel probabilistic approach to this problem that extends the binary cross entropy to the PML setup. In contrast to existing methods, it does not require suboptimal disambiguation and, as such, can be applied to any deep architecture. Furthermore, experiments conducted on artificial and real-world datasets indicate that \our{} outperforms existing approaches, especially for high noise in a candidate set.
Authors: Vinay Chakravarthi Gogineni, Esmaeil S. Nadimi
Abstract: Machine unlearning has garnered significant attention due to its ability to selectively erase knowledge obtained from specific training data samples in an already trained machine learning model. This capability enables data holders to adhere strictly to data protection regulations. However, existing unlearning techniques face practical constraints, often causing performance degradation, demanding brief fine-tuning post unlearning, and requiring significant storage. In response, this paper introduces a novel class of machine unlearning algorithms. First method is partial amnesiac unlearning, integration of layer-wise pruning with amnesiac unlearning. In this method, updates made to the model during training are pruned and stored, subsequently used to forget specific data from trained model. The second method assimilates layer-wise partial-updates into label-flipping and optimization-based unlearning to mitigate the adverse effects of data deletion on model efficacy. Through a detailed experimental evaluation, we showcase the effectiveness of proposed unlearning methods. Experimental results highlight that the partial amnesiac unlearning not only preserves model efficacy but also eliminates the necessity for brief post fine-tuning, unlike conventional amnesiac unlearning. Moreover, employing layer-wise partial updates in label-flipping and optimization-based unlearning techniques demonstrates superiority in preserving model efficacy compared to their naive counterparts.
Authors: Gregory W. Kyro, Matthew T. Martin, Eric D. Watt, Victor S. Batista
Abstract: Drug-induced cardiotoxicity is a major health concern which can lead to serious adverse effects including life-threatening cardiac arrhythmias via the blockade of the voltage-gated hERG potassium ion channel. It is therefore of tremendous interest to develop advanced methods to identify hERG-active compounds in early stages of drug development, as well as to optimize commercially available drugs for reduced hERG activity. In this work, we present CardioGenAI, a machine learning-based framework for re-engineering both developmental and marketed drugs for reduced hERG activity while preserving their pharmacological activity. The framework incorporates novel state-of-the-art discriminative models for predicting hERG channel activity, as well as activity against the voltage-gated NaV1.5 and CaV1.2 channels due to their potential implications in modulating the arrhythmogenic potential induced by hERG channel blockade. These models can also serve independently as effective components of a virtual screening pipeline. We applied the complete framework to pimozide, an FDA-approved antipsychotic agent that demonstrates high affinity to the hERG channel, and generated 100 refined candidates. Remarkably, among the candidates is fluspirilene, a compound which is of the same class of drugs (diphenylmethanes) as pimozide and therefore has similar pharmacological activity, yet exhibits over 700-fold weaker binding to hERG. We have made all of our software open-source to facilitate integration of the CardioGenAI framework for molecular hypothesis generation into drug discovery workflows.
Authors: Quzhe Huang, Zhenwei An, Nan Zhuang, Mingxu Tao, Chen Zhang, Yang Jin, Kun Xu, Kun Xu, Liwei Chen, Songfang Huang, Yansong Feng
Abstract: In this paper, we introduce a novel dynamic expert selection framework for Mixture of Experts (MoE) models, aiming to enhance computational efficiency and model performance by adjusting the number of activated experts based on input difficulty. Unlike traditional MoE approaches that rely on fixed Top-K routing, which activates a predetermined number of experts regardless of the input's complexity, our method dynamically selects experts based on the confidence level in expert selection for each input. This allows for a more efficient utilization of computational resources, activating more experts for complex tasks requiring advanced reasoning and fewer for simpler tasks. Through extensive evaluations, our dynamic routing method demonstrates substantial improvements over conventional Top-2 routing across various benchmarks, achieving an average improvement of 0.7% with less than 90% activated parameters. Further analysis shows our model dispatches more experts to tasks requiring complex reasoning skills, like BBH, confirming its ability to dynamically allocate computational resources in alignment with the input's complexity. Our findings also highlight a variation in the number of experts needed across different layers of the transformer model, offering insights into the potential for designing heterogeneous MoE frameworks. The code and models are available at https://github.com/ZhenweiAn/Dynamic_MoE.
Authors: Feras Saad, Jacob Burnim, Colin Carroll, Brian Patton, Urs K\"oster, Rif A. Saurous, Matthew Hoffman
Abstract: Spatiotemporal datasets, which consist of spatially-referenced time series, are ubiquitous in many scientific and business-intelligence applications, such as air pollution monitoring, disease tracking, and cloud-demand forecasting. As modern datasets continue to increase in size and complexity, there is a growing need for new statistical methods that are flexible enough to capture complex spatiotemporal dynamics and scalable enough to handle large prediction problems. This work presents the Bayesian Neural Field (BayesNF), a domain-general statistical model for inferring rich probability distributions over a spatiotemporal domain, which can be used for data-analysis tasks including forecasting, interpolation, and variography. BayesNF integrates a novel deep neural network architecture for high-capacity function estimation with hierarchical Bayesian inference for robust uncertainty quantification. By defining the prior through a sequence of smooth differentiable transforms, posterior inference is conducted on large-scale data using variationally learned surrogates trained via stochastic gradient descent. We evaluate BayesNF against prominent statistical and machine-learning baselines, showing considerable improvements on diverse prediction problems from climate and public health datasets that contain tens to hundreds of thousands of measurements. The paper is accompanied with an open-source software package (https://github.com/google/bayesnf) that is easy-to-use and compatible with modern GPU and TPU accelerators on the JAX machine learning platform.
Authors: Rory Bunker, Calvin Yeung, Keisuke Fujii
Abstract: Machine learning has become a common approach to predicting the outcomes of soccer matches, and the body of literature in this domain has grown substantially in the past decade and a half. This chapter discusses available datasets, the types of models and features, and ways of evaluating model performance in this application domain. The aim of this chapter is to give a broad overview of the current state and potential future developments in machine learning for soccer match results prediction, as a resource for those interested in conducting future studies in the area. Our main findings are that while gradient-boosted tree models such as CatBoost, applied to soccer-specific ratings such as pi-ratings, are currently the best-performing models on datasets containing only goals as the match features, there needs to be a more thorough comparison of the performance of deep learning models and Random Forest on a range of datasets with different types of features. Furthermore, new rating systems using both player- and team-level information and incorporating additional information from, e.g., spatiotemporal tracking and event data, could be investigated further. Finally, the interpretability of match result prediction models needs to be enhanced for them to be more useful for team management.
Authors: Simon Dufort-Labb\'e, Pierluca D'Oro, Evgenii Nikishin, Razvan Pascanu, Pierre-Luc Bacon, Aristide Baratin
Abstract: When training deep neural networks, the phenomenon of $\textit{dying neurons}$ $\unicode{x2013}$units that become inactive or saturated, output zero during training$\unicode{x2013}$ has traditionally been viewed as undesirable, linked with optimization challenges, and contributing to plasticity loss in continual learning scenarios. In this paper, we reassess this phenomenon, focusing on sparsity and pruning. By systematically exploring the impact of various hyperparameter configurations on dying neurons, we unveil their potential to facilitate simple yet effective structured pruning algorithms. We introduce $\textit{Demon Pruning}$ (DemP), a method that controls the proliferation of dead neurons, dynamically leading to network sparsity. Achieved through a combination of noise injection on active units and a one-cycled schedule regularization strategy, DemP stands out for its simplicity and broad applicability. Experiments on CIFAR10 and ImageNet datasets demonstrate that DemP surpasses existing structured pruning techniques, showcasing superior accuracy-sparsity tradeoffs and training speedups. These findings suggest a novel perspective on dying neurons as a valuable resource for efficient model compression and optimization.
Authors: Motoki Omura, Takayuki Osa, Yusuke Mukuta, Tatsuya Harada
Abstract: In deep reinforcement learning, estimating the value function to evaluate the quality of states and actions is essential. The value function is often trained using the least squares method, which implicitly assumes a Gaussian error distribution. However, a recent study suggested that the error distribution for training the value function is often skewed because of the properties of the Bellman operator, and violates the implicit assumption of normal error distribution in the least squares method. To address this, we proposed a method called Symmetric Q-learning, in which the synthetic noise generated from a zero-mean distribution is added to the target values to generate a Gaussian error distribution. We evaluated the proposed method on continuous control benchmark tasks in MuJoCo. It improved the sample efficiency of a state-of-the-art reinforcement learning method by reducing the skewness of the error distribution.
Authors: Alexandre Drouin, Maxime Gasse, Massimo Caccia, Issam H. Laradji, Manuel Del Verme, Tom Marty, L\'eo Boisvert, Megh Thakkar, Quentin Cappart, David Vazquez, Nicolas Chapados, Alexandre Lacoste
Abstract: We study the use of large language model-based agents for interacting with software via web browsers. Unlike prior work, we focus on measuring the agents' ability to perform tasks that span the typical daily work of knowledge workers utilizing enterprise software systems. To this end, we propose WorkArena, a remote-hosted benchmark of 29 tasks based on the widely-used ServiceNow platform. We also introduce BrowserGym, an environment for the design and evaluation of such agents, offering a rich set of actions as well as multimodal observations. Our empirical evaluation reveals that while current agents show promise on WorkArena, there remains a considerable gap towards achieving full task automation. Notably, our analysis uncovers a significant performance disparity between open and closed-source LLMs, highlighting a critical area for future exploration and development in the field.
Authors: Zijian Liu, Zhengyuan Zhou
Abstract: Shuffling gradient methods, which are also known as stochastic gradient descent (SGD) without replacement, are widely implemented in practice, particularly including three popular algorithms: Random Reshuffle (RR), Shuffle Once (SO), and Incremental Gradient (IG). Compared to the empirical success, the theoretical guarantee of shuffling gradient methods was not well-understanding for a long time. Until recently, the convergence rates had just been established for the average iterate for convex functions and the last iterate for strongly convex problems (using squared distance as the metric). However, when using the function value gap as the convergence criterion, existing theories cannot interpret the good performance of the last iterate in different settings (e.g., constrained optimization). To bridge this gap between practice and theory, we prove last-iterate convergence rates for shuffling gradient methods with respect to the objective value even without strong convexity. Our new results either (nearly) match the existing last-iterate lower bounds or are as fast as the previous best upper bounds for the average iterate.
Authors: Zachary McBride Lazri, Danial Dervovic, Antigoni Polychroniadou, Ivan Brugere, Dana Dachman-Soled, Min Wu
Abstract: Applications that deal with sensitive information may have restrictions placed on the data available to a machine learning (ML) classifier. For example, in some applications, a classifier may not have direct access to sensitive attributes, affecting its ability to produce accurate and fair decisions. This paper proposes a framework that models the trade-off between accuracy and fairness under four practical scenarios that dictate the type of data available for analysis. Prior works examine this trade-off by analyzing the outputs of a scoring function that has been trained to implicitly learn the underlying distribution of the feature vector, class label, and sensitive attribute of a dataset. In contrast, our framework directly analyzes the behavior of the optimal Bayesian classifier on this underlying distribution by constructing a discrete approximation it from the dataset itself. This approach enables us to formulate multiple convex optimization problems, which allow us to answer the question: How is the accuracy of a Bayesian classifier affected in different data restricting scenarios when constrained to be fair? Analysis is performed on a set of fairness definitions that include group and individual fairness. Experiments on three datasets demonstrate the utility of the proposed framework as a tool for quantifying the trade-offs among different fairness notions and their distributional dependencies.
Authors: Miguel Fuentes, Brett Mullins, Ryan McKenna, Gerome Miklau, Daniel Sheldon
Abstract: Mechanisms for generating differentially private synthetic data based on marginals and graphical models have been successful in a wide range of settings. However, one limitation of these methods is their inability to incorporate public data. Initializing a data generating model by pre-training on public data has shown to improve the quality of synthetic data, but this technique is not applicable when model structure is not determined a priori. We develop the mechanism jam-pgm, which expands the adaptive measurements framework to jointly select between measuring public data and private data. This technique allows for public data to be included in a graphical-model-based mechanism. We show that jam-pgm is able to outperform both publicly assisted and non publicly assisted synthetic data generation mechanisms even when the public data distribution is biased.
Authors: Zhengxuan Wu, Atticus Geiger, Aryaman Arora, Jing Huang, Zheng Wang, Noah D. Goodman, Christopher D. Manning, Christopher Potts
Abstract: Interventions on model-internal states are fundamental operations in many areas of AI, including model editing, steering, robustness, and interpretability. To facilitate such research, we introduce $\textbf{pyvene}$, an open-source Python library that supports customizable interventions on a range of different PyTorch modules. $\textbf{pyvene}$ supports complex intervention schemes with an intuitive configuration format, and its interventions can be static or include trainable parameters. We show how $\textbf{pyvene}$ provides a unified and extensible framework for performing interventions on neural models and sharing the intervened upon models with others. We illustrate the power of the library via interpretability analyses using causal abstraction and knowledge localization. We publish our library through Python Package Index (PyPI) and provide code, documentation, and tutorials at https://github.com/stanfordnlp/pyvene.
Authors: Abdul Fatir Ansari, Lorenzo Stella, Caner Turkmen, Xiyuan Zhang, Pedro Mercado, Huibin Shen, Oleksandr Shchur, Syama Sundar Rangapuram, Sebastian Pineda Arango, Shubham Kapoor, Jasper Zschiegner, Danielle C. Maddix, Michael W. Mahoney, Kari Torkkola, Andrew Gordon Wilson, Michael Bohlke-Schneider, Yuyang Wang
Abstract: We introduce Chronos, a simple yet effective framework for pretrained probabilistic time series models. Chronos tokenizes time series values using scaling and quantization into a fixed vocabulary and trains existing transformer-based language model architectures on these tokenized time series via the cross-entropy loss. We pretrained Chronos models based on the T5 family (ranging from 20M to 710M parameters) on a large collection of publicly available datasets, complemented by a synthetic dataset that we generated via Gaussian processes to improve generalization. In a comprehensive benchmark consisting of 42 datasets, and comprising both classical local models and deep learning methods, we show that Chronos models: (a) significantly outperform other methods on datasets that were part of the training corpus; and (b) have comparable and occasionally superior zero-shot performance on new datasets, relative to methods that were trained specifically on them. Our results demonstrate that Chronos models can leverage time series data from diverse domains to improve zero-shot accuracy on unseen forecasting tasks, positioning pretrained models as a viable tool to greatly simplify forecasting pipelines.
Authors: Chaoyi Zhu, Jiayi Tang, Hans Brouwer, Juan F. P\'erez, Marten van Dijk, Lydia Y. Chen
Abstract: Synthetic data from generative models emerges as the privacy-preserving data-sharing solution. Such a synthetic data set shall resemble the original data without revealing identifiable private information. The backbone technology of tabular synthesizers is rooted in image generative models, ranging from Generative Adversarial Networks (GANs) to recent diffusion models. Recent prior work sheds light on the utility-privacy tradeoff on tabular data, revealing and quantifying privacy risks on synthetic data. We first conduct an exhaustive empirical analysis, highlighting the utility-privacy tradeoff of five state-of-the-art tabular synthesizers, against eight privacy attacks, with a special focus on membership inference attacks. Motivated by the observation of high data quality but also high privacy risk in tabular diffusion, we propose DP-TLDM, Differentially Private Tabular Latent Diffusion Model, which is composed of an autoencoder network to encode the tabular data and a latent diffusion model to synthesize the latent tables. Following the emerging f-DP framework, we apply DP-SGD to train the auto-encoder in combination with batch clipping and use the separation value as the privacy metric to better capture the privacy gain from DP algorithms. Our empirical evaluation demonstrates that DP-TLDM is capable of achieving a meaningful theoretical privacy guarantee while also significantly enhancing the utility of synthetic data. Specifically, compared to other DP-protected tabular generative models, DP-TLDM improves the synthetic quality by an average of 35% in data resemblance, 15% in the utility for downstream tasks, and 50% in data discriminability, all while preserving a comparable level of privacy risk.
Authors: Tuhin Subhra De, Pranjal Singh, Alok Patel
Abstract: In the context of developing nations like India, traditional business to business (B2B) commerce heavily relies on the establishment of robust relationships, trust, and credit arrangements between buyers and sellers. Consequently, ecommerce enterprises frequently. Established in 2016 with a vision to revolutionize trade in India through technology, Udaan is the countrys largest business to business ecommerce platform. Udaan operates across diverse product categories, including lifestyle, electronics, home and employ telecallers to cultivate buyer relationships, streamline order placement procedures, and promote special promotions. The accurate anticipation of buyer order placement behavior emerges as a pivotal factor for attaining sustainable growth, heightening competitiveness, and optimizing the efficiency of these telecallers. To address this challenge, we have employed an ensemble approach comprising XGBoost and a modified version of Poisson Gamma model to predict customer order patterns with precision. This paper provides an in-depth exploration of the strategic fusion of machine learning and an empirical Bayesian approach, bolstered by the judicious selection of pertinent features. This innovative approach has yielded a remarkable 3 times increase in customer order rates, show casing its potential for transformative impact in the ecommerce industry.
Authors: Harish G. Naik, Jan Polster, Raj Shekhar, Tam\'as Horv\'ath, Gy\"orgy Tur\'an
Abstract: We formulate an XAI-based model improvement approach for Graph Neural Networks (GNNs) for node classification, called Explanation Enhanced Graph Learning (EEGL). The goal is to improve predictive performance of GNN using explanations. EEGL is an iterative self-improving algorithm, which starts with a learned "vanilla" GNN, and repeatedly uses frequent subgraph mining to find relevant patterns in explanation subgraphs. These patterns are then filtered further to obtain application-dependent features corresponding to the presence of certain subgraphs in the node neighborhoods. Giving an application-dependent algorithm for such a subgraph-based extension of the Weisfeiler-Leman (1-WL) algorithm has previously been posed as an open problem. We present experimental evidence, with synthetic and real-world data, which show that EEGL outperforms related approaches in predictive performance and that it has a node-distinguishing power beyond that of vanilla GNNs. We also analyze EEGL's training dynamics.
Authors: Yoga Esa Wibowo, Cristian Cioflan, Thorir Mar Ingolfsson, Michael Hersche, Leo Zhao, Abbas Rahimi, Luca Benini
Abstract: Few-Shot Class-Incremental Learning (FSCIL) enables machine learning systems to expand their inference capabilities to new classes using only a few labeled examples, without forgetting the previously learned classes. Classical backpropagation-based learning and its variants are often unsuitable for battery-powered, memory-constrained systems at the extreme edge. In this work, we introduce Online Few-Shot Class-Incremental Learning (O-FSCIL), based on a lightweight model consisting of a pretrained and metalearned feature extractor and an expandable explicit memory storing the class prototypes. The architecture is pretrained with a novel feature orthogonality regularization and metalearned with a multi-margin loss. For learning a new class, our approach extends the explicit memory with novel class prototypes, while the remaining architecture is kept frozen. This allows learning previously unseen classes based on only a few examples with one single pass (hence online). O-FSCIL obtains an average accuracy of 68.62% on the FSCIL CIFAR100 benchmark, achieving state-of-the-art results. Tailored for ultra-low-power platforms, we implement O-FSCIL on the 60 mW GAP9 microcontroller, demonstrating online learning capabilities within just 12 mJ per new class.
Authors: Walid El Maouaki, Taoufik Said, Mohamed Bennai
Abstract: This study addresses the urgent need for improved prostate cancer detection methods by harnessing the power of advanced technological solutions. We introduce the application of Quantum Support Vector Machine (QSVM) to this critical healthcare challenge, showcasing an enhancement in diagnostic performance over the classical Support Vector Machine (SVM) approach. Our study not only outlines the remarkable improvements in diagnostic performance made by QSVM over the classic SVM technique, but it delves into the advancements brought about by the quantum feature map architecture, which has been carefully identified and evaluated, ensuring it aligns seamlessly with the unique characteristics of our prostate cancer dataset. This architecture succeded in creating a distinct feature space, enabling the detection of complex, non-linear patterns in the data. The findings reveal not only a comparable accuracy with classical SVM ($92\%$) but also a $7.14\%$ increase in sensitivity and a notably high F1-Score ($93.33\%$). This study's important combination of quantum computing in medical diagnostics marks a pivotal step forward in cancer detection, offering promising implications for the future of healthcare technology.
Authors: Sierra Wyllie, Ilia Shumailov, Nicolas Papernot
Abstract: Model-induced distribution shifts (MIDS) occur as previous model outputs pollute new model training sets over generations of models. This is known as model collapse in the case of generative models, and performative prediction or unfairness feedback loops for supervised models. When a model induces a distribution shift, it also encodes its mistakes, biases, and unfairnesses into the ground truth of its data ecosystem. We introduce a framework that allows us to track multiple MIDS over many generations, finding that they can lead to loss in performance, fairness, and minoritized group representation, even in initially unbiased datasets. Despite these negative consequences, we identify how models might be used for positive, intentional, interventions in their data ecosystems, providing redress for historical discrimination through a framework called algorithmic reparation (AR). We simulate AR interventions by curating representative training batches for stochastic gradient descent to demonstrate how AR can improve upon the unfairnesses of models and data ecosystems subject to other MIDS. Our work takes an important step towards identifying, mitigating, and taking accountability for the unfair feedback loops enabled by the idea that ML systems are inherently neutral and objective.
Authors: Koichiro Yawata, Kai Fukami, Kunihiko Taira, Hiroya Nakao
Abstract: We present a phase autoencoder that encodes the asymptotic phase of a limit-cycle oscillator, a fundamental quantity characterizing its synchronization dynamics. This autoencoder is trained in such a way that its latent variables directly represent the asymptotic phase of the oscillator. The trained autoencoder can perform two functions without relying on the mathematical model of the oscillator: first, it can evaluate the asymptotic phase and phase sensitivity function of the oscillator; second, it can reconstruct the oscillator state on the limit cycle in the original space from the phase value as an input. Using several examples of limit-cycle oscillators, we demonstrate that the asymptotic phase and phase sensitivity function can be estimated only from time-series data by the trained autoencoder. We also present a simple method for globally synchronizing two oscillators as an application of the trained autoencoder.
Authors: Wenjian Sun, Linying Pan, Jingyu Xu, Weixiang Wan, Yong Wang
Abstract: Autonomous driving technology can improve traffic safety and reduce traffic accidents. In addition, it improves traffic flow, reduces congestion, saves energy and increases travel efficiency. In the relatively mature automatic driving technology, the automatic driving function is divided into several modules: perception, decision-making, planning and control, and a reasonable division of labor can improve the stability of the system. Therefore, autonomous vehicles need to have the ability to predict the trajectory of surrounding vehicles in order to make reasonable decision planning and safety measures to improve driving safety. By using deep learning method, a safety-sensitive deep learning model based on short term memory (LSTM) network is proposed. This model can alleviate the shortcomings of current automatic driving trajectory planning, and the output trajectory not only ensures high accuracy but also improves safety. The cell state simulation algorithm simulates the trackability of the trajectory generated by this model. The research results show that compared with the traditional model-based method, the trajectory prediction method based on LSTM network has obvious advantages in predicting the trajectory in the long time domain. The intention recognition module considering interactive information has higher prediction and accuracy, and the algorithm results show that the trajectory is very smooth based on the premise of safe prediction and efficient lane change. And autonomous vehicles can efficiently and safely complete lane changes.
Authors: Zeyuan Qu, Tiange Huang, Yuxin Ji, Yongjun Li
Abstract: Fall detection based on embedded sensor is a practical and popular research direction in recent years. In terms of a specific application: fall detection methods based upon physics sensors such as [gyroscope and accelerator] have been exploited using traditional hand crafted features and feed them in machine learning models like Markov chain or just threshold based classification methods. In this paper, we build a complete system named TSFallDetect including data receiving device based on embedded sensor, mobile deep-learning model deploying platform, and a simple server, which will be used to gather models and data for future expansion. On the other hand, we exploit the sequential deep-learning methods to address this falling motion prediction problem based on data collected by inertial and film pressure sensors. We make a empirical study based on existing datasets and our datasets collected from our system separately, which shows that the deep-learning model has more potential advantage than other traditional methods, and we proposed a new deep-learning model based on the time series data to predict the fall, and it may be superior to other sequential models in this particular field.
Authors: Anuj Abraham, Yi Zhang, Shitala Prasad
Abstract: A smart city solution toward future 6G network deployment allows small and medium sized enterprises (SMEs), industry, and government entities to connect with the infrastructures and play a crucial role in enhancing emergency preparedness with advanced sensors. The objective of this work is to propose a set of coordinated technological solutions to transform an existing emergency response system into an intelligent interactive system, thereby improving the public services and the quality of life for residents at home, on road, in hospitals, transport hubs, etc. In this context, we consider a city wide view from three different application scenes that are closely related to peoples daily life, to optimize the actions taken at relevant departments. Therefore, using artificial intelligence (AI) and machine learning (ML) techniques to enable the next generation connected vehicle experiences, we specifically focus on accidents happening in indoor households, urban roads, and at large public facilities. This smart interactive response system will benefit from advanced sensor fusion and AI by formulating a real time dynamic model.
Authors: Vaclav Voracek, Tomas Werner
Abstract: A popular approach to the MAP inference problem in graphical models is to minimize an upper bound obtained from a dual linear programming or Lagrangian relaxation by (block-)coordinate descent. Examples of such algorithms are max-sum diffusion and sequential tree-reweighted message passing. Convergence properties of these methods are currently not fully understood. They have been proved to converge to the set characterized by local consistency of active constraints, with unknown convergence rate; however, it was not clear if the iterates converge at all (to any single point). We prove a stronger result (which was conjectured before but never proved): the iterates converge to a fixed point of the algorithm. Moreover, we show that they achieve precision $\varepsilon>0$ in $\mathcal{O}(1/\varepsilon)$ iterations. We first prove this for a version of coordinate descent applied to a general piecewise-affine convex objective, using a novel proof technique. Then we demonstrate the generality of this approach by reducing some popular coordinate-descent algorithms to this problem. Finally we show that, in contrast to our main result, a similar version of coordinate descent applied to a constrained optimization problem need not converge.
Authors: Xuejing Zheng, Chao Yu
Abstract: In this paper, we study the cooperative Multi-Agent Reinforcement Learning (MARL) problems using Reward Machines (RMs) to specify the reward functions such that the prior knowledge of high-level events in a task can be leveraged to facilitate the learning efficiency. Unlike the existing work that RMs have been incorporated into MARL for task decomposition and policy learning in relatively simple domains or with an assumption of independencies among the agents, we present Multi-Agent Reinforcement Learning with a Hierarchy of RMs (MAHRM) that is capable of dealing with more complex scenarios when the events among agents can occur concurrently and the agents are highly interdependent. MAHRM exploits the relationship of high-level events to decompose a task into a hierarchy of simpler subtasks that are assigned to a small group of agents, so as to reduce the overall computational complexity. Experimental results in three cooperative MARL domains show that MAHRM outperforms other MARL methods using the same prior knowledge of high-level events.
Authors: Jun Xia, Shaorong Chen, Jingbo Zhou, Tianze Lin, Wenjie Du, Sizhe Liu, Stan Z. Li
Abstract: Tandem mass spectrometry has played a pivotal role in advancing proteomics, enabling the analysis of protein composition in biological samples. Despite the development of various deep learning methods for identifying amino acid sequences (peptides) responsible for observed spectra, challenges persist in \emph{de novo} peptide sequencing. Firstly, prior methods struggle to identify amino acids with post-translational modifications (PTMs) due to their lower frequency in training data compared to canonical amino acids, further resulting in decreased peptide-level identification precision. Secondly, diverse types of noise and missing peaks in mass spectra reduce the reliability of training data (peptide-spectrum matches, PSMs). To address these challenges, we propose AdaNovo, a novel framework that calculates conditional mutual information (CMI) between the spectrum and each amino acid/peptide, using CMI for adaptive model training. Extensive experiments demonstrate AdaNovo's state-of-the-art performance on a 9-species benchmark, where the peptides in the training set are almost completely disjoint from the peptides of the test sets. Moreover, AdaNovo excels in identifying amino acids with PTMs and exhibits robustness against data noise. The supplementary materials contain the official code.
Authors: Subhasree Bhattacharjee, Soumyadip Sarkar, Kunal Das, Bikramjit Sarkar
Abstract: In the emergent realm of quantum computing, the Variational Quantum Eigensolver (VQE) stands out as a promising algorithm for solving complex quantum problems, especially in the noisy intermediate-scale quantum (NISQ) era. However, the ubiquitous presence of noise in quantum devices often limits the accuracy and reliability of VQE outcomes. This research introduces a novel approach to ameliorate this challenge by utilizing neural networks for zero noise extrapolation (ZNE) in VQE computations. By employing the Qiskit framework, we crafted parameterized quantum circuits using the RY-RZ ansatz and examined their behavior under varying levels of depolarizing noise. Our investigations spanned from determining the expectation values of a Hamiltonian, defined as a tensor product of Z operators, under different noise intensities to extracting the ground state energy. To bridge the observed outcomes under noise with the ideal noise-free scenario, we trained a Feed Forward Neural Network on the error probabilities and their associated expectation values. Remarkably, our model proficiently predicted the VQE outcome under hypothetical noise-free conditions. By juxtaposing the simulation results with real quantum device executions, we unveiled the discrepancies induced by noise and showcased the efficacy of our neural network-based ZNE technique in rectifying them. This integrative approach not only paves the way for enhanced accuracy in VQE computations on NISQ devices but also underlines the immense potential of hybrid quantum-classical paradigms in circumventing the challenges posed by quantum noise. Through this research, we envision a future where quantum algorithms can be reliably executed on noisy devices, bringing us one step closer to realizing the full potential of quantum computing.
Authors: Carlo Santambrogio, Monica Pragliola, Alessandro Lanza, Marco Donatelli, Luca Calatroni
Abstract: We consider an unsupervised bilevel optimization strategy for learning regularization parameters in the context of imaging inverse problems in the presence of additive white Gaussian noise. Compared to supervised and semi-supervised metrics relying either on the prior knowledge of reference data and/or on some (partial) knowledge on the noise statistics, the proposed approach optimizes the whiteness of the residual between the observed data and the observation model with no need of ground-truth data.We validate the approach on standard Total Variation-regularized image deconvolution problems which show that the proposed quality metric provides estimates close to the mean-square error oracle and to discrepancy-based principles.
Authors: Juan Zou, Han Chu, Yizhang Xia, Junwen Xu, Yuan Liu, Zhanglu Hou
Abstract: The effectiveness of Evolutionary Neural Architecture Search (ENAS) is influenced by the design of the search space. Nevertheless, common methods including the global search space, scalable search space and hierarchical search space have certain limitations. Specifically, the global search space requires a significant amount of computational resources and time, the scalable search space sacrifices the diversity of network structures and the hierarchical search space increases the search cost in exchange for network diversity. To address above limitation, we propose a novel paradigm of searching neural network architectures and design the Multiple Population Alternate Evolution Neural Architecture Search (MPAE), which can achieve module diversity with a smaller search cost. MPAE converts the search space into L interconnected units and sequentially searches the units, then the above search of the entire network be cycled several times to reduce the impact of previous units on subsequent units. To accelerate the population evolution process, we also propose the the population migration mechanism establishes an excellent migration archive and transfers the excellent knowledge and experience in the migration archive to new populations. The proposed method requires only 0.3 GPU days to search a neural network on the CIFAR dataset and achieves the state-of-the-art results.
Authors: Joseph Bowles, Shahnawaz Ahmed, Maria Schuld
Abstract: Benchmarking models via classical simulations is one of the main ways to judge ideas in quantum machine learning before noise-free hardware is available. However, the huge impact of the experimental design on the results, the small scales within reach today, as well as narratives influenced by the commercialisation of quantum technologies make it difficult to gain robust insights. To facilitate better decision-making we develop an open-source package based on the PennyLane software framework and use it to conduct a large-scale study that systematically tests 12 popular quantum machine learning models on 6 binary classification tasks used to create 160 individual datasets. We find that overall, out-of-the-box classical machine learning models outperform the quantum classifiers. Moreover, removing entanglement from a quantum model often results in as good or better performance, suggesting that "quantumness" may not be the crucial ingredient for the small learning tasks considered here. Our benchmarks also unlock investigations beyond simplistic leaderboard comparisons, and we identify five important questions for quantum model design that follow from our results.
Authors: Philip Harris, Michael Kagan, Jeffrey Krupa, Benedikt Maier, Nathaniel Woodward
Abstract: Self-Supervised Learning (SSL) is at the core of training modern large machine learning models, providing a scheme for learning powerful representations that can be used in a variety of downstream tasks. However, SSL strategies must be adapted to the type of training data and downstream tasks required. We propose RS3L, a novel simulation-based SSL strategy that employs a method of re-simulation to drive data augmentation for contrastive learning. By intervening in the middle of the simulation process and re-running simulation components downstream of the intervention, we generate multiple realizations of an event, thus producing a set of augmentations covering all physics-driven variations available in the simulator. Using experiments from high-energy physics, we explore how this strategy may enable the development of a foundation model; we show how R3SL pre-training enables powerful performance in downstream tasks such as discrimination of a variety of objects and uncertainty mitigation. In addition to our results, we make the RS3L dataset publicly available for further studies on how to improve SSL strategies.
Authors: Shadab Ahamed, Natalia Dubljevic, Ingrid Bloise, Claire Gowdy, Patrick Martineau, Don Wilson, Carlos F. Uribe, Arman Rahmim, Fereshteh Yousefirizi
Abstract: Accurate detection and segmentation of diffuse large B-cell lymphoma (DLBCL) from PET images has important implications for estimation of total metabolic tumor volume, radiomics analysis, surgical intervention and radiotherapy. Manual segmentation of tumors in whole-body PET images is time-consuming, labor-intensive and operator-dependent. In this work, we develop and validate a fast and efficient three-step cascaded deep learning model for automated detection and segmentation of DLBCL tumors from PET images. As compared to a single end-to-end network for segmentation of tumors in whole-body PET images, our three-step model is more effective (improves 3D Dice score from 58.9% to 78.1%) since each of its specialized modules, namely the slice classifier, the tumor detector and the tumor segmentor, can be trained independently to a high degree of skill to carry out a specific task, rather than a single network with suboptimal performance on overall segmentation.
Authors: Shadab Ahamed, Yixi Xu, Ingrid Bloise, Joo H. O, Carlos F. Uribe, Rahul Dodhia, Juan L. Ferres, Arman Rahmim
Abstract: Automated slice classification is clinically relevant since it can be incorporated into medical image segmentation workflows as a preprocessing step that would flag slices with a higher probability of containing tumors, thereby directing physicians attention to the important slices. In this work, we train a ResNet-18 network to classify axial slices of lymphoma PET/CT images (collected from two institutions) depending on whether the slice intercepted a tumor (positive slice) in the 3D image or if the slice did not (negative slice). Various instances of the network were trained on 2D axial datasets created in different ways: (i) slice-level split and (ii) patient-level split; inputs of different types were used: (i) only PET slices and (ii) concatenated PET and CT slices; and different training strategies were employed: (i) center-aware (CAW) and (ii) center-agnostic (CAG). Model performances were compared using the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC), and various binary classification metrics. We observe and describe a performance overestimation in the case of slice-level split as compared to the patient-level split training. The model trained using patient-level split data with the network input containing only PET slices in the CAG training regime was the best performing/generalizing model on a majority of metrics. Our models were additionally more closely compared using the sensitivity metric on the positive slices from their respective test sets.
Authors: Nieves Crasto
Abstract: Object detection, a pivotal task in computer vision, is frequently hindered by dataset imbalances, particularly the under-explored issue of foreground-foreground class imbalance. This lack of attention to foreground-foreground class imbalance becomes even more pronounced in the context of single-stage detectors. This study introduces a benchmarking framework utilizing the YOLOv5 single-stage detector to address the problem of foreground-foreground class imbalance. We crafted a novel 10-class long-tailed dataset from the COCO dataset, termed COCO-ZIPF, tailored to reflect common real-world detection scenarios with a limited number of object classes. Against this backdrop, we scrutinized three established techniques: sampling, loss weighing, and data augmentation. Our comparative analysis reveals that sampling and loss reweighing methods, while shown to be beneficial in two-stage detector settings, do not translate as effectively in improving YOLOv5's performance on the COCO-ZIPF dataset. On the other hand, data augmentation methods, specifically mosaic and mixup, significantly enhance the model's mean Average Precision (mAP), by introducing more variability and complexity into the training data. (Code available: https://github.com/craston/object_detection_cib)
Authors: Keith Rush, Zachary Charles, Zachary Garrett
Abstract: We present FAX, a JAX-based library designed to support large-scale distributed and federated computations in both data center and cross-device applications. FAX leverages JAX's sharding mechanisms to enable native targeting of TPUs and state-of-the-art JAX runtimes, including Pathways. FAX embeds building blocks for federated computations as primitives in JAX. This enables three key benefits. First, FAX computations can be translated to XLA HLO. Second, FAX provides a full implementation of federated automatic differentiation, greatly simplifying the expression of federated computations. Last, FAX computations can be interpreted out to existing production cross-device federated compute systems. We show that FAX provides an easily programmable, performant, and scalable framework for federated computations in the data center. FAX is available at https://github.com/google-research/google-research/tree/master/fax .
URLs: https://github.com/google-research/google-research/tree/master/fax
Authors: Gabriel Toshio Hirokawa Higa, Joyce Katiuccia Medeiros Ramos Carvalho, Paolo Brito Pascoalini Zanoni, Gisele Braziliano de Andrade, Hemerson Pistori
Abstract: Brachycephaly, a conformation trait in some dog breeds, causes BOAS, a respiratory disorder that affects the health and welfare of the dogs with various symptoms. In this paper, a new annotated dataset composed of 190 images of bulldogs' nostrils is presented. Three degrees of stenosis are approximately equally represented in the dataset: mild, moderate and severe stenosis. The dataset also comprises a small quantity of non stenotic nostril images. To the best of our knowledge, this is the first image dataset addressing this problem. Furthermore, deep learning is investigated as an alternative to automatically infer stenosis degree using nostril images. In this work, several neural networks were tested: ResNet50, MobileNetV3, DenseNet201, SwinV2 and MaxViT. For this evaluation, the problem was modeled in two different ways: first, as a three-class classification problem (mild or open, moderate, and severe); second, as a binary classification problem, with severe stenosis as target. For the multiclass classification, a maximum median f-score of 53.77\% was achieved by the MobileNetV3. For binary classification, a maximum median f-score of 72.08\% has been reached by ResNet50, indicating that the problem is challenging but possibly tractable.
Authors: Alexandre de Oliveira Bezerra, Rodrigo Goncalves Mateus, Vanessa Ap. de Moraes Weber, Fabricio de Lima Weber, Yasmin Alves de Arruda, Rodrigo da Costa Gomes, Gabriel Toshio Hirokawa Higa, Hemerson Pistori
Abstract: Assessing the biotype of cattle through human visual inspection is a very common and important practice in precision cattle breeding. This paper presents the results of a correlation analysis between scores produced by humans for Nelore cattle and a variety of measurements that can be derived from images or other instruments. It also presents a study using the k-means algorithm to generate new ways of clustering a batch of cattle using the measurements that most correlate with the animal's body weight and visual scores.
Authors: Ali Abbasi, Ashkan Shahbazi, Hamed Pirsiavash, Soheil Kolouri
Abstract: The extensive amounts of data required for training deep neural networks pose significant challenges on storage and transmission fronts. Dataset distillation has emerged as a promising technique to condense the information of massive datasets into a much smaller yet representative set of synthetic samples. However, traditional dataset distillation approaches often struggle to scale effectively with high-resolution images and more complex architectures due to the limitations in bi-level optimization. Recently, several works have proposed exploiting knowledge distillation with decoupled optimization schemes to scale up dataset distillation. Although these methods effectively address the scalability issue, they rely on extensive image augmentations requiring the storage of soft labels for augmented images. In this paper, we introduce Dataset Distillation using Diffusion Models (D3M) as a novel paradigm for dataset distillation, leveraging recent advancements in generative text-to-image foundation models. Our approach utilizes textual inversion, a technique for fine-tuning text-to-image generative models, to create concise and informative representations for large datasets. By employing these learned text prompts, we can efficiently store and infer new samples for introducing data variability within a fixed memory budget. We show the effectiveness of our method through extensive experiments across various computer vision benchmark datasets with different memory budgets.
Authors: Shiliang Zuo
Abstract: This work studies the repeated principal-agent problem from an online learning perspective. The principal's goal is to learn the optimal contract that maximizes her utility through repeated interactions, without prior knowledge of the agent's type (i.e., the agent's cost and production functions). I study three different settings when the principal contracts with a $\textit{single}$ agent each round: 1. The agents are heterogeneous; 2. the agents are homogenous; 3. the principal interacts with the same agent and the agent is non-myopic. I present different approaches and techniques for designing learning algorithms in each setting. For heterogeneous agent types, I identify a condition that allows the problem to be reduced to Lipschitz bandits directly. For identical agents, I give a polynomial sample complexity scheme to learn the optimal contract based on inverse game theory. For strategic non-myopic agents, I design a low strategic-regret mechanism. Also, I identify a connection between linear contracts and posted-price auctions, showing the two can be reduced to one another, and give a regret lower bound on learning the optimal linear contract based on this observation. I also study a $\textit{team production}$ model. I identify a condition under which the principal's learning problem can be reformulated as solving a family of convex programs, thereby showing the optimal contract can be found efficiently.
Authors: Konstantinos Emmanouilidis, Ren\'e Vidal, Nicolas Loizou
Abstract: The Stochastic Extragradient (SEG) method is one of the most popular algorithms for solving finite-sum min-max optimization and variational inequality problems (VIPs) appearing in various machine learning tasks. However, existing convergence analyses of SEG focus on its with-replacement variants, while practical implementations of the method randomly reshuffle components and sequentially use them. Unlike the well-studied with-replacement variants, SEG with Random Reshuffling (SEG-RR) lacks established theoretical guarantees. In this work, we provide a convergence analysis of SEG-RR for three classes of VIPs: (i) strongly monotone, (ii) affine, and (iii) monotone. We derive conditions under which SEG-RR achieves a faster convergence rate than the uniform with-replacement sampling SEG. In the monotone setting, our analysis of SEG-RR guarantees convergence to an arbitrary accuracy without large batch sizes, a strong requirement needed in the classical with-replacement SEG. As a byproduct of our results, we provide convergence guarantees for Shuffle Once SEG (shuffles the data only at the beginning of the algorithm) and the Incremental Extragradient (does not shuffle the data). We supplement our analysis with experiments validating empirically the superior performance of SEG-RR over the classical with-replacement sampling SEG.
Authors: Weixin Liang, Zachary Izzo, Yaohui Zhang, Haley Lepp, Hancheng Cao, Xuandong Zhao, Lingjiao Chen, Haotian Ye, Sheng Liu, Zhi Huang, Daniel A. McFarland, James Y. Zou
Abstract: We present an approach for estimating the fraction of text in a large corpus which is likely to be substantially modified or produced by a large language model (LLM). Our maximum likelihood model leverages expert-written and AI-generated reference texts to accurately and efficiently examine real-world LLM-use at the corpus level. We apply this approach to a case study of scientific peer review in AI conferences that took place after the release of ChatGPT: ICLR 2024, NeurIPS 2023, CoRL 2023 and EMNLP 2023. Our results suggest that between 6.5% and 16.9% of text submitted as peer reviews to these conferences could have been substantially modified by LLMs, i.e. beyond spell-checking or minor writing updates. The circumstances in which generated text occurs offer insight into user behavior: the estimated fraction of LLM-generated text is higher in reviews which report lower confidence, were submitted close to the deadline, and from reviewers who are less likely to respond to author rebuttals. We also observe corpus-level trends in generated text which may be too subtle to detect at the individual level, and discuss the implications of such trends on peer review. We call for future interdisciplinary work to examine how LLM use is changing our information and knowledge practices.
Authors: W. Chango, R. Cerezo, M. Sanchez-Santillan, R. Azevedo, C. Romero
Abstract: The aim of this study was to predict university students' learning performance using different sources of data from an Intelligent Tutoring System. We collected and preprocessed data from 40 students from different multimodal sources: learning strategies from system logs, emotions from face recording videos, interaction zones from eye tracking, and test performance from final knowledge evaluation. Our objective was to test whether the prediction could be improved by using attribute selection and classification ensembles. We carried out three experiments by applying six classification algorithms to numerical and discretized preprocessed multimodal data. The results show that the best predictions were produced using ensembles and selecting the best attributes approach with numerical data.
Authors: Yinsong Wang, Yu Ding, Shahin Shahrampour
Abstract: Dynamic density estimation is ubiquitous in many applications, including computer vision and signal processing. One popular method to tackle this problem is the "sliding window" kernel density estimator. There exist various implementations of this method that use heuristically defined weight sequences for the observed data. The weight sequence, however, is a key aspect of the estimator affecting the tracking performance significantly. In this work, we study the exact mean integrated squared error (MISE) of "sliding window" Gaussian Kernel Density Estimators for evolving Gaussian densities. We provide a principled guide for choosing the optimal weight sequence by theoretically characterizing the exact MISE, which can be formulated as constrained quadratic programming. We present empirical evidence with synthetic datasets to show that our weighting scheme indeed improves the tracking performance compared to heuristic approaches.
Authors: Mike Timmerman, Aryan Patel, Tim Reinhart
Abstract: The paper presents a technique using reinforcement learning (RL) to adapt the control gains of a quadcopter controller. Specifically, we employed Proximal Policy Optimization (PPO) to train a policy which adapts the gains of a cascaded feedback controller in-flight. The primary goal of this controller is to minimize tracking error while following a specified trajectory. The paper's key objective is to analyze the effectiveness of the adaptive gain policy and compare it to the performance of a static gain control algorithm, where the Integral Squared Error and Integral Time Squared Error are used as metrics. The results show that the adaptive gain scheme achieves over 40$\%$ decrease in tracking error as compared to the static gain controller.
Authors: Erik Buchholz, Alsharif Abuadbba, Shuo Wang, Surya Nepal, Salil S. Kanhere
Abstract: While location trajectories represent a valuable data source for analyses and location-based services, they can reveal sensitive information, such as political and religious preferences. Differentially private publication mechanisms have been proposed to allow for analyses under rigorous privacy guarantees. However, the traditional protection schemes suffer from a limiting privacy-utility trade-off and are vulnerable to correlation and reconstruction attacks. Synthetic trajectory data generation and release represent a promising alternative to protection algorithms. While initial proposals achieve remarkable utility, they fail to provide rigorous privacy guarantees. This paper proposes a framework for designing a privacy-preserving trajectory publication approach by defining five design goals, particularly stressing the importance of choosing an appropriate Unit of Privacy. Based on this framework, we briefly discuss the existing trajectory protection approaches, emphasising their shortcomings. This work focuses on the systematisation of the state-of-the-art generative models for trajectories in the context of the proposed framework. We find that no existing solution satisfies all requirements. Thus, we perform an experimental study evaluating the applicability of six sequential generative models to the trajectory domain. Finally, we conclude that a generative trajectory model providing semantic guarantees remains an open research question and propose concrete next steps for future research.
Authors: Pulkit Pattnaik, Rishabh Maheshwary, Kelechi Ogueji, Vikas Yadav, Sathwik Tejaswi Madhusudhan
Abstract: Direct Preference Optimization (DPO) is an effective technique that leverages pairwise preference data (usually one chosen and rejected response pair per user prompt) to align LLMs to human preferences. In practice, multiple responses can exist for a given prompt with varying quality relative to each other. With availability of such quality ratings for multiple responses, we propose utilizing these responses to create multiple preference pairs for a given prompt. Our work focuses on systematically using the constructed multiple preference pair in DPO training via curriculum learning methodology. In particular, we order these multiple pairs of preference data from easy to hard (emulating curriculum training) according to various criteria. We show detailed comparisons of our proposed approach to the standard single-pair DPO setting. Our method, which we call Curry-DPO consistently shows increased performance gains on MTbench, Vicuna, WizardLM, and the UltraFeedback test set, highlighting its effectiveness. More specifically, Curry-DPO achieves a score of 7.43 on MT-bench with Zephy-7B model outperforming majority of existing LLMs with similar parameter size. Curry-DPO also achieves the highest adjusted win rates on Vicuna, WizardLM, and UltraFeedback test datasets (90.7%, 87.1%, and 87.9% respectively) in our experiments, with notable gains of upto 7.5% when compared to standard DPO technique.
Authors: Adam Villaflor, Brian Yang, Huangyuan Su, Katerina Fragkiadaki, John Dolan, Jeff Schneider
Abstract: Significant progress has been made in training multimodal trajectory forecasting models for autonomous driving. However, effectively integrating these models with downstream planners and model-based control approaches is still an open problem. Although these models have conventionally been evaluated for open-loop prediction, we show that they can be used to parameterize autoregressive closed-loop models without retraining. We consider recent trajectory prediction approaches which leverage learned anchor embeddings to predict multiple trajectories, finding that these anchor embeddings can parameterize discrete and distinct modes representing high-level driving behaviors. We propose to perform fully reactive closed-loop planning over these discrete latent modes, allowing us to tractably model the causal interactions between agents at each step. We validate our approach on a suite of more dynamic merging scenarios, finding that our approach avoids the $\textit{frozen robot problem}$ which is pervasive in conventional planners. Our approach also outperforms the previous state-of-the-art in CARLA on challenging dense traffic scenarios when evaluated at realistic speeds.
Authors: Chenyu You, Yifei Min, Weicheng Dai, Jasjeet S. Sekhon, Lawrence Staib, James S. Duncan
Abstract: Fine-tuning pre-trained vision-language models, like CLIP, has yielded success on diverse downstream tasks. However, several pain points persist for this paradigm: (i) directly tuning entire pre-trained models becomes both time-intensive and computationally costly. Additionally, these tuned models tend to become highly specialized, limiting their practicality for real-world deployment; (ii) recent studies indicate that pre-trained vision-language classifiers may overly depend on spurious features -- patterns that correlate with the target in training data, but are not related to the true labeling function; and (iii) existing studies on mitigating the reliance on spurious features, largely based on the assumption that we can identify such features, does not provide definitive assurance for real-world applications. As a piloting study, this work focuses on exploring mitigating the reliance on spurious features for CLIP without using any group annotation. To this end, we systematically study the existence of spurious correlation on CLIP and CILP+ERM. We first, following recent work on Deep Feature Reweighting (DFR), verify that last-layer retraining can greatly improve group robustness on pretrained CLIP. In view of them, we advocate a lightweight representation calibration method for fine-tuning CLIP, by first generating a calibration set using the pretrained CLIP, and then calibrating representations of samples within this set through contrastive learning, all without the need for group labels. Extensive experiments and in-depth visualizations on several benchmarks validate the effectiveness of our proposals, largely reducing reliance and significantly boosting the model generalization.
Authors: Linrui Dai, Rongzhao Zhang, Zhongzhen Huang, Xiaofan Zhang
Abstract: The annotation burden and extensive labor for gathering a large medical dataset with images and corresponding labels are rarely cost-effective and highly intimidating. This results in a lack of abundant training data that undermines downstream tasks and partially contributes to the challenge image analysis faces in the medical field. As a workaround, given the recent success of generative neural models, it is now possible to synthesize image datasets at a high fidelity guided by external constraints. This paper explores this possibility and presents \textbf{GuideGen}: a pipeline that jointly generates CT images and tissue masks for abdominal organs and colorectal cancer conditioned on a text prompt. Firstly, we introduce Volumetric Mask Sampler to fit the discrete distribution of mask labels and generate low-resolution 3D tissue masks. Secondly, our Conditional Image Generator autoregressively generates CT slices conditioned on a corresponding mask slice to incorporate both style information and anatomical guidance. This pipeline guarantees high fidelity and variability as well as exact alignment between generated CT volumes and tissue masks. Both qualitative and quantitative experiments on 3D abdominal CTs demonstrate a high performance of our proposed pipeline, thereby proving our method can serve as a dataset generator and provide potential benefits to downstream tasks. It is hoped that our work will offer a promising solution on the multimodality generation of CT and its anatomical mask. Our source code is publicly available at https://github.com/OvO1111/JointImageGeneration.
Authors: Yongjeong Oh, Jaehong Jo, Byonghyo Shim, Yo-Seb Jeon
Abstract: In this paper, we present a novel approach for joint activity detection (AD), channel estimation (CE), and data detection (DD) in uplink grant-free non-orthogonal multiple access (NOMA) systems. Our approach employs an iterative and parallel interference removal strategy inspired by parallel interference cancellation (PIC), enhanced with deep learning to jointly tackle the AD, CE, and DD problems. Based on this approach, we develop three PIC frameworks, each of which is designed for either coherent or non-coherence schemes. The first framework performs joint AD and CE using received pilot signals in the coherent scheme. Building upon this framework, the second framework utilizes both the received pilot and data signals for CE, further enhancing the performances of AD, CE, and DD in the coherent scheme. The third framework is designed to accommodate the non-coherent scheme involving a small number of data bits, which simultaneously performs AD and DD. Through joint loss functions and interference cancellation modules, our approach supports end-to-end training, contributing to enhanced performances of AD, CE, and DD for both coherent and non-coherent schemes. Simulation results demonstrate the superiority of our approach over traditional techniques, exhibiting enhanced performances of AD, CE, and DD while maintaining lower computational complexity.
Authors: Alexander Timans, Christoph-Nikolas Straehle, Kaspar Sakmann, Eric Nalisnick
Abstract: Quantifying a model's predictive uncertainty is essential for safety-critical applications such as autonomous driving. We consider quantifying such uncertainty for multi-object detection. In particular, we leverage conformal prediction to obtain uncertainty intervals with guaranteed coverage for object bounding boxes. One challenge in doing so is that bounding box predictions are conditioned on the object's class label. Thus, we develop a novel two-step conformal approach that propagates uncertainty in predicted class labels into the uncertainty intervals for the bounding boxes. This broadens the validity of our conformal coverage guarantees to include incorrectly classified objects, ensuring their usefulness when maximal safety assurances are required. Moreover, we investigate novel ensemble and quantile regression formulations to ensure the bounding box intervals are adaptive to object size, leading to a more balanced coverage across sizes. Validating our two-step approach on real-world datasets for 2D bounding box localization, we find that desired coverage levels are satisfied with actionably tight predictive uncertainty intervals.
Authors: Yutong Wang, Rishi Sonthalia, Wei Hu
Abstract: We study the generalization capability of nearly-interpolating linear regressors: $\boldsymbol{\beta}$'s whose training error $\tau$ is positive but small, i.e., below the noise floor. Under a random matrix theoretic assumption on the data distribution and an eigendecay assumption on the data covariance matrix $\boldsymbol{\Sigma}$, we demonstrate that any near-interpolator exhibits rapid norm growth: for $\tau$ fixed, $\boldsymbol{\beta}$ has squared $\ell_2$-norm $\mathbb{E}[\|{\boldsymbol{\beta}}\|_{2}^{2}] = \Omega(n^{\alpha})$ where $n$ is the number of samples and $\alpha >1$ is the exponent of the eigendecay, i.e., $\lambda_i(\boldsymbol{\Sigma}) \sim i^{-\alpha}$. This implies that existing data-independent norm-based bounds are necessarily loose. On the other hand, in the same regime we precisely characterize the asymptotic trade-off between interpolation and generalization. Our characterization reveals that larger norm scaling exponents $\alpha$ correspond to worse trade-offs between interpolation and generalization. We verify empirically that a similar phenomenon holds for nearly-interpolating shallow neural networks.
Authors: Kexin Li
Abstract: Iteratively reweighted L1 (IRL1) algorithm is a common algorithm for solving sparse optimization problems with nonconvex and nonsmooth regularization. The development of its acceleration algorithm, often employing Nesterov acceleration, has sparked significant interest. Nevertheless, the convergence and complexity analysis of these acceleration algorithms consistently poses substantial challenges. Recently, Anderson acceleration has gained prominence owing to its exceptional performance for speeding up fixed-point iteration, with numerous recent studies applying it to gradient-based algorithms. Motivated by the powerful impact of Anderson acceleration, we propose an Anderson-accelerated IRL1 algorithm and establish its local linear convergence rate. We extend this convergence result, typically observed in smooth settings, to a nonsmooth scenario. Importantly, our theoretical results do not depend on the Kurdyka-Lojasiewicz condition, a necessary condition in existing Nesterov acceleration-based algorithms. Furthermore, to ensure global convergence, we introduce a globally convergent Anderson accelerated IRL1 algorithm by incorporating a classical nonmonotone line search condition. Experimental results indicate that our algorithm outperforms existing Nesterov acceleration-based algorithms.
Authors: Zhiyu Chen, Yu Li, Suochao Zhang, Jingbo Zhou, Jiwen Zhou, Chenfu Bao, Dianhai Yu
Abstract: As Large Language Models (LLMs) gain great success in real-world applications, an increasing number of users are seeking to develop and deploy their customized LLMs through cloud services. Nonetheless, in some specific domains, there are still concerns regarding cost and trade-offs between privacy issues and accuracy. In this study, we introduce a cost-effective and self-adaptive LLM shaking tuning and recovery mechanism, named CypherTalk. With carefully designed horizontal and vertical shaking operators, we can achieve comparable accuracy results with SOTA privacy-preserving LLM schemes using Cryptography-based or Differential Privacy-based methods. Experiments also show that with the CypherTalk framework, users can achieve reliable accuracy when using optimized shaking operator settings. To our best knowledge, this is the first work that considers cost, and trade-off between model utility and privacy in LLM scenarios.
Authors: Hongkang Li, Shuai Zhang, Yihua Zhang, Meng Wang, Sijia Liu, Pin-Yu Chen
Abstract: Group imbalance has been a known problem in empirical risk minimization (ERM), where the achieved high average accuracy is accompanied by low accuracy in a minority group. Despite algorithmic efforts to improve the minority group accuracy, a theoretical generalization analysis of ERM on individual groups remains elusive. By formulating the group imbalance problem with the Gaussian Mixture Model, this paper quantifies the impact of individual groups on the sample complexity, the convergence rate, and the average and group-level testing performance. Although our theoretical framework is centered on binary classification using a one-hidden-layer neural network, to the best of our knowledge, we provide the first theoretical analysis of the group-level generalization of ERM in addition to the commonly studied average generalization performance. Sample insights of our theoretical results include that when all group-level co-variance is in the medium regime and all mean are close to zero, the learning performance is most desirable in the sense of a small sample complexity, a fast training rate, and a high average and group-level testing accuracy. Moreover, we show that increasing the fraction of the minority group in the training data does not necessarily improve the generalization performance of the minority group. Our theoretical results are validated on both synthetic and empirical datasets, such as CelebA and CIFAR-10 in image classification.
Authors: Dong Shu, Tianle Chen, Mingyu Jin, Yiting Zhang, Mengnan Du, Yongfeng Zhang
Abstract: The task of predicting multiple links within knowledge graphs (KGs) stands as a challenge in the field of knowledge graph analysis, a challenge increasingly resolvable due to advancements in natural language processing (NLP) and KG embedding techniques. This paper introduces a novel methodology, the Knowledge Graph Large Language Model Framework (KG-LLM), which leverages pivotal NLP paradigms, including chain-of-thought (CoT) prompting and in-context learning (ICL), to enhance multi-hop link prediction in KGs. By converting the KG to a CoT prompt, our framework is designed to discern and learn the latent representations of entities and their interrelations. To show the efficacy of the KG-LLM Framework, we fine-tune three leading Large Language Models (LLMs) within this framework, employing both non-ICL and ICL tasks for a comprehensive evaluation. Further, we explore the framework's potential to provide LLMs with zero-shot capabilities for handling previously unseen prompts. Our experimental findings discover that integrating ICL and CoT not only augments the performance of our approach but also significantly boosts the models' generalization capacity, thereby ensuring more precise predictions in unfamiliar scenarios.
Authors: Megan A. Witherow, Crystal Butler, Winston J. Shields, Furkan Ilgin, Norou Diawara, Janice Keener, John W. Harrington, Khan M. Iftekharuddin
Abstract: Customizable 3D avatar-based facial expression stimuli may improve user engagement in behavioral biomarker discovery and therapeutic intervention for autism, Alzheimer's disease, facial palsy, and more. However, there is a lack of customizable avatar-based stimuli with Facial Action Coding System (FACS) action unit (AU) labels. Therefore, this study focuses on (1) FACS-labeled, customizable avatar-based expression stimuli for maintaining subjects' engagement, (2) learning-based measurements that quantify subjects' facial responses to such stimuli, and (3) validation of constructs represented by stimulus-measurement pairs. We propose Customizable Avatars with Dynamic Facial Action Coded Expressions (CADyFACE) labeled with AUs by a certified FACS expert. To measure subjects' AUs in response to CADyFACE, we propose a novel Beta-guided Correlation and Multi-task Expression learning neural network (BeCoME-Net) for multi-label AU detection. The beta-guided correlation loss encourages feature correlation with AUs while discouraging correlation with subject identities for improved generalization. We train BeCoME-Net for unilateral and bilateral AU detection and compare with state-of-the-art approaches. To assess construct validity of CADyFACE and BeCoME-Net, twenty healthy adult volunteers complete expression recognition and mimicry tasks in an online feasibility study while webcam-based eye-tracking and video are collected. We test validity of multiple constructs, including face preference during recognition and AUs during mimicry.
Authors: Eric Lei, Hamed Hassani, Shirin Saeedi Bidokhti
Abstract: Neural compression has brought tremendous progress in designing lossy compressors with good rate-distortion (RD) performance at low complexity. Thus far, neural compression design involves transforming the source to a latent vector, which is then rounded to integers and entropy coded. While this approach has been shown to be optimal in a one-shot sense on certain sources, we show that it is highly sub-optimal on i.i.d. sequences, and in fact always recovers scalar quantization of the original source sequence. We demonstrate that the sub-optimality is due to the choice of quantization scheme in the latent space, and not the transform design. By employing lattice quantization instead of scalar quantization in the latent space, we demonstrate that Lattice Transform Coding (LTC) is able to recover optimal vector quantization at various dimensions and approach the asymptotically-achievable rate-distortion function at reasonable complexity. On general vector sources, LTC improves upon standard neural compressors in one-shot coding performance. LTC also enables neural compressors that perform block coding on i.i.d. vector sources, which yields coding gain over optimal one-shot coding.
Authors: Hengyuan Zhang, Zitao Liu, Chenming Shang, Dawei Li, Yong Jiang
Abstract: Knowledge tracing (KT) plays a crucial role in predicting students' future performance by analyzing their historical learning processes. Deep neural networks (DNNs) have shown great potential in solving the KT problem. However, there still exist some important challenges when applying deep learning techniques to model the KT process. The first challenge lies in taking the individual information of the question into modeling. This is crucial because, despite questions sharing the same knowledge component (KC), students' knowledge acquisition on homogeneous questions can vary significantly. The second challenge lies in interpreting the prediction results from existing deep learning-based KT models. In real-world applications, while it may not be necessary to have complete transparency and interpretability of the model parameters, it is crucial to present the model's prediction results in a manner that teachers find interpretable. This makes teachers accept the rationale behind the prediction results and utilize them to design teaching activities and tailored learning strategies for students. However, the inherent black-box nature of deep learning techniques often poses a hurdle for teachers to fully embrace the model's prediction results. To address these challenges, we propose a Question-centric Multi-experts Contrastive Learning framework for KT called Q-MCKT.
Authors: Mark D. McDonnell, Dong Gong, Ehsan Abbasnejad, Anton van den Hengel
Abstract: Continual learning requires a model to adapt to ongoing changes in the data distribution, and often to the set of tasks to be performed. It is rare, however, that the data and task changes are completely unpredictable. Given a description of an overarching goal or data theme, which we call a realm, humans can often guess what concepts are associated with it. We show here that the combination of a large language model and an image generation model can similarly provide useful premonitions as to how a continual learning challenge might develop over time. We use the large language model to generate text descriptions of semantically related classes that might potentially appear in the data stream in future. These descriptions are then rendered using Stable Diffusion to generate new labelled image samples. The resulting synthetic dataset is employed for supervised pre-training, but is discarded prior to commencing continual learning, along with the pre-training classification head. We find that the backbone of our pre-trained networks can learn representations useful for the downstream continual learning problem, thus becoming a valuable input to any existing continual learning method. Although there are complexities arising from the domain gap between real and synthetic images, we show that pre-training models in this manner improves multiple Class Incremenal Learning (CIL) methods on fine-grained image classification benchmarks. Supporting code can be found at https://github.com/cl-premonition/premonition.
Authors: Jonghyun Lee, Dahuin Jung, Saehyung Lee, Junsung Park, Juhyeon Shin, Uiwon Hwang, Sungroh Yoon
Abstract: Test-time adaptation (TTA) fine-tunes pre-trained deep neural networks for unseen test data. The primary challenge of TTA is limited access to the entire test dataset during online updates, causing error accumulation. To mitigate it, TTA methods have utilized the model output's entropy as a confidence metric that aims to determine which samples have a lower likelihood of causing error. Through experimental studies, however, we observed the unreliability of entropy as a confidence metric for TTA under biased scenarios and theoretically revealed that it stems from the neglect of the influence of latent disentangled factors of data on predictions. Building upon these findings, we introduce a novel TTA method named Destroy Your Object (DeYO), which leverages a newly proposed confidence metric named Pseudo-Label Probability Difference (PLPD). PLPD quantifies the influence of the shape of an object on prediction by measuring the difference between predictions before and after applying an object-destructive transformation. DeYO consists of sample selection and sample weighting, which employ entropy and PLPD concurrently. For robust adaptation, DeYO prioritizes samples that dominantly incorporate shape information when making predictions. Our extensive experiments demonstrate the consistent superiority of DeYO over baseline methods across various scenarios, including biased and wild. Project page is publicly available at https://whitesnowdrop.github.io/DeYO/.
Authors: Xin Wang, Yu Zheng, Zhongwei Wan, Mi Zhang
Abstract: The advancements in Large Language Models (LLMs) have been hindered by their substantial sizes, which necessitate LLM compression methods for practical deployment. Singular Value Decomposition (SVD) offers a promising solution for LLM compression. However, state-of-the-art SVD-based LLM compression methods have two key limitations: truncating smaller singular values may lead to higher compression loss, and the lack of update on the remaining model parameters after SVD truncation. In this work, we propose SVD-LLM, a new SVD-based LLM compression method that addresses the limitations of existing methods. SVD-LLM incorporates a truncation-aware data whitening strategy to ensure a direct mapping between singular values and compression loss. Moreover, SVD-LLM adopts a layer-wise closed-form model parameter update strategy to compensate for accuracy degradation caused by SVD truncation. We evaluate SVD-LLM on a total of 11 datasets and seven models from three different LLM families at four different scales. Our results demonstrate the superiority of SVD-LLM over state-of-the-arts, especially at high model compression ratios. The source code is available at https://github.com/AIoT-MLSys-Lab/SVD-LLM.
Authors: Yu Yang, Siddhartha Mishra, Jeffrey N Chiang, Baharan Mirzasoleiman
Abstract: Despite the effectiveness of data selection for large language models (LLMs) during pretraining and instruction fine-tuning phases, improving data efficiency in supervised fine-tuning (SFT) for specialized domains poses significant challenges due to the complexity of fine-tuning data. To bridge this gap, we introduce an effective and scalable data selection method for SFT, SmallToLarge (S2L), which leverages training trajectories from small models to guide the data selection for larger models. We demonstrate through extensive experiments that S2L significantly improves data efficiency in SFT for mathematical problem-solving, reducing the training data to just 11% of the original MathInstruct dataset (Yue et al., 2023) to match full dataset performance while outperforming state-of-the-art data selection algorithms by an average of 4.7% across 6 in- and out-domain evaluation datasets. Remarkably, selecting only 50K data for SFT, S2L achieves a 32.7% accuracy on the most challenging MATH (Hendrycks et al., 2021) benchmark, improving Phi-2 (Li et al., 2023b) by 16.6%. In clinical text summarization on the MIMIC-III dataset (Johnson et al., 2016), S2L again outperforms training on the full dataset using only 50% of the data. Notably, S2L can perform data selection using a reference model 40x smaller than the target model, proportionally reducing the cost of data selection.
Authors: Zeyu Li, Kangxiang Qin, Yong He, Wang Zhou, Xinsheng Zhang
Abstract: Transfer learning has aroused great interest in the statistical community. In this article, we focus on knowledge transfer for unsupervised learning tasks in contrast to the supervised learning tasks in the literature. Given the transferable source populations, we propose a two-step transfer learning algorithm to extract useful information from multiple source principal component analysis (PCA) studies, thereby enhancing estimation accuracy for the target PCA task. In the first step, we integrate the shared subspace information across multiple studies by a proposed method named as Grassmannian barycenter, instead of directly performing PCA on the pooled dataset. The proposed Grassmannian barycenter method enjoys robustness and computational advantages in more general cases. Then the resulting estimator for the shared subspace from the first step is further utilized to estimate the target private subspace in the second step. Our theoretical analysis credits the gain of knowledge transfer between PCA studies to the enlarged eigenvalue gap, which is different from the existing supervised transfer learning tasks where sparsity plays the central role. In addition, we prove that the bilinear forms of the empirical spectral projectors have asymptotic normality under weaker eigenvalue gap conditions after knowledge transfer. When the set of informativesources is unknown, we endow our algorithm with the capability of useful dataset selection by solving a rectified optimization problem on the Grassmann manifold, which in turn leads to a computationally friendly rectified Grassmannian K-means procedure. In the end, extensive numerical simulation results and a real data case concerning activity recognition are reported to support our theoretical claims and to illustrate the empirical usefulness of the proposed transfer learning methods.
Authors: Jannes Nys, Gabriel Pescia, Giuseppe Carleo
Abstract: Describing the dynamics of many-electron quantum systems is crucial for applications such as predicting electronic structures in quantum chemistry, the properties of condensed matter systems, and the behaviors of complex materials. However, the real-time evolution of non-equilibrium quantum electronic systems poses a significant challenge for theoretical and computational approaches, due to the system's exploration of a vast configuration space. This work introduces a variational approach for fermionic time-dependent wave functions, surpassing mean-field approximations by capturing many-body correlations. The proposed methodology involves parameterizing the time-evolving quantum state, enabling the approximation of the state's evolution. To account for electron correlations, we employ time-dependent Jastrow factors and backflow transformations. We also show that we can incorporate neural networks to parameterize these functions. The time-dependent variational Monte Carlo technique is employed to efficiently compute the optimal time-dependent parameters. The approach is demonstrated in three distinct systems: the solvable harmonic interaction model, the dynamics of a diatomic molecule in intense laser fields, and a quenched quantum dot. In all cases, we show clear signatures of many-body correlations in the dynamics not captured by mean-field methods. The results showcase the ability of our variational approach to accurately capture the time evolution of quantum states, providing insight into the quantum dynamics of interacting electronic systems, beyond the capabilities of mean-field.
Authors: Henrik H\"aggstr\"om, Pedro L. C. Rodrigues, Geoffroy Oudoumanessah, Florence Forbes, Umberto Picchini
Abstract: Bayesian inference for complex models with an intractable likelihood can be tackled using algorithms performing many calls to computer simulators. These approaches are collectively known as "simulation-based inference" (SBI). Recent SBI methods have made use of neural networks (NN) to provide approximate, yet expressive constructs for the unavailable likelihood function and the posterior distribution. However, they do not generally achieve an optimal trade-off between accuracy and computational demand. In this work, we propose an alternative that provides both approximations to the likelihood and the posterior distribution, using structured mixtures of probability distributions. Our approach produces accurate posterior inference when compared to state-of-the-art NN-based SBI methods, while exhibiting a much smaller computational footprint. We illustrate our results on several benchmark models from the SBI literature.
Authors: Marco Chilese, Richard Mitev, Meni Orenbach, Robert Thorburn, Ahmad Atamli, Ahmad-Reza Sadeghi
Abstract: Control-Flow Attestation (CFA) is a security service that allows an entity (verifier) to verify the integrity of code execution on a remote computer system (prover). Existing CFA schemes suffer from impractical assumptions, such as requiring access to the prover's internal state (e.g., memory or code), the complete Control-Flow Graph (CFG) of the prover's software, large sets of measurements, or tailor-made hardware. Moreover, current CFA schemes are inadequate for attesting embedded systems due to their high computational overhead and resource usage. In this paper, we overcome the limitations of existing CFA schemes for embedded devices by introducing RAGE, a novel, lightweight CFA approach with minimal requirements. RAGE can detect Code Reuse Attacks (CRA), including control- and non-control-data attacks. It efficiently extracts features from one execution trace and leverages Unsupervised Graph Neural Networks (GNNs) to identify deviations from benign executions. The core intuition behind RAGE is to exploit the correspondence between execution trace, execution graph, and execution embeddings to eliminate the unrealistic requirement of having access to a complete CFG. We evaluate RAGE on embedded benchmarks and demonstrate that (i) it detects 40 real-world attacks on embedded software; (ii) Further, we stress our scheme with synthetic return-oriented programming (ROP) and data-oriented programming (DOP) attacks on the real-world embedded software benchmark Embench, achieving 98.03% (ROP) and 91.01% (DOP) F1-Score while maintaining a low False Positive Rate of 3.19%; (iii) Additionally, we evaluate RAGE on OpenSSL, used by millions of devices and achieve 97.49% and 84.42% F1-Score for ROP and DOP attack detection, with an FPR of 5.47%.
Authors: Lucas de Lara (UT3, IMT), Mathis Deronzier (UT3, IMT), Alberto Gonz\'alez-Sanz (UT3, IMT), Virgile Foy (UT3, IMT)
Abstract: The push-forward operation enables one to redistribute a probability measure through a deterministic map. It plays a key role in statistics and optimization: many learning problems (notably from optimal transport, generative modeling, and algorithmic fairness) include constraints or penalties framed as push-forward conditions on the model. However, the literature lacks general theoretical insights on the (non)convexity of such constraints and its consequences on the associated learning problems. This paper aims at filling this gap. In a first part, we provide a range of sufficient and necessary conditions for the (non)convexity of two sets of functions: the maps transporting one probability measure to another; the maps inducing equal output distributions across distinct probability measures. This highlights that for most probability measures, these push-forward constraints are not convex. In a second time, we show how this result implies critical limitations on the design of convex optimization problems for learning generative models or group-fair predictors. This work will hopefully help researchers and practitioners have a better understanding of the critical impact of push-forward conditions onto convexity.
Authors: Andreas Damianou, Francesco Fabbri, Paul Gigioli, Marco De Nadai, Alice Wang, Enrico Palumbo, Mounia Lalmas
Abstract: In the realm of personalization, integrating diverse information sources such as consumption signals and content-based representations is becoming increasingly critical to build state-of-the-art solutions. In this regard, two of the biggest trends in research around this subject are Graph Neural Networks (GNNs) and Foundation Models (FMs). While GNNs emerged as a popular solution in industry for powering personalization at scale, FMs have only recently caught attention for their promising performance in personalization tasks like ranking and retrieval. In this paper, we present a graph-based foundation modeling approach tailored to personalization. Central to this approach is a Heterogeneous GNN (HGNN) designed to capture multi-hop content and consumption relationships across a range of recommendable item types. To ensure the generality required from a Foundation Model, we employ a Large Language Model (LLM) text-based featurization of nodes that accommodates all item types, and construct the graph using co-interaction signals, which inherently transcend content specificity. To facilitate practical generalization, we further couple the HGNN with an adaptation mechanism based on a two-tower (2T) architecture, which also operates agnostically to content type. This multi-stage approach ensures high scalability; while the HGNN produces general purpose embeddings, the 2T component models in a continuous space the sheer size of user-item interaction data. Our comprehensive approach has been rigorously tested and proven effective in delivering recommendations across a diverse array of products within a real-world, industrial audio streaming platform.
Authors: Janina Schreiber, Pau Batlle, Damar Wicaksono, Michael Hecht
Abstract: We introduce a surrogate-based black-box optimization method, termed Polynomial-model-based optimization (PMBO). The algorithm alternates polynomial approximation with Bayesian optimization steps, using Gaussian processes to model the error between the objective and its polynomial fit. We describe the algorithmic design of PMBO and compare the results of the performance of PMBO with several optimization methods for a set of analytic test functions. The results show that PMBO outperforms the classic Bayesian optimization and is robust with respect to the choice of its correlation function family and its hyper-parameter setting, which, on the contrary, need to be carefully tuned in classic Bayesian optimization. Remarkably, PMBO performs comparably with state-of-the-art evolutionary algorithms such as the Covariance Matrix Adaptation -- Evolution Strategy (CMA-ES). This finding suggests that PMBO emerges as the pivotal choice among surrogate-based optimization methods when addressing low-dimensional optimization problems. Hereby, the simple nature of polynomials opens the opportunity for interpretation and analysis of the inferred surrogate model, providing a macroscopic perspective on the landscape of the objective function.
Authors: Fernando Diaz-Diaz, Ernesto Estrada
Abstract: Signed graphs are an emergent way of representing data in a variety of contexts were conflicting interactions exist. These include data from biological, ecological, and social systems. Here we propose the concept of communicability geometry for signed graphs, proving that metrics in this space, such as the communicability distance and angles, are Euclidean and spherical. We then apply these metrics to solve several problems in data analysis of signed graphs in a unified way. They include the partitioning of signed graphs, dimensionality reduction, finding hierarchies of alliances in signed networks as well as the quantification of the degree of polarization between the existing factions in systems represented by this type of graphs.
Authors: Philip W. Livermore, Leyuan Wu, Longwei Chen, Sjoerd A. L. de Ridder
Abstract: Magnetic sounding using data collected from the Juno mission can be used to provide constraints on Jupiter's interior. However, inwards continuation of reconstructions assuming zero electrical conductivity and a representation in spherical harmonics are limited by the enhancement of noise at small scales. In this paper we describe new reconstructions of Jupiter's internal magnetic field based on physics-informed neural networks and either the first 33 (PINN33) or the first 50 (PINN50) of Juno's orbits. The method can resolve local structures, and allows for weak ambient electrical currents. Compared with other methods, our reconstructions of Jupiter's magnetic field both on and above the surface are similar, and we achieve a similar fit to the Juno data. However, our models are not hampered by noise at depth, and so offer a much clearer picture of the interior structure. We estimate that the dynamo boundary is at a fractional radius of 0.8. At this depth, the magnetic field is arranged into longitudinal bands, and the great blue spot appears to be rooted in neighbouring structures of oppositely signed flux.
Authors: Yingjie Zhao, Zian Zhang, Zhiping Xu
Abstract: The strength of materials, like many problems in the natural sciences, spans multiple length and time scales, and the solution has to balance accuracy and performance. Peierls stress is one of the central concepts in crystal plasticity that measures the strength through the resistance of a dislocation to plastic flow. The determination of Peierls stress involves a multiscale nature depending on both elastic lattice responses and the energy landscape of crystal slips. Material screening by strength via the Peierls stress from first-principles calculations is computationally intractable for the nonlocal characteristics of dislocations, and not included in the state-of-the-art computational material databases. In this work, we propose a physics-transfer framework to learn the physics of crystal plasticity from empirical atomistic simulations and then predict the Peierls stress from chemically accurate density functional theory-based calculations of material parameters. Notably, the strengths of single-crystalline metals can be predicted from a few single-point calculations for the deformed lattice and on the {\gamma} surface, allowing efficient, high-throughput screening for material discovery. Uncertainty quantification is carried out to assess the accuracy of models and sources of errors, showing reduced physical and system uncertainties in the predictions by elevating the fidelity of training models. This physics-transfer framework can be generalized to other problems facing the accuracy-performance dilemma, by harnessing the hierarchy of physics in the multiscale models of materials science.
Authors: Julian Suk, Baris Imre, Jelmer M. Wolterink
Abstract: Many anatomical structures can be described by surface or volume meshes. Machine learning is a promising tool to extract information from these 3D models. However, high-fidelity meshes often contain hundreds of thousands of vertices, which creates unique challenges in building deep neural network architectures. Furthermore, patient-specific meshes may not be canonically aligned which limits the generalisation of machine learning algorithms. We propose LaB-GATr, a transfomer neural network with geometric tokenisation that can effectively learn with large-scale (bio-)medical surface and volume meshes through sequence compression and interpolation. Our method extends the recently proposed geometric algebra transformer (GATr) and thus respects all Euclidean symmetries, i.e. rotation, translation and reflection, effectively mitigating the problem of canonical alignment between patients. LaB-GATr achieves state-of-the-art results on three tasks in cardiovascular hemodynamics modelling and neurodevelopmental phenotype prediction, featuring meshes of up to 200,000 vertices. Our results demonstrate that LaB-GATr is a powerful architecture for learning with high-fidelity meshes which has the potential to enable interesting downstream applications. Our implementation is publicly available.
Authors: Quoc-Vinh Lai-Dang
Abstract: This survey explores the adaptation of visual transformer models in Autonomous Driving, a transition inspired by their success in Natural Language Processing. Surpassing traditional Recurrent Neural Networks in tasks like sequential image processing and outperforming Convolutional Neural Networks in global context capture, as evidenced in complex scene recognition, Transformers are gaining traction in computer vision. These capabilities are crucial in Autonomous Driving for real-time, dynamic visual scene processing. Our survey provides a comprehensive overview of Vision Transformer applications in Autonomous Driving, focusing on foundational concepts such as self-attention, multi-head attention, and encoder-decoder architecture. We cover applications in object detection, segmentation, pedestrian detection, lane detection, and more, comparing their architectural merits and limitations. The survey concludes with future research directions, highlighting the growing role of Vision Transformers in Autonomous Driving.
Authors: Byeonghwi Kim, Minhyuk Seo, Jonghyun Choi
Abstract: In learning an embodied agent executing daily tasks via language directives, the literature largely assumes that the agent learns all training data at the beginning. We argue that such a learning scenario is less realistic since a robotic agent is supposed to learn the world continuously as it explores and perceives it. To take a step towards a more realistic embodied agent learning scenario, we propose two continual learning setups for embodied agents; learning new behaviors (Behavior Incremental Learning, Behavior-IL) and new environments (Environment Incremental Learning, Environment-IL) For the tasks, previous 'data prior' based continual learning methods maintain logits for the past tasks. However, the stored information is often insufficiently learned information and requires task boundary information, which might not always be available. Here, we propose to update them based on confidence scores without task boundary information during training (i.e., task-free) in a moving average fashion, named Confidence-Aware Moving Average (CAMA). In the proposed Behavior-IL and Environment-IL setups, our simple CAMA outperforms prior state of the art in our empirical validations by noticeable margins. The project page including codes is https://github.com/snumprlab/cl-alfred.
Authors: Jiuding Yang, Hui Liu, Weidong Guo, Zhuwei Rao, Yu Xu, Di Niu
Abstract: Ensuring factual consistency between the summary and the original document is paramount in summarization tasks. Consequently, considerable effort has been dedicated to detecting inconsistencies. With the advent of Large Language Models (LLMs), recent studies have begun to leverage their advanced language understanding capabilities for inconsistency detection. However, early attempts have shown that LLMs underperform traditional models due to their limited ability to follow instructions and the absence of an effective detection methodology. In this study, we reassess summary inconsistency detection with LLMs, comparing the performances of GPT-3.5 and GPT-4. To advance research in LLM-based inconsistency detection, we propose SIFiD (Summary Inconsistency Detection with Filtered Document) that identify key sentences within documents by either employing natural language inference or measuring semantic similarity between summaries and documents.
Authors: Huijie Tang, Federico Berto, Jinkyoo Park
Abstract: Multi-Agent Reinforcement Learning (MARL) based Multi-Agent Path Finding (MAPF) has recently gained attention due to its efficiency and scalability. Several MARL-MAPF methods choose to use communication to enrich the information one agent can perceive. However, existing works still struggle in structured environments with high obstacle density and a high number of agents. To further improve the performance of the communication-based MARL-MAPF solvers, we propose a new method, Ensembling Prioritized Hybrid Policies (EPH). We first propose a selective communication block to gather richer information for better agent coordination within multi-agent environments and train the model with a Q-learning-based algorithm. We further introduce three advanced inference strategies aimed at bolstering performance during the execution phase. First, we hybridize the neural policy with single-agent expert guidance for navigating conflict-free zones. Secondly, we propose Q value-based methods for prioritized resolution of conflicts as well as deadlock situations. Finally, we introduce a robust ensemble method that can efficiently collect the best out of multiple possible solutions. We empirically evaluate EPH in complex multi-agent environments and demonstrate competitive performance against state-of-the-art neural methods for MAPF.
Authors: Miguel Perez, Selin Aydin, Horst Lichter
Abstract: Jupyter Notebook is an interactive development environment commonly used for rapid experimentation of machine learning (ML) solutions. Describing the ML activities performed along code cells improves the readability and understanding of Notebooks. Manual annotation of code cells is time-consuming and error-prone. Therefore, tools have been developed that classify the cells of a notebook concerning the ML activity performed in them. However, the current tools are not flexible, as they work based on look-up tables that have been created, which map function calls of commonly used ML libraries to ML activities. These tables must be manually adjusted to account for new or changed libraries. This paper presents a more flexible approach to cell classification based on a hybrid classification approach that combines a rule-based and a decision tree classifier. We discuss the design rationales and describe the developed classifiers in detail. We implemented the new flexible cell classification approach in a tool called JupyLabel. Its evaluation and the obtained metric scores regarding precision, recall, and F1-score are discussed. Additionally, we compared JupyLabel with HeaderGen, an existing cell classification tool. We were able to show that the presented flexible cell classification approach outperforms this tool significantly.
Authors: Ri-Zhao Qiu, Yafei Hu, Ge Yang, Yuchen Song, Yang Fu, Jianglong Ye, Jiteng Mu, Ruihan Yang, Nikolay Atanasov, Sebastian Scherer, Xiaolong Wang
Abstract: An open problem in mobile manipulation is how to represent objects and scenes in a unified manner, so that robots can use it both for navigating in the environment and manipulating objects. The latter requires capturing intricate geometry while understanding fine-grained semantics, whereas the former involves capturing the complexity inherit to an expansive physical scale. In this work, we present GeFF (Generalizable Feature Fields), a scene-level generalizable neural feature field that acts as a unified representation for both navigation and manipulation that performs in real-time. To do so, we treat generative novel view synthesis as a pre-training task, and then align the resulting rich scene priors with natural language via CLIP feature distillation. We demonstrate the effectiveness of this approach by deploying GeFF on a quadrupedal robot equipped with a manipulator. We evaluate GeFF's ability to generalize to open-set objects as well as running time, when performing open-vocabulary mobile manipulation in dynamic scenes.
Authors: \"Umit Mert \c{C}a\u{g}lar, Baris Yilmaz, Melek T\"urkmen, Erdem Akag\"und\"uz, Salih Tileylioglu
Abstract: Contemporary deep learning models have demonstrated promising results across various applications within seismology and earthquake engineering. These models rely primarily on utilizing ground motion records for tasks such as earthquake event classification, localization, earthquake early warning systems, and structural health monitoring. However, the extent to which these models effectively learn from these complex time-series signals has not been thoroughly analyzed. In this study, our objective is to evaluate the degree to which auxiliary information, such as seismic phase arrival times or seismic station distribution within a network, dominates the process of deep learning from ground motion records, potentially hindering its effectiveness. We perform a hyperparameter search on two deep learning models to assess their effectiveness in deep learning from ground motion records while also examining the impact of auxiliary information on model performance. Experimental results reveal a strong reliance on the highly correlated P and S phase arrival information. Our observations highlight a potential gap in the field, indicating an absence of robust methodologies for deep learning of single-station ground motion recordings independent of any auxiliary information.
Authors: Masoud Shokrnezhad, Hao Yu, Tarik Taleb, Richard Li, Kyunghan Lee, Jaeseung Song, Cedric Westphal
Abstract: In the context of advancing 6G, a substantial paradigm shift is anticipated, highlighting comprehensive everything-to-everything interactions characterized by numerous connections and stringent adherence to Quality of Service/Experience (QoS/E) prerequisites. The imminent challenge stems from resource scarcity, prompting a deliberate transition to Computing-Network Convergence (CNC) as an auspicious approach for joint resource orchestration. While CNC-based mechanisms have garnered attention, their effectiveness in realizing future services, particularly in use cases like the Metaverse, may encounter limitations due to the continually changing nature of users, services, and resources. Hence, this paper presents the concept of Adaptable CNC (ACNC) as an autonomous Machine Learning (ML)-aided mechanism crafted for the joint orchestration of computing and network resources, catering to dynamic and voluminous user requests with stringent requirements. ACNC encompasses two primary functionalities: state recognition and context detection. Given the intricate nature of the user-service-computing-network space, the paper employs dimension reduction to generate live, holistic, abstract system states in a hierarchical structure. To address the challenges posed by dynamic changes, Continual Learning (CL) is employed, classifying the system state into contexts controlled by dedicated ML agents, enabling them to operate efficiently. These two functionalities are intricately linked within a closed loop overseen by the End-to-End (E2E) orchestrator to allocate resources. The paper introduces the components of ACNC, proposes a Metaverse scenario to exemplify ACNC's role in resource provisioning with Segment Routing v6 (SRv6), outlines ACNC's workflow, details a numerical analysis for efficiency assessment, and concludes with discussions on relevant challenges and potential avenues for future research.
Authors: Yunze Wei, Tianshuo Hu, Cong Liang, Yong Cui
Abstract: The past few years have witnessed the flourishing of large-scale deep neural network models with ever-growing parameter numbers. Training such large-scale models typically requires massive memory and computing resources that exceed those of a single GPU, necessitating distributed training. As GPU performance has rapidly evolved in recent years, computation time has shrunk, thereby increasing the proportion of communication in the overall training time. Therefore, optimizing communication for distributed training has become an urgent issue. In this article, we briefly introduce the general architecture of distributed deep neural network training and analyze relationships among Parallelization Strategy, Collective Communication Library, and Network from the perspective of communication optimization, which forms a three-layer paradigm. We then review current representative research advances with this three-layer paradigm. We find that layers in the current three-layer paradigm are relatively independent, but there is a rich design space for cross-layer collaborative optimization in distributed training scenarios. Therefore, we further advocate a communication-efficient five-layer paradigm underlining opportunities for collaboration designs and look forward to the perspectives of "Vertical", "Horizontal", "Intra-Inter" and "Host-Net" collaboration designs. We hope this article can shed some light on future research on communication optimization for distributed training.
Authors: Michael Ogezi, Ning Shi
Abstract: In text-to-image generation, using negative prompts, which describe undesirable image characteristics, can significantly boost image quality. However, producing good negative prompts is manual and tedious. To address this, we propose NegOpt, a novel method for optimizing negative prompt generation toward enhanced image generation, using supervised fine-tuning and reinforcement learning. Our combined approach results in a substantial increase of 25% in Inception Score compared to other approaches and surpasses ground-truth negative prompts from the test set. Furthermore, with NegOpt we can preferentially optimize the metrics most important to us. Finally, we construct Negative Prompts DB, a dataset of negative prompts.
Authors: Xiaoda Wang, Yuan Tang, Tengda Guo, Bo Sang, Jingji Wu, Jian Sha, Ke Zhang, Jiang Qian, Mingjie Tang
Abstract: Machine Learning (ML) has become ubiquitous, fueling data-driven applications across various organizations. Contrary to the traditional perception of ML in research, ML workflows can be complex, resource-intensive, and time-consuming. Expanding an ML workflow to encompass a wider range of data infrastructure and data types may lead to larger workloads and increased deployment costs. Currently, numerous workflow engines are available (with over ten being widely recognized). This variety poses a challenge for end-users in terms of mastering different engine APIs. While efforts have primarily focused on optimizing ML Operations (MLOps) for a specific workflow engine, current methods largely overlook workflow optimization across different engines. In this work, we design and implement Couler, a system designed for unified ML workflow optimization in the cloud. Our main insight lies in the ability to generate an ML workflow using natural language (NL) descriptions. We integrate Large Language Models (LLMs) into workflow generation, and provide a unified programming interface for various workflow engines. This approach alleviates the need to understand various workflow engines' APIs. Moreover, Couler enhances workflow computation efficiency by introducing automated caching at multiple stages, enabling large workflow auto-parallelization and automatic hyperparameters tuning. These enhancements minimize redundant computational costs and improve fault tolerance during deep learning workflow training. Couler is extensively deployed in real-world production scenarios at Ant Group, handling approximately 22k workflows daily, and has successfully improved the CPU/Memory utilization by more than 15% and the workflow completion rate by around 17%.
Authors: Thilo Spinner, Rebecca Kehlbeck, Rita Sevastjanova, Tobias St\"ahle, Daniel A. Keim, Oliver Deussen, Mennatallah El-Assady
Abstract: Large language models (LLMs) are widely deployed in various downstream tasks, e.g., auto-completion, aided writing, or chat-based text generation. However, the considered output candidates of the underlying search algorithm are under-explored and under-explained. We tackle this shortcoming by proposing a tree-in-the-loop approach, where a visual representation of the beam search tree is the central component for analyzing, explaining, and adapting the generated outputs. To support these tasks, we present generAItor, a visual analytics technique, augmenting the central beam search tree with various task-specific widgets, providing targeted visualizations and interaction possibilities. Our approach allows interactions on multiple levels and offers an iterative pipeline that encompasses generating, exploring, and comparing output candidates, as well as fine-tuning the model based on adapted data. Our case study shows that our tool generates new insights in gender bias analysis beyond state-of-the-art template-based methods. Additionally, we demonstrate the applicability of our approach in a qualitative user study. Finally, we quantitatively evaluate the adaptability of the model to few samples, as occurring in text-generation use cases.
Authors: Qinghao Hu, Zhisheng Ye, Zerui Wang, Guoteng Wang, Meng Zhang, Qiaoling Chen, Peng Sun, Dahua Lin, Xiaolin Wang, Yingwei Luo, Yonggang Wen, Tianwei Zhang
Abstract: Large Language Models (LLMs) have presented impressive performance across several transformative tasks. However, it is non-trivial to efficiently utilize large-scale cluster resources to develop LLMs, often riddled with numerous challenges such as frequent hardware failures, intricate parallelization strategies, and imbalanced resource utilization. In this paper, we present an in-depth characterization study of a six-month LLM development workload trace collected from our GPU datacenter Acme. Specifically, we investigate discrepancies between LLMs and prior task-specific Deep Learning (DL) workloads, explore resource utilization patterns, and identify the impact of various job failures. Our analysis summarizes hurdles we encountered and uncovers potential opportunities to optimize systems tailored for LLMs. Furthermore, we introduce our system efforts: (1) fault-tolerant pretraining, which enhances fault tolerance through LLM-involved failure diagnosis and automatic recovery. (2) decoupled scheduling for evaluation, which achieves timely performance feedback via trial decomposition and scheduling optimization.
Authors: Meir Yossef Levi, Guy Gilboa
Abstract: We propose a fast and simple explainable AI (XAI) method for point cloud data. It computes pointwise importance with respect to a trained network downstream task. This allows better understanding of the network properties, which is imperative for safety-critical applications. In addition to debugging and visualization, our low computational complexity facilitates online feedback to the network at inference. This can be used to reduce uncertainty and to increase robustness. In this work, we introduce \emph{Feature Based Interpretability} (FBI), where we compute the features' norm, per point, before the bottleneck. We analyze the use of gradients and post- and pre-bottleneck strategies, showing pre-bottleneck is preferred, in terms of smoothness and ranking. We obtain at least three orders of magnitude speedup, compared to current XAI methods, thus, scalable for big point clouds or large-scale architectures. Our approach achieves SOTA results, in terms of classification explainability. We demonstrate how the proposed measure is helpful in analyzing and characterizing various aspects of 3D learning, such as rotation invariance, robustness to out-of-distribution (OOD) outliers or domain shift and dataset bias.
Authors: Yajie Bao, Yuyang Huo, Haojie Ren, Changliang Zou
Abstract: We study the problem of post-selection predictive inference in an online fashion. To avoid devoting resources to unimportant units, a preliminary selection of the current individual before reporting its prediction interval is common and meaningful in online predictive tasks. Since the online selection causes a temporal multiplicity in the selected prediction intervals, it is important to control the real-time false coverage-statement rate (FCR) to measure the averaged miscoverage error. We develop a general framework named CAS (Calibration after Adaptive Selection) that can wrap around any prediction model and online selection rule to output post-selection prediction intervals. If the current individual is selected, we first perform an adaptive selection on historical data to construct a calibration set, then output a conformal prediction interval for the unobserved label. We provide tractable constructions for the calibration set for popular online selection rules. We proved that CAS can achieve an exact selection-conditional coverage guarantee in the finite-sample and distribution-free regimes. For the decision-driven selection rule, including most online multiple-testing procedures, CAS can exactly control the real-time FCR below the target level without any distributional assumptions. For the online selection with symmetric thresholds, we establish the error bound for the control gap of FCR under mild distributional assumptions. To account for the distribution shift in online data, we also embed CAS into some recent dynamic conformal prediction methods and examine the long-run FCR control. Numerical results on both synthetic and real data corroborate that CAS can effectively control FCR around the target level and yield more narrowed prediction intervals over existing baselines across various settings.
Authors: Florian Kalinke, Zoltan Szabo
Abstract: Kernel techniques are among the most influential approaches in data science and statistics. Under mild conditions, the reproducing kernel Hilbert space associated to a kernel is capable of encoding the independence of $M\ge 2$ random variables. Probably the most widespread independence measure relying on kernels is the so-called Hilbert-Schmidt independence criterion (HSIC; also referred to as distance covariance in the statistics literature). Despite various existing HSIC estimators designed since its introduction close to two decades ago, the fundamental question of the rate at which HSIC can be estimated is still open. In this work, we prove that the minimax optimal rate of HSIC estimation on $\mathbb R^d$ for Borel measures containing the Gaussians with continuous bounded translation-invariant characteristic kernels is $\mathcal O\!\left(n^{-1/2}\right)$. Specifically, our result implies the optimality in the minimax sense of many of the most-frequently used estimators (including the U-statistic, the V-statistic, and the Nystr\"om-based one) on $\mathbb R^d$.
Authors: Neel Kanwal, Farbod Khoraminia, Umay Kiraz, Andres Mosquera-Zamudio, Carlos Monteagudo, Emiel A. M. Janssen, Tahlita C. M. Zuiverloon, Chunmig Rong, Kjersti Engan
Abstract: Histopathology is a gold standard for cancer diagnosis under a microscopic examination. However, histological tissue processing procedures result in artifacts, which are ultimately transferred to the digitized version of glass slides, known as whole slide images (WSIs). Artifacts are diagnostically irrelevant areas and may result in wrong deep learning (DL) algorithms predictions. Therefore, detecting and excluding artifacts in the computational pathology (CPATH) system is essential for reliable automated diagnosis. In this paper, we propose a mixture of experts (MoE) scheme for detecting five notable artifacts, including damaged tissue, blur, folded tissue, air bubbles, and histologically irrelevant blood from WSIs. First, we train independent binary DL models as experts to capture particular artifact morphology. Then, we ensemble their predictions using a fusion mechanism. We apply probabilistic thresholding over the final probability distribution to improve the sensitivity of the MoE. We developed DL pipelines using two MoEs and two multiclass models of state-of-the-art deep convolutional neural networks (DCNNs) and vision transformers (ViTs). DCNNs-based MoE and ViTs-based MoE schemes outperformed simpler multiclass models and were tested on datasets from different hospitals and cancer types, where MoE using DCNNs yielded the best results. The proposed MoE yields 86.15% F1 and 97.93% sensitivity scores on unseen data, retaining less computational cost for inference than MoE using ViTs. This best performance of MoEs comes with relatively higher computational trade-offs than multiclass models. The proposed artifact detection pipeline will not only ensure reliable CPATH predictions but may also provide quality control.
Authors: Usef Faghihi, Amir Saki
Abstract: Let $X$ and $Z$ be random vectors, and $Y=g(X,Z)$. In this paper, on the one hand, for the case that $X$ and $Z$ are continuous, by using the ideas from the total variation and the flux of $g$, we develop a point of view in causal inference capable of dealing with a broad domain of causal problems. Indeed, we focus on a function, called Probabilistic Easy Variational Causal Effect (PEACE), which can measure the direct causal effect of $X$ on $Y$ with respect to continuously and interventionally changing the values of $X$ while keeping the value of $Z$ constant. PEACE is a function of $d\ge 0$, which is a degree managing the strengths of probability density values $f(x|z)$. On the other hand, we generalize the above idea for the discrete case and show its compatibility with the continuous case. Further, we investigate some properties of PEACE using measure theoretical concepts. Furthermore, we provide some identifiability criteria and several examples showing the generic capability of PEACE. We note that PEACE can deal with the causal problems for which micro-level or just macro-level changes in the value of the input variables are important. Finally, PEACE is stable under small changes in $\partial g_{in}/\partial x$ and the joint distribution of $X$ and $Z$, where $g_{in}$ is obtained from $g$ by removing all functional relationships defining $X$ and $Z$.
Authors: Jan Pe\v{s}\'an, Santosh Kesiraju, Luk\'a\v{s} Burget, Jan ''Honza'' \v{C}ernock\'y
Abstract: Paralinguistic traits like cognitive load and emotion are increasingly recognized as pivotal areas in speech recognition research, often examined through specialized datasets like CLSE and IEMOCAP. However, the integrity of these datasets is seldom scrutinized for text-dependency. This paper critically evaluates the prevalent assumption that machine learning models trained on such datasets genuinely learn to identify paralinguistic traits, rather than merely capturing lexical features. By examining the lexical overlap in these datasets and testing the performance of machine learning models, we expose significant text-dependency in trait-labeling. Our results suggest that some machine learning models, especially large pre-trained models like HuBERT, might inadvertently focus on lexical characteristics rather than the intended paralinguistic features. The study serves as a call to action for the research community to reevaluate the reliability of existing datasets and methodologies, ensuring that machine learning models genuinely learn what they are designed to recognize.
Authors: Xianli Zeng, Joshua Ward, Guang Cheng
Abstract: The increasing usage of machine learning models in consequential decision-making processes has spurred research into the fairness of these systems. While significant work has been done to study group fairness in the in-processing and post-processing setting, there has been little that theoretically connects these results to the pre-processing domain. This paper proposes that achieving group fairness in downstream models can be formulated as finding the optimal design matrix in which to modify a response variable in a Randomized Response framework. We show that measures of group fairness can be directly controlled for with optimal model utility, proposing a pre-processing algorithm called FairRR that yields excellent downstream model utility and fairness.
Authors: Chen Wang, Haochen Shi, Weizhuo Wang, Ruohan Zhang, Li Fei-Fei, C. Karen Liu
Abstract: Imitation learning from human hand motion data presents a promising avenue for imbuing robots with human-like dexterity in real-world manipulation tasks. Despite this potential, substantial challenges persist, particularly with the portability of existing hand motion capture (mocap) systems and the difficulty of translating mocap data into effective control policies. To tackle these issues, we introduce DexCap, a portable hand motion capture system, alongside DexIL, a novel imitation algorithm for training dexterous robot skills directly from human hand mocap data. DexCap offers precise, occlusion-resistant tracking of wrist and finger motions based on SLAM and electromagnetic field together with 3D observations of the environment. Utilizing this rich dataset, DexIL employs inverse kinematics and point cloud-based imitation learning to replicate human actions with robot hands. Beyond learning from human motion, DexCap also offers an optional human-in-the-loop correction mechanism to refine and further improve robot performance. Through extensive evaluation across six dexterous manipulation tasks, our approach not only demonstrates superior performance but also showcases the system's capability to effectively learn from in-the-wild mocap data, paving the way for future data collection methods for dexterous manipulation. More details can be found at https://dex-cap.github.io
Authors: Cristian Cioflan, Lukas Cavigelli, Luca Benini
Abstract: Keyword spotting systems for always-on TinyML-constrained applications require on-site tuning to boost the accuracy of offline trained classifiers when deployed in unseen inference conditions. Adapting to the speech peculiarities of target users requires many in-domain samples, often unavailable in real-world scenarios. Furthermore, current on-device learning techniques rely on computationally intensive and memory-hungry backbone update schemes, unfit for always-on, battery-powered devices. In this work, we propose a novel on-device learning architecture, composed of a pretrained backbone and a user-aware embedding learning the user's speech characteristics. The so-generated features are fused and used to classify the input utterance. For domain shifts generated by unseen speakers, we measure error rate reductions of up to 19% from 30.1% to 24.3% based on the 35-class problem of the Google Speech Commands dataset, through the inexpensive update of the user projections. We moreover demonstrate the few-shot learning capabilities of our proposed architecture in sample- and class-scarce learning conditions. With 23.7 kparameters and 1 MFLOP per epoch required for on-device training, our system is feasible for TinyML applications aimed at battery-powered microcontrollers.
Authors: Iman Islam (King's College London), Esther Puyol-Ant\'on (King's College London), Bram Ruijsink (King's College London), Andrew J. Reader (King's College London), Andrew P. King (King's College London)
Abstract: Echocardiography (echo) is the first imaging modality used when assessing cardiac function. The measurement of functional biomarkers from echo relies upon the segmentation of cardiac structures and deep learning models have been proposed to automate the segmentation process. However, in order to translate these tools to widespread clinical use it is important that the segmentation models are robust to a wide variety of images (e.g. acquired from different scanners, by operators with different levels of expertise etc.). To achieve this level of robustness it is necessary that the models are trained with multiple diverse datasets. A significant challenge faced when training with multiple diverse datasets is the variation in label presence, i.e. the combined data are often partially-labelled. Adaptations of the cross entropy loss function have been proposed to deal with partially labelled data. In this paper we show that training naively with such a loss function and multiple diverse datasets can lead to a form of shortcut learning, where the model associates label presence with domain characteristics, leading to a drop in performance. To address this problem, we propose a novel label dropout scheme to break the link between domain characteristics and the presence or absence of labels. We demonstrate that label dropout improves echo segmentation Dice score by 62% and 25% on two cardiac structures when training using multiple diverse partially labelled datasets.
Authors: Jacob A. Johnson, Matthew J. Heaton, William F. Christensen, Lynsie R. Warr, Summer B. Rupper
Abstract: Autoencoders are powerful machine learning models used to compress information from multiple data sources. However, autoencoders, like all artificial neural networks, are often unidentifiable and uninterpretable. This research focuses on creating an identifiable and interpretable autoencoder that can be used to meld and combine climate data products. The proposed autoencoder utilizes a Bayesian statistical framework, allowing for probabilistic interpretations while also varying spatially to capture useful spatial patterns across the various data products. Constraints are placed on the autoencoder as it learns patterns in the data, creating an interpretable consensus that includes the important features from each input. We demonstrate the utility of the autoencoder by combining information from multiple precipitation products in High Mountain Asia.
Authors: Emanuel Ben-Baruch, Adam Botach, Igor Kviatkovsky, Manoj Aggarwal, G\'erard Medioni
Abstract: With the increasing size of datasets used for training neural networks, data pruning becomes an attractive field of research. However, most current data pruning algorithms are limited in their ability to preserve accuracy compared to models trained on the full data, especially in high pruning regimes. In this paper we explore the application of data pruning while incorporating knowledge distillation (KD) when training on a pruned subset. That is, rather than relying solely on ground-truth labels, we also use the soft predictions from a teacher network pre-trained on the complete data. By integrating KD into training, we demonstrate significant improvement across datasets, pruning methods, and on all pruning fractions. We first establish a theoretical motivation for employing self-distillation to improve training on pruned data. Then, we empirically make a compelling and highly practical observation: using KD, simple random pruning is comparable or superior to sophisticated pruning methods across all pruning regimes. On ImageNet for example, we achieve superior accuracy despite training on a random subset of only 50% of the data. Additionally, we demonstrate a crucial connection between the pruning factor and the optimal knowledge distillation weight. This helps mitigate the impact of samples with noisy labels and low-quality images retained by typical pruning algorithms. Finally, we make an intriguing observation: when using lower pruning fractions, larger teachers lead to accuracy degradation, while surprisingly, employing teachers with a smaller capacity than the student's may improve results. Our code will be made available.
Authors: Qibing Ren, Chang Gao, Jing Shao, Junchi Yan, Xin Tan, Wai Lam, Lizhuang Ma
Abstract: The rapid advancement of Large Language Models (LLMs) has brought about remarkable capabilities in natural language processing but also raised concerns about their potential misuse. While strategies like supervised fine-tuning and reinforcement learning from human feedback have enhanced their safety, these methods primarily focus on natural languages, which may not generalize to other domains. This paper introduces CodeAttack, a framework that transforms natural language inputs into code inputs, presenting a novel environment for testing the safety generalization of LLMs. Our comprehensive studies on state-of-the-art LLMs including GPT-4, Claude-2, and Llama-2 series reveal a common safety vulnerability of these models against code input: CodeAttack consistently bypasses the safety guardrails of all models more than 80\% of the time. Furthermore, we find that a larger distribution gap between CodeAttack and natural language leads to weaker safety generalization, such as encoding natural language input with data structures or using less popular programming languages. These findings highlight new safety risks in the code domain and the need for more robust safety alignment algorithms to match the code capabilities of LLMs.
Authors: Shivin Dass, Wensi Ai, Yuqian Jiang, Samik Singh, Jiaheng Hu, Ruohan Zhang, Peter Stone, Ben Abbatematteo, Roberto Martin-Martin
Abstract: A critical bottleneck limiting imitation learning in robotics is the lack of data. This problem is more severe in mobile manipulation, where collecting demonstrations is harder than in stationary manipulation due to the lack of available and easy-to-use teleoperation interfaces. In this work, we demonstrate TeleMoMa, a general and modular interface for whole-body teleoperation of mobile manipulators. TeleMoMa unifies multiple human interfaces including RGB and depth cameras, virtual reality controllers, keyboard, joysticks, etc., and any combination thereof. In its more accessible version, TeleMoMa works using simply vision (e.g., an RGB-D camera), lowering the entry bar for humans to provide mobile manipulation demonstrations. We demonstrate the versatility of TeleMoMa by teleoperating several existing mobile manipulators - PAL Tiago++, Toyota HSR, and Fetch - in simulation and the real world. We demonstrate the quality of the demonstrations collected with TeleMoMa by training imitation learning policies for mobile manipulation tasks involving synchronized whole-body motion. Finally, we also show that TeleMoMa's teleoperation channel enables teleoperation on site, looking at the robot, or remote, sending commands and observations through a computer network, and perform user studies to evaluate how easy it is for novice users to learn to collect demonstrations with different combinations of human interfaces enabled by our system. We hope TeleMoMa becomes a helpful tool for the community enabling researchers to collect whole-body mobile manipulation demonstrations. For more information and video results, https://robin-lab.cs.utexas.edu/telemoma-web.
Authors: Jiabao Cui, Xuewei Li, Bin Li, Hanbin Zhao, Bourahla Omar, Xi Li
Abstract: In this paper, we propose a novel learning scheme called epoch-evolving Gaussian Process Guided Learning (GPGL), which aims at characterizing the correlation information between the batch-level distribution and the global data distribution. Such correlation information is encoded as context labels and needs renewal every epoch. With the guidance of the context label and ground truth label, GPGL scheme provides a more efficient optimization through updating the model parameters with a triangle consistency loss. Furthermore, our GPGL scheme can be further generalized and naturally applied to the current deep models, outperforming the existing batch-based state-of-the-art models on mainstream datasets (CIFAR-10, CIFAR-100, and Tiny-ImageNet) remarkably.
Authors: Jianpeng Chen, Yujing Wang, Ming Zeng, Zongyi Xiang, Bitan Hou, Yunhai Tong, Ole J. Mengshoel, Yazhou Ren
Abstract: Graph Neural Networks (GNNs) have been extensively used for mining graph-structured data with impressive performance. However, because these traditional GNNs do not distinguish among various downstream tasks, embeddings embedded by them are not always effective. Intuitively, paths in a graph imply different semantics for different downstream tasks. Inspired by this, we design a novel GNN solution, namely Customized Graph Neural Network with Path Reweighting (CustomGNN for short). Specifically, the proposed CustomGNN can automatically learn the high-level semantics for specific downstream tasks to highlight semantically relevant paths as well to filter out task-irrelevant noises in a graph. Furthermore, we empirically analyze the semantics learned by CustomGNN and demonstrate its ability to avoid the three inherent problems in traditional GNNs, i.e., over-smoothing, poor robustness, and overfitting. In experiments with the node classification task, CustomGNN achieves state-of-the-art accuracies on three standard graph datasets and four large graph datasets. The source code of the proposed CustomGNN is available at \url{https://github.com/cjpcool/CustomGNN}.
Authors: {\L}ukasz Struski, Pawe{\l} Morkisz, Przemys{\l}aw Spurek, Samuel Rodriguez Bernabeu, Tomasz Trzci\'nski
Abstract: Matrix decompositions are ubiquitous in machine learning, including applications in dimensionality reduction, data compression and deep learning algorithms. Typical solutions for matrix decompositions have polynomial complexity which significantly increases their computational cost and time. In this work, we leverage efficient processing operations that can be run in parallel on modern Graphical Processing Units (GPUs), predominant computing architecture used e.g. in deep learning, to reduce the computational burden of computing matrix decompositions. More specifically, we reformulate the randomized decomposition problem to incorporate fast matrix multiplication operations (BLAS-3) as building blocks. We show that this formulation, combined with fast random number generators, allows to fully exploit the potential of parallel processing implemented in GPUs. Our extensive evaluation confirms the superiority of this approach over the competing methods and we release the results of this research as a part of the official CUDA implementation (https://docs.nvidia.com/cuda/cusolver/index.html).
Authors: Md Saiful Islam, Sahil Shikalgar, Md. Noor-E-Alam
Abstract: A Randomized Control Trial (RCT) is considered as the gold standard for evaluating the effect of any intervention or treatment. However, its feasibility is often hindered by ethical, economical, and legal considerations, making observational data a valuable alternative for drawing causal conclusions. Nevertheless, healthcare observational data presents a difficult challenge due to its high dimensionality, requiring careful consideration to ensure unbiased, reliable, and robust causal inferences. To overcome this challenge, in this study, we propose a novel two-stage feature selection technique called, Outcome Adaptive Elastic Net (OAENet), explicitly designed for making robust causal inference decisions using matching techniques. OAENet offers several key advantages over existing methods: superior performance on correlated and high-dimensional data compared to the existing methods and the ability to select specific sets of variables (including confounders and variables associated only with the outcome). This ensures robustness and facilitates an unbiased estimate of the causal effect. Numerical experiments on simulated data demonstrate that OAENet significantly outperforms state-of-the-art methods by either producing a higher-quality estimate or a comparable estimate in significantly less time. To illustrate the applicability of OAENet, we employ large-scale US healthcare data to estimate the effect of Opioid Use Disorder (OUD) on suicidal behavior. When compared to competing methods, OAENet closely aligns with existing literature on the relationship between OUD and suicidal behavior. Performance on both simulated and real-world data highlights that OAENet notably enhances the accuracy of estimating treatment effects or evaluating policy decision-making with causal inference.
Authors: Xiaoqian Ruan, Gaoang Wang
Abstract: Large-scale datasets are important for the development of deep learning models. Such datasets usually require a heavy workload of annotations, which are extremely time-consuming and expensive. To accelerate the annotation procedure, multiple annotators may be employed to label different subsets of the data. However, the inconsistency and bias among different annotators are harmful to the model training, especially for qualitative and subjective tasks.To address this challenge, in this paper, we propose a novel contrastive regression framework to address the disjoint annotations problem, where each sample is labeled by only one annotator and multiple annotators work on disjoint subsets of the data. To take account of both the intra-annotator consistency and inter-annotator inconsistency, two strategies are employed.Firstly, a contrastive-based loss is applied to learn the relative ranking among different samples of the same annotator, with the assumption that the ranking of samples from the same annotator is unanimous. Secondly, we apply the gradient reversal layer to learn robust representations that are invariant to different annotators. Experiments on the facial expression prediction task, as well as the image quality assessment task, verify the effectiveness of our proposed framework.
Authors: Mingguo He, Zhewei Wei, Ji-Rong Wen
Abstract: Designing spectral convolutional networks is a challenging problem in graph learning. ChebNet, one of the early attempts, approximates the spectral graph convolutions using Chebyshev polynomials. GCN simplifies ChebNet by utilizing only the first two Chebyshev polynomials while still outperforming it on real-world datasets. GPR-GNN and BernNet demonstrate that the Monomial and Bernstein bases also outperform the Chebyshev basis in terms of learning the spectral graph convolutions. Such conclusions are counter-intuitive in the field of approximation theory, where it is established that the Chebyshev polynomial achieves the optimum convergent rate for approximating a function. In this paper, we revisit the problem of approximating the spectral graph convolutions with Chebyshev polynomials. We show that ChebNet's inferior performance is primarily due to illegal coefficients learnt by ChebNet approximating analytic filter functions, which leads to over-fitting. We then propose ChebNetII, a new GNN model based on Chebyshev interpolation, which enhances the original Chebyshev polynomial approximation while reducing the Runge phenomenon. We conducted an extensive experimental study to demonstrate that ChebNetII can learn arbitrary graph convolutions and achieve superior performance in both full- and semi-supervised node classification tasks. Most notably, we scale ChebNetII to a billion graph ogbn-papers100M, showing that spectral-based GNNs have superior performance. Our code is available at https://github.com/ivam-he/ChebNetII.
Authors: Arthur Marmin, Jos\'e Henrique de Morais Goulart, C\'edric F\'evotte
Abstract: This article introduces new multiplicative updates for nonnegative matrix factorization with the $\beta$-divergence and sparse regularization of one of the two factors (say, the activation matrix). It is well known that the norm of the other factor (the dictionary matrix) needs to be controlled in order to avoid an ill-posed formulation. Standard practice consists in constraining the columns of the dictionary to have unit norm, which leads to a nontrivial optimization problem. Our approach leverages a reparametrization of the original problem into the optimization of an equivalent scale-invariant objective function. From there, we derive block-descent majorization-minimization algorithms that result in simple multiplicative updates for either $\ell_{1}$-regularization or the more "aggressive" log-regularization. In contrast with other state-of-the-art methods, our algorithms are universal in the sense that they can be applied to any $\beta$-divergence (i.e., any value of $\beta$) and that they come with convergence guarantees. We report numerical comparisons with existing heuristic and Lagrangian methods using various datasets: face images, an audio spectrogram, hyperspectral data, and song play counts. We show that our methods obtain solutions of similar quality at convergence (similar objective values) but with significantly reduced CPU times.
Authors: Shangchao Su, Mingzhao Yang, Bin Li, Xiangyang Xue
Abstract: Federated learning (FL) enables multiple clients to collaboratively train a global model without disclosing their data. Previous researches often require training the complete model parameters. However, the emergence of powerful pre-trained models makes it possible to achieve higher performance with fewer learnable parameters in FL. In this paper, we propose a federated adaptive prompt tuning algorithm, FedAPT, for multi-domain collaborative image classification with powerful foundation models, like CLIP. Compared with direct federated prompt tuning, our core idea is to adaptively unlock specific domain knowledge for each test sample in order to provide them with personalized prompts. To implement this idea, we design an adaptive prompt tuning module, which consists of a meta prompt, an adaptive network, and some keys. The server randomly generates a set of keys and assigns a unique key to each client. Then all clients cooperatively train the global adaptive network and meta prompt with the local datasets and the frozen keys. Ultimately, the global aggregation model can assign a personalized prompt to CLIP based on the domain features of each test sample. We perform extensive experiments on two multi-domain image classification datasets across two different settings -- supervised and unsupervised. The results show that FedAPT can achieve better performance with less than 10\% of the number of parameters of the fully trained model, and the global model can perform well in diverse client domains simultaneously. The source code is available at \url{https://github.com/leondada/FedAPT}.
Authors: Tue Boesen, Eldad Haber, Uri Michael Ascher
Abstract: This article investigates the effect of explicitly adding auxiliary algebraic trajectory information to neural networks for dynamical systems. We draw inspiration from the field of differential-algebraic equations and differential equations on manifolds and implement related methods in residual neural networks, despite some fundamental scenario differences. Constraint or auxiliary information effects are incorporated through stabilization as well as projection methods, and we show when to use which method based on experiments involving simulations of multi-body pendulums and molecular dynamics scenarios. Several of our methods are easy to implement in existing code and have limited impact on training performance while giving significant boosts in terms of inference.
Authors: Mohammad Hossein Jarrahi, Ali Memariani, Shion Guha
Abstract: Data is a crucial infrastructure to how artificial intelligence (AI) systems learn. However, these systems to date have been largely model-centric, putting a premium on the model at the expense of the data quality. Data quality issues beset the performance of AI systems, particularly in downstream deployments and in real-world applications. Data-centric AI (DCAI) as an emerging concept brings data, its quality and its dynamism to the forefront in considerations of AI systems through an iterative and systematic approach. As one of the first overviews, this article brings together data-centric perspectives and concepts to outline the foundations of DCAI. It specifically formulates six guiding principles for researchers and practitioners and gives direction for future advancement of DCAI.
Authors: Minghan Fu, Fang-Xiang Wu
Abstract: The learning rate is a critical hyperparameter for deep learning tasks since it determines the extent to which the model parameters are updated during the learning course. However, the choice of learning rates typically depends on empirical judgment, which may not result in satisfactory outcomes without intensive try-and-error experiments. In this study, we propose a novel learning rate adaptation scheme called QLABGrad. Without any user-specified hyperparameter, QLABGrad automatically determines the learning rate by optimizing the Quadratic Loss Approximation-Based (QLAB) function for a given gradient descent direction, where only one extra forward propagation is required. We theoretically prove the convergence of QLABGrad with a smooth Lipschitz condition on the loss function. Experiment results on multiple architectures, including MLP, CNN, and ResNet, on MNIST, CIFAR10, and ImageNet datasets, demonstrate that QLABGrad outperforms various competing schemes for deep learning.
Authors: Yinsong Wang, Shahin Shahrampour
Abstract: This paper addresses a cross-modal learning framework, where the objective is to enhance the performance of supervised learning in the primary modality using an unlabeled, unpaired secondary modality. Taking a probabilistic approach for missing information estimation, we show that the extra information contained in the secondary modality can be estimated via Nadaraya-Watson (NW) kernel regression, which can further be expressed as a kernelized cross-attention module (under linear transformation). Our results lay the foundations for introducing The Attention Patch (TAP), a simple neural network add-on that allows data-level knowledge transfer from the unlabeled modality. We provide extensive numerical simulations using four real-world datasets to show that TAP can provide statistically significant improvement in generalization across different domains and different neural network architectures, making use of seemingly unusable unlabeled cross-modal data.
Authors: Ali Beikmohammadi, Sindri Magn\'usson
Abstract: Reinforcement learning (RL) is crucial for data science decision-making but suffers from sample inefficiency, particularly in real-world scenarios with costly physical interactions. This paper introduces a novel human-inspired framework to enhance RL algorithm sample efficiency. It achieves this by initially exposing the learning agent to simpler tasks that progressively increase in complexity, ultimately leading to the main task. This method requires no pre-training and involves learning simpler tasks for just one iteration. The resulting knowledge can facilitate various transfer learning approaches, such as value and policy transfer, without increasing computational complexity. It can be applied across different goals, environments, and RL algorithms, including value-based, policy-based, tabular, and deep RL methods. Experimental evaluations demonstrate the framework's effectiveness in enhancing sample efficiency, especially in challenging main tasks, demonstrated through both a simple Random Walk and more complex optimal control problems with constraints.
Authors: Huaijun Jiang, Yu Shen, Yang Li, Beicheng Xu, Sixian Du, Wentao Zhang, Ce Zhang, Bin Cui
Abstract: Black-box optimization (BBO) has a broad range of applications, including automatic machine learning, experimental design, and database knob tuning. However, users still face challenges when applying BBO methods to their problems at hand with existing software packages in terms of applicability, performance, and efficiency. This paper presents OpenBox, an open-source BBO toolkit with improved usability. It implements user-friendly inferfaces and visualization for users to define and manage their tasks. The modular design behind OpenBox facilitates its flexible deployment in existing systems. Experimental results demonstrate the effectiveness and efficiency of OpenBox over existing systems. The source code of OpenBox is available at https://github.com/PKU-DAIR/open-box.
Authors: Prajjwal Bhargava, Rohan Chitnis, Alborz Geramifard, Shagun Sodhani, Amy Zhang
Abstract: Offline reinforcement learning (RL) allows agents to learn effective, return-maximizing policies from a static dataset. Three popular algorithms for offline RL are Conservative Q-Learning (CQL), Behavior Cloning (BC), and Decision Transformer (DT), from the class of Q-Learning, Imitation Learning, and Sequence Modeling respectively. A key open question is: which algorithm is preferred under what conditions? We study this question empirically by exploring the performance of these algorithms across the commonly used D4RL and Robomimic benchmarks. We design targeted experiments to understand their behavior concerning data suboptimality, task complexity, and stochasticity. Our key findings are: (1) DT requires more data than CQL to learn competitive policies but is more robust; (2) DT is a substantially better choice than both CQL and BC in sparse-reward and low-quality data settings; (3) DT and BC are preferable as task horizon increases, or when data is obtained from human demonstrators; and (4) CQL excels in situations characterized by the combination of high stochasticity and low data quality. We also investigate architectural choices and scaling trends for DT on Atari and D4RL and make design/scaling recommendations. We find that scaling the amount of data for DT by 5x gives a 2.5x average score improvement on Atari.
Authors: Andrew Engel, Zhichao Wang, Natalie S. Frank, Ioana Dumitriu, Sutanay Choudhury, Anand Sarwate, Tony Chiang
Abstract: A recent trend in explainable AI research has focused on surrogate modeling, where neural networks are approximated as simpler ML algorithms such as kernel machines. A second trend has been to utilize kernel functions in various explain-by-example or data attribution tasks. In this work, we combine these two trends to analyze approximate empirical neural tangent kernels (eNTK) for data attribution. Approximation is critical for eNTK analysis due to the high computational cost to compute the eNTK. We define new approximate eNTK and perform novel analysis on how well the resulting kernel machine surrogate models correlate with the underlying neural network. We introduce two new random projection variants of approximate eNTK which allow users to tune the time and memory complexity of their calculation. We conclude that kernel machines using approximate neural tangent kernel as the kernel function are effective surrogate models, with the introduced trace NTK the most consistent performer. Open source software allowing users to efficiently calculate kernel functions in the PyTorch framework is available (https://github.com/pnnl/projection\_ntk).
Authors: Ming Shi, Yingbin Liang, Ness Shroff
Abstract: Partially observable Markov decision processes (POMDPs) have been widely applied in various real-world applications. However, existing theoretical results have shown that learning in POMDPs is intractable in the worst case, where the main challenge lies in the lack of latent state information. A key fundamental question here is: how much online state information (OSI) is sufficient to achieve tractability? In this paper, we establish a lower bound that reveals a surprising hardness result: unless we have full OSI, we need an exponentially scaling sample complexity to obtain an $\epsilon$-optimal policy solution for POMDPs. Nonetheless, inspired by the insights in our lower-bound design, we identify important tractable subclasses of POMDPs, even with only partial OSI. In particular, for two subclasses of POMDPs with partial OSI, we provide new algorithms that are proved to be near-optimal by establishing new regret upper and lower bounds. Both our algorithm design and regret analysis involve non-trivial developments for joint OSI query and action control.
Authors: Yuequn Liu, Ruichu Cai, Wei Chen, Jie Qiao, Yuguang Yan, Zijian Li, Keli Zhang, Zhifeng Hao
Abstract: Learning Granger causality from event sequences is a challenging but essential task across various applications. Most existing methods rely on the assumption that event sequences are independent and identically distributed (i.i.d.). However, this i.i.d. assumption is often violated due to the inherent dependencies among the event sequences. Fortunately, in practice, we find these dependencies can be modeled by a topological network, suggesting a potential solution to the non-i.i.d. problem by introducing the prior topological network into Granger causal discovery. This observation prompts us to tackle two ensuing challenges: 1) how to model the event sequences while incorporating both the prior topological network and the latent Granger causal structure, and 2) how to learn the Granger causal structure. To this end, we devise a unified topological neural Poisson auto-regressive model with two processes. In the generation process, we employ a variant of the neural Poisson process to model the event sequences, considering influences from both the topological network and the Granger causal structure. In the inference process, we formulate an amortized inference algorithm to infer the latent Granger causal structure. We encapsulate these two processes within a unified likelihood function, providing an end-to-end framework for this task. Experiments on simulated and real-world data demonstrate the effectiveness of our approach.
Authors: Nanqing Dong, Zhipeng Wang, Jiahao Sun, Michael Kampffmeyer, William Knottenbelt, Eric Xing
Abstract: In the era of deep learning, federated learning (FL) presents a promising approach that allows multi-institutional data owners, or clients, to collaboratively train machine learning models without compromising data privacy. However, most existing FL approaches rely on a centralized server for global model aggregation, leading to a single point of failure. This makes the system vulnerable to malicious attacks when dealing with dishonest clients. In this work, we address this problem by proposing a secure and reliable FL system based on blockchain and distributed ledger technology. Our system incorporates a peer-to-peer voting mechanism and a reward-and-slash mechanism, which are powered by on-chain smart contracts, to detect and deter malicious behaviors. Both theoretical and empirical analyses are presented to demonstrate the effectiveness of the proposed approach, showing that our framework is robust against malicious client-side behaviors.
Authors: Danny Halawi, Jean-Stanislas Denain, Jacob Steinhardt
Abstract: Modern language models can imitate complex patterns through few-shot learning, enabling them to complete challenging tasks without fine-tuning. However, imitation can also lead models to reproduce inaccuracies or harmful content if present in the context. We study harmful imitation through the lens of a model's internal representations, and identify two related phenomena: "overthinking" and "false induction heads". The first phenomenon, overthinking, appears when we decode predictions from intermediate layers, given correct vs. incorrect few-shot demonstrations. At early layers, both demonstrations induce similar model behavior, but the behavior diverges sharply at some "critical layer", after which the accuracy given incorrect demonstrations progressively decreases. The second phenomenon, false induction heads, are a possible mechanistic cause of overthinking: these are heads in late layers that attend to and copy false information from previous demonstrations, and whose ablation reduces overthinking. Beyond scientific understanding, our results suggest that studying intermediate model computations could be a promising avenue for understanding and guarding against harmful model behaviors.
Authors: Boris Flach, Dmitrij Schlesinger, Alexander Shekhovtsov
Abstract: We view variational autoencoders (VAE) as decoder-encoder pairs, which map distributions in the data space to distributions in the latent space and vice versa. The standard learning approach for VAEs is the maximisation of the evidence lower bound (ELBO). It is asymmetric in that it aims at learning a latent variable model while using the encoder as an auxiliary means only. Moreover, it requires a closed form a-priori latent distribution. This limits its applicability in more complex scenarios, such as general semi-supervised learning and employing complex generative models as priors. We propose a Nash equilibrium learning approach, which is symmetric with respect to the encoder and decoder and allows learning VAEs in situations where both the data and the latent distributions are accessible only by sampling. The flexibility and simplicity of this approach allows its application to a wide range of learning scenarios and downstream tasks.
Authors: Ademide O. Mabadeje, Michael J. Pyrcz
Abstract: Subsurface datasets inherently possess big data characteristics such as vast volume, diverse features, and high sampling speeds, further compounded by the curse of dimensionality from various physical, engineering, and geological inputs. Among the existing dimensionality reduction (DR) methods, nonlinear dimensionality reduction (NDR) methods, especially Metric-multidimensional scaling (MDS), are preferred for subsurface datasets due to their inherent complexity. While MDS retains intrinsic data structure and quantifies uncertainty, its limitations include unstabilized unique solutions invariant to Euclidean transformations and an absence of out-of-sample points (OOSP) extension. To enhance subsurface inferential and machine learning workflows, datasets must be transformed into stable, reduced-dimension representations that accommodate OOSP. Our solution employs rigid transformations for a stabilized Euclidean invariant representation for LDS. By computing an MDS input dissimilarity matrix, and applying rigid transformations on multiple realizations, we ensure transformation invariance and integrate OOSP. This process leverages a convex hull algorithm and incorporates loss function and normalized stress for distortion quantification. We validate our approach with synthetic data, varying distance metrics, and real-world wells from the Duvernay Formation. Results confirm our method's efficacy in achieving consistent LDS representations. Furthermore, our proposed "stress ratio" (SR) metric provides insight into uncertainty, beneficial for model adjustments and inferential analysis. Consequently, our workflow promises enhanced repeatability and comparability in NDR for subsurface energy resource engineering and associated big data workflows.
Authors: Yang Liu, Jiashun Cheng, Haihong Zhao, Tingyang Xu, Peilin Zhao, Fugee Tsung, Jia Li, Yu Rong
Abstract: Graph Neural Networks (GNNs) with equivariant properties have emerged as powerful tools for modeling complex dynamics of multi-object physical systems. However, their generalization ability is limited by the inadequate consideration of physical inductive biases: (1) Existing studies overlook the continuity of transitions among system states, opting to employ several discrete transformation layers to learn the direct mapping between two adjacent states; (2) Most models only account for first-order velocity information, despite the fact that many physical systems are governed by second-order motion laws. To incorporate these inductive biases, we propose the Second-order Equivariant Graph Neural Ordinary Differential Equation (SEGNO). Specifically, we show how the second-order continuity can be incorporated into GNNs while maintaining the equivariant property. Furthermore, we offer theoretical insights into SEGNO, highlighting that it can learn a unique trajectory between adjacent states, which is crucial for model generalization. Additionally, we prove that the discrepancy between this learned trajectory of SEGNO and the true trajectory is bounded. Extensive experiments on complex dynamical systems including molecular dynamics and motion capture demonstrate that our model yields a significant improvement over the state-of-the-art baselines.
Authors: Spencer Hutchinson, Berkay Turan, Mahnoosh Alizadeh
Abstract: The safe linear bandit problem is a version of the classical stochastic linear bandit problem where the learner's actions must satisfy an uncertain constraint at all rounds. Due its applicability to many real-world settings, this problem has received considerable attention in recent years. By leveraging a novel approach that we call directional optimism, we find that it is possible to achieve improved regret guarantees for both well-separated problem instances and action sets that are finite star convex sets. Furthermore, we propose a novel algorithm for this setting that improves on existing algorithms in terms of empirical performance, while enjoying matching regret guarantees. Lastly, we introduce a generalization of the safe linear bandit setting where the constraints are convex and adapt our algorithms and analyses to this setting by leveraging a novel convex-analysis based approach.
Authors: Frederiek Wesel, Kim Batselier
Abstract: In the context of kernel machines, polynomial and Fourier features are commonly used to provide a nonlinear extension to linear models by mapping the data to a higher-dimensional space. Unless one considers the dual formulation of the learning problem, which renders exact large-scale learning unfeasible, the exponential increase of model parameters in the dimensionality of the data caused by their tensor-product structure prohibits to tackle high-dimensional problems. One of the possible approaches to circumvent this exponential scaling is to exploit the tensor structure present in the features by constraining the model weights to be an underparametrized tensor network. In this paper we quantize, i.e. further tensorize, polynomial and Fourier features. Based on this feature quantization we propose to quantize the associated model weights, yielding quantized models. We show that, for the same number of model parameters, the resulting quantized models have a higher bound on the VC-dimension as opposed to their non-quantized counterparts, at no additional computational cost while learning from identical features. We verify experimentally how this additional tensorization regularizes the learning problem by prioritizing the most salient features in the data and how it provides models with increased generalization capabilities. We finally benchmark our approach on large regression task, achieving state-of-the-art results on a laptop computer.
Authors: Sascha Marton, Stefan L\"udtke, Christian Bartelt, Heiner Stuckenschmidt
Abstract: Despite the success of deep learning for text and image data, tree-based ensemble models are still state-of-the-art for machine learning with heterogeneous tabular data. However, there is a significant need for tabular-specific gradient-based methods due to their high flexibility. In this paper, we propose $\text{GRANDE}$, $\text{GRA}$die$\text{N}$t-Based $\text{D}$ecision Tree $\text{E}$nsembles, a novel approach for learning hard, axis-aligned decision tree ensembles using end-to-end gradient descent. GRANDE is based on a dense representation of tree ensembles, which affords to use backpropagation with a straight-through operator to jointly optimize all model parameters. Our method combines axis-aligned splits, which is a useful inductive bias for tabular data, with the flexibility of gradient-based optimization. Furthermore, we introduce an advanced instance-wise weighting that facilitates learning representations for both, simple and complex relations, within a single model. We conducted an extensive evaluation on a predefined benchmark with 19 classification datasets and demonstrate that our method outperforms existing gradient-boosting and deep learning frameworks on most datasets. The method is available under: https://github.com/s-marton/GRANDE
Authors: Fran Jeleni\'c, Josip Juki\'c, Martin Tutek, Mate Puljiz, Jan \v{S}najder
Abstract: Effective out-of-distribution (OOD) detection is crucial for reliable machine learning models, yet most current methods are limited in practical use due to requirements like access to training data or intervention in training. We present a novel method for detecting OOD data in Transformers based on transformation smoothness between intermediate layers of a network (BLOOD), which is applicable to pre-trained models without access to training data. BLOOD utilizes the tendency of between-layer representation transformations of in-distribution (ID) data to be smoother than the corresponding transformations of OOD data, a property that we also demonstrate empirically. We evaluate BLOOD on several text classification tasks with Transformer networks and demonstrate that it outperforms methods with comparable resource requirements. Our analysis also suggests that when learning simpler tasks, OOD data transformations maintain their original sharpness, whereas sharpness increases with more complex tasks.
Authors: Tom Sherborne, Naomi Saphra, Pradeep Dasigi, Hao Peng
Abstract: Sharpness-aware minimization (SAM) reports improving domain generalization by reducing the loss surface curvature in the parameter space. However, generalization during fine-tuning is often more dependent on the transferability of representations in the function space. Trust-region methods (TR) target this goal by regularizing representation curvature to reduce catastrophic forgetting of pre-trained task-agnostic information while adopting task-specific skills. We consider unifying these strategies for low curvature in both parameter space and function space to improve out-of-domain (OOD) generalization. We propose Trust Region Aware Minimization (TRAM), a SAM algorithm fine-tuning for low parameter sharpness and smooth, informative representations preserving pre-trained structure. TRAM uses a trust region bound to inform the SAM adversarial neighborhood, introducing an awareness of function curvature within optimization for flatter minima. We empirically validate TRAM in vision (cross-dataset adaptation) and text (OOD language modeling, zero-shot cross-lingual transfer) tasks where robust domain transfer and representation generality are critical. TRAM outperforms SAM- and TR-based optimization across all tasks, notably surpassing competing methods for hard transfer between anticorrelated domains. TRAM establishes a novel standard in fine-tuning for domain-generalizable models with minimal additional computation over previous sharpness-aware methods.
Authors: Huaixiu Steven Zheng, Swaroop Mishra, Xinyun Chen, Heng-Tze Cheng, Ed H. Chi, Quoc V Le, Denny Zhou
Abstract: We present Step-Back Prompting, a simple prompting technique that enables LLMs to do abstractions to derive high-level concepts and first principles from instances containing specific details. Using the concepts and principles to guide reasoning, LLMs significantly improve their abilities in following a correct reasoning path towards the solution. We conduct experiments of Step-Back Prompting with PaLM-2L, GPT-4 and Llama2-70B models, and observe substantial performance gains on various challenging reasoning-intensive tasks including STEM, Knowledge QA, and Multi-Hop Reasoning. For instance, Step-Back Prompting improves PaLM-2L performance on MMLU (Physics and Chemistry) by 7% and 11% respectively, TimeQA by 27%, and MuSiQue by 7%.
Authors: Rujie Wu, Xiaojian Ma, Zhenliang Zhang, Wei Wang, Qing Li, Song-Chun Zhu, Yizhou Wang
Abstract: We introduce Bongard-OpenWorld, a new benchmark for evaluating real-world few-shot reasoning for machine vision. It originates from the classical Bongard Problems (BPs): Given two sets of images (positive and negative), the model needs to identify the set that query images belong to by inducing the visual concepts, which is exclusively depicted by images from the positive set. Our benchmark inherits the few-shot concept induction of the original BPs while adding the two novel layers of challenge: 1) open-world free-form concepts, as the visual concepts in Bongard-OpenWorld are unique compositions of terms from an open vocabulary, ranging from object categories to abstract visual attributes and commonsense factual knowledge; 2) real-world images, as opposed to the synthetic diagrams used by many counterparts. In our exploration, Bongard-OpenWorld already imposes a significant challenge to current few-shot reasoning algorithms. We further investigate to which extent the recently introduced Large Language Models (LLMs) and Vision-Language Models (VLMs) can solve our task, by directly probing VLMs, and combining VLMs and LLMs in an interactive reasoning scheme. We even conceived a neuro-symbolic reasoning approach that reconciles LLMs & VLMs with logical reasoning to emulate the human problem-solving process for Bongard Problems. However, none of these approaches manage to close the human-machine gap, as the best learner achieves 64% accuracy while human participants easily reach 91%. We hope Bongard-OpenWorld can help us better understand the limitations of current visual intelligence and facilitate future research on visual agents with stronger few-shot visual reasoning capabilities.
Authors: Somnath Basu Roy Chowdhury, Nicholas Monath, Ahmad Beirami, Rahul Kidambi, Avinava Dubey, Amr Ahmed, Snigdha Chaturvedi
Abstract: Fairness, especially group fairness, is an important consideration in the context of machine learning systems. The most commonly adopted group fairness-enhancing techniques are in-processing methods that rely on a mixture of a fairness objective (e.g., demographic parity) and a task-specific objective (e.g., cross-entropy) during the training process. However, when data arrives in an online fashion -- one instance at a time -- optimizing such fairness objectives poses several challenges. In particular, group fairness objectives are defined using expectations of predictions across different demographic groups. In the online setting, where the algorithm has access to a single instance at a time, estimating the group fairness objective requires additional storage and significantly more computation (e.g., forward/backward passes) than the task-specific objective at every time step. In this paper, we propose Aranyani, an ensemble of oblique decision trees, to make fair decisions in online settings. The hierarchical tree structure of Aranyani enables parameter isolation and allows us to efficiently compute the fairness gradients using aggregate statistics of previous decisions, eliminating the need for additional storage and forward/backward passes. We also present an efficient framework to train Aranyani and theoretically analyze several of its properties. We conduct empirical evaluations on 5 publicly available benchmarks (including vision and language datasets) to show that Aranyani achieves a better accuracy-fairness trade-off compared to baseline approaches.
Authors: Yuya Yoshikawa, Tomoharu Iwata
Abstract: The quality of explanations for the predictions made by complex machine learning predictors is often measured using insertion and deletion metrics, which assess the faithfulness of the explanations, i.e., how accurately the explanations reflect the predictor's behavior. To improve the faithfulness, we propose insertion/deletion metric-aware explanation-based optimization (ID-ExpO), which optimizes differentiable predictors to improve both the insertion and deletion scores of the explanations while maintaining their predictive accuracy. Because the original insertion and deletion metrics are non-differentiable with respect to the explanations and directly unavailable for gradient-based optimization, we extend the metrics so that they are differentiable and use them to formalize insertion and deletion metric-based regularizers. Our experimental results on image and tabular datasets show that the deep neural network-based predictors that are fine-tuned using ID-ExpO enable popular post-hoc explainers to produce more faithful and easier-to-interpret explanations while maintaining high predictive accuracy. The code is available at https://github.com/yuyay/idexpo.
Authors: Thomas Falconer, Jalal Kazempour, Pierre Pinson
Abstract: Machine learning tasks are vulnerable to the quality of data used as input. Yet, it is often challenging for firms to obtain adequate datasets, with them being naturally distributed amongst owners, that in practice, may be competitors in a downstream market and reluctant to share information. Focusing on supervised learning for regression tasks, we develop a regression market to provide a monetary incentive for data sharing. Our proposed mechanism adopts a Bayesian framework, allowing us to consider a more general class of regression tasks. We present a thorough exploration of the market properties, and show that similar proposals in current literature expose the market agents to sizeable financial risks, which can be mitigated in our setup.
Authors: Soo Min Kwon, Zekai Zhang, Dogyoon Song, Laura Balzano, Qing Qu
Abstract: Overparameterized models have proven to be powerful tools for solving various machine learning tasks. However, overparameterization often leads to a substantial increase in computational and memory costs, which in turn requires extensive resources to train. In this work, we present a novel approach for compressing overparameterized models, developed through studying their learning dynamics. We observe that for many deep models, updates to the weight matrices occur within a low-dimensional invariant subspace. For deep linear models, we demonstrate that their principal components are fitted incrementally within a small subspace, and use these insights to propose a compression algorithm for deep linear networks that involve decreasing the width of their intermediate layers. We empirically evaluate the effectiveness of our compression technique on matrix recovery problems. Remarkably, by using an initialization that exploits the structure of the problem, we observe that our compressed network converges faster than the original network, consistently yielding smaller recovery errors. We substantiate this observation by developing a theory focused on deep matrix factorization. Finally, we empirically demonstrate how our compressed model has the potential to improve the utility of deep nonlinear models. Overall, our algorithm improves the training efficiency by more than 2x, without compromising generalization.
Authors: Shangchao Su, Bin Li, Xiangyang Xue
Abstract: With the increasing availability of Foundation Models, federated tuning has garnered attention in the field of federated learning, utilizing data and computation resources from multiple clients to collaboratively fine-tune foundation models. However, in real-world federated scenarios, there often exist a multitude of heterogeneous clients with varying computation and communication resources, rendering them incapable of supporting the entire model fine-tuning process. In response to this challenge, we propose a novel federated tuning algorithm, FedRA. The implementation of FedRA is straightforward and can be seamlessly integrated into any transformer-based model without the need for further modification to the original model. Specifically, in each communication round, FedRA randomly generates an allocation matrix. For resource-constrained clients, it reorganizes a small number of layers from the original model based on the allocation matrix and fine-tunes using adapters. Subsequently, the server aggregates the updated adapter parameters from the clients according to the current allocation matrix into the corresponding layers of the original model. It is worth noting that FedRA also supports scenarios where none of the clients can support the entire global model, which is an impressive advantage. We conduct experiments on two large-scale image datasets, DomainNet and NICO++, under various non-iid settings. The results demonstrate that FedRA outperforms the compared methods significantly. The source code is available at \url{https://github.com/leondada/FedRA}.
Authors: Luka Ribar, Ivan Chelombiev, Luke Hudlass-Galley, Charlie Blake, Carlo Luschi, Douglas Orr
Abstract: The computational difficulties of large language model (LLM) inference remain a significant obstacle to their widespread deployment. The need for many applications to support long input sequences and process them in large batches typically causes token-generation to be bottlenecked by data-transfer. For this reason, we introduce SparQ Attention, a technique for increasing the inference throughput of LLMs by utilising memory bandwidth more efficiently within the attention layers, through selective fetching of the cached history. Our proposed technique can be applied directly to off-the-shelf LLMs during inference, without requiring any modification to the pre-training setup or additional fine-tuning. We show that SparQ Attention brings up to 8x savings in attention data-transfers without substantial drops in accuracy, by evaluating Llama 2, Mistral and Pythia models on a wide range of downstream tasks.
Authors: Zijian Liu, Zhengyuan Zhou
Abstract: In the past several years, the last-iterate convergence of the Stochastic Gradient Descent (SGD) algorithm has triggered people's interest due to its good performance in practice but lack of theoretical understanding. For Lipschitz convex functions, different works have established the optimal $O(\log(1/\delta)\log T/\sqrt{T})$ or $O(\sqrt{\log(1/\delta)/T})$ high-probability convergence rates for the final iterate, where $T$ is the time horizon and $\delta$ is the failure probability. However, to prove these bounds, all the existing works are either limited to compact domains or require almost surely bounded noises. It is natural to ask whether the last iterate of SGD can still guarantee the optimal convergence rate but without these two restrictive assumptions. Besides this important question, there are still lots of theoretical problems lacking an answer. For example, compared with the last-iterate convergence of SGD for non-smooth problems, only few results for smooth optimization have yet been developed. Additionally, the existing results are all limited to a non-composite objective and the standard Euclidean norm. It still remains unclear whether the last-iterate convergence can be provably extended to wider composite optimization and non-Euclidean norms. In this work, to address the issues mentioned above, we revisit the last-iterate convergence of stochastic gradient methods and provide the first unified way to prove the convergence rates both in expectation and in high probability to accommodate general domains, composite objectives, non-Euclidean norms, Lipschitz conditions, smoothness, and (strong) convexity simultaneously. Additionally, we extend our analysis to obtain the last-iterate convergence under heavy-tailed noises.
Authors: Jungtaek Kim
Abstract: Bayesian optimization is a principled optimization strategy for a black-box objective function. It shows its effectiveness in a wide variety of real-world applications such as scientific discovery and experimental design. In general, the performance of Bayesian optimization is reported through regret-based metrics such as instantaneous, simple, and cumulative regrets. These metrics only rely on function evaluations, so that they do not consider geometric relationships between query points and global solutions, or query points themselves. Notably, they cannot discriminate if multiple global solutions are successfully found. Moreover, they do not evaluate Bayesian optimization's abilities to exploit and explore a search space given. To tackle these issues, we propose four new geometric metrics, i.e., precision, recall, average degree, and average distance. These metrics allow us to compare Bayesian optimization algorithms considering the geometry of both query points and global optima, or query points. However, they are accompanied by an extra parameter, which needs to be carefully determined. We therefore devise the parameter-free forms of the respective metrics by integrating out the additional parameter. Finally, we empirically validate that our proposed metrics can provide more delicate interpretation of Bayesian optimization algorithms, on top of assessment via the conventional metrics.
Authors: Jing Wu, Mehrtash Harandi
Abstract: Machine unlearning has become a pivotal task to erase the influence of data from a trained model. It adheres to recent data regulation standards and enhances the privacy and security of machine learning applications. In this work, we present a new machine unlearning approach Scissorhands. Initially, Scissorhands identifies the most pertinent parameters in the given model relative to the forgetting data via connection sensitivity. By reinitializing the most influential top-k percent of these parameters, a trimmed model for erasing the influence of the forgetting data is obtained. Subsequently, Scissorhands fine-tunes the trimmed model with a gradient projection-based approach, seeking parameters that preserve information on the remaining data while discarding information related to the forgetting data. Our experimental results, conducted across image classification and image generation tasks, demonstrate that Scissorhands, showcases competitive performance when compared to existing methods.
Authors: Yihan Du, R. Srikant, Wei Chen
Abstract: Cascading bandits have gained popularity in recent years due to their applicability to recommendation systems and online advertising. In the cascading bandit model, at each timestep, an agent recommends an ordered subset of items (called an item list) from a pool of items, each associated with an unknown attraction probability. Then, the user examines the list, and clicks the first attractive item (if any), and after that, the agent receives a reward. The goal of the agent is to maximize the expected cumulative reward. However, the prior literature on cascading bandits ignores the influences of user states (e.g., historical behaviors) on recommendations and the change of states as the session proceeds. Motivated by this fact, we propose a generalized cascading RL framework, which considers the impact of user states and state transition into decisions. In cascading RL, we need to select items not only with large attraction probabilities but also leading to good successor states. This imposes a huge computational challenge due to the combinatorial action space. To tackle this challenge, we delve into the properties of value functions, and design an oracle BestPerm to efficiently find the optimal item list. Equipped with BestPerm, we develop two algorithms CascadingVI and CascadingBPI, which are both computationally-efficient and sample-efficient, and provide near-optimal regret and sample complexity guarantees. Furthermore, we present experiments to show the improved computational and sample efficiencies of our algorithms compared to straightforward adaptations of existing RL algorithms in practice.
Authors: Raj Ghugare, Matthieu Geist, Glen Berseth, Benjamin Eysenbach
Abstract: Some reinforcement learning (RL) algorithms can stitch pieces of experience to solve a task never seen before during training. This oft-sought property is one of the few ways in which RL methods based on dynamic-programming differ from RL methods based on supervised-learning (SL). Yet, certain RL methods based on off-the-shelf SL algorithms achieve excellent results without an explicit mechanism for stitching; it remains unclear whether those methods forgo this important stitching property. This paper studies this question for the problems of achieving a target goal state and achieving a target return value. Our main result is to show that the stitching property corresponds to a form of combinatorial generalization: after training on a distribution of (state, goal) pairs, one would like to evaluate on (state, goal) pairs not seen together in the training data. Our analysis shows that this sort of generalization is different from i.i.d. generalization. This connection between stitching and generalisation reveals why we should not expect SL-based RL methods to perform stitching, even in the limit of large datasets and models. Based on this analysis, we construct new datasets to explicitly test for this property, revealing that SL-based methods lack this stitching property and hence fail to perform combinatorial generalization. Nonetheless, the connection between stitching and combinatorial generalisation also suggests a simple remedy for improving generalisation in SL: data augmentation. We propose a temporal data augmentation and demonstrate that adding it to SL-based methods enables them to successfully complete tasks not seen together during training. On a high level, this connection illustrates the importance of combinatorial generalization for data efficiency in time-series data beyond tasks beyond RL, like audio, video, or text.
Authors: Tzu-Hsien Tsai, Yun-Da Tsai, Shou-De Lin
Abstract: Good arm identification (GAI) is a pure-exploration bandit problem in which a single learner outputs an arm as soon as it is identified as a good arm. A good arm is defined as an arm with an expected reward greater than or equal to a given threshold. This paper focuses on the GAI problem under a small threshold gap, which refers to the distance between the expected rewards of arms and the given threshold. We propose a new algorithm called lil'HDoC to significantly improve the total sample complexity of the HDoC algorithm. We demonstrate that the sample complexity of the first $\lambda$ output arm in lil'HDoC is bounded by the original HDoC algorithm, except for one negligible term, when the distance between the expected reward and threshold is small. Extensive experiments confirm that our algorithm outperforms the state-of-the-art algorithms in both synthetic and real-world datasets.
Authors: Meng-Chieh Lee, Haiyang Yu, Jian Zhang, Vassilis N. Ioannidis, Xiang Song, Soji Adeshina, Da Zheng, Christos Faloutsos
Abstract: Given a node-attributed graph, and a graph task (link prediction or node classification), can we tell if a graph neural network (GNN) will perform well? More specifically, do the graph structure and the node features carry enough usable information for the task? Our goals are (1) to develop a fast tool to measure how much information is in the graph structure and in the node features, and (2) to exploit the information to solve the task, if there is enough. We propose NetInfoF, a framework including NetInfoF_Probe and NetInfoF_Act, for the measurement and the exploitation of network usable information (NUI), respectively. Given a graph data, NetInfoF_Probe measures NUI without any model training, and NetInfoF_Act solves link prediction and node classification, while two modules share the same backbone. In summary, NetInfoF has following notable advantages: (a) General, handling both link prediction and node classification; (b) Principled, with theoretical guarantee and closed-form solution; (c) Effective, thanks to the proposed adjustment to node similarity; (d) Scalable, scaling linearly with the input size. In our carefully designed synthetic datasets, NetInfoF correctly identifies the ground truth of NUI and is the only method being robust to all graph scenarios. Applied on real-world datasets, NetInfoF wins in 11 out of 12 times on link prediction compared to general GNN baselines.
Authors: Marios Papachristou, M. Amin Rahimian
Abstract: How can individuals exchange information to learn from each other despite their privacy needs and security concerns? For example, consider individuals deliberating a contentious topic and being concerned about divulging their private experiences. Preserving individual privacy and enabling efficient social learning are both important desiderata but seem fundamentally at odds with each other and very hard to reconcile. We do so by controlling information leakage using rigorous statistical guarantees that are based on differential privacy (DP). Our agents use log-linear rules to update their beliefs after communicating with their neighbors. Adding DP randomization noise to beliefs provides communicating agents with plausible deniability with regard to their private information and their network neighborhoods. We consider two learning environments one for distributed maximum-likelihood estimation given a finite number of private signals and another for online learning from an infinite, intermittent signal stream. Noisy information aggregation in the finite case leads to interesting tradeoffs between rejecting low-quality states and making sure all high-quality states are accepted in the algorithm output. Our results flesh out the nature of the trade-offs in both cases between the quality of the group decision outcomes, learning accuracy, communication cost, and the level of privacy protections that the agents are afforded.
Authors: Mingtian Zhang, Shawn Lan, Peter Hayes, David Barber
Abstract: Retrieval Augmented Generation (RAG) has emerged as an effective solution for mitigating hallucinations in Large Language Models (LLMs). The retrieval stage in RAG typically involves a pre-trained embedding model, which converts queries and passages into vectors to capture their semantics. However, a standard pre-trained embedding model may exhibit sub-optimal performance when applied to specific domain knowledge, necessitating fine-tuning. This paper addresses scenarios where the embeddings are only available from a black-box model. We introduce Model augmented fine-tuning (Mafin) -- a novel approach for fine-tuning a black-box embedding model by augmenting it with a trainable embedding model. Our results demonstrate that Mafin significantly enhances the performance of the black-box embeddings by only requiring the training of a small augmented model. We validate the effectiveness of our method on both labeled and unlabeled datasets, illustrating its broad applicability and efficiency.
Authors: Nils Graef
Abstract: This micro-paper describes a trick to speed up inference of transformers with RoPE (such as LLaMA, Mistral, PaLM, and Gemma). For these models, a large portion of the first transformer layer can be precomputed, which results in slightly lower latency and lower cost-per-token. Because this trick optimizes only one layer, the relative savings depend on the total number of layers. For example, the maximum savings for a model with only 4 layers (such as Whisper tiny) is limited to 25%, while a 32-layer model is limited to 3% savings. See https://github.com/OpenMachine-ai/transformer-tricks for code and more transformer tricks.
Authors: Jonas H\"ubotter, Bhavya Sukhija, Lenart Treven, Yarden As, Andreas Krause
Abstract: We study the active few-shot fine-tuning of large neural networks to downstream tasks. We show that few-shot fine-tuning is an instance of a generalization of classical active learning, transductive active learning, and we propose ITL, short for information-based transductive learning, an approach which samples adaptively to maximize the information gained about specified downstream tasks. Under general regularity assumptions, we prove that ITL converges uniformly to the smallest possible uncertainty obtainable from the accessible data. To the best of our knowledge, we are the first to derive generalization bounds of this kind, and they may be of independent interest for active learning. We apply ITL to the few-shot fine-tuning of large neural networks and show that ITL substantially improves upon the state-of-the-art.
Authors: Jonas H\"ubotter, Bhavya Sukhija, Lenart Treven, Yarden As, Andreas Krause
Abstract: We generalize active learning to address real-world settings where sampling is restricted to an accessible region of the domain, while prediction targets may lie outside this region. To this end, we propose ITL, short for information-based transductive learning, an approach which samples adaptively to maximize the information gained about specified prediction targets. We show, under general regularity assumptions, that ITL converges uniformly to the smallest possible uncertainty obtainable from the accessible data. We demonstrate ITL in two key applications: Few-shot fine-tuning of large neural networks and safe Bayesian optimization, and in both cases, ITL significantly outperforms the state-of-the-art.
Authors: Jie Cheng, Gang Xiong, Xingyuan Dai, Qinghai Miao, Yisheng Lv, Fei-Yue Wang
Abstract: Preference-based Reinforcement Learning (PbRL) avoids the need for reward engineering by harnessing human preferences as the reward signal. However, current PbRL algorithms over-reliance on high-quality feedback from domain experts, which results in a lack of robustness. In this paper, we present RIME, a robust PbRL algorithm for effective reward learning from noisy preferences. Our method incorporates a sample selection-based discriminator to dynamically filter denoised preferences for robust training. To mitigate the accumulated error caused by incorrect selection, we propose to warm start the reward model, which additionally bridges the performance gap during transition from pre-training to online training in PbRL. Our experiments on robotic manipulation and locomotion tasks demonstrate that RIME significantly enhances the robustness of the current state-of-the-art PbRL method. Ablation studies further demonstrate that the warm start is crucial for both robustness and feedback-efficiency in limited-feedback cases.
Authors: Yanjie Li, Jingyi Liu, Weijun Li, Lina Yu, Min Wu, Wenqiang Li, Meilan Hao, Su Wei, Yusong Deng
Abstract: Mathematical formulas are the crystallization of human wisdom in exploring the laws of nature for thousands of years. Describing the complex laws of nature with a concise mathematical formula is a constant pursuit of scientists and a great challenge for artificial intelligence. This field is called symbolic regression. Symbolic regression was originally formulated as a combinatorial optimization problem, and GP and reinforcement learning algorithms were used to solve it. However, GP is sensitive to hyperparameters, and these two types of algorithms are inefficient. To solve this problem, researchers treat the mapping from data to expressions as a translation problem. And the corresponding large-scale pre-trained model is introduced. However, the data and expression skeletons do not have very clear word correspondences as the two languages do. Instead, they are more like two modalities (e.g., image and text). Therefore, in this paper, we proposed MMSR. The SR problem is solved as a pure multimodal problem, and contrastive learning is also introduced in the training process for modal alignment to facilitate later modal feature fusion. It is worth noting that in order to better promote the modal feature fusion, we adopt the strategy of training contrastive learning loss and other losses at the same time, which only needs one-step training, instead of training contrastive learning loss first and then training other losses. Because our experiments prove training together can make the feature extraction module and feature fusion module running-in better. Experimental results show that compared with multiple large-scale pre-training baselines, MMSR achieves the most advanced results on multiple mainstream datasets including SRBench.
Authors: Ruizhe Zhong, Junjie Ye, Zhentao Tang, Shixiong Kai, Mingxuan Yuan, Jianye Hao, Junchi Yan
Abstract: Pre-routing timing prediction has been recently studied for evaluating the quality of a candidate cell placement in chip design. It involves directly estimating the timing metrics for both pin-level (slack, slew) and edge-level (net delay, cell delay), without time-consuming routing. However, it often suffers from signal decay and error accumulation due to the long timing paths in large-scale industrial circuits. To address these challenges, we propose a two-stage approach. First, we propose global circuit training to pre-train a graph auto-encoder that learns the global graph embedding from circuit netlist. Second, we use a novel node updating scheme for message passing on GCN, following the topological sorting sequence of the learned graph embedding and circuit graph. This scheme residually models the local time delay between two adjacent pins in the updating sequence, and extracts the lookup table information inside each cell via a new attention mechanism. To handle large-scale circuits efficiently, we introduce an order preserving partition scheme that reduces memory consumption while maintaining the topological dependencies. Experiments on 21 real world circuits achieve a new SOTA R2 of 0.93 for slack prediction, which is significantly surpasses 0.59 by previous SOTA method. Code will be available at: https://github.com/Thinklab-SJTU/EDA-AI.
Authors: Yanxiao Zhao, Yangge Qian, Tianyi Wang, Jingyang Shan, Xiaolin Qin
Abstract: Deep reinforcement learning (DRL) algorithms require substantial samples and computational resources to achieve higher performance, which restricts their practical application and poses challenges for further development. Given the constraint of limited resources, it is essential to leverage existing computational work (e.g., learned policies, samples) to enhance sample efficiency and reduce the computational resource consumption of DRL algorithms. Previous works to leverage existing computational work require intrusive modifications to existing algorithms and models, designed specifically for specific algorithms, lacking flexibility and universality. In this paper, we present the Snapshot Reinforcement Learning (SnapshotRL) framework, which enhances sample efficiency by simply altering environments, without making any modifications to algorithms and models. By allowing student agents to choose states in teacher trajectories as the initial state to sample, SnapshotRL can effectively utilize teacher trajectories to assist student agents in training, allowing student agents to explore a larger state space at the early training phase. We propose a simple and effective SnapshotRL baseline algorithm, S3RL, which integrates well with existing DRL algorithms. Our experiments demonstrate that integrating S3RL with TD3, SAC, and PPO algorithms on the MuJoCo benchmark significantly improves sample efficiency and average return, without extra samples and additional computational resources.
Authors: Asif Iqbal, Prosanta Gope, Biplab Sikdar
Abstract: Accurate load forecasting is crucial for energy management, infrastructure planning, and demand-supply balancing. Smart meter data availability has led to the demand for sensor-based load forecasting. Conventional ML allows training a single global model using data from multiple smart meters requiring data transfer to a central server, raising concerns for network requirements, privacy, and security. We propose a split learning-based framework for load forecasting to alleviate this issue. We split a deep neural network model into two parts, one for each Grid Station (GS) responsible for an entire neighbourhood's smart meters and the other for the Service Provider (SP). Instead of sharing their data, client smart meters use their respective GSs' model split for forward pass and only share their activations with the GS. Under this framework, each GS is responsible for training a personalized model split for their respective neighbourhoods, whereas the SP can train a single global or personalized model for each GS. Experiments show that the proposed models match or exceed a centrally trained model's performance and generalize well. Privacy is analyzed by assessing information leakage between data and shared activations of the GS model split. Additionally, differential privacy enhances local data privacy while examining its impact on performance. A transformer model is used as our base learner.
Authors: Yingrong Wang, Anpeng Wu, Haoxuan Li, Weiming Liu, Qiaowei Miao, Ruoxuan Xiong, Fei Wu, Kun Kuang
Abstract: This paper focuses on developing Pareto-optimal estimation and policy learning to identify the most effective treatment that maximizes the total reward from both short-term and long-term effects, which might conflict with each other. For example, a higher dosage of medication might increase the speed of a patient's recovery (short-term) but could also result in severe long-term side effects. Although recent works have investigated the problems about short-term or long-term effects or the both, how to trade-off between them to achieve optimal treatment remains an open challenge. Moreover, when multiple objectives are directly estimated using conventional causal representation learning, the optimization directions among various tasks can conflict as well. In this paper, we systematically investigate these issues and introduce a Pareto-Efficient algorithm, comprising Pareto-Optimal Estimation (POE) and Pareto-Optimal Policy Learning (POPL), to tackle them. POE incorporates a continuous Pareto module with representation balancing, enhancing estimation efficiency across multiple tasks. As for POPL, it involves deriving short-term and long-term outcomes linked with various treatment levels, facilitating an exploration of the Pareto frontier emanating from these outcomes. Results on both the synthetic and real-world datasets demonstrate the superiority of our method.
Authors: Tim Lenz, Omar S. M. El Nahhas, Marta Ligero, Jakob Nikolas Kather
Abstract: Deep Learning models have been successfully utilized to extract clinically actionable insights from routinely available histology data. Generally, these models require annotations performed by clinicians, which are scarce and costly to generate. The emergence of self-supervised learning (SSL) methods remove this barrier, allowing for large-scale analyses on non-annotated data. However, recent SSL approaches apply increasingly expansive model architectures and larger datasets, causing the rapid escalation of data volumes, hardware prerequisites, and overall expenses, limiting access to these resources to few institutions. Therefore, we investigated the complexity of contrastive SSL in computational pathology in relation to classification performance with the utilization of consumer-grade hardware. Specifically, we analyzed the effects of adaptations in data volume, architecture, and algorithms on downstream classification tasks, emphasizing their impact on computational resources. We trained breast cancer foundation models on a large public patient cohort and validated them on various downstream classification tasks in a weakly supervised manner on two external public patient cohorts. Our experiments demonstrate that we can improve downstream classification performance whilst reducing SSL training duration by 90%. In summary, we propose a set of adaptations which enable the utilization of SSL in computational pathology in non-resource abundant environments.
Authors: Teng-Hui Huang, Hesham El Gamal
Abstract: We propose an efficient solver for the privacy funnel (PF) method, leveraging its difference-of-convex (DC) structure. The proposed DC separation results in a closed-form update equation, which allows straightforward application to both known and unknown distribution settings. For known distribution case, we prove the convergence (local stationary points) of the proposed non-greedy solver, and empirically show that it outperforms the state-of-the-art approaches in characterizing the privacy-utility trade-off. The insights of our DC approach apply to unknown distribution settings where labeled empirical samples are available instead. Leveraging the insights, our alternating minimization solver satisfies the fundamental Markov relation of PF in contrast to previous variational inference-based solvers. Empirically, we evaluate the proposed solver with MNIST and Fashion-MNIST datasets. Our results show that under a comparable reconstruction quality, an adversary suffers from higher prediction error from clustering our compressed codes than that with the compared methods. Most importantly, our solver is independent to private information in inference phase contrary to the baselines.
Authors: Alex Ayoub, Kaiwen Wang, Vincent Liu, Samuel Robertson, James McInerney, Dawen Liang, Nathan Kallus, Csaba Szepesv\'ari
Abstract: We propose training fitted Q-iteration with log-loss (FQI-LOG) for batch reinforcement learning (RL). We show that the number of samples needed to learn a near-optimal policy with FQI-LOG scales with the accumulated cost of the optimal policy, which is zero in problems where acting optimally achieves the goal and incurs no cost. In doing so, we provide a general framework for proving $\textit{small-cost}$ bounds, i.e. bounds that scale with the optimal achievable cost, in batch RL. Moreover, we empirically verify that FQI-LOG uses fewer samples than FQI trained with squared loss on problems where the optimal policy reliably achieves the goal.
Authors: Hao Kang, Qingru Zhang, Souvik Kundu, Geonhwa Jeong, Zaoxing Liu, Tushar Krishna, Tuo Zhao
Abstract: Key-value (KV) caching has become the de-facto to accelerate generation speed for large language models (LLMs) inference. However, the growing cache demand with increasing sequence length has transformed LLM inference to be a memory bound problem, significantly constraining the system throughput. Existing methods rely on dropping unimportant tokens or quantizing all entries uniformly. Such methods, however, often incur high approximation errors to represent the compressed matrices. The autoregressive decoding process further compounds the error of each step, resulting in critical deviation in model generation and deterioration of performance. To tackle this challenge, we propose GEAR, an efficient KV cache compression framework that achieves near-lossless high-ratio compression. GEAR first applies quantization to majority of entries of similar magnitudes to ultra-low precision. It then employs a low rank matrix to approximate the quantization error, and a sparse matrix to remedy individual errors from outlier entries. By adeptly integrating three techniques, GEAR is able to fully exploit their synergistic potentials. Our experiments demonstrate that compared to alternatives, GEAR achieves near-lossless 4-bit KV cache compression with up to 2.38x throughput improvement, while reducing peak-memory size up to 2.29x. Our code is publicly available at https://github.com/HaoKang-Timmy/GEAR.
Authors: R. Li, J. Liu, X. L. Deng, X. Liu, J. C. Guo, W. Y. Wu, L. Yang
Abstract: The diagnosis and monitoring of Castrate Resistant Prostate Cancer (CRPC) are crucial for cancer patients, but the current models (such as P-NET) have limitations in terms of parameter count, generalization, and cost. To address the issue, we develop a more accurate and efficient Prostate Cancer patient condition prediction model, named PR-NET. By compressing and optimizing the network structure of P-NET, the model complexity is reduced while maintaining high accuracy and interpretability. The PR-NET demonstrated superior performance in predicting prostate cancer patient outcomes, outshining P-NET and six other traditional models with a significant margin. In our rigorous evaluation, PR-NET not only achieved impressive average AUC and Recall scores of 0.94 and 0.83, respectively, on known data but also maintained robust generalizability on five unknown datasets with a higher average AUC of 0.73 and Recall of 0.72, compared to P-NET's 0.68 and 0.5. PR-NET's efficiency was evidenced by its shorter average training and inference times, and its gene-level analysis revealed 46 key genes, demonstrating its enhanced predictive power and efficiency in identifying critical biomarkers for prostate cancer. Future research can further expand its application domains and optimize the model's performance and reliability.
Authors: Ming Zheng, Yang Yang, Zhi-Hang Zhao, Shan-Chao Gan, Yang Chen, Si-Kai Ni, Yang Lu
Abstract: In the field of data mining and machine learning, commonly used classification models cannot effectively learn in unbalanced data. In order to balance the data distribution before model training, oversampling methods are often used to generate data for a small number of classes to solve the problem of classifying unbalanced data. Most of the classical oversampling methods are based on the SMOTE technique, which only focuses on the local information of the data, and therefore the generated data may have the problem of not being realistic enough. In the current oversampling methods based on generative networks, the methods based on GANs can capture the true distribution of data, but there is the problem of pattern collapse and training instability in training; in the oversampling methods based on denoising diffusion probability models, the neural network of the inverse diffusion process using the U-Net is not applicable to tabular data, and although the MLP can be used to replace the U-Net, the problem exists due to the simplicity of the structure and the poor effect of removing noise. problem of poor noise removal. In order to overcome the above problems, we propose a novel oversampling method SEMRes-DDPM.In the SEMRes-DDPM backward diffusion process, a new neural network structure SEMST-ResNet is used, which is suitable for tabular data and has good noise removal effect, and it can generate tabular data with higher quality. Experiments show that the SEMResNet network removes noise better than MLP; SEMRes-DDPM generates data distributions that are closer to the real data distributions than TabDDPM with CWGAN-GP; on 20 real unbalanced tabular datasets with 9 classification models, SEMRes-DDPM improves the quality of the generated tabular data in terms of three evaluation metrics (F1, G-mean, AUC) with better classification performance than other SOTA oversampling methods.
Authors: Xuefeng Wang, Henglin Pu, Hyung Jun Kim, Husheng Li
Abstract: Safe Multi-agent reinforcement learning (safe MARL) has increasingly gained attention in recent years, emphasizing the need for agents to not only optimize the global return but also adhere to safety requirements through behavioral constraints. Some recent work has integrated control theory with multi-agent reinforcement learning to address the challenge of ensuring safety. However, there have been only very limited applications of Model Predictive Control (MPC) methods in this domain, primarily due to the complex and implicit dynamics characteristic of multi-agent environments. To bridge this gap, we propose a novel method called Deep Learning-Based Model Predictive Control for Safe Multi-Agent Reinforcement Learning (DeepSafeMPC). The key insight of DeepSafeMPC is leveraging a entralized deep learning model to well predict environmental dynamics. Our method applies MARL principles to search for optimal solutions. Through the employment of MPC, the actions of agents can be restricted within safe states concurrently. We demonstrate the effectiveness of our approach using the Safe Multi-agent MuJoCo environment, showcasing significant advancements in addressing safety concerns in MARL.
Authors: Sharmita Dey, Sarath R. Nair
Abstract: Mobility impairment caused by limb loss is a significant challenge faced by millions of individuals worldwide. The development of advanced assistive technologies, such as prosthetic devices, has the potential to greatly improve the quality of life for amputee patients. A critical component in the design of such technologies is the accurate prediction of reference joint motion for the missing limb. However, this task is hindered by the scarcity of joint motion data available for amputee patients, in contrast to the substantial quantity of data from able-bodied subjects. To overcome this, we leverage deep learning's reprogramming property to repurpose well-trained models for a new goal without altering the model parameters. With only data-level manipulation, we adapt models originally designed for able-bodied people to forecast joint motion in amputees. The findings in this study have significant implications for advancing assistive tech and amputee mobility.
Authors: Hanbin Zhao, Yongjian Fu, Mintong Kang, Qi Tian, Fei Wu, Xi Li
Abstract: As a challenging problem, few-shot class-incremental learning (FSCIL) continually learns a sequence of tasks, confronting the dilemma between slow forgetting of old knowledge and fast adaptation to new knowledge. In this paper, we concentrate on this "slow vs. fast" (SvF) dilemma to determine which knowledge components to be updated in a slow fashion or a fast fashion, and thereby balance old-knowledge preservation and new-knowledge adaptation. We propose a multi-grained SvF learning strategy to cope with the SvF dilemma from two different grains: intra-space (within the same feature space) and inter-space (between two different feature spaces). The proposed strategy designs a novel frequency-aware regularization to boost the intra-space SvF capability, and meanwhile develops a new feature space composition operation to enhance the inter-space SvF learning performance. With the multi-grained SvF learning strategy, our method outperforms the state-of-the-art approaches by a large margin.
Authors: Haitong Tang, Shuang He, Mengduo Yang, Xia Lu, Qin Yu, Kaiyue Liu, Hongjie Yan, Nizhuan Wang
Abstract: It is a challenging task to accurately perform semantic segmentation due to the complexity of real picture scenes. Many semantic segmentation methods based on traditional deep learning insufficiently captured the semantic and appearance information of images, which put limit on their generality and robustness for various application scenes. In this paper, we proposed a novel strategy that reformulated the popularly-used convolution operation to multi-layer convolutional sparse coding block to ease the aforementioned deficiency. This strategy can be possibly used to significantly improve the segmentation performance of any semantic segmentation model that involves convolutional operations. To prove the effectiveness of our idea, we chose the widely-used U-Net model for the demonstration purpose, and we designed CSC-Unet model series based on U-Net. Through extensive analysis and experiments, we provided credible evidence showing that the multi-layer convolutional sparse coding block enables semantic segmentation model to converge faster, can extract finer semantic and appearance information of images, and improve the ability to recover spatial detail information. The best CSC-Unet model significantly outperforms the results of the original U-Net on three public datasets with different scenarios, i.e., 87.14% vs. 84.71% on DeepCrack dataset, 68.91% vs. 67.09% on Nuclei dataset, and 53.68% vs. 48.82% on CamVid dataset, respectively.
Authors: Amine Bennouna, Bart P. G. Van Parys
Abstract: We study the problem of designing optimal learning and decision-making formulations when only historical data is available. Prior work typically commits to a particular class of data-driven formulation and subsequently tries to establish out-of-sample performance guarantees. We take here the opposite approach. We define first a sensible yard stick with which to measure the quality of any data-driven formulation and subsequently seek to find an optimal such formulation. Informally, any data-driven formulation can be seen to balance a measure of proximity of the estimated cost to the actual cost while guaranteeing a level of out-of-sample performance. Given an acceptable level of out-of-sample performance, we construct explicitly a data-driven formulation that is uniformly closer to the true cost than any other formulation enjoying the same out-of-sample performance. We show the existence of three distinct out-of-sample performance regimes (a superexponential regime, an exponential regime and a subexponential regime) between which the nature of the optimal data-driven formulation experiences a phase transition. The optimal data-driven formulations can be interpreted as a classically robust formulation in the superexponential regime, an entropic distributionally robust formulation in the exponential regime and finally a variance penalized formulation in the subexponential regime. This final observation unveils a surprising connection between these three, at first glance seemingly unrelated, data-driven formulations which until now remained hidden.
Authors: Kai Yi, Paul Janson, Wenxuan Zhang, Mohamed Elhoseiny
Abstract: Modern visual systems have a wide range of potential applications in vision tasks for natural science research, such as aiding in species discovery, monitoring animals in the wild, and so on. However, real-world vision tasks may experience changes in environmental conditions, leading to shifts in how captured images are presented. To address this issue, we introduce Domain-Aware Continual Zero-Shot Learning (DACZSL), a task to recognize images of unseen categories in continuously changing domains. Accordingly, we propose a Domain-Invariant Network (DIN) to learn factorized features for shifting domains and improved textual representation for unseen classes. DIN continually learns a global shared network for domain-invariant and task-invariant features, and per-task private networks for task-specific features. Furthermore, we enhance the dual network with class-wise learnable prompts to improve class-level text representation, thereby improving zero-shot prediction of future unseen classes. To evaluate DACZSL, we introduce two benchmarks, DomainNet-CZSL and iWildCam-CZSL. Our results show that DIN significantly outperforms existing baselines by over 5% in harmonic accuracy and over 1% in backward transfer and achieves a new SoTA.
Authors: Chen Xu, Xiuyuan Cheng, Yao Xie
Abstract: We propose an alternative approach to neural network training using the monotone vector field, an idea inspired by the seminal work of Juditsky and Nemirovski [Juditsky & Nemirovsky, 2019] developed originally to solve parameter estimation problems for generalized linear models (GLM) by reducing the original non-convex problem to a convex problem of solving a monotone variational inequality (VI). Our approach leads to computationally efficient procedures that converge fast and offer guarantee in some special cases, such as training a single-layer neural network or fine-tuning the last layer of the pre-trained model. Our approach can be used for more efficient fine-tuning of a pre-trained model while freezing the bottom layers, an essential step for deploying many machine learning models such as large language models (LLM). We demonstrate its applicability in training fully-connected (FC) neural networks, graph neural networks (GNN), and convolutional neural networks (CNN) and show the competitive or better performance of our approach compared to stochastic gradient descent methods on both synthetic and real network data prediction tasks regarding various performance metrics.
Authors: Zhengyuan Shi (The Chinese University of Hong Kong), Min Li (The Chinese University of Hong Kong), Yi Liu (The Chinese University of Hong Kong), Sadaf Khan (The Chinese University of Hong Kong), Junhua Huang (Huawei Noah's Ark Lab), Hui-Ling Zhen (Huawei Noah's Ark Lab), Mingxuan Yuan (Huawei Noah's Ark Lab), Qiang Xu (The Chinese University of Hong Kong)
Abstract: This paper introduces SATformer, a novel Transformer-based approach for the Boolean Satisfiability (SAT) problem. Rather than solving the problem directly, SATformer approaches the problem from the opposite direction by focusing on unsatisfiability. Specifically, it models clause interactions to identify any unsatisfiable sub-problems. Using a graph neural network, we convert clauses into clause embeddings and employ a hierarchical Transformer-based model to understand clause correlation. SATformer is trained through a multi-task learning approach, using the single-bit satisfiability result and the minimal unsatisfiable core (MUC) for UNSAT problems as clause supervision. As an end-to-end learning-based satisfiability classifier, the performance of SATformer surpasses that of NeuroSAT significantly. Furthermore, we integrate the clause predictions made by SATformer into modern heuristic-based SAT solvers and validate our approach with a logic equivalence checking task. Experimental results show that our SATformer can decrease the runtime of existing solvers by an average of 21.33%.
Authors: Jiashuo Sun, Hang Zhang, Chen Lin, Xiangdong Su, Yeyun Gong, Jian Guo
Abstract: Long-form numerical reasoning in financial analysis aims to generate a reasoning program to calculate the correct answer for a given question. Previous work followed a retriever-generator framework, where the retriever selects key facts from a long-form document, and the generator generates a reasoning program based on retrieved facts. However, they treated all facts equally without considering the different contributions of facts with and without numbers. Meanwhile, the program consistency were ignored under supervised training, resulting in lower training accuracy and diversity. To solve these problems, we proposed APOLLO to improve the long-form numerical reasoning framework. For the retriever, we adopt a number-aware negative sampling strategy to enable the retriever to be more discriminative on key numerical facts. For the generator, we design consistency-based reinforcement learning and target program augmentation strategy based on the consistency of program execution results. Experimental results on the FinQA and ConvFinQA leaderboard verify the effectiveness of our proposed method, achieving the new state-of-the-art.
Authors: Jean-Marie Lemercier, Julius Richter, Simon Welker, Timo Gerkmann
Abstract: Diffusion models have shown a great ability at bridging the performance gap between predictive and generative approaches for speech enhancement. We have shown that they may even outperform their predictive counterparts for non-additive corruption types or when they are evaluated on mismatched conditions. However, diffusion models suffer from a high computational burden, mainly as they require to run a neural network for each reverse diffusion step, whereas predictive approaches only require one pass. As diffusion models are generative approaches they may also produce vocalizing and breathing artifacts in adverse conditions. In comparison, in such difficult scenarios, predictive models typically do not produce such artifacts but tend to distort the target speech instead, thereby degrading the speech quality. In this work, we present a stochastic regeneration approach where an estimate given by a predictive model is provided as a guide for further diffusion. We show that the proposed approach uses the predictive model to remove the vocalizing and breathing artifacts while producing very high quality samples thanks to the diffusion model, even in adverse conditions. We further show that this approach enables to use lighter sampling schemes with fewer diffusion steps without sacrificing quality, thus lifting the computational burden by an order of magnitude. Source code and audio examples are available online (https://uhh.de/inf-sp-storm).
Authors: Akifumi Okuno, Kazuharu Harada
Abstract: This study proposes an interpretable neural network-based non-proportional odds model (N$^3$POM) for ordinal regression. N$^3$POM is different from conventional approaches to ordinal regression with non-proportional models in several ways: (1) N$^3$POM is defined for both continuous and discrete responses, whereas standard methods typically treat the ordered continuous variables as if they are discrete, (2) instead of estimating response-dependent finite-dimensional coefficients of linear models from discrete responses as is done in conventional approaches, we train a non-linear neural network to serve as a coefficient function. Thanks to the neural network, N$^3$POM offers flexibility while preserving the interpretability of conventional ordinal regression. We establish a sufficient condition under which the predicted conditional cumulative probability locally satisfies the monotonicity constraint over a user-specified region in the covariate space. Additionally, we provide a monotonicity-preserving stochastic (MPS) algorithm for effectively training the neural network. We apply N$^3$POM to several real-world datasets.
Authors: Shirong Xu, Will Wei Sun, Guang Cheng
Abstract: Synthetic data algorithms are widely employed in industries to generate artificial data for downstream learning tasks. While existing research primarily focuses on empirically evaluating utility of synthetic data, its theoretical understanding is largely lacking. This paper bridges the practice-theory gap by establishing relevant utility theory in a statistical learning framework. It considers two utility metrics: generalization and ranking of models trained on synthetic data. The former is defined as the generalization difference between models trained on synthetic and on real data. By deriving analytical bounds for this utility metric, we demonstrate that the synthetic feature distribution does not need to be similar as that of real data for ensuring comparable generalization of synthetic models, provided proper model specifications in downstream learning tasks. The latter utility metric studies the relative performance of models trained on synthetic data. In particular, we discover that the distribution of synthetic data is not necessarily similar as the real one to ensure consistent model comparison. Interestingly, consistent model comparison is still achievable even when synthetic responses are not well generated, as long as downstream models are separable by a generalization gap. Finally, extensive experiments on non-parametric models and deep neural networks have been conducted to validate these theoretical findings.
Authors: Lucas David, Helio Pedrini, Zanoni Dias
Abstract: Weakly Supervised Semantic Segmentation (WSSS) techniques explore individual regularization strategies to refine Class Activation Maps (CAMs). In this work, we first analyze complementary WSSS techniques in the literature, their segmentation properties, and the conditions in which they are most effective. Based on these findings, we devise two new techniques: P-NOC and CCAM-H. In the first, we promote the conjoint training of two adversarial CAM generating networks: the generator, which progressively learns to erase regions containing class-specific features, and a discriminator, which is refined to gradually shift its attention to new class discriminant features. In the latter, we employ the high quality pseudo-segmentation priors produced by P-NOC to guide the learning to saliency information in a weakly supervised fashion. Finally, we employ both pseudo-segmentation priors and pseudo-saliency proposals in the random walk procedure, resulting in higher quality pseudo-semantic segmentation masks, and competitive results with the state of the art.
Authors: Aakash Lahoti, Spandan Senapati, Ketan Rajawat, Alec Koppel
Abstract: The problem of minimizing the sum of $n$ functions in $d$ dimensions is ubiquitous in machine learning and statistics. In many applications where the number of observations $n$ is large, it is necessary to use incremental or stochastic methods, as their per-iteration cost is independent of $n$. Of these, Quasi-Newton (QN) methods strike a balance between the per-iteration cost and the convergence rate. Specifically, they exhibit a superlinear rate with $O(d^2)$ cost in contrast to the linear rate of first-order methods with $O(d)$ cost and the quadratic rate of second-order methods with $O(d^3)$ cost. However, existing incremental methods have notable shortcomings: Incremental Quasi-Newton (IQN) only exhibits asymptotic superlinear convergence. In contrast, Incremental Greedy BFGS (IGS) offers explicit superlinear convergence but suffers from poor empirical performance and has a per-iteration cost of $O(d^3)$. To address these issues, we introduce the Sharpened Lazy Incremental Quasi-Newton Method (SLIQN) that achieves the best of both worlds: an explicit superlinear convergence rate, and superior empirical performance at a per-iteration $O(d^2)$ cost. SLIQN features two key changes: first, it incorporates a hybrid strategy of using both classic and greedy BFGS updates, allowing it to empirically outperform both IQN and IGS. Second, it employs a clever constant multiplicative factor along with a lazy propagation strategy, which enables it to have a cost of $O(d^2)$. Additionally, our experiments demonstrate the superiority of SLIQN over other incremental and stochastic Quasi-Newton variants and establish its competitiveness with second-order incremental methods.
Authors: Jiarui Lu, Bozitao Zhong, Zuobai Zhang, Jian Tang
Abstract: The dynamic nature of proteins is crucial for determining their biological functions and properties, for which Monte Carlo (MC) and molecular dynamics (MD) simulations stand as predominant tools to study such phenomena. By utilizing empirically derived force fields, MC or MD simulations explore the conformational space through numerically evolving the system via Markov chain or Newtonian mechanics. However, the high-energy barrier of the force fields can hamper the exploration of both methods by the rare event, resulting in inadequately sampled ensemble without exhaustive running. Existing learning-based approaches perform direct sampling yet heavily rely on target-specific simulation data for training, which suffers from high data acquisition cost and poor generalizability. Inspired by simulated annealing, we propose Str2Str, a novel structure-to-structure translation framework capable of zero-shot conformation sampling with roto-translation equivariant property. Our method leverages an amortized denoising score matching objective trained on general crystal structures and has no reliance on simulation data during both training and inference. Experimental results across several benchmarking protein systems demonstrate that Str2Str outperforms previous state-of-the-art generative structure prediction models and can be orders of magnitude faster compared to long MD simulations. Our open-source implementation is available at https://github.com/lujiarui/Str2Str
Authors: Xuewei Li, Tao Wu, Zhongang Qi, Gaoang Wang, Ying Shan, Xi Li
Abstract: As an important and challenging problem in computer vision, PAnoramic Semantic Segmentation (PASS) gives complete scene perception based on an ultra-wide angle of view. Usually, prevalent PASS methods with 2D panoramic image input focus on solving image distortions but lack consideration of the 3D properties of original $360^{\circ}$ data. Therefore, their performance will drop a lot when inputting panoramic images with the 3D disturbance. To be more robust to 3D disturbance, we propose our Spherical Geometry-Aware Transformer for PAnoramic Semantic Segmentation (SGAT4PASS), considering 3D spherical geometry knowledge. Specifically, a spherical geometry-aware framework is proposed for PASS. It includes three modules, i.e., spherical geometry-aware image projection, spherical deformable patch embedding, and a panorama-aware loss, which takes input images with 3D disturbance into account, adds a spherical geometry-aware constraint on the existing deformable patch embedding, and indicates the pixel density of original $360^{\circ}$ data, respectively. Experimental results on Stanford2D3D Panoramic datasets show that SGAT4PASS significantly improves performance and robustness, with approximately a 2% increase in mIoU, and when small 3D disturbances occur in the data, the stability of our performance is improved by an order of magnitude. Our code and supplementary material are available at https://github.com/TencentARC/SGAT4PASS.
Authors: {\L}ukasz Struski, Dawid Rymarczyk, Arkadiusz Lewicki, Robert Sabiniewicz, Jacek Tabor, Bartosz Zieli\'nski
Abstract: Multiple Instance Learning (MIL) is a weakly-supervised problem in which one label is assigned to the whole bag of instances. An important class of MIL models is instance-based, where we first classify instances and then aggregate those predictions to obtain a bag label. The most common MIL model is when we consider a bag as positive if at least one of its instances has a positive label. However, this reasoning does not hold in many real-life scenarios, where the positive bag label is often a consequence of a certain percentage of positive instances. To address this issue, we introduce a dedicated instance-based method called ProMIL, based on deep neural networks and Bernstein polynomial estimation. An important advantage of ProMIL is that it can automatically detect the optimal percentage level for decision-making. We show that ProMIL outperforms standard instance-based MIL in real-world medical applications. We make the code available.
Authors: Lang Zeng, Jipeng Zhang, Wei Chen, Ying Ding
Abstract: The aim of dynamic prediction is to provide individualized risk predictions over time, which are updated as new data become available. In pursuit of constructing a dynamic prediction model for a progressive eye disorder, age-related macular degeneration (AMD), we propose a time-dependent Cox survival neural network (tdCoxSNN) to predict its progression using longitudinal fundus images. tdCoxSNN builds upon the time-dependent Cox model by utilizing a neural network to capture the non-linear effect of time-dependent covariates on the survival outcome. Moreover, by concurrently integrating a convolutional neural network (CNN) with the survival network, tdCoxSNN can directly take longitudinal images as input. We evaluate and compare our proposed method with joint modeling and landmarking approaches through extensive simulations. We applied the proposed approach to two real datasets. One is a large AMD study, the Age-Related Eye Disease Study (AREDS), in which more than 50,000 fundus images were captured over a period of 12 years for more than 4,000 participants. Another is a public dataset of the primary biliary cirrhosis (PBC) disease, where multiple lab tests were longitudinally collected to predict the time-to-liver transplant. Our approach demonstrates commendable predictive performance in both simulation studies and the analysis of the two real datasets.
Authors: Hong-Hai Nguyen, Ngumimi Karen Iyortsuun, Seungwon Kim, Hyung-Jeong Yang, Soo-Hyung Kim
Abstract: The human brain remains continuously active, whether an individual is working or at rest. Mental activity is a daily process, and if the brain becomes excessively active, known as overload, it can adversely affect human health. Recently, advancements in early prediction of mental health conditions have emerged, aiming to prevent serious consequences and enhance the overall quality of life. Consequently, the estimation of mental status has garnered significant attention from diverse researchers due to its potential benefits. While various signals are employed to assess mental state, the electroencephalogram, containing extensive information about the brain, is widely utilized by researchers. In this paper, we categorize mental workload into three states (low, middle, and high) and estimate a continuum of mental workload levels. Our method leverages information from multiple spatial dimensions to achieve optimal results in mental estimation. For the time domain approach, we employ Temporal Convolutional Networks. In the frequency domain, we introduce a novel architecture based on combining residual blocks, termed the Multi-Dimensional Residual Block. The integration of these two domains yields significant results compared to individual estimates in each domain. Our approach achieved a 74.98% accuracy in the three-class classification, surpassing the provided data results at 69.00%. Specially, our method demonstrates efficacy in estimating continuous levels, evidenced by a corresponding Concordance Correlation Coefficient (CCC) result of 0.629. The combination of time and frequency domain analysis in our approach highlights the exciting potential to improve healthcare applications in the future.
Authors: Hamza Kheddar, Mustapha Hemis, Yassine Himeur, David Meg\'ias, Abbes Amira
Abstract: Steganography and steganalysis are two interrelated aspects of the field of information security. Steganography seeks to conceal communications, whereas steganalysis is aimed to either find them or even, if possible, recover the data they contain. Steganography and steganalysis have attracted a great deal of interest, particularly from law enforcement. Steganography is often used by cybercriminals and even terrorists to avoid being captured while in possession of incriminating evidence, even encrypted, since cryptography is prohibited or restricted in many countries. Therefore, knowledge of cutting-edge techniques to uncover concealed information is crucial in exposing illegal acts. Over the last few years, a number of strong and reliable steganography and steganalysis techniques have been introduced in the literature. This review paper provides a comprehensive overview of deep learning-based steganalysis techniques used to detect hidden information within digital media. The paper covers all types of cover in steganalysis, including image, audio, and video, and discusses the most commonly used deep learning techniques. In addition, the paper explores the use of more advanced deep learning techniques, such as deep transfer learning (DTL) and deep reinforcement learning (DRL), to enhance the performance of steganalysis systems. The paper provides a systematic review of recent research in the field, including data sets and evaluation metrics used in recent studies. It also presents a detailed analysis of DTL-based steganalysis approaches and their performance on different data sets. The review concludes with a discussion on the current state of deep learning-based steganalysis, challenges, and future research directions.
Authors: Meir Yossef Levi, Guy Gilboa
Abstract: The ability to cope with out-of-distribution (OOD) corruptions and adversarial attacks is crucial in real-world safety-demanding applications. In this study, we develop a general mechanism to increase neural network robustness based on focus analysis. Recent studies have revealed the phenomenon of \textit{Overfocusing}, which leads to a performance drop. When the network is primarily influenced by small input regions, it becomes less robust and prone to misclassify under noise and corruptions. However, quantifying overfocusing is still vague and lacks clear definitions. Here, we provide a mathematical definition of \textbf{focus}, \textbf{overfocusing} and \textbf{underfocusing}. The notions are general, but in this study, we specifically investigate the case of 3D point clouds. We observe that corrupted sets result in a biased focus distribution compared to the clean training set. We show that as focus distribution deviates from the one learned in the training phase - classification performance deteriorates. We thus propose a parameter-free \textbf{refocusing} algorithm that aims to unify all corruptions under the same distribution. We validate our findings on a 3D zero-shot classification task, achieving SOTA in robust 3D classification on ModelNet-C dataset, and in adversarial defense against Shape-Invariant attack. Code is available in: https://github.com/yossilevii100/refocusing.
Authors: Jun Chen, Haishan Ye, Mengmeng Wang, Tianxin Huang, Guang Dai, Ivor W. Tsang, Yong Liu
Abstract: The conjugate gradient method is a crucial first-order optimization method that generally converges faster than the steepest descent method, and its computational cost is much lower than that of second-order methods. However, while various types of conjugate gradient methods have been studied in Euclidean spaces and on Riemannian manifolds, there is little study for those in distributed scenarios. This paper proposes a decentralized Riemannian conjugate gradient descent (DRCGD) method that aims at minimizing a global function over the Stiefel manifold. The optimization problem is distributed among a network of agents, where each agent is associated with a local function, and the communication between agents occurs over an undirected connected graph. Since the Stiefel manifold is a non-convex set, a global function is represented as a finite sum of possibly non-convex (but smooth) local functions. The proposed method is free from expensive Riemannian geometric operations such as retractions, exponential maps, and vector transports, thereby reducing the computational complexity required by each agent. To the best of our knowledge, DRCGD is the first decentralized Riemannian conjugate gradient algorithm to achieve global convergence over the Stiefel manifold.
Authors: Isabel O. Gallegos, Ryan A. Rossi, Joe Barrow, Md Mehrab Tanjim, Sungchul Kim, Franck Dernoncourt, Tong Yu, Ruiyi Zhang, Nesreen K. Ahmed
Abstract: Rapid advancements of large language models (LLMs) have enabled the processing, understanding, and generation of human-like text, with increasing integration into systems that touch our social sphere. Despite this success, these models can learn, perpetuate, and amplify harmful social biases. In this paper, we present a comprehensive survey of bias evaluation and mitigation techniques for LLMs. We first consolidate, formalize, and expand notions of social bias and fairness in natural language processing, defining distinct facets of harm and introducing several desiderata to operationalize fairness for LLMs. We then unify the literature by proposing three intuitive taxonomies, two for bias evaluation, namely metrics and datasets, and one for mitigation. Our first taxonomy of metrics for bias evaluation disambiguates the relationship between metrics and evaluation datasets, and organizes metrics by the different levels at which they operate in a model: embeddings, probabilities, and generated text. Our second taxonomy of datasets for bias evaluation categorizes datasets by their structure as counterfactual inputs or prompts, and identifies the targeted harms and social groups; we also release a consolidation of publicly-available datasets for improved access. Our third taxonomy of techniques for bias mitigation classifies methods by their intervention during pre-processing, in-training, intra-processing, and post-processing, with granular subcategories that elucidate research trends. Finally, we identify open problems and challenges for future work. Synthesizing a wide range of recent research, we aim to provide a clear guide of the existing literature that empowers researchers and practitioners to better understand and prevent the propagation of bias in LLMs.
Authors: George Stoica, Mihaela Breaban, Vlad Barbu
Abstract: Using additional training data is known to improve the results, especially for medical image 3D segmentation where there is a lack of training material and the model needs to generalize well from few available data. However, the new data could have been acquired using other instruments and preprocessed such its distribution is significantly different from the original training data. Therefore, we study techniques which ameliorate domain shift during training so that the additional data becomes better usable for preprocessing and training together with the original data. Our results show that transforming the additional data using histogram matching has better results than using simple normalization.
Authors: Xingyao Wang, Zihan Wang, Jiateng Liu, Yangyi Chen, Lifan Yuan, Hao Peng, Heng Ji
Abstract: To solve complex tasks, large language models (LLMs) often require multiple rounds of interactions with the user, sometimes assisted by external tools. However, current evaluation protocols often emphasize benchmark performance with single-turn exchanges, neglecting the nuanced interactions among the user, LLMs, and external tools, while also underestimating the importance of natural language feedback from users. These oversights contribute to discrepancies between research benchmark evaluations and real-world use cases. We introduce MINT, a benchmark that evaluates LLMs' ability to solve tasks with multi-turn interactions by (1) using tools and (2) leveraging natural language feedback. To ensure reproducibility, we provide an evaluation framework where LLMs can access tools by executing Python code and receive users' natural language feedback simulated by GPT-4. We repurpose a diverse set of established evaluation datasets focusing on reasoning, coding, and decision-making and carefully curate them into a compact subset for efficient evaluation. Our analysis of 20 open- and closed-source LLMs offers intriguing findings. (a) LLMs generally benefit from tools and language feedback, with performance gains (absolute, same below) of 1-8% for each turn of tool use and 2-17% with natural language feedback. (b) Better single-turn performance does not guarantee better multi-turn performance. (c) Surprisingly, on the LLMs evaluated, supervised instruction-finetuning (SIFT) and reinforcement learning from human feedback (RLHF) generally hurt multi-turn capabilities. We expect MINT can help measure progress and incentivize research in improving LLMs' capabilities in multi-turn interactions, especially for open-source communities where multi-turn human evaluation can be less accessible compared to commercial LLMs with a larger user base.
Authors: Zhoubo Li, Ningyu Zhang, Yunzhi Yao, Mengru Wang, Xi Chen, Huajun Chen
Abstract: As the cost associated with fine-tuning Large Language Models (LLMs) continues to rise, recent research efforts have pivoted towards developing methodologies to edit implicit knowledge embedded within LLMs. Yet, there's still a dark cloud lingering overhead -- will knowledge editing trigger butterfly effect? since it is still unclear whether knowledge editing might introduce side effects that pose potential risks or not. This paper pioneers the investigation into the potential pitfalls associated with knowledge editing for LLMs. To achieve this, we introduce new benchmark datasets and propose innovative evaluation metrics. Our results underline two pivotal concerns: (1) Knowledge Conflict: Editing groups of facts that logically clash can magnify the inherent inconsistencies in LLMs-a facet neglected by previous methods. (2) Knowledge Distortion: Altering parameters with the aim of editing factual knowledge can irrevocably warp the innate knowledge structure of LLMs. Experimental results vividly demonstrate that knowledge editing might inadvertently cast a shadow of unintended consequences on LLMs, which warrant attention and efforts for future works. Code and data are available at https://github.com/zjunlp/PitfallsKnowledgeEditing.
Authors: Fran\c{c}ois H\'el\'enon, Johann Huber, Fa\"iz Ben Amar, St\'ephane Doncieux
Abstract: Despite recent advancements in AI for robotics, grasping remains a partially solved challenge, hindered by the lack of benchmarks and reproducibility constraints. This paper introduces a vision-based grasping framework that can easily be transferred across multiple manipulators. Leveraging Quality-Diversity (QD) algorithms, the framework generates diverse repertoires of open-loop grasping trajectories, enhancing adaptability while maintaining a diversity of grasps. This framework addresses two main issues: the lack of an off-the-shelf vision module for detecting object pose and the generalization of QD trajectories to the whole robot operational space. The proposed solution combines multiple vision modules for 6DoF object detection and tracking while rigidly transforming QD-generated trajectories into the object frame. Experiments on a Franka Research 3 arm and a UR5 arm with a SIH Schunk hand demonstrate comparable performance when the real scene aligns with the simulation used for grasp generation. This work represents a significant stride toward building a reliable vision-based grasping module transferable to new platforms, while being adaptable to diverse scenarios without further training iterations.
Authors: Xiaoxue Zhang, Yifan Hua, Chen Qian
Abstract: Federated Learning (FL) is a well-known paradigm of distributed machine learning on mobile and IoT devices, which preserves data privacy and optimizes communication efficiency. To avoid the single point of failure problem in FL, decentralized federated learning (DFL) has been proposed to use peer-to-peer communication for model aggregation, which has been considered an attractive solution for machine learning tasks on distributed personal devices. However, this process is vulnerable to attackers who share false models and data. If there exists a group of malicious clients, they might harm the performance of the model by carrying out a poisoning attack. In addition, in DFL, clients often lack the incentives to contribute their computing powers to do model training. In this paper, we proposed Blockchain-based Decentralized Federated Learning (BDFL), which leverages a blockchain for decentralized model verification and auditing. BDFL includes an auditor committee for model verification, an incentive mechanism to encourage the participation of clients, a reputation model to evaluate the trustworthiness of clients, and a protocol suite for dynamic network updates. Evaluation results show that, with the reputation mechanism, BDFL achieves fast model convergence and high accuracy on real datasets even if there exist 30\% malicious clients in the system.
Authors: Chen Zhao, Kuan-Jui Su, Chong Wu, Xuewei Cao, Qiuying Sha, Wu Li, Zhe Luo, Tian Qin, Chuan Qiu, Lan Juan Zhao, Anqi Liu, Lindong Jiang, Xiao Zhang, Hui Shen, Weihua Zhou, Hong-Wen Deng
Abstract: Background: Missing data is a common challenge in mass spectrometry-based metabolomics, which can lead to biased and incomplete analyses. The integration of whole-genome sequencing (WGS) data with metabolomics data has emerged as a promising approach to enhance the accuracy of data imputation in metabolomics studies. Method: In this study, we propose a novel method that leverages the information from WGS data and reference metabolites to impute unknown metabolites. Our approach utilizes a multi-view variational autoencoder to jointly model the burden score, polygenetic risk score (PGS), and linkage disequilibrium (LD) pruned single nucleotide polymorphisms (SNPs) for feature extraction and missing metabolomics data imputation. By learning the latent representations of both omics data, our method can effectively impute missing metabolomics values based on genomic information. Results: We evaluate the performance of our method on empirical metabolomics datasets with missing values and demonstrate its superiority compared to conventional imputation techniques. Using 35 template metabolites derived burden scores, PGS and LD-pruned SNPs, the proposed methods achieved R^2-scores > 0.01 for 71.55% of metabolites. Conclusion: The integration of WGS data in metabolomics imputation not only improves data completeness but also enhances downstream analyses, paving the way for more comprehensive and accurate investigations of metabolic pathways and disease associations. Our findings offer valuable insights into the potential benefits of utilizing WGS data for metabolomics data imputation and underscore the importance of leveraging multi-modal data integration in precision medicine research.
Authors: Weikang Wan, Yifeng Zhu, Rutav Shah, Yuke Zhu
Abstract: We introduce LOTUS, a continual imitation learning algorithm that empowers a physical robot to continuously and efficiently learn to solve new manipulation tasks throughout its lifespan. The core idea behind LOTUS is constructing an ever-growing skill library from a sequence of new tasks with a small number of human demonstrations. LOTUS starts with a continual skill discovery process using an open-vocabulary vision model, which extracts skills as recurring patterns presented in unsegmented demonstrations. Continual skill discovery updates existing skills to avoid catastrophic forgetting of previous tasks and adds new skills to solve novel tasks. LOTUS trains a meta-controller that flexibly composes various skills to tackle vision-based manipulation tasks in the lifelong learning process. Our comprehensive experiments show that LOTUS outperforms state-of-the-art baselines by over 11% in success rate, showing its superior knowledge transfer ability compared to prior methods. More results and videos can be found on the project website: https://ut-austin-rpl.github.io/Lotus/.
Authors: Hongwu Peng, Caiwen Ding, Tong Geng, Sutanay Choudhury, Kevin Barker, Ang Li
Abstract: The relentless advancement of artificial intelligence (AI) and machine learning (ML) applications necessitates the development of specialized hardware accelerators capable of handling the increasing complexity and computational demands. Traditional computing architectures, based on the von Neumann model, are being outstripped by the requirements of contemporary AI/ML algorithms, leading to a surge in the creation of accelerators like the Graphcore Intelligence Processing Unit (IPU), Sambanova Reconfigurable Dataflow Unit (RDU), and enhanced GPU platforms. These hardware accelerators are characterized by their innovative data-flow architectures and other design optimizations that promise to deliver superior performance and energy efficiency for AI/ML tasks. This research provides a preliminary evaluation and comparison of these commercial AI/ML accelerators, delving into their hardware and software design features to discern their strengths and unique capabilities. By conducting a series of benchmark evaluations on common DNN operators and other AI/ML workloads, we aim to illuminate the advantages of data-flow architectures over conventional processor designs and offer insights into the performance trade-offs of each platform. The findings from our study will serve as a valuable reference for the design and performance expectations of research prototypes, thereby facilitating the development of next-generation hardware accelerators tailored for the ever-evolving landscape of AI/ML applications. Through this analysis, we aspire to contribute to the broader understanding of current accelerator technologies and to provide guidance for future innovations in the field.
Authors: Artem Tsypin, Leonid Ugadiarov, Kuzma Khrabrov, Alexander Telepov, Egor Rumiantsev, Alexey Skrynnik, Aleksandr I. Panov, Dmitry Vetrov, Elena Tutubalina, Artur Kadurin
Abstract: Molecular conformation optimization is crucial to computer-aided drug discovery and materials design. Traditional energy minimization techniques rely on iterative optimization methods that use molecular forces calculated by a physical simulator (oracle) as anti-gradients. However, this is a computationally expensive approach that requires many interactions with a physical simulator. One way to accelerate this procedure is to replace the physical simulator with a neural network. Despite recent progress in neural networks for molecular conformation energy prediction, such models are prone to distribution shift, leading to inaccurate energy minimization. We find that the quality of energy minimization with neural networks can be improved by providing optimization trajectories as additional training data. Still, it takes around $5 \times 10^5$ additional conformations to match the physical simulator's optimization quality. In this work, we present the Gradual Optimization Learning Framework (GOLF) for energy minimization with neural networks that significantly reduces the required additional data. The framework consists of an efficient data-collecting scheme and an external optimizer. The external optimizer utilizes gradients from the energy prediction model to generate optimization trajectories, and the data-collecting scheme selects additional training data to be processed by the physical simulator. Our results demonstrate that the neural network trained with GOLF performs on par with the oracle on a benchmark of diverse drug-like molecules using $50$x less additional data.
Authors: Kylie J. Trettner, Jeremy Hsieh, Weikun Xiao, Jerry S. H. Lee, Andrea M. Armani
Abstract: Ascertaining the collective viability of cells in different cell culture conditions has typically relied on averaging colorimetric indicators and is often reported out in simple binary readouts. Recent research has combined viability assessment techniques with image-based deep-learning models to automate the characterization of cellular properties. However, further development of viability measurements to assess the continuity of possible cellular states and responses to perturbation across cell culture conditions is needed. In this work, we demonstrate an image processing algorithm for quantifying cellular viability in 3D cultures without the need for assay-based indicators. We show that our algorithm performs similarly to a pair of human experts in whole-well images over a range of days and culture matrix compositions. To demonstrate potential utility, we perform a longitudinal study investigating the impact of a known therapeutic on pancreatic cancer spheroids. Using images taken with a high content imaging system, the algorithm successfully tracks viability at the individual spheroid and whole-well level. The method we propose reduces analysis time by 97% in comparison to the experts. Because the method is independent of the microscope or imaging system used, this approach lays the foundation for accelerating progress in and for improving the robustness and reproducibility of 3D culture analysis across biological and clinical research.
Authors: Akira Sone, Akira Tanji, Naoki Yamamoto
Abstract: Motivated by the great success of classical generative models in machine learning, enthusiastic exploration of their quantum version has recently started. To depart on this journey, it is important to develop a relevant metric to evaluate the quality of quantum generative models; in the classical case, one such example is the inception score. In this paper, we propose the quantum inception score, which relates the quality to the Holevo information of the quantum channel that classifies a given dataset. We prove that, under this proposed measure, the quantum generative models provide better quality than their classical counterparts because of the presence of quantum coherence, characterized by the resource theory of asymmetry, and entanglement. Furthermore, we harness the quantum fluctuation theorem to characterize the physical limitation of the quality of quantum generative models. Finally, we apply the quantum inception score to assess the quality of the one-dimensional spin chain model as a quantum generative model, with the quantum convolutional neural network as a quantum classifier, for the phase classification problem in the quantum many-body physics.
Authors: Amir H. Ashouri, Muhammad Asif Manzoor, Duc Minh Vu, Raymond Zhang, Ziwen Wang, Angel Zhang, Bryan Chan, Tomasz S. Czajkowski, Yaoqing Gao
Abstract: The key to performance optimization of a program is to decide correctly when a certain transformation should be applied by a compiler. This is an ideal opportunity to apply machine-learning models to speed up the tuning process; while this realization has been around since the late 90s, only recent advancements in ML enabled a practical application of ML to compilers as an end-to-end framework. This paper presents ACPO: \textbf{\underline{A}}I-Enabled \textbf{\underline{C}}ompiler-driven \textbf{\underline{P}}rogram \textbf{\underline{O}}ptimization; a novel framework to provide LLVM with simple and comprehensive tools to benefit from employing ML models for different optimization passes. We first showcase the high-level view, class hierarchy, and functionalities of ACPO and subsequently, demonstrate a couple of use cases of ACPO by ML-enabling the Loop Unroll and Function Inlining passes and describe how ACPO can be leveraged to optimize other passes. Experimental results reveal that ACPO model for Loop Unroll is able to gain on average 4\% compared to LLVM's O3 optimization when deployed on Polybench. Furthermore, by adding the Inliner model as well, ACPO is able to provide up to 4.5\% and 2.4\% on Polybench and Cbench compared with LLVM's O3 optimization, respectively.
Authors: Siamul Karim Khan, Patrick Tinsley, Mahsa Mitcheff, Patrick Flynn, Kevin W. Bowyer, Adam Czajka
Abstract: Synthesis of same-identity biometric iris images, both for existing and non-existing identities while preserving the identity across a wide range of pupil sizes, is complex due to intricate iris muscle constriction mechanism, requiring a precise model of iris non-linear texture deformations to be embedded into the synthesis pipeline. This paper presents the first method of fully data-driven, identity-preserving, pupil size-varying s ynthesis of iris images. This approach is capable of synthesizing images of irises with different pupil sizes representing non-existing identities as well as non-linearly deforming the texture of iris images of existing subjects given the segmentation mask of the target iris image. Iris recognition experiments suggest that the proposed deformation model not only preserves the identity when changing the pupil size but offers better similarity between same-identity iris samples with significant differences in pupil size, compared to state-of-the-art linear and non-linear (bio-mechanical-based) iris deformation models. Two immediate applications of the proposed approach are: (a) synthesis of, or enhancement of the existing biometric datasets for iris recognition, mimicking those acquired with iris sensors, and (b) helping forensic human experts in examining iris image pairs with significant differences in pupil dilation. Source codes and weights of the models are made available with the paper.
Authors: Mengyao Lyu, Yuhong Yang, Haiwen Hong, Hui Chen, Xuan Jin, Yuan He, Hui Xue, Jungong Han, Guiguang Ding
Abstract: The prevalent use of commercial and open-source diffusion models (DMs) for text-to-image generation prompts risk mitigation to prevent undesired behaviors. Existing concept erasing methods in academia are all based on full parameter or specification-based fine-tuning, from which we observe the following issues: 1) Generation alternation towards erosion: Parameter drift during target elimination causes alternations and potential deformations across all generations, even eroding other concepts at varying degrees, which is more evident with multi-concept erased; 2) Transfer inability & deployment inefficiency: Previous model-specific erasure impedes the flexible combination of concepts and the training-free transfer towards other models, resulting in linear cost growth as the deployment scenarios increase. To achieve non-invasive, precise, customizable, and transferable elimination, we ground our erasing framework on one-dimensional adapters to erase multiple concepts from most DMs at once across versatile erasing applications. The concept-SemiPermeable structure is injected as a Membrane (SPM) into any DM to learn targeted erasing, and meantime the alteration and erosion phenomenon is effectively mitigated via a novel Latent Anchoring fine-tuning strategy. Once obtained, SPMs can be flexibly combined and plug-and-play for other DMs without specific re-tuning, enabling timely and efficient adaptation to diverse scenarios. During generation, our Facilitated Transport mechanism dynamically regulates the permeability of each SPM to respond to different input prompts, further minimizing the impact on other concepts. Quantitative and qualitative results across ~40 concepts, 7 DMs and 4 erasing applications have demonstrated the superior erasing of SPM. Our code and pre-tuned SPMs are available on the project page https://lyumengyao.github.io/projects/spm.
Authors: Jonas Dippel, Barbara Feulner, Tobias Winterhoff, Simon Schallenberg, Gabriel Dernbach, Andreas Kunft, Stephan Tietz, Timo Milbich, Simon Heinke, Marie-Lisa Eich, Julika Ribbat-Idel, Rosemarie Krupar, Philipp Jurmeister, David Horst, Lukas Ruff, Klaus-Robert M\"uller, Frederick Klauschen, Maximilian Alber
Abstract: Histopathology plays a central role in clinical medicine and biomedical research. While artificial intelligence shows promising results on many pathological tasks, generalization and dealing with rare diseases, where training data is scarce, remains a challenge. Distilling knowledge from unlabelled data into a foundation model before learning from, potentially limited, labelled data provides a viable path to address these challenges. In this work, we extend the state of the art of foundation models for digital pathology whole slide images by semi-automated data curation and incorporating pathologist domain knowledge. Specifically, we combine computational and pathologist domain knowledge (1) to curate a diverse dataset of 133k slides corresponding to 1.2 billion image patches covering data from different fixation, staining, and scanning protocols as well as data from different indications and labs across the EU and US, (2) for grouping semantically similar slides and tissue patches, and (3) to augment the input images during training. We evaluate the resulting model on a set of public and internal benchmarks and show that although our foundation model is trained with an order of magnitude less slides, it performs on par or better than competing models. We expect that scaling our approach to more data and larger models will further increase its performance and capacity to deal with increasingly complex real world tasks in diagnostics and biomedical research.
Authors: Vincent Roca, Gr\'egory Kuchcinski, Jean-Pierre Pruvo, Dorian Manouvriez, Renaud Lopes
Abstract: In MRI studies, the aggregation of imaging data from multiple acquisition sites enhances sample size but may introduce site-related variabilities that hinder consistency in subsequent analyses. Deep learning methods for image translation have emerged as a solution for harmonizing MR images across sites. In this study, we introduce IGUANe (Image Generation with Unified Adversarial Networks), an original 3D model that leverages the strengths of domain translation and straightforward application of style transfer methods for multicenter brain MR image harmonization. IGUANe extends CycleGAN architecture by integrating an arbitrary number of domains for training through a many-to-one strategy. During inference, the model can be applied to any image, even from an unknown acquisition site, making it a universal generator for harmonization. Trained on a dataset comprising T1-weighted images from 11 different scanners, IGUANe was evaluated on data from unseen sites. The assessments included the transformation of MR images with traveling subjects, the preservation of pairwise distances between MR images within domains, the evolution of volumetric patterns related to age and Alzheimer$^\prime$s disease (AD), and the performance in age regression and patient classification tasks. Comparisons with other harmonization and normalization methods suggest that IGUANe better preserves individual information in MR images and is more suitable for maintaining and reinforcing variabilities related to age and AD. Future studies may further assess IGUANe in other multicenter contexts, either using the same model or retraining it for applications to different image modalities.
Authors: Yizhou Zhang, Lun Du, Defu Cao, Qiang Fu, Yan Liu
Abstract: Foundation models, such as Large language Models (LLMs), have attracted significant amount of interest due to their large number of applications. Existing works show that appropriate prompt design, such as Chain-of-Thoughts, can unlock LLM's powerful capacity in diverse areas. However, when handling tasks involving repetitive sub-tasks and/or deceptive contents, such as arithmetic calculation and article-level fake news detection, existing prompting strategies either suffers from insufficient expressive power or intermediate errors triggered by hallucination. To make LLM more discerning to such intermediate errors, we propose to guide LLM with a Divide-and-Conquer program that simultaneously ensures superior expressive power and disentangles task decomposition, sub-task resolution, and resolution assembly process. Theoretic analysis reveals that our strategy can guide LLM to extend the expressive power of fixed-depth Transformer. Experiments indicate that our proposed method can achieve better performance than typical prompting strategies in tasks bothered by intermediate errors and deceptive contents, such as large integer multiplication, hallucination detection and misinformation detection.
Authors: Cho-Yuan Lee, Kuan-Chen Wang, Kai-Chun Liu, Xugang Lu, Ping-Cheng Yeh, Yu Tsao
Abstract: In practical scenarios involving the measurement of surface electromyography (sEMG) in muscles, particularly those areas near the heart, one of the primary sources of contamination is the presence of electrocardiogram (ECG) signals. To assess the quality of real-world sEMG data more effectively, this study proposes QASE-net, a new non-intrusive model that predicts the SNR of sEMG signals. QASE-net combines CNN-BLSTM with attention mechanisms and follows an end-to-end training strategy. Our experimental framework utilizes real-world sEMG and ECG data from two open-access databases, the Non-Invasive Adaptive Prosthetics Database and the MIT-BIH Normal Sinus Rhythm Database, respectively. The experimental results demonstrate the superiority of QASE-net over the previous assessment model, exhibiting significantly reduced prediction errors and notably higher linear correlations with the ground truth. These findings show the potential of QASE-net to substantially enhance the reliability and precision of sEMG quality assessment in practical applications.
Authors: Alvin Grissom II, Ryan F. Lei, Matt Gusdorff, Jeova Farias Sales Rocha Neto, Bailey Lin, Ryan Trotter
Abstract: Generative adversarial networks (GANs) generate photorealistic faces that are often indistinguishable by humans from real faces. While biases in machine learning models are often assumed to be due to biases in training data, we find pathological internal color and luminance biases in the discriminator of a pre-trained StyleGAN3-r model that are not explicable by the training data. We also find that the discriminator systematically stratifies scores by both image- and face-level qualities and that this disproportionately affects images across gender, race, and other categories. We examine axes common in research on stereotyping in social psychology.
Authors: Jiarui Lu, Zuobai Zhang, Bozitao Zhong, Chence Shi, Jian Tang
Abstract: The protein dynamics are common and important for their biological functions and properties, the study of which usually involves time-consuming molecular dynamics (MD) simulations in silico. Recently, generative models has been leveraged as a surrogate sampler to obtain conformation ensembles with orders of magnitude faster and without requiring any simulation data (a "zero-shot" inference). However, being agnostic of the underlying energy landscape, the accuracy of such generative model may still be limited. In this work, we explore the few-shot setting of such pre-trained generative sampler which incorporates MD simulations in a tractable manner. Specifically, given a target protein of interest, we first acquire some seeding conformations from the pre-trained sampler followed by a number of physical simulations in parallel starting from these seeding samples. Then we fine-tuned the generative model using the simulation trajectories above to become a target-specific sampler. Experimental results demonstrated the superior performance of such few-shot conformation sampler at a tractable computational cost.
Authors: Tsung-Wei Ke, Nikolaos Gkanatsios, Katerina Fragkiadaki
Abstract: We marry diffusion policies and 3D scene representations for robot manipulation. Diffusion policies learn the action distribution conditioned on the robot and environment state using conditional diffusion models. They have recently shown to outperform both deterministic and alternative state-conditioned action distribution learning methods. 3D robot policies use 3D scene feature representations aggregated from a single or multiple camera views using sensed depth. They have shown to generalize better than their 2D counterparts across camera viewpoints. We unify these two lines of work and present 3D Diffuser Actor, a neural policy architecture that, given a language instruction, builds a 3D representation of the visual scene and conditions on it to iteratively denoise 3D rotations and translations for the robot's end-effector. At each denoising iteration, our model represents end-effector pose estimates as 3D scene tokens and predicts the 3D translation and rotation error for each of them, by featurizing them using 3D relative attention to other 3D visual and language tokens. 3D Diffuser Actor sets a new state-of-the-art on RLBench with an absolute performance gain of 16.3% over the current SOTA on a multi-view setup and an absolute gain of 13.1% on a single-view setup. On the CALVIN benchmark, it outperforms the current SOTA in the setting of zero-shot unseen scene generalization by being able to successfully run 0.2 more tasks, a 7% relative increase. It also works in the real world from a handful of demonstrations. We ablate our model's architectural design choices, such as 3D scene featurization and 3D relative attentions, and show they all help generalization. Our results suggest that 3D scene representations and powerful generative modeling are keys to efficient robot learning from demonstrations.
Authors: Jianrui Zhang, Mu Cai, Tengyang Xie, Yong Jae Lee
Abstract: We propose CounterCurate, a framework to comprehensively improve the visio-linguistic compositional reasoning capability for both contrastive and generative multimodal models. In particular, we identify two critical under-explored problems: the neglect of the physically grounded reasoning (counting and position understanding) and the potential of using highly capable text and image generation models for semantic counterfactual fine-tuning. Our work pioneers an approach that addresses these gaps. We first spotlight the near-chance performance of multimodal models like CLIP and LLaVA in physically grounded compositional reasoning. We then apply simple data augmentation using grounded image generation model GLIGEN to generate fine-tuning data, resulting in significant performance improvements: +33% and +37% for CLIP and LLaVA, respectively, on our newly curated Flickr30k-Positions benchmark. Moreover, we exploit the capabilities of high-performing text generation and image generation models, specifically GPT-4V and DALLE-3, to curate challenging semantic counterfactuals, thereby further enhancing compositional reasoning capabilities on benchmarks such as SugarCrepe, where CounterCurate outperforms GPT-4V.
Authors: Paola Arrubarrena, Maud Lemercier, Bojan Nikolic, Terry Lyons, Thomas Cass
Abstract: We introduce SigNova, a new semi-supervised framework for detecting anomalies in streamed data. While our initial examples focus on detecting radio-frequency interference (RFI) in digitized signals within the field of radio astronomy, it is important to note that SigNova's applicability extends to any type of streamed data. The framework comprises three primary components. Firstly, we use the signature transform to extract a canonical collection of summary statistics from observational sequences. This allows us to represent variable-length visibility samples as finite-dimensional feature vectors. Secondly, each feature vector is assigned a novelty score, calculated as the Mahalanobis distance to its nearest neighbor in an RFI-free training set. By thresholding these scores we identify observation ranges that deviate from the expected behavior of RFI-free visibility samples without relying on stringent distributional assumptions. Thirdly, we integrate this anomaly detector with Pysegments, a segmentation algorithm, to localize consecutive observations contaminated with RFI, if any. This approach provides a compelling alternative to classical windowing techniques commonly used for RFI detection. Importantly, the complexity of our algorithm depends on the RFI pattern rather than on the size of the observation window. We demonstrate how SigNova improves the detection of various types of RFI (e.g., broadband and narrowband) in time-frequency visibility data. We validate our framework on the Murchison Widefield Array (MWA) telescope and simulated data and the Hydrogen Epoch of Reionization Array (HERA).
Authors: Sirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu, Binhao Wu, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Li Zhang, Lingyao Zhang, Min Yang, Mingchen Zhuge, Taicheng Guo, Tuo Zhou, Wei Tao, Wenyi Wang, Xiangru Tang, Xiangtao Lu, Xiawu Zheng, Xinbing Liang, Yaying Fei, Yuheng Cheng, Zongze Xu, Chenglin Wu
Abstract: Large Language Model (LLM)-based agents have demonstrated remarkable effectiveness. However, their performance can be compromised in data science scenarios that require real-time data adjustment, expertise in optimization due to complex dependencies among various tasks, and the ability to identify logical errors for precise reasoning. In this study, we introduce the Data Interpreter, a solution designed to solve with code that emphasizes three pivotal techniques to augment problem-solving in data science: 1) dynamic planning with hierarchical graph structures for real-time data adaptability;2) tool integration dynamically to enhance code proficiency during execution, enriching the requisite expertise;3) logical inconsistency identification in feedback, and efficiency enhancement through experience recording. We evaluate the Data Interpreter on various data science and real-world tasks. Compared to open-source baselines, it demonstrated superior performance, exhibiting significant improvements in machine learning tasks, increasing from 0.86 to 0.95. Additionally, it showed a 26% increase in the MATH dataset and a remarkable 112% improvement in open-ended tasks. The solution will be released at https://github.com/geekan/MetaGPT.
Authors: Salah Ghamizi, Jun Cao, Aoxiang Ma, Pedro Rodriguez
Abstract: Efficiently solving unbalanced three-phase power flow in distribution grids is pivotal for grid analysis and simulation. There is a pressing need for scalable algorithms capable of handling large-scale unbalanced power grids that can provide accurate and fast solutions. To address this, deep learning techniques, especially Graph Neural Networks (GNNs), have emerged. However, existing literature primarily focuses on balanced networks, leaving a critical gap in supporting unbalanced three-phase power grids. This letter introduces PowerFlowMultiNet, a novel multigraph GNN framework explicitly designed for unbalanced three-phase power grids. The proposed approach models each phase separately in a multigraph representation, effectively capturing the inherent asymmetry in unbalanced grids. A graph embedding mechanism utilizing message passing is introduced to capture spatial dependencies within the power system network. PowerFlowMultiNet outperforms traditional methods and other deep learning approaches in terms of accuracy and computational speed. Rigorous testing reveals significantly lower error rates and a notable hundredfold increase in computational speed for large power networks compared to model-based methods.
Authors: Shiqi Chen, Miao Xiong, Junteng Liu, Zhengxuan Wu, Teng Xiao, Siyang Gao, Junxian He
Abstract: Large language models (LLMs) frequently hallucinate and produce factual errors, yet our understanding of why they make these errors remains limited. In this study, we delve into the underlying mechanisms of LLM hallucinations from the perspective of inner representations, and discover a salient pattern associated with hallucinations: correct generations tend to have sharper context activations in the hidden states of the in-context tokens, compared to the incorrect ones. Leveraging this insight, we propose an entropy-based metric to quantify the ``sharpness'' among the in-context hidden states and incorporate it into the decoding process to formulate a constrained decoding approach. Experiments on various knowledge-seeking and hallucination benchmarks demonstrate our approach's consistent effectiveness, for example, achieving up to an 8.6 point improvement on TruthfulQA. We believe this study can improve our understanding of hallucinations and serve as a practical solution for hallucination mitigation.
Authors: Jiahuan Yan, Bo Zheng, Hongxia Xu, Yiheng Zhu, Danny Z. Chen, Jimeng Sun, Jian Wu, Jintai Chen
Abstract: The transferability of deep neural networks (DNNs) has made significant progress in image and language processing. However, due to the heterogeneity among tables, such DNN bonus is still far from being well exploited on tabular data prediction (e.g., regression or classification tasks). Condensing knowledge from diverse domains, language models (LMs) possess the capability to comprehend feature names from various tables, potentially serving as versatile learners in transferring knowledge across distinct tables and diverse prediction tasks, but their discrete text representation space is inherently incompatible with numerical feature values in tables. In this paper, we present TP-BERTa, a specifically pre-trained LM for tabular data prediction. Concretely, a novel relative magnitude tokenization converts scalar numerical feature values to finely discrete, high-dimensional tokens, and an intra-feature attention approach integrates feature values with the corresponding feature names. Comprehensive experiments demonstrate that our pre-trained TP-BERTa leads the performance among tabular DNNs and is competitive with Gradient Boosted Decision Tree models in typical tabular data regime.
Authors: Tuan A. Bohoran, Polydoros N. Kampaktsis, Laura McLaughlin, Jay Leb, Gerry P. McCann, Archontis Giannakidis
Abstract: The right ventricular (RV) function deterioration strongly predicts clinical outcomes in numerous circumstances. To boost the clinical deployment of ensemble regression methods that quantify RV volumes using tabular data from the widely available two-dimensional echocardiography (2DE), we propose to complement the volume predictions with uncertainty scores. To this end, we employ an instance-based method which uses the learned tree structure to identify the nearest training samples to a target instance and then uses a number of distribution types to more flexibly model the output. The probabilistic and point-prediction performances of the proposed framework are evaluated on a relatively small-scale dataset, comprising 100 end-diastolic and end-systolic RV volumes. The reference values for point performance were obtained from MRI. The results demonstrate that our flexible approach yields improved probabilistic and point performances over other state-of-the-art methods. The appropriateness of the proposed framework is showcased by providing exemplar cases. The estimated uncertainty embodies both aleatoric and epistemic types. This work aligns with trustworthy artificial intelligence since it can be used to enhance the decision-making process and reduce risks. The feature importance scores of our framework can be exploited to reduce the number of required 2DE views which could enhance the proposed pipeline's clinical application.
Authors: Ivan Lau, Shiqian Ma, C\'esar A. Uribe
Abstract: This paper considers the decentralized (discrete) optimal transport (D-OT) problem. In this setting, a network of agents seeks to design a transportation plan jointly, where the cost function is the sum of privately held costs for each agent. We reformulate the D-OT problem as a constraint-coupled optimization problem and propose a single-loop decentralized algorithm with an iteration complexity of O(1/{\epsilon}) that matches existing centralized first-order approaches. Moreover, we propose the decentralized equitable optimal transport (DE-OT) problem. In DE-OT, in addition to cooperatively designing a transportation plan that minimizes transportation costs, agents seek to ensure equity in their individual costs. The iteration complexity of the proposed method to solve DE-OT is also O(1/{\epsilon}). This rate improves existing centralized algorithms, where the best iteration complexity obtained is O(1/{\epsilon}^2).
Authors: Yi-An Chen, Kai-Feng Chen
Abstract: Machine learning, particularly deep neural networks, has been widely utilized in high energy physics and has shown remarkable results in various applications. Moreover, the concept of machine learning has been extended to quantum computers, giving rise to a new research area known as quantum machine learning. In this paper, we propose a novel variational quantum circuit model, Quantum Complete Graph Neural Network (QCGNN), designed for learning complete graphs. We argue that QCGNN has a polynomial speedup against its classical counterpart, due to the property of quantum parallelism. In this paper, we study the application of QCGNN through the challenging jet discrimination, where the jets are represented with complete graphs. Subsequently, we conduct a comparative analysis with classical graph neural networks to establish a benchmark.
Authors: Samuel Schmidgall, Ji Woong Kim, Jeffery Jopling, Axel Krieger
Abstract: The absence of openly accessible data and specialized foundation models is a major barrier for computational research in surgery. Toward this, (i) we open-source the largest dataset of general surgery videos to-date, consisting of 680 hours of surgical videos, including data from robotic and laparoscopic techniques across 28 procedures; (ii) we propose a technique for video pre-training a general surgery vision transformer (GSViT) on surgical videos based on forward video prediction that can run in real-time for surgical applications, toward which we open-source the code and weights of GSViT; (iii) we also release code and weights for procedure-specific fine-tuned versions of GSViT across 10 procedures; (iv) we demonstrate the performance of GSViT on the Cholec80 phase annotation task, displaying improved performance over state-of-the-art single frame predictors.
Authors: Xiang Li, Soo Min Kwon, Ismail R. Alkhouri, Saiprasad Ravishanka, Qing Qu
Abstract: Diffusion models have recently gained traction as a powerful class of deep generative priors, excelling in a wide range of image restoration tasks due to their exceptional ability to model data distributions. To solve image restoration problems, many existing techniques achieve data consistency by incorporating additional likelihood gradient steps into the reverse sampling process of diffusion models. However, the additional gradient steps pose a challenge for real-world practical applications as they incur a large computational overhead, thereby increasing inference time. They also present additional difficulties when using accelerated diffusion model samplers, as the number of data consistency steps is limited by the number of reverse sampling steps. In this work, we propose a novel diffusion-based image restoration solver that addresses these issues by decoupling the reverse process from the data consistency steps. Our method involves alternating between a reconstruction phase to maintain data consistency and a refinement phase that enforces the prior via diffusion purification. Our approach demonstrates versatility, making it highly adaptable for efficient problem-solving in latent space. Additionally, it reduces the necessity for numerous sampling steps through the integration of consistency models. The efficacy of our approach is validated through comprehensive experiments across various image restoration tasks, including image denoising, deblurring, inpainting, and super-resolution.
Authors: Wenpin Tang
Abstract: This paper aims to develop and provide a rigorous treatment to the problem of entropy regularized fine-tuning in the context of continuous-time diffusion models, which was recently proposed by Uehara et al. (arXiv:2402.15194, 2024). The idea is to use stochastic control for sample generation, where the entropy regularizer is introduced to mitigate reward collapse. We also show how the analysis can be extended to fine-tuning involving a general $f$-divergence regularizer.