Authors: Hanchen David Wang, Nibraas Khan, Anna Chen, Nilanjan Sarkar, Pamela Wisniewski, Meiyi Ma
Abstract: Recent global estimates suggest that as many as 2.41 billion individuals have health conditions that would benefit from rehabilitation services. Home-based Physical Therapy (PT) faces significant challenges in providing interactive feedback and meaningful observation for therapists and patients. To fill this gap, we present MicroXercise, which integrates micro-motion analysis with wearable sensors, providing therapists and patients with a comprehensive feedback interface, including video, text, and scores. Crucially, it employs multi-dimensional Dynamic Time Warping (DTW) and attribution-based explainable methods to analyze the existing deep learning neural networks in monitoring exercises, focusing on a high granularity of exercise. This synergistic approach is pivotal, providing output matching the input size to precisely highlight critical subtleties and movements in PT, thus transforming complex AI analysis into clear, actionable feedback. By highlighting these micro-motions in different metrics, such as stability and range of motion, MicroXercise significantly enhances the understanding and relevance of feedback for end-users. Comparative performance metrics underscore its effectiveness over traditional methods, such as a 39% and 42% improvement in Feature Mutual Information (FMI) and Continuity. MicroXercise is a step ahead in home-based physical therapy, providing a technologically advanced and intuitively helpful solution to enhance patient care and outcomes.
Authors: Hongye Zheng, Bingxing Wang, Minheng Xiao, Honglin Qin, Zhizhong Wu, Lianghao Tan
Abstract: Adaptive optimizers are pivotal in guiding the weight updates of deep neural networks, yet they often face challenges such as poor generalization and oscillation issues. To counter these, we introduce sigSignGrad and tanhSignGrad, two novel optimizers that integrate adaptive friction coefficients based on the Sigmoid and Tanh functions, respectively. These algorithms leverage short-term gradient information, a feature overlooked in traditional Adam variants like diffGrad and AngularGrad, to enhance parameter updates and convergence.Our theoretical analysis demonstrates the wide-ranging adjustment capability of the friction coefficient S, which aligns with targeted parameter update strategies and outperforms existing methods in both optimization trajectory smoothness and convergence rate. Extensive experiments on CIFAR-10, CIFAR-100, and Mini-ImageNet datasets using ResNet50 and ViT architectures confirm the superior performance of our proposed optimizers, showcasing improved accuracy and reduced training time. The innovative approach of integrating adaptive friction coefficients as plug-ins into existing optimizers, exemplified by the sigSignAdamW and sigSignAdamP variants, presents a promising strategy for boosting the optimization performance of established algorithms. The findings of this study contribute to the advancement of optimizer design in deep learning.
Authors: Yukun Zhang
Abstract: This paper explores the application of Stochastic Differential Equations (SDE) to interpret the text generation process of Large Language Models (LLMs) such as GPT-4. Text generation in LLMs is modeled as a stochastic process where each step depends on previously generated content and model parameters, sampling the next word from a vocabulary distribution. We represent this generation process using SDE to capture both deterministic trends and stochastic perturbations. The drift term describes the deterministic trends in the generation process, while the diffusion term captures the stochastic variations. We fit these functions using neural networks and validate the model on real-world text corpora. Through numerical simulations and comprehensive analyses, including drift and diffusion analysis, stochastic process property evaluation, and phase space exploration, we provide deep insights into the dynamics of text generation. This approach not only enhances the understanding of the inner workings of LLMs but also offers a novel mathematical perspective on language generation, which is crucial for diagnosing, optimizing, and controlling the quality of generated text.
Authors: Bowen Wei, Ziwei Zhu
Abstract: Rule-based neural networks stand out for enabling interpretable classification by learning logical rules for both prediction and interpretation. However, existing models often lack flexibility due to the fixed model structure. Addressing this, we introduce the Normal Form Rule Learner (NFRL) algorithm, leveraging a selective discrete neural network, that treat weight parameters as hard selectors, to learn rules in both Conjunctive Normal Form (CNF) and Disjunctive Normal Form (DNF) for enhanced accuracy and interpretability. Instead of adopting a deep, complex structure, the NFRL incorporates two specialized Normal Form Layers (NFLs) with adaptable AND/OR neurons, a Negation Layer for input negations, and a Normal Form Constraint (NFC) to streamline neuron connections. We also show the novel network architecture can be optimized using adaptive gradient update together with Straight-Through Estimator to overcome the gradient vanishing challenge. Through extensive experiments on 11 datasets, NFRL demonstrates superior classification performance, quality of learned rules, efficiency and interpretability compared to 12 state-of-the-art alternatives. Code and data are available at \url{https://anonymous.4open.science/r/NFRL-27B4/}.
Authors: Logan Cummins, Alexander Sommers, Sudip Mittal, Shahram Rahimi, Maria Seale, Joseph Jaboure, Thomas Arnold
Abstract: There exists three main areas of study inside of the field of predictive maintenance: anomaly detection, fault diagnosis, and remaining useful life prediction. Notably, anomaly detection alerts the stakeholder that an anomaly is occurring. This raises two fundamental questions: what is causing the fault and how can we fix it? Inside of the field of explainable artificial intelligence, counterfactual explanations can give that information in the form of what changes to make to put the data point into the opposing class, in this case "healthy". The suggestions are not always actionable which may raise the interest in asking "what if we do this instead?" In this work, we provide a proof of concept for utilizing counterfactual explanations as what-if analysis. We perform this on the PRONOSTIA dataset with a temporal convolutional network as the anomaly detector. Our method presents the counterfactuals in the form of a what-if analysis for this base problem to inspire future work for more complex systems and scenarios.
Authors: Abhimanyu Mukerji, Sushant More, Ashwin Viswanathan Kannan, Lakshmi Ravi, Hua Chen, Naman Kohli, Chris Khawand, Dinesh Mandalapu
Abstract: With recent rapid growth in online shopping, AI-powered Engagement Surfaces (ES) have become ubiquitous across retail services. These engagement surfaces perform an increasing range of functions, including recommending new products for purchase, reminding customers of their orders and providing delivery notifications. Understanding the causal effect of engagement surfaces on value driven for customers and businesses remains an open scientific question. In this paper, we develop a dynamic causal model at scale to disentangle value attributable to an ES, and to assess its effectiveness. We demonstrate the application of this model to inform business decision-making by understanding returns on investment in the ES, and identifying product lines and features where the ES adds the most value.
Authors: Tianyi Lin, Chi Jin, Michael. I. Jordan
Abstract: We provide a unified analysis of two-timescale gradient descent ascent (TTGDA) for solving structured nonconvex minimax optimization problems in the form of $\min_\textbf{x} \max_{\textbf{y} \in Y} f(\textbf{x}, \textbf{y})$, where the objective function $f(\textbf{x}, \textbf{y})$ is nonconvex in $\textbf{x}$ and concave in $\textbf{y}$, and the constraint set $Y \subseteq \mathbb{R}^n$ is convex and bounded. In the convex-concave setting, the single-timescale GDA achieves strong convergence guarantees and has been used for solving application problems arising from operations research and computer science. However, it can fail to converge in more general settings. Our contribution in this paper is to design the simple deterministic and stochastic TTGDA algorithms that efficiently find one stationary point of the function $\Phi(\cdot) := \max_{\textbf{y} \in Y} f(\cdot, \textbf{y})$. Specifically, we prove the theoretical bounds on the complexity of solving both smooth and nonsmooth nonconvex-concave minimax optimization problems. To our knowledge, this is the first systematic analysis of TTGDA for nonconvex minimax optimization, shedding light on its superior performance in training generative adversarial networks (GANs) and in solving other real-world application problems.
Authors: Francesco Innocenti, El Mehdi Achour, Ryan Singh, Christopher L. Buckley
Abstract: Predictive coding (PC) is an energy-based learning algorithm that performs iterative inference over network activities before weight updates. Recent work suggests that PC can converge in fewer learning steps than backpropagation thanks to its inference procedure. However, these advantages are not always observed, and the impact of PC inference on learning is theoretically not well understood. Here, we study the geometry of the PC energy landscape at the (inference) equilibrium of the network activities. For deep linear networks, we first show that the equilibrated energy is simply a rescaled mean squared error loss with a weight-dependent rescaling. We then prove that many highly degenerate (non-strict) saddles of the loss including the origin become much easier to escape (strict) in the equilibrated energy. Our theory is validated by experiments on both linear and non-linear networks. Based on these results, we conjecture that all the saddles of the equilibrated energy are strict. Overall, this work suggests that PC inference makes the loss landscape more benign and robust to vanishing gradients, while also highlighting the challenge of speeding up PC inference on large-scale models.
Authors: Alireza Jafari, Geoffrey Fox, John B. Rundle, Andrea Donnellan, Lisa Grant Ludwig
Abstract: Advancing the capabilities of earthquake nowcasting, the real-time forecasting of seismic activities remains a crucial and enduring objective aimed at reducing casualties. This multifaceted challenge has recently gained attention within the deep learning domain, facilitated by the availability of extensive, long-term earthquake datasets. Despite significant advancements, existing literature on earthquake nowcasting lacks comprehensive evaluations of pre-trained foundation models and modern deep learning architectures. These architectures, such as transformers or graph neural networks, uniquely focus on different aspects of data, including spatial relationships, temporal patterns, and multi-scale dependencies. This paper addresses the mentioned gap by analyzing different architectures and introducing two innovation approaches called MultiFoundationQuake and GNNCoder. We formulate earthquake nowcasting as a time series forecasting problem for the next 14 days within 0.1-degree spatial bins in Southern California, spanning from 1986 to 2024. Earthquake time series is forecasted as a function of logarithm energy released by quakes. Our comprehensive evaluation employs several key performance metrics, notably Nash-Sutcliffe Efficiency and Mean Squared Error, over time in each spatial region. The results demonstrate that our introduced models outperform other custom architectures by effectively capturing temporal-spatial relationships inherent in seismic data. The performance of existing foundation models varies significantly based on the pre-training datasets, emphasizing the need for careful dataset selection. However, we introduce a new general approach termed MultiFoundationPattern that combines a bespoke pattern with foundation model results handled as auxiliary streams. In the earthquake case, the resultant MultiFoundationQuake model achieves the best overall performance.
Authors: Brian M Cho, Ana-Roxana Pop, Kyra Gan, Sam Corbett-Davies, Israel Nir, Ariel Evnine, Nathan Kallus
Abstract: When modifying existing policies in high-risk settings, it is often necessary to ensure with high certainty that the newly proposed policy improves upon a baseline, such as the status quo. In this work, we consider the problem of safe policy improvement, where one only adopts a new policy if it is deemed to be better than the specified baseline with at least pre-specified probability. We focus on threshold policies, a ubiquitous class of policies with applications in economics, healthcare, and digital advertising. Existing methods rely on potentially underpowered safety checks and limit the opportunities for finding safe improvements, so too often they must revert to the baseline to maintain safety. We overcome these issues by leveraging the most powerful safety test in the asymptotic regime and allowing for multiple candidates to be tested for improvement over the baseline. We show that in adversarial settings, our approach controls the rate of adopting a policy worse than the baseline to the pre-specified error level, even in moderate sample sizes. We present CSPI and CSPI-MT, two novel heuristics for selecting cutoff(s) to maximize the policy improvement from baseline. We demonstrate through both synthetic and external datasets that our approaches improve both the detection rates of safe policies and the realized improvement, particularly under stringent safety requirements and low signal-to-noise conditions.
Authors: Andr\'e Snoeck, Aniruddha Bhargava, Daniel Merchan, Josiah Davis, Julian Pachon
Abstract: Last-mile carriers increasingly incorporate electric vehicles (EVs) into their delivery fleet to achieve sustainability goals. This goal presents many challenges across multiple planning spaces including but not limited to how to plan EV routes. In this paper, we address the problem of predicting energy consumption of EVs for Last-Mile delivery routes using deep learning. We demonstrate the need to move away from thinking about range and we propose using energy as the basic unit of analysis. We share a range of deep learning solutions, beginning with a Feed Forward Neural Network (NN) and Recurrent Neural Network (RNN) and demonstrate significant accuracy improvements relative to pure physics-based and distance-based approaches. Finally, we present Route Energy Transformer (RET) a decoder-only Transformer model sized according to Chinchilla scaling laws. RET yields a +217 Basis Points (bps) improvement in Mean Absolute Percentage Error (MAPE) relative to the Feed Forward NN and a +105 bps improvement relative to the RNN.
Authors: Abdallah Aaraba, Soumaya Cherkaoui, Ola Ahmad, Jean-Fr\'ed\'eric Laprade, Olivier Nahman-L\'evesque, Alexis Vieloszynski, Shengrui Wang
Abstract: Forecasting in probabilistic time series is a complex endeavor that extends beyond predicting future values to also quantifying the uncertainty inherent in these predictions. Gaussian process regression stands out as a Bayesian machine learning technique adept at addressing this multifaceted challenge. This paper introduces a novel approach that blends the robustness of this Bayesian technique with the nuanced insights provided by the kernel perspective on quantum models, aimed at advancing quantum kernelized probabilistic forecasting. We incorporate a quantum feature map inspired by Ising interactions and demonstrate its effectiveness in capturing the temporal dependencies critical for precise forecasting. The optimization of our model's hyperparameters circumvents the need for computationally intensive gradient descent by employing gradient-free Bayesian optimization. Comparative benchmarks against established classical kernel models are provided, affirming that our quantum-enhanced approach achieves competitive performance.
Authors: Harish Haresamudram, Apoorva Beedu, Mashfiqui Rabbi, Sankalita Saha, Irfan Essa, Thomas Ploetz
Abstract: Cross-modal contrastive pre-training between natural language and other modalities, e.g., vision and audio, has demonstrated astonishing performance and effectiveness across a diverse variety of tasks and domains. In this paper, we investigate whether such natural language supervision can be used for wearable sensor based Human Activity Recognition (HAR), and discover that-surprisingly-it performs substantially worse than standard end-to-end training and self-supervision. We identify the primary causes for this as: sensor heterogeneity and the lack of rich, diverse text descriptions of activities. To mitigate their impact, we also develop strategies and assess their effectiveness through an extensive experimental evaluation. These strategies lead to significant increases in activity recognition, bringing performance closer to supervised and self-supervised training, while also enabling the recognition of unseen activities and cross modal retrieval of videos. Overall, our work paves the way for better sensor-language learning, ultimately leading to the development of foundational models for HAR using wearables.
Authors: Elvis Hsieh, Preston Fu, Jonathan Chen
Abstract: Language models (LMs) trained on web-scale datasets are largely successful due to their ability to memorize large amounts of training data, even if only present in a few examples. These capabilities are often desirable in evaluation on tasks such as question answering but raise questions about whether these models can exhibit genuine reasoning or succeed only at mimicking patterns from the training data. This distinction is particularly salient in forecasting tasks, where the answer is not present in the training data, and the model must reason to make logical deductions. We present Reasoning and Tools for Forecasting (RTF), a framework of reasoning-and-acting (ReAct) agents that can dynamically retrieve updated information and run numerical simulation with equipped tools. We evaluate our model with questions from competitive forecasting platforms and demonstrate that our method is competitive with and can outperform human predictions. This suggests that LMs, with the right tools, can indeed think and adapt like humans, offering valuable insights for real-world decision-making.
Authors: Zixuan Weng, Jindong Han, Wenzhao Jiang, Hao Liu
Abstract: Recently many deep learning models have been proposed for Long-term Time Series Forecasting (LTSF). Based on previous literature, we identify three critical patterns that can improve forecasting accuracy: the order and semantic dependencies in time dimension as well as cross-variate dependency. However, little effort has been made to simultaneously consider order and semantic dependencies when developing forecasting models. Moreover, existing approaches utilize cross-variate dependency by mixing information from different timestamps and variates, which may introduce irrelevant or harmful cross-variate information to the time dimension and largely hinder forecasting performance. To overcome these limitations, we investigate the potential of Mamba for LTSF and discover two key advantages benefiting forecasting: (i) the selection mechanism makes Mamba focus on or ignore specific inputs and learn semantic dependency easily, and (ii) Mamba preserves order dependency by processing sequences recursively. After that, we empirically find that the non-linear activation used in Mamba is unnecessary for semantically sparse time series data. Therefore, we further propose SAMBA, a Simplified Mamba with disentangled dependency encoding. Specifically, we first remove the non-linearities of Mamba to make it more suitable for LTSF. Furthermore, we propose a disentangled dependency encoding strategy to endow Mamba with cross-variate dependency modeling capabilities while reducing the interference between time and variate dimensions. Extensive experimental results on seven real-world datasets demonstrate the effectiveness of SAMBA over state-of-the-art forecasting models.
Authors: Chusheng Zeng, Bocheng Wang, Jinghui Yuan, Rong Wang, Mulin Chen
Abstract: Recent advances in unsupervised deep graph clustering have been significantly promoted by contrastive learning. Despite the strides, most graph contrastive learning models face challenges: 1) graph augmentation is used to improve learning diversity, but commonly used random augmentation methods may destroy inherent semantics and cause noise; 2) the fixed positive and negative sample selection strategy is limited to deal with complex real data, thereby impeding the model's capability to capture fine-grained patterns and relationships. To reduce these problems, we propose the Clustering-guided Curriculum Graph contrastive Learning (CCGL) framework. CCGL uses clustering entropy as the guidance of the following graph augmentation and contrastive learning. Specifically, according to the clustering entropy, the intra-class edges and important features are emphasized in augmentation. Then, a multi-task curriculum learning scheme is proposed, which employs the clustering guidance to shift the focus from the discrimination task to the clustering task. In this way, the sample selection strategy of contrastive learning can be adjusted adaptively from early to late stage, which enhances the model's flexibility for complex data structure. Experimental results demonstrate that CCGL has achieved excellent performance compared to state-of-the-art competitors.
Authors: Sai Koukuntla, Joshua B. Julian, Jesse C. Kaminsky, Manuel Schottdorf, David W. Tank, Carlos D. Brody, Adam S. Charles
Abstract: Modern applications often leverage multiple views of a subject of study. Within neuroscience, there is growing interest in large-scale simultaneous recordings across multiple brain regions. Understanding the relationship between views (e.g., the neural activity in each region recorded) can reveal fundamental principles about the characteristics of each representation and about the system. However, existing methods to characterize such relationships either lack the expressivity required to capture complex nonlinearities, describe only sources of variance that are shared between views, or discard geometric information that is crucial to interpreting the data. Here, we develop a nonlinear neural network-based method that, given paired samples of high-dimensional views, disentangles low-dimensional shared and private latent variables underlying these views while preserving intrinsic data geometry. Across multiple simulated and real datasets, we demonstrate that our method outperforms competing methods. Using simulated populations of lateral geniculate nucleus (LGN) and V1 neurons we demonstrate our model's ability to discover interpretable shared and private structure across different noise conditions. On a dataset of unrotated and corresponding but randomly rotated MNIST digits, we recover private latents for the rotated view that encode rotation angle regardless of digit class, and places the angle representation on a 1-d manifold, while shared latents encode digit class but not rotation angle. Applying our method to simultaneous Neuropixels recordings of hippocampus and prefrontal cortex while mice run on a linear track, we discover a low-dimensional shared latent space that encodes the animal's position. We propose our approach as a general-purpose method for finding succinct and interpretable descriptions of paired data sets in terms of disentangled shared and private latent variables.
Authors: S. Nishio, H. Nonaka, N. Tsuchiya, A. Migita, Y. Banno, T. Hayashi, H. Sakaji, T. Sakumoto, K. Watabe
Abstract: Machine learning is widely utilized across various industries. Identifying the appropriate machine learning models and datasets for specific tasks is crucial for the effective industrial application of machine learning. However, this requires expertise in both machine learning and the relevant domain, leading to a high learning cost. Therefore, research focused on extracting combinations of tasks, machine learning models, and datasets from academic papers is critically important, as it can facilitate the automatic recommendation of suitable methods. Conventional information extraction methods from academic papers have been limited to identifying machine learning models and other entities as named entities. To address this issue, this study proposes a methodology extracting tasks, machine learning methods, and dataset names from scientific papers and analyzing the relationships between these information by using LLM, embedding model, and network clustering. The proposed method's expression extraction performance, when using Llama3, achieves an F-score exceeding 0.8 across various categories, confirming its practical utility. Benchmarking results on financial domain papers have demonstrated the effectiveness of this method, providing insights into the use of the latest datasets, including those related to ESG (Environmental, Social, and Governance) data.
Authors: Luyao Cheng, Hui Wang, Siqi Zheng, Yafeng Chen, Rongjie Huang, Qinglin Zhang, Qian Chen, Xihao Li
Abstract: Speaker diarization, the process of segmenting an audio stream or transcribed speech content into homogenous partitions based on speaker identity, plays a crucial role in the interpretation and analysis of human speech. Most existing speaker diarization systems rely exclusively on unimodal acoustic information, making the task particularly challenging due to the innate ambiguities of audio signals. Recent studies have made tremendous efforts towards audio-visual or audio-semantic modeling to enhance performance. However, even the incorporation of up to two modalities often falls short in addressing the complexities of spontaneous and unstructured conversations. To exploit more meaningful dialogue patterns, we propose a novel multimodal approach that jointly utilizes audio, visual, and semantic cues to enhance speaker diarization. Our method elegantly formulates the multimodal modeling as a constrained optimization problem. First, we build insights into the visual connections among active speakers and the semantic interactions within spoken content, thereby establishing abundant pairwise constraints. Then we introduce a joint pairwise constraint propagation algorithm to cluster speakers based on these visual and semantic constraints. This integration effectively leverages the complementary strengths of different modalities, refining the affinity estimation between individual speaker embeddings. Extensive experiments conducted on multiple multimodal datasets demonstrate that our approach consistently outperforms state-of-the-art speaker diarization methods.
Authors: Weiyu Chen, James Kwok
Abstract: Model merging, which combines multiple models into a single model, has gained increasing popularity in recent years. By efficiently integrating the capabilities of various models without their original training data, this significantly reduces the parameter count and memory usage. However, current methods can only produce one single merged model. This necessitates a performance trade-off due to conflicts among the various models, and the resultant one-size-fits-all model may not align with the preferences of different users who may prioritize certain models over others. To address this issue, we propose preference-aware model merging, and formulate this as a multi-objective optimization problem in which the performance of the merged model on each base model's task is treated as an objective. In only one merging process, the proposed parameter-efficient structure can generate the whole Pareto set of merged models, each representing the Pareto-optimal model for a given user-specified preference. Merged models can also be selected from the learned Pareto set that are tailored to different user preferences. Experimental results on a number of benchmark datasets demonstrate that the proposed preference-aware Pareto Merging can obtain a diverse set of trade-off models and outperforms state-of-the-art model merging baselines.
Authors: Woo Kyung Kim, Minjong Yoo, Honguk Woo
Abstract: Data-driven offline reinforcement learning and imitation learning approaches have been gaining popularity in addressing sequential decision-making problems. Yet, these approaches rarely consider learning Pareto-optimal policies from a limited pool of expert datasets. This becomes particularly marked due to practical limitations in obtaining comprehensive datasets for all preferences, where multiple conflicting objectives exist and each expert might hold a unique optimization preference for these objectives. In this paper, we adapt inverse reinforcement learning (IRL) by using reward distance estimates for regularizing the discriminator. This enables progressive generation of a set of policies that accommodate diverse preferences on the multiple objectives, while using only two distinct datasets, each associated with a different expert preference. In doing so, we present a Pareto IRL framework (ParIRL) that establishes a Pareto policy set from these limited datasets. In the framework, the Pareto policy set is then distilled into a single, preference-conditioned diffusion model, thus allowing users to immediately specify which expert's patterns they prefer. Through experiments, we show that ParIRL outperforms other IRL algorithms for various multi-objective control tasks, achieving the dense approximation of the Pareto frontier. We also demonstrate the applicability of ParIRL with autonomous driving in CARLA.
Authors: Shresth Verma, Niclas Boehmer, Lingkai Kong, Milind Tambe
Abstract: LLMs are increasingly used to design reward functions based on human preferences in Reinforcement Learning (RL). We focus on LLM-designed rewards for Restless Multi-Armed Bandits, a framework for allocating limited resources among agents. In applications such as public health, this approach empowers grassroots health workers to tailor automated allocation decisions to community needs. In the presence of multiple agents, altering the reward function based on human preferences can impact subpopulations very differently, leading to complex tradeoffs and a multi-objective resource allocation problem. We are the first to present a principled method termed Social Choice Language Model for dealing with these tradeoffs for LLM-designed rewards for multiagent planners in general and restless bandits in particular. The novel part of our model is a transparent and configurable selection component, called an adjudicator, external to the LLM that controls complex tradeoffs via a user-selected social welfare function. Our experiments demonstrate that our model reliably selects more effective, aligned, and balanced reward functions compared to purely LLM-based approaches.
Authors: Yaowen Huang, Jun Der Leu, Baoli Lu, Yan Zhou
Abstract: Risk analysis is an important business decision support task in customer relationship management (CRM), involving the identification of potential risks or challenges that may affect customer satisfaction, retention rates, and overall business performance. To enhance risk analysis in CRM, this paper combines the advantages of quantile region convolutional neural network-long short-term memory (QRCNN-LSTM) and cross-attention mechanisms for modeling. The QRCNN-LSTM model combines sequence modeling with deep learning architectures commonly used in natural language processing tasks, enabling the capture of both local and global dependencies in sequence data. The cross-attention mechanism enhances interactions between different input data parts, allowing the model to focus on specific areas or features relevant to CRM risk analysis. By applying QRCNN-LSTM and cross-attention mechanisms to CRM risk analysis, empirical evidence demonstrates that this approach can effectively identify potential risks and provide data-driven support for business decisions.
Authors: Lijuan Wang, Yijia Hu, Yan Zhou
Abstract: In the context of global trade, cross-border commodity pricing largely determines the competitiveness and market share of businesses. However, existing methodologies often prove inadequate, as they lack the agility and precision required to effectively respond to the dynamic international markets. Time series data is of great significance in commodity pricing and can reveal market dynamics and trends. Therefore, we propose a new method based on the hybrid neural network model CNN-BiGRU-SSA. The goal is to achieve accurate prediction and optimization of cross-border commodity pricing strategies through in-depth analysis and optimization of time series data. Our model undergoes experimental validation across multiple datasets. The results show that our method achieves significant performance advantages on datasets such as UNCTAD, IMF, WITS and China Customs. For example, on the UNCTAD dataset, our model reduces MAE to 4.357, RMSE to 5.406, and R2 to 0.961, significantly better than other models. On the IMF and WITS datasets, our method also achieves similar excellent performance. These experimental results verify the effectiveness and reliability of our model in the field of cross-border commodity pricing. Overall, this study provides an important reference for enterprises to formulate more reasonable and effective cross-border commodity pricing strategies, thereby enhancing market competitiveness and profitability. At the same time, our method also lays a foundation for the application of deep learning in the fields of international trade and economic strategy optimization, which has important theoretical and practical significance.
Authors: Jingyi Wang, Zhiqun Wang, Guiran Liu
Abstract: Electroencephalography (EEG) signals are crucial for investigating brain function and cognitive processes. This study aims to address the challenges of efficiently recording and analyzing high-dimensional EEG signals while listening to music to recognize emotional states. We propose a method combining Bidirectional Long Short-Term Memory (Bi-LSTM) networks with attention mechanisms for EEG signal processing. Using wearable EEG devices, we collected brain activity data from participants listening to music. The data was preprocessed, segmented, and Differential Entropy (DE) features were extracted. We then constructed and trained a Bi-LSTM model to enhance key feature extraction and improve emotion recognition accuracy. Experiments were conducted on the SEED and DEAP datasets. The Bi-LSTM-AttGW model achieved 98.28% accuracy on the SEED dataset and 92.46% on the DEAP dataset in multi-class emotion recognition tasks, significantly outperforming traditional models such as SVM and EEG-Net. This study demonstrates the effectiveness of combining Bi-LSTM with attention mechanisms, providing robust technical support for applications in brain-computer interfaces (BCI) and affective computing. Future work will focus on improving device design, incorporating multimodal data, and further enhancing emotion recognition accuracy, aiming to achieve practical applications in real-world scenarios.
Authors: Zecheng Zhang
Abstract: Grid startup, an integral component of the power system, holds strategic importance for ensuring the reliability and efficiency of the electrical grid. However, current methodologies for in-depth analysis and precise prediction of grid startup scenarios are inadequate. To address these challenges, we propose a novel method based on the Transformer-LSTM-PSO model. This model uniquely combines the Transformer's self-attention mechanism, LSTM's temporal modeling capabilities, and the parameter tuning features of the particle swarm optimization algorithm. It is designed to more effectively capture the complex temporal relationships in grid startup schemes. Our experiments demonstrate significant improvements, with our model achieving lower RMSE and MAE values across multiple datasets compared to existing benchmarks, particularly in the NYISO Electric Market dataset where the RMSE was reduced by approximately 15% and the MAE by 20% compared to conventional models. Our main contribution is the development of a Transformer-LSTM-PSO model that significantly enhances the accuracy and efficiency of smart grid startup predictions. The application of the Transformer-LSTM-PSO model represents a significant advancement in smart grid predictive analytics, concurrently fostering the development of more reliable and intelligent grid management systems.
Authors: Weiqin Chen, Sandipan Mishra, Santiago Paternain
Abstract: Offline reinforcement learning (RL) learns effective policies from a static target dataset. Despite state-of-the-art (SOTA) offline RL algorithms being promising, they highly rely on the quality of the target dataset. The performance of SOTA algorithms can degrade in scenarios with limited samples in the target dataset, which is often the case in real-world applications. To address this issue, domain adaptation that leverages auxiliary samples from related source datasets (such as simulators) can be beneficial. In this context, determining the optimal way to trade off the source and target datasets remains a critical challenge in offline RL. To the best of our knowledge, this paper proposes the first framework that theoretically and experimentally explores how the weight assigned to each dataset affects the performance of offline RL. We establish the performance bounds and convergence neighborhood of our framework, both of which depend on the selection of the weight. Furthermore, we identify the existence of an optimal weight for balancing the two datasets. All theoretical guarantees and optimal weight depend on the quality of the source dataset and the size of the target dataset. Our empirical results on the well-known Procgen Benchmark substantiate our theoretical contributions.
Authors: Haoyuan Shi, Tao Xu, Xiaodi Li, Qian Gao, Junfeng Xia, Zhenyu Yue
Abstract: Predicting the response of a cancer cell line to a therapeutic drug is pivotal for personalized medicine. Despite numerous deep learning methods that have been developed for drug response prediction, integrating diverse information about biological entities and predicting the directional response remain major challenges. Here, we propose a novel interpretable predictive model, DRExplainer, which leverages a directed graph convolutional network to enhance the prediction in a directed bipartite network framework. DRExplainer constructs a directed bipartite network integrating multi-omics profiles of cell lines, the chemical structure of drugs and known drug response to achieve directed prediction. Then, DRExplainer identifies the most relevant subgraph to each prediction in this directed bipartite network by learning a mask, facilitating critical medical decision-making. Additionally, we introduce a quantifiable method for model interpretability that leverages a ground truth benchmark dataset curated from biological features. In computational experiments, DRExplainer outperforms state-of-the-art predictive methods and another graph-based explanation method under the same experimental setting. Finally, the case studies further validate the interpretability and the effectiveness of DRExplainer in predictive novel drug response. Our code is available at: https://github.com/vshy-dream/DRExplainer.
Authors: Haixin Wang, Yadi Cao, Zijie Huang, Yuxuan Liu, Peiyan Hu, Xiao Luo, Zezheng Song, Wanjia Zhao, Jilin Liu, Jinan Sun, Shikun Zhang, Long Wei, Yue Wang, Tailin Wu, Zhi-Ming Ma, Yizhou Sun
Abstract: This paper explores the recent advancements in enhancing Computational Fluid Dynamics (CFD) tasks through Machine Learning (ML) techniques. We begin by introducing fundamental concepts, traditional methods, and benchmark datasets, then examine the various roles ML plays in improving CFD. The literature systematically reviews papers in recent five years and introduces a novel classification for forward modeling: Data-driven Surrogates, Physics-Informed Surrogates, and ML-assisted Numerical Solutions. Furthermore, we also review the latest ML methods in inverse design and control, offering a novel classification and providing an in-depth discussion. Then we highlight real-world applications of ML for CFD in critical scientific and engineering disciplines, including aerodynamics, combustion, atmosphere & ocean science, biology fluid, plasma, symbolic regression, and reduced order modeling. Besides, we identify key challenges and advocate for future research directions to address these challenges, such as multi-scale representation, physical knowledge encoding, scientific foundation model and automatic scientific discovery. This review serves as a guide for the rapidly expanding ML for CFD community, aiming to inspire insights for future advancements. We draw the conclusion that ML is poised to significantly transform CFD research by enhancing simulation accuracy, reducing computational time, and enabling more complex analyses of fluid dynamics. The paper resources can be viewed at https://github.com/WillDreamer/Awesome-AI4CFD.
Authors: Ivo Pascal de Jong, Andreea Ioana Sburlea, Matias Valdenegro-Toro
Abstract: Uncertainty Quantification in Machine Learning has progressed to predicting the source of uncertainty in a prediction: Uncertainty from stochasticity in the data (aleatoric), or uncertainty from limitations of the model (epistemic). Generally, each uncertainty is evaluated in isolation, but this obscures the fact that they are often not truly disentangled. This work proposes a set of experiments to evaluate disentanglement of aleatoric and epistemic uncertainty, and uses these methods to compare two competing formulations for disentanglement (the Information Theoretic approach, and the Gaussian Logits approach). The results suggest that the Information Theoretic approach gives better disentanglement, but that either predicted source of uncertainty is still largely contaminated by the other for both methods. We conclude that with the current methods for disentangling, aleatoric and epistemic uncertainty are not reliably separated, and we provide a clear set of experimental criteria that good uncertainty disentanglement should follow.
Authors: Junyu Luo, Zhiping Xiao, Yifan Wang, Xiao Luo, Jingyang Yuan, Wei Ju, Langechuan Liu, Ming Zhang
Abstract: Graph neural networks (GNNs) have achieved impressive performance in graph domain adaptation. However, extensive source graphs could be unavailable in real-world scenarios due to privacy and storage concerns. To this end, we investigate an underexplored yet practical problem of source-free graph domain adaptation, which transfers knowledge from source models instead of source graphs to a target domain. To solve this problem, we introduce a novel GNN-based approach called Rank and Align (RNA), which ranks graph similarities with spectral seriation for robust semantics learning, and aligns inharmonic graphs with harmonic graphs which close to the source domain for subgraph extraction. In particular, to overcome label scarcity, we employ the spectral seriation algorithm to infer the robust pairwise rankings, which can guide semantic learning using a similarity learning objective. To depict distribution shifts, we utilize spectral clustering and the silhouette coefficient to detect harmonic graphs, which the source model can easily classify. To reduce potential domain discrepancy, we extract domain-invariant subgraphs from inharmonic graphs by an adversarial edge sampling process, which guides the invariant learning of GNNs. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our proposed RNA.
Authors: Victorita Dolean, Serge Gratton, Alexander Heinlein, Valentin Mercier
Abstract: This study presents a two-level Deep Domain Decomposition Method (Deep-DDM) augmented with a coarse-level network for solving boundary value problems using physics-informed neural networks (PINNs). The addition of the coarse level network improves scalability and convergence rates compared to the single level method. Tested on a Poisson equation with Dirichlet boundary conditions, the two-level deep DDM demonstrates superior performance, maintaining efficient convergence regardless of the number of subdomains. This advance provides a more scalable and effective approach to solving complex partial differential equations with machine learning.
Authors: Paul Jeha, Will Grathwohl, Michael Riis Andersen, Carl Henrik Ek, Jes Frellsen
Abstract: Score-based models, trained with denoising score matching, are remarkably effective in generating high dimensional data. However, the high variance of their training objective hinders optimisation. We attempt to reduce it with a control variate, derived via a $k$-th order Taylor expansion on the training objective and its gradient. We prove an equivalence between the two and demonstrate empirically the effectiveness of our approach on a low dimensional problem setting; and study its effect on larger problems.
Authors: Igor V. Netay
Abstract: We present results of numerical experiments for neural networks with stochastic gradient-based optimization with adaptive momentum. This widely applied optimization has proved convergence and practical efficiency, but for long-run training becomes numerically unstable. We show that numerical artifacts are observable not only for large-scale models and finally lead to divergence also for case of shallow narrow networks. We argue this theory by experiments with more than 1600 neural networks trained for 50000 epochs. Local observations show presence of the same behavior of network parameters in both stable and unstable training segments. Geometrical behavior of parameters forms double twisted spirals in the parameter space and is caused by alternating of numerical perturbations with next relaxation oscillations in values for 1st and 2nd momentum.
Authors: Shuang Zeng, Pengxin Guo, Shuai Wang, Jianbo Wang, Yuyin Zhou, Liangqiong Qu
Abstract: Federated Learning (FL) is a rising approach towards collaborative and privacy-preserving machine learning where large-scale medical datasets remain localized to each client. However, the issue of data heterogeneity among clients often compels local models to diverge, leading to suboptimal global models. To mitigate the impact of data heterogeneity on FL performance, we start with analyzing how FL training influence FL performance by decomposing the global loss into three terms: local loss, distribution shift loss and aggregation loss. Remarkably, our loss decomposition reveals that existing local training-based FL methods attempt to reduce the distribution shift loss, while the global aggregation-based FL methods propose better aggregation strategies to reduce the aggregation loss. Nevertheless, a comprehensive joint effort to minimize all three terms is currently limited in the literature, leading to subpar performance when dealing with data heterogeneity challenges. To fill this gap, we propose a novel FL method based on global loss decomposition, called FedLD, to jointly reduce these three loss terms. Our FedLD involves a margin control regularization in local training to reduce the distribution shift loss, and a principal gradient-based server aggregation strategy to reduce the aggregation loss. Notably, under different levels of data heterogeneity, our strategies achieve better and more robust performance on retinal and chest X-ray classification compared to other FL algorithms. Our code is available at \href{https://github.com/Zeng-Shuang/FedLD}{https://github.com/Zeng-Shuang/FedLD}.
URLs: https://github.com/Zeng-Shuang/FedLD, https://github.com/Zeng-Shuang/FedLD
Authors: Yen-Ru Lai, Fu-Chieh Chang, Pei-Yuan Wu
Abstract: Offline reinforcement learning (RL) learns policies from a fixed dataset, but often requires large amounts of data. The challenge arises when labeled datasets are expensive, especially when rewards have to be provided by human labelers for large datasets. In contrast, unlabelled data tends to be less expensive. This situation highlights the importance of finding effective ways to use unlabelled data in offline RL, especially when labelled data is limited or expensive to obtain. In this paper, we present the algorithm to utilize the unlabeled data in the offline RL method with kernel function approximation and give the theoretical guarantee. We present various eigenvalue decay conditions of $\mathcal{H}_k$ which determine the complexity of the algorithm. In summary, our work provides a promising approach for exploiting the advantages offered by unlabeled data in offline RL, whilst maintaining theoretical assurances.
Authors: Niloofar Azizi, Nils Kriege, Horst Bischof
Abstract: Graph Neural Networks (GNNs) excel in handling graph-structured data but often underperform in link prediction tasks compared to classical methods, mainly due to the limitations of the commonly used Message Passing GNNs (MPNNs). Notably, their ability to distinguish non-isomorphic graphs is limited by the 1-dimensional Weisfeiler-Lehman test. Our study presents a novel method to enhance the expressivity of GNNs by embedding induced subgraphs into the graph Laplacian matrix's eigenbasis. We introduce a Learnable Lanczos algorithm with Linear Constraints (LLwLC), proposing two novel subgraph extraction strategies: encoding vertex-deleted subgraphs and applying Neumann eigenvalue constraints. For the former, we conjecture that LLwLC establishes a universal approximator, offering efficient time complexity. The latter focuses on link representations enabling differentiation between $k$-regular graphs and node automorphism, a vital aspect for link prediction tasks. Our approach results in an extremely lightweight architecture, reducing the need for extensive training datasets. Empirically, our method improves performance in challenging link prediction tasks across benchmark datasets, establishing its practical utility and supporting our theoretical findings. Notably, LLwLC achieves 20x and 10x speedup by only requiring 5% and 10% data from the PubMed and OGBL-Vessel datasets while comparing to the state-of-the-art.
Authors: Yingzhuo Deng, Ke Hu, Bo Li, Yao Zhang
Abstract: Principal component analysis (PCA) is a classical feature extraction method, but it may be adversely affected by outliers, resulting in inaccurate learning of the projection matrix. This paper proposes a robust method to estimate both the data mean and the PCA projection matrix by learning discriminant sample weights from data containing outliers. Each sample in the dataset is assigned a weight, and the proposed algorithm iteratively learns the weights, the mean, and the projection matrix, respectively. Specifically, when the mean and the projection matrix are available, via fine-grained analysis of outliers, a weight for each sample is learned hierarchically so that outliers have small weights while normal samples have large weights. With the learned weights available, a weighted optimization problem is solved to estimate both the data mean and the projection matrix. Because the learned weights discriminate outliers from normal samples, the adverse influence of outliers is mitigated due to the corresponding small weights. Experiments on toy data, UCI dataset, and face dataset demonstrate the effectiveness of the proposed method in estimating the mean and the projection matrix from the data containing outliers.
Authors: Xinyu Yuan, Zhihao Zhan, Zuobai Zhang, Manqi Zhou, Jianan Zhao, Boyu Han, Yue Li, Jian Tang
Abstract: Transcriptome foundation models TFMs hold great promises of deciphering the transcriptomic language that dictate diverse cell functions by self-supervised learning on large-scale single-cell gene expression data, and ultimately unraveling the complex mechanisms of human diseases. However, current TFMs treat cells as independent samples and ignore the taxonomic relationships between cell types, which are available in cell ontology graphs. We argue that effectively leveraging this ontology information during the TFM pre-training can improve learning biologically meaningful gene co-expression patterns while preserving TFM as a general purpose foundation model for downstream zero-shot and fine-tuning tasks. To this end, we present \textbf{s}ingle \textbf{c}ell, \textbf{Cell}-\textbf{o}ntology guided TFM scCello. We introduce cell-type coherence loss and ontology alignment loss, which are minimized along with the masked gene expression prediction loss during the pre-training. The novel loss component guide scCello to learn the cell-type-specific representation and the structural relation between cell types from the cell ontology graph, respectively. We pre-trained scCello on 22 million cells from CellxGene database leveraging their cell-type labels mapped to the cell ontology graph from Open Biological and Biomedical Ontology Foundry. Our TFM demonstrates competitive generalization and transferability performance over the existing TFMs on biologically important tasks including identifying novel cell types of unseen cells, prediction of cell-type-specific marker genes, and cancer drug responses.
Authors: Haoyang Jiang, Yongzhi Qu
Abstract: In this paper, we present a novel Fredholm Integral Equation Neural Operator (FIE-NO) method, an integration of Random Fourier Features and Fredholm Integral Equations (FIE) into the deep learning framework, tailored for solving data-driven Boundary Value Problems (BVPs) with irregular boundaries. Unlike traditional computational approaches that struggle with the computational intensity and complexity of such problems, our method offers a robust, efficient, and accurate solution mechanism, using a physics inspired design of the learning structure. We demonstrate that the proposed physics-guided operator learning method (FIE-NO) achieves superior performance in addressing BVPs. Notably, our approach can generalize across multiple scenarios, including those with unknown equation forms and intricate boundary shapes, after being trained only on one boundary condition. Experimental validation demonstrates that the FIE-NO method performs well in simulated examples, including Darcy flow equation and typical partial differential equations such as the Laplace and Helmholtz equations. The proposed method exhibits robust performance across different boundary conditions. Experimental results indicate that FIE-NO achieves higher accuracy and stability compared to other methods when addressing complex boundary value problems with varying numbers of interior points.
Authors: Gonzalo Lopez Gil, Paul Duhamel-Sebline, Andrew McCarren
Abstract: The stock market is a fundamental component of financial systems, reflecting economic health, providing investment opportunities, and influencing global dynamics. Accurate stock market predictions can lead to significant gains and promote better investment decisions. However, predicting stock market trends is challenging due to their non-linear and stochastic nature. This study investigates the efficacy of advanced deep learning models for short-term trend forecasting using daily and hourly closing prices from the S&P 500 index and the Brazilian ETF EWZ. The models explored include Temporal Convolutional Networks (TCN), Neural Basis Expansion Analysis for Time Series Forecasting (N-BEATS), Temporal Fusion Transformers (TFT), Neural Hierarchical Interpolation for Time Series Forecasting (N-HiTS), and Time-series Dense Encoder (TiDE). Furthermore, we introduce the Extended Long Short-Term Memory for Time Series (xLSTM-TS) model, an xLSTM adaptation optimised for time series prediction. Wavelet denoising techniques were applied to smooth the signal and reduce minor fluctuations, providing cleaner data as input for all approaches. Denoising significantly improved performance in predicting stock price direction. Among the models tested, xLSTM-TS consistently outperformed others. For example, it achieved a test accuracy of 72.82% and an F1 score of 73.16% on the EWZ daily dataset. By leveraging advanced deep learning models and effective data preprocessing techniques, this research provides valuable insights into the application of machine learning for market movement forecasting, highlighting both the potential and the challenges involved.
Authors: Sagar Srinivas Sakhinana, Krishna Sai Sudhir Aripirala, Shivam Gupta, Venkataramana Runkana
Abstract: Accurately predicting the behavior of complex dynamical systems, characterized by high-dimensional multivariate time series(MTS) in interconnected sensor networks, is crucial for informed decision-making in various applications to minimize risk. While graph forecasting networks(GFNs) are ideal for forecasting MTS data that exhibit spatio-temporal dependencies, prior works rely solely on the domain-specific knowledge of time-series variables inter-relationships to model the nonlinear dynamics, neglecting inherent relational structural dependencies among the variables within the MTS data. In contrast, contemporary works infer relational structures from MTS data but neglect domain-specific knowledge. The proposed hybrid architecture addresses these limitations by combining both domain-specific knowledge and implicit knowledge of the relational structure underlying the MTS data using Knowledge-Based Compositional Generalization. The hybrid architecture shows promising results on multiple benchmark datasets, outperforming state-of-the-art forecasting methods. Additionally, the architecture models the time varying uncertainty of multi-horizon forecasts.
Authors: Kaihui Cheng, Ce Liu, Qingkun Su, Jun Wang, Liwei Zhang, Yining Tang, Yao Yao, Siyu Zhu, Yuan Qi
Abstract: Protein structure prediction is pivotal for understanding the structure-function relationship of proteins, advancing biological research, and facilitating pharmaceutical development and experimental design. While deep learning methods and the expanded availability of experimental 3D protein structures have accelerated structure prediction, the dynamic nature of protein structures has received limited attention. This study introduces an innovative 4D diffusion model incorporating molecular dynamics (MD) simulation data to learn dynamic protein structures. Our approach is distinguished by the following components: (1) a unified diffusion model capable of generating dynamic protein structures, including both the backbone and side chains, utilizing atomic grouping and side-chain dihedral angle predictions; (2) a reference network that enhances structural consistency by integrating the latent embeddings of the initial 3D protein structures; and (3) a motion alignment module aimed at improving temporal structural coherence across multiple time steps. To our knowledge, this is the first diffusion-based model aimed at predicting protein trajectories across multiple time steps simultaneously. Validation on benchmark datasets demonstrates that our model exhibits high accuracy in predicting dynamic 3D structures of proteins containing up to 256 amino acids over 32 time steps, effectively capturing both local flexibility in stable states and significant conformational changes.
Authors: Sagar Srinivas Sakhinana, Shivam Gupta, Krishna Sai Sudhir Aripirala, Venkataramana Runkana
Abstract: Forecasting the behaviour of complex dynamical systems such as interconnected sensor networks characterized by high-dimensional multivariate time series(MTS) is of paramount importance for making informed decisions and planning for the future in a broad spectrum of applications. Graph forecasting networks(GFNs) are well-suited for forecasting MTS data that exhibit spatio-temporal dependencies. However, most prior works of GFN-based methods on MTS forecasting rely on domain-expertise to model the nonlinear dynamics of the system, but neglect the potential to leverage the inherent relational-structural dependencies among time series variables underlying MTS data. On the other hand, contemporary works attempt to infer the relational structure of the complex dependencies between the variables and simultaneously learn the nonlinear dynamics of the interconnected system but neglect the possibility of incorporating domain-specific prior knowledge to improve forecast accuracy. To this end, we propose a hybrid architecture that combines explicit prior knowledge with implicit knowledge of the relational structure within the MTS data. It jointly learns intra-series temporal dependencies and inter-series spatial dependencies by encoding time-conditioned structural spatio-temporal inductive biases to provide more accurate and reliable forecasts. It also models the time-varying uncertainty of the multi-horizon forecasts to support decision-making by providing estimates of prediction uncertainty. The proposed architecture has shown promising results on multiple benchmark datasets and outperforms state-of-the-art forecasting methods by a significant margin. We report and discuss the ablation studies to validate our forecasting architecture.
Authors: Arjun Shah, Varun Viswanath, Kashish Gandhi, Dr. Nilesh Madhukar Patil
Abstract: This paper addresses the pressing need for an accurate solar energy prediction model, which is crucial for efficient grid integration. We explore the influence of the Air Quality Index and weather features on solar energy generation, employing advanced Machine Learning and Deep Learning techniques. Our methodology uses time series modeling and makes novel use of power transform normalization and zero-inflated modeling. Various Machine Learning algorithms and Conv2D Long Short-Term Memory model based Deep Learning models are applied to these transformations for precise predictions. Results underscore the effectiveness of our approach, demonstrating enhanced prediction accuracy with Air Quality Index and weather features. We achieved a 0.9691 $R^2$ Score, 0.18 MAE, 0.10 RMSE with Conv2D Long Short-Term Memory model, showcasing the power transform technique's innovation in enhancing time series forecasting for solar energy generation. Such results help our research contribute valuable insights to the synergy between Air Quality Index, weather features, and Deep Learning techniques for solar energy prediction.
Authors: Khang T. Doan, Bao G. Huynh, Dung T. Hoang, Thuc D. Pham, Nhat H. Pham, Quan T. M. Nguyen, Bang Q. Vo, Suong N. Hoang
Abstract: In this report, we introduce Vintern-1B, a reliable 1-billion-parameters multimodal large language model (MLLM) for Vietnamese language tasks. By integrating the Qwen2-0.5B-Instruct language model with the InternViT-300M-448px visual model, Vintern-1B is optimized for a range of applications, including optical character recognition (OCR), document extraction, and general question-answering in Vietnamese context. The model is fine-tuned on an extensive dataset of over 3 million image-question-answer pairs, achieving robust performance and reliable results across multiple Vietnamese language benchmarks like OpenViVQA and ViTextVQA. Vintern-1B is small enough to fit into various on-device applications easily. Additionally, we have open-sourced several Vietnamese vision question answering (VQA) datasets for text and diagrams, created with Gemini 1.5 Flash. Our models are available at: https://huggingface.co/5CD-AI/Vintern-1B-v2.
Authors: Sina Sarparast, Aldo Zaimi, Maximilian Ebert, Michael-Rock Goldsmith
Abstract: Protein dynamics play a crucial role in many biological processes and drug interactions. However, measuring, and simulating protein dynamics is challenging and time-consuming. While machine learning holds promise in deciphering the determinants of protein dynamics from structural information, most existing methods for protein representation learning operate at the residue level, ignoring the finer details of atomic interactions. In this work, we propose for the first time to use graph neural networks (GNNs) to learn protein representations at the atomic level and predict B-factors from protein 3D structures. The B-factor reflects the atomic displacement of atoms in proteins, and can serve as a surrogate for protein flexibility. We compared different GNN architectures to assess their performance. The Meta-GNN model achieves a correlation coefficient of 0.71 on a large and diverse test set of over 4k proteins (17M atoms) from the Protein Data Bank (PDB), outperforming previous methods by a large margin. Our work demonstrates the potential of representations learned by GNNs for protein flexibility prediction and other related tasks.
Authors: Sam Earle, Zehua Jiang, Julian Togelius
Abstract: Procedural Content Generation via Reinforcement Learning (PCGRL) has been introduced as a means by which controllable designer agents can be trained based only on a set of computable metrics acting as a proxy for the level's quality and key characteristics. While PCGRL offers a unique set of affordances for game designers, it is constrained by the compute-intensive process of training RL agents, and has so far been limited to generating relatively small levels. To address this issue of scale, we implement several PCGRL environments in Jax so that all aspects of learning and simulation happen in parallel on the GPU, resulting in faster environment simulation; removing the CPU-GPU transfer of information bottleneck during RL training; and ultimately resulting in significantly improved training speed. We replicate several key results from prior works in this new framework, letting models train for much longer than previously studied, and evaluating their behavior after 1 billion timesteps. Aiming for greater control for human designers, we introduce randomized level sizes and frozen "pinpoints" of pivotal game tiles as further ways of countering overfitting. To test the generalization ability of learned generators, we evaluate models on large, out-of-distribution map sizes, and find that partial observation sizes learn more robust design strategies.
Authors: Weiyan Wang, Yilun Jin, Yiming Zhang, Victor Junqiu Wei, Han Tian, Li Chen, Kai Chen
Abstract: Due to high accuracy, BERT-like models have been widely adopted by discriminative text mining and web searching. However, large BERT-like models suffer from inefficient online inference, as they face the following two problems on GPUs. First, they rely on the large model depth to achieve high accuracy, which linearly increases the sequential computation on GPUs. Second, stochastic and dynamic online workloads cause extra costs. In this paper, we present Academus for low-latency online inference of BERT-like models. At the core of Academus is the novel student parallelism, which adopts boosting ensemble and stacking distillation to distill the original deep model into an equivalent group of parallel and shallow student models. This enables Academus to achieve the lower model depth (e.g., two layers) than baselines and consequently the lowest inference latency without affecting the accuracy.For occasional workload bursts, it can temporarily decrease the number of students with minimal accuracy loss to improve throughput. Additionally, it employs specialized system designs for student parallelism to better handle stochastic online workloads. We conduct comprehensive experiments to verify the effectiveness. The results show that Academus outperforms the baselines by 4.1X~1.6X in latency without compromising accuracy, and achieves up to 22.27X higher throughput for workload bursts.
Authors: Hui Wang, Cho Tung Yip, Bo Li
Abstract: Gradient-based meta-learning algorithms have gained popularity for their ability to train models on new tasks using limited data. Empirical observations indicate that such algorithms are able to learn a shared representation across tasks, which is regarded as a key factor in their success. However, the in-depth theoretical understanding of the learning dynamics and the origin of the shared representation remains underdeveloped. In this work, we investigate the meta-learning dynamics of the non-linear two-layer neural networks trained on streaming tasks in the teach-student scenario. Through the lens of statistical physics analysis, we characterize the macroscopic behavior of the meta-training processes, the formation of the shared representation, and the generalization ability of the model on new tasks. The analysis also points to the importance of the choice of certain hyper-parameters of the learning algorithms.
Authors: Yousef Emami, Kai Li, Luis Almeida, Wei Ni, Zhu Han
Abstract: Rapid advances in Machine Learning (ML) have triggered new trends in Autonomous Vehicles (AVs). ML algorithms play a crucial role in interpreting sensor data, predicting potential hazards, and optimizing navigation strategies. However, achieving full autonomy in cluttered and complex situations, such as intricate intersections, diverse sceneries, varied trajectories, and complex missions, is still challenging, and the cost of data labeling remains a significant bottleneck. The adaptability and robustness of humans in complex scenarios motivate the inclusion of humans in ML process, leveraging their creativity, ethical power, and emotional intelligence to improve ML effectiveness. The scientific community knows this approach as Human-In-The-Loop Machine Learning (HITL-ML). Towards safe and ethical autonomy, we present a review of HITL-ML for AVs, focusing on Curriculum Learning (CL), Human-In-The-Loop Reinforcement Learning (HITL-RL), Active Learning (AL), and ethical principles. In CL, human experts systematically train ML models by starting with simple tasks and gradually progressing to more difficult ones. HITL-RL significantly enhances the RL process by incorporating human input through techniques like reward shaping, action injection, and interactive learning. AL streamlines the annotation process by targeting specific instances that need to be labeled with human oversight, reducing the overall time and cost associated with training. Ethical principles must be embedded in AVs to align their behavior with societal values and norms. In addition, we provide insights and specify future research directions.
Authors: Lujia Zhong, Shuo Huang, Yonggang Shi
Abstract: Recently, deep learning has made remarkable strides, especially with generative modeling, such as large language models and probabilistic diffusion models. However, training these models often involves significant computational resources, requiring billions of petaFLOPs. This high resource consumption results in substantial energy usage and a large carbon footprint, raising critical environmental concerns. Back-propagation (BP) is a major source of computational expense during training deep learning models. To advance research on energy-efficient training and allow for sparse learning on any machine and device, we propose a general, energy-efficient convolution module that can be seamlessly integrated into any deep learning architecture. Specifically, we introduce channel-wise sparsity with additional gradient selection schedulers during backward based on the assumption that BP is often dense and inefficient, which can lead to over-fitting and high computational consumption. Our experiments demonstrate that our approach reduces 40\% computations while potentially improving model performance, validated on image classification and generation tasks. This reduction can lead to significant energy savings and a lower carbon footprint during the research and development phases of large-scale AI systems. Additionally, our method mitigates over-fitting in a manner distinct from Dropout, allowing it to be combined with Dropout to further enhance model performance and reduce computational resource usage. Extensive experiments validate that our method generalizes to a variety of datasets and tasks and is compatible with a wide range of deep learning architectures and modules. Code is publicly available at https://github.com/lujiazho/ssProp.
Authors: Ekdeep Singh Lubana, Kyogo Kawaguchi, Robert P. Dick, Hidenori Tanaka
Abstract: Increase in data, size, or compute can lead to sudden learning of specific capabilities by a neural network -- a phenomenon often called "emergence". Beyond scientific understanding, establishing the causal factors underlying such emergent capabilities is crucial to enable risk regulation frameworks for AI. In this work, we seek inspiration from study of emergent properties in other fields and propose a phenomenological definition for the concept in the context of neural networks. Our definition implicates the acquisition of specific structures underlying the data-generating process as a cause of sudden performance growth for specific, narrower tasks. We empirically investigate this definition by proposing an experimental system grounded in a context-sensitive formal language and find that Transformers trained to perform tasks on top of strings from this language indeed exhibit emergent capabilities. Specifically, we show that once the language's underlying grammar and context-sensitivity inducing structures are learned by the model, performance on narrower tasks suddenly begins to improve. We then analogize our network's learning dynamics with the process of percolation on a bipartite graph, establishing a formal phase transition model that predicts the shift in the point of emergence observed in experiment when changing the data structure. Overall, our experimental and theoretical frameworks yield a step towards better defining, characterizing, and predicting emergence in neural networks.
Authors: Phurinut Srisawad, Juergen Branke, Long Tran-Thanh
Abstract: This paper formulates a new Best-Arm Identification problem in the non-stationary stochastic bandits setting, where the means of all arms are shifted in the same way due to a global influence of the environment. The aim is to identify the unique best arm across environmental change given a fixed total budget. While this setting can be regarded as a special case of Adversarial Bandits or Corrupted Bandits, we demonstrate that existing solutions tailored to those settings do not fully utilise the nature of this global influence, and thus, do not work well in practice (despite their theoretical guarantees). To overcome this issue, in this paper we develop a novel selection policy that is consistent and robust in dealing with global environmental shifts. We then propose an allocation policy, LinLUCB, which exploits information about global shifts across all arms in each environment. Empirical tests depict a significant improvement in our policies against other existing methods.
Authors: Xingtong Yu, Jie Zhang, Yuan Fang, Renhe Jiang
Abstract: Graphs are ubiquitous for modeling complex relationships between objects across various fields. Graph neural networks (GNNs) have become a mainstream technique for graph-based applications, but their performance heavily relies on abundant labeled data. To reduce labeling requirement, pre-training and prompt learning has become a popular alternative. However, most existing prompt methods do not differentiate homophilic and heterophilic characteristics of real-world graphs. In particular, many real-world graphs are non-homophilic, not strictly or uniformly homophilic with mixing homophilic and heterophilic patterns, exhibiting varying non-homophilic characteristics across graphs and nodes. In this paper, we propose ProNoG, a novel pre-training and prompt learning framework for such non-homophilic graphs. First, we analyze existing graph pre-training methods, providing theoretical insights into the choice of pre-training tasks. Second, recognizing that each node exhibits unique non-homophilic characteristics, we propose a conditional network to characterize the node-specific patterns in downstream tasks. Finally, we thoroughly evaluate and analyze ProNoG through extensive experiments on ten public datasets.
Authors: Musfiqur Rahman, SayedHassan Khatoonabadi, Ahmad Abdellatif, Haya Samaana, Emad Shihab
Abstract: [Context] Nowadays, many software systems include Artificial Intelligence (AI) components and changes in the development environment have been known to induce variability in an AI-based system. [Objective] However, how an environment configuration impacts the variability of these systems is yet to be explored. Understanding and quantifying the degree of variability due to such configurations can help practitioners decide the best environment configuration for the most stable AI products. [Method] To achieve this goal, we performed experiments with eight different combinations of three key environment variables (operating system, Python version, and CPU architecture) on 30 open-source AI-based systems using the Travis CI platform. We evaluate variability using three metrics: the output of an AI component like an ML model (performance), the time required to build and run a system (processing time), and the cost associated with building and running a system (expense). [Results] Our results indicate that variability exists in all three metrics; however, it is observed more frequently with respect to processing time and expense than performance. For example, between Linux and MacOS, variabilities are observed in 23%, 96.67%, and 100% of the studied projects in performance, processing time, and expense, respectively. [Conclusion] Our findings underscore the importance of identifying the optimal combination of configuration settings to mitigate performance drops and reduce retraining time and cost before deploying an AI-based system.
Authors: Jasmine Latendresse, SayedHassan Khatoonabadi, Ahmad Abdellatif, Emad Shihab
Abstract: Software libraries play a critical role in the functionality, efficiency, and maintainability of software systems. As developers increasingly rely on Large Language Models (LLMs) to streamline their coding processes, the effectiveness of these models in recommending appropriate libraries becomes crucial yet remains largely unexplored. In this paper, we assess the effectiveness of ChatGPT as a software librarian and identify areas for improvement. We conducted an empirical study using GPT-3.5 Turbo to generate Python code for 10,000 Stack Overflow questions. Our findings show that ChatGPT uses third-party libraries nearly 10% more often than human developers, favoring widely adopted and well-established options. However, 14.2% of the recommended libraries had restrictive copyleft licenses, which were not explicitly communicated by ChatGPT. Additionally, 6.5% of the libraries did not work out of the box, leading to potential developer confusion and wasted time. While ChatGPT can be an effective software librarian, it should be improved by providing more explicit information on maintainability metrics and licensing. We recommend that developers implement rigorous dependency management practices and double-check library licenses before integrating LLM-generated code into their projects.
Authors: Ammar Mansoor Kamoona, Hui Song, Mahdi Jalili, Hao Wang, Reza Razzaghi, Xinghuo Yu
Abstract: The growing popularity of Electric Vehicles (EVs) poses unique challenges for grid operators and infrastructure, which requires effectively managing these vehicles' integration into the grid. Identification of EVs charging is essential to electricity Distribution Network Operators (DNOs) for better planning and managing the distribution grid. One critical aspect is the ability to accurately identify the presence of EV charging in the grid. EV charging identification using smart meter readings obtained from behind-the-meter devices is a challenging task that enables effective managing the integration of EVs into the existing power grid. Different from the existing supervised models that require addressing the imbalance problem caused by EVs and non-EVs data, we propose a novel unsupervised memory-based transformer (M-TR) that can run in real-time (online) to detect EVs charging from a streaming smart meter. It dynamically leverages coarse-scale historical information using an M-TR encoder from an extended global temporal window, in conjunction with an M-TR decoder that concentrates on a limited time frame, local window, aiming to capture the fine-scale characteristics of the smart meter data. The M-TR is based on an anomaly detection technique that does not require any prior knowledge about EVs charging profiles, nor it does only require real power consumption data of non-EV users. In addition, the proposed model leverages the power of transfer learning. The M-TR is compared with different state-of-the-art methods and performs better than other unsupervised learning models. The model can run with an excellent execution time of 1.2 sec. for 1-minute smart recordings.
Authors: Byunghyun Ban, Hyoseok Lee
Abstract: In the contemporary digital era, protection of personal information has become a paramount issue. The exponential growth of the media industry has heightened concerns regarding the anonymization of individuals captured in video footage. Traditional methods, such as blurring or pixelation, are commonly employed, while recent advancements have introduced generative adversarial networks (GAN) to redraw faces in videos. In this study, we propose a novel approach that employs a significantly smaller model to achieve real-time full-body anonymization of individuals in videos. Unlike conventional techniques that often fail to effectively remove personal identification information such as skin color, clothing, accessories, and body shape while our method successfully eradicates all such details. Furthermore, by leveraging pose estimation algorithms, our approach accurately represents information regarding individuals' positions, movements, and postures. This algorithm can be seamlessly integrated into CCTV or IP camera systems installed in various industrial settings, functioning in real-time and thus facilitating the widespread adoption of full-body anonymization technology.
Authors: Milad Fotouhi, Mohammad Taha Bahadori, Oluwaseyi Feyisetan, Payman Arabshahi, David Heckerman
Abstract: We investigate the use of in-context learning and prompt engineering to estimate the contributions of training data in the outputs of instruction-tuned large language models (LLMs). We propose two novel approaches: (1) a similarity-based approach that measures the difference between LLM outputs with and without provided context, and (2) a mixture distribution model approach that frames the problem of identifying contribution scores as a matrix factorization task. Our empirical comparison demonstrates that the mixture model approach is more robust to retrieval noise in in-context learning, providing a more reliable estimation of data contributions.
Authors: Yanjun Gao, Skatje Myers, Shan Chen, Dmitriy Dligach, Timothy A Miller, Danielle Bitterman, Matthew Churpek, Majid Afshar
Abstract: The introduction of Large Language Models (LLMs) has advanced data representation and analysis, bringing significant progress in their use for medical questions and answering. Despite these advancements, integrating tabular data, especially numerical data pivotal in clinical contexts, into LLM paradigms has not been thoroughly explored. In this study, we examine the effectiveness of vector representations from last hidden states of LLMs for medical diagnostics and prognostics using electronic health record (EHR) data. We compare the performance of these embeddings with that of raw numerical EHR data when used as feature inputs to traditional machine learning (ML) algorithms that excel at tabular data learning, such as eXtreme Gradient Boosting. We focus on instruction-tuned LLMs in a zero-shot setting to represent abnormal physiological data and evaluating their utilities as feature extractors to enhance ML classifiers for predicting diagnoses, length of stay, and mortality. Furthermore, we examine prompt engineering techniques on zero-shot and few-shot LLM embeddings to measure their impact comprehensively. Although findings suggest the raw data features still prevails in medical ML tasks, zero-shot LLM embeddings demonstrate competitive results, suggesting a promising avenue for future research in medical applications.
Authors: Zhongyu Zhao, Menghang Dong, Rongyu Zhang, Wenzhao Zheng, Yunpeng Zhang, Huanrui Yang, Dalong Du, Kurt Keutzer, Shanghang Zhang
Abstract: Recent research has demonstrated that Feed-Forward Networks (FFNs) in Large Language Models (LLMs) play a pivotal role in storing diverse linguistic and factual knowledge. Conventional methods frequently face challenges due to knowledge confusion stemming from their monolithic and redundant architectures, which calls for more efficient solutions with minimal computational overhead, particularly for LLMs. In this paper, we explore the FFN computation paradigm in LLMs and introduce FactorLLM, a novel approach that decomposes well-trained dense FFNs into sparse sub-networks without requiring any further modifications, while maintaining the same level of performance. Furthermore, we embed a router from the Mixture-of-Experts (MoE), combined with our devised Prior-Approximate (PA) loss term that facilitates the dynamic activation of experts and knowledge adaptation, thereby accelerating computational processes and enhancing performance using minimal training data and fine-tuning steps. FactorLLM thus enables efficient knowledge factorization and activates select groups of experts specifically tailored to designated tasks, emulating the interactive functional segmentation of the human brain. Extensive experiments across various benchmarks demonstrate the effectiveness of our proposed FactorLLM which achieves comparable performance to the source model securing up to 85% model performance while obtaining over a 30% increase in inference speed. Code: https://github.com/zhenwuweihe/FactorLLM.
Authors: Sina Montazeri, Haseebullah Jumakhan, Sonia Abrasiabian, Amir Mirzaeinia
Abstract: Building on our prior explorations of convolutional neural networks (CNNs) for financial data processing, this paper introduces two significant enhancements to refine our CNN model's predictive performance and robustness for financial tabular data. Firstly, we integrate a normalization layer at the input stage to ensure consistent feature scaling, addressing the issue of disparate feature magnitudes that can skew the learning process. This modification is hypothesized to aid in stabilizing the training dynamics and improving the model's generalization across diverse financial datasets. Secondly, we employ a Gradient Reduction Architecture, where earlier layers are wider and subsequent layers are progressively narrower. This enhancement is designed to enable the model to capture more complex and subtle patterns within the data, a crucial factor in accurately predicting financial outcomes. These advancements directly respond to the limitations identified in previous studies, where simpler models struggled with the complexity and variability inherent in financial applications. Initial tests confirm that these changes improve accuracy and model stability, suggesting that deeper and more nuanced network architectures can significantly benefit financial predictive tasks. This paper details the implementation of these enhancements and evaluates their impact on the model's performance in a controlled experimental setting.
Authors: Arindam Sett, Somaye Hashemifar, Mrunal Yadav, Yogesh Pandit, Mohsen Hejrati
Abstract: The implementation of Artificial Intelligence (AI) in the healthcare industry has garnered considerable attention, attributable to its prospective enhancement of clinical outcomes, expansion of access to superior healthcare, cost reduction, and elevation of patient satisfaction. Nevertheless, the primary hurdle that persists is related to the quality of accessible multi-modal healthcare data in conjunction with the evolution of AI methodologies. This study delves into the adoption of large language models to address specific challenges, specifically, the standardization of healthcare data. We advocate the use of these models to identify and map clinical data schemas to established data standard attributes, such as the Fast Healthcare Interoperability Resources. Our results illustrate that employing large language models significantly diminishes the necessity for manual data curation and elevates the efficacy of the data standardization process. Consequently, the proposed methodology has the propensity to expedite the integration of AI in healthcare, ameliorate the quality of patient care, whilst minimizing the time and financial resources necessary for the preparation of data for AI.
Authors: Sotiris Anagnostidis, Jannis Bulian
Abstract: Large Language Models (LLMs) are highly sensitive to prompts, including additional context provided therein. As LLMs grow in capability, understanding their prompt-sensitivity becomes increasingly crucial for ensuring reliable and robust performance, particularly since evaluating these models becomes more challenging. In this work, we investigate how current models (Llama, Mixtral, Falcon) respond when presented with additional input from another model, mimicking a scenario where a more capable model -- or a system with access to more external information -- provides supplementary information to the target model. Across a diverse spectrum of question-answering tasks, we study how an LLM's response to multiple-choice questions changes when the prompt includes a prediction and explanation from another model. Specifically, we explore the influence of the presence of an explanation, the stated authoritativeness of the source, and the stated confidence of the supplementary input. Our findings reveal that models are strongly influenced, and when explanations are provided they are swayed irrespective of the quality of the explanation. The models are more likely to be swayed if the input is presented as being authoritative or confident, but the effect is small in size. This study underscores the significant prompt-sensitivity of LLMs and highlights the potential risks of incorporating outputs from external sources without thorough scrutiny and further validation. As LLMs continue to advance, understanding and mitigating such sensitivities will be crucial for their reliable and trustworthy deployment.
Authors: Sakhinana Sagar Srinivas, Venkataramana Runkana
Abstract: Molecule design is a multifaceted approach that leverages computational methods and experiments to optimize molecular properties, fast-tracking new drug discoveries, innovative material development, and more efficient chemical processes. Recently, text-based molecule design has emerged, inspired by next-generation AI tasks analogous to foundational vision-language models. Our study explores the use of knowledge-augmented prompting of large language models (LLMs) for the zero-shot text-conditional de novo molecular generation task. Our approach uses task-specific instructions and a few demonstrations to address distributional shift challenges when constructing augmented prompts for querying LLMs to generate molecules consistent with technical descriptions. Our framework proves effective, outperforming state-of-the-art (SOTA) baseline models on benchmark datasets.
Authors: Jun Lu, David Li, Bill Ding, Yu Kang
Abstract: This paper presents an approach to improve text embedding models through contrastive fine-tuning on small datasets augmented with expert scores. It focuses on enhancing semantic textual similarity tasks and addressing text retrieval problems. The proposed method uses soft labels derived from expert-augmented scores to fine-tune embedding models, preserving their versatility and ensuring retrieval capability is improved. The paper evaluates the method using a Q\&A dataset from an online shopping website and eight expert models. Results show improved performance over a benchmark model across multiple metrics on various retrieval tasks from the massive text embedding benchmark (MTEB). The method is cost-effective and practical for real-world applications, especially when labeled data is scarce.
Authors: Jiaang Li, Quan Wang, Zhongnan Wang, Yongdong Zhang, Zhendong Mao
Abstract: Large language models (LLMs) require model editing to efficiently update specific knowledge within them and avoid factual errors. Most model editing methods are solely designed for single-time use and lead to a significant forgetting effect after sequential edits over time, referred to as lifelong editing. Current approaches manage sequential edits by freezing original parameters and allocating new adapters for each knowledge modification. However, these methods lack robustness to minor input variations. To address this challenge, we propose ELDER, \textbf{E}nhancing \textbf{L}ifelong mo\textbf{D}el \textbf{E}diting with mixtu\textbf{R}e of Low-Rank Adapter (LoRA). ELDER is an adaptive approach that integrates multiple LoRAs through a router network. It learns to create a continuous and smooth association between data and adapters, thereby enhancing robustness and generalization to semantically equivalent inputs. Additionally, we introduce a novel loss to help learn associations between adapter allocations and edit semantics. A deferral mechanism is also proposed to retain the original LLM capabilities post-edit. Extensive experiments on GPT-2 XL and LLaMA2-7B demonstrate that ELDER effectively edits models in the lifelong setting and exhibits strong scalability, while retaining LLM's general abilities on downstream tasks.
Authors: Xuan Kan, Yonghui Xiao, Tien-Ju Yang, Nanxin Chen, Rajiv Mathews
Abstract: This work explores the challenge of enhancing Automatic Speech Recognition (ASR) model performance across various user-specific domains while preserving user data privacy. We employ federated learning and parameter-efficient domain adaptation methods to solve the (1) massive data requirement of ASR models from user-specific scenarios and (2) the substantial communication cost between servers and clients during federated learning. We demonstrate that when equipped with proper adapters, ASR models under federated tuning can achieve similar performance compared with centralized tuning ones, thus providing a potential direction for future privacy-preserved ASR services. Besides, we investigate the efficiency of different adapters and adapter incorporation strategies under the federated learning setting.
Authors: Guy Lutsker, Gal Sapir, Anastasia Godneva, Smadar Shilo, Jerry R Greenfield, Dorit Samocha-Bonet, Shie Mannor, Eli Meirom, Gal Chechik, Hagai Rossman, Eran Segal
Abstract: Recent advances in self-supervised learning enabled novel medical AI models, known as foundation models (FMs) that offer great potential for characterizing health from diverse biomedical data. Continuous glucose monitoring (CGM) provides rich, temporal data on glycemic patterns, but its full potential for predicting broader health outcomes remains underutilized. Here, we present GluFormer, a generative foundation model on biomedical temporal data based on a transformer architecture, and trained on over 10 million CGM measurements from 10,812 non-diabetic individuals. We tokenized the CGM training data and trained GluFormer using next token prediction in a generative, autoregressive manner. We demonstrate that GluFormer generalizes effectively to 15 different external datasets, including 4936 individuals across 5 different geographical regions, 6 different CGM devices, and several metabolic disorders, including normoglycemic, prediabetic, and diabetic populations, as well as those with gestational diabetes and obesity. GluFormer produces embeddings which outperform traditional CGM analysis tools, and achieves high Pearson correlations in predicting clinical parameters such as HbA1c, liver-related parameters, blood lipids, and sleep-related indices. Notably, GluFormer can also predict onset of future health outcomes even 4 years in advance. We also show that CGM embeddings from pre-intervention periods in Randomized Clinical Trials (RCTs) outperform other methods in predicting primary and secondary outcomes. When integrating dietary data into GluFormer, we show that the enhanced model can accurately generate CGM data based only on dietary intake data, simulate outcomes of dietary interventions, and predict individual responses to specific foods. Overall, we show that GluFormer accurately predicts health outcomes which generalize across different populations metabolic conditions.
Authors: Muhammad Rafsan Kabir, Rafeed Mohammad Sultan, Ihsanul Haque Asif, Jawad Ibn Ahad, Fuad Rahman, Mohammad Ruhul Amin, Nabeel Mohammed, Shafin Rahman
Abstract: Aligning large language models (LLMs) with a human reasoning approach ensures that LLMs produce morally correct and human-like decisions. Ethical concerns are raised because current models are prone to generating false positives and providing malicious responses. To contribute to this issue, we have curated an ethics dataset named Dataset for Aligning Reasons (DFAR), designed to aid in aligning language models to generate human-like reasons. The dataset comprises statements with ethical-unethical labels and their corresponding reasons. In this study, we employed a unique and novel fine-tuning approach that utilizes ethics labels and their corresponding reasons (L+R), in contrast to the existing fine-tuning approach that only uses labels (L). The original pre-trained versions, the existing fine-tuned versions, and our proposed fine-tuned versions of LLMs were then evaluated on an ethical-unethical classification task and a reason-generation task. Our proposed fine-tuning strategy notably outperforms the others in both tasks, achieving significantly higher accuracy scores in the classification task and lower misalignment rates in the reason-generation task. The increase in classification accuracies and decrease in misalignment rates indicate that the L+R fine-tuned models align more with human ethics. Hence, this study illustrates that injecting reasons has substantially improved the alignment of LLMs, resulting in more human-like responses. We have made the DFAR dataset and corresponding codes publicly available at https://github.com/apurba-nsu-rnd-lab/DFAR.
Authors: Jingying Ma, Qika Lin, Ziyu Jia, Mengling Feng
Abstract: Sleep staging is critical for assessing sleep quality and diagnosing disorders. Recent advancements in artificial intelligence have driven the development of automated sleep staging models, which still face two significant challenges. 1) Simultaneously extracting prominent temporal and spatial sleep features from multi-channel raw signals, including characteristic sleep waveforms and salient spatial brain networks. 2) Capturing the spatial-temporal coupling patterns essential for accurate sleep staging. To address these challenges, we propose a novel framework named ST-USleepNet, comprising a spatial-temporal graph construction module (ST) and a U-shaped sleep network (USleepNet). The ST module converts raw signals into a spatial-temporal graph to model spatial-temporal couplings. The USleepNet utilizes a U-shaped structure originally designed for image segmentation. Similar to how image segmentation isolates significant targets, when applied to both raw sleep signals and ST module-generated graph data, USleepNet segments these inputs to extract prominent temporal and spatial sleep features simultaneously. Testing on three datasets demonstrates that ST-USleepNet outperforms existing baselines, and model visualizations confirm its efficacy in extracting prominent sleep features and temporal-spatial coupling patterns across various sleep stages. The code is available at: https://github.com/Majy-Yuji/ST-USleepNet.git.
Authors: Eric R. Anschuetz
Abstract: Classical neural networks with random initialization famously behave as Gaussian processes in the limit of many neurons, with the architecture of the network determining the covariance of the associated process. This limit allows one to completely characterize the training behavior of such networks and show that, generally, classical neural networks train efficiently via gradient descent. No such general understanding exists for quantum neural networks (QNNs), which -- outside of certain special cases -- are known to not behave as Gaussian processes when randomly initialized. We here prove that instead QNNs and their first two derivatives generally form what we call Wishart processes, where now certain algebraic properties of the network determine the hyperparameters of the process. This Wishart process description allows us to, for the first time: 1. Give necessary and sufficient conditions for a QNN architecture to have a Gaussian process limit. 2. Calculate the full gradient distribution, unifying previously known barren plateau results. 3. Calculate the local minima distribution of algebraically constrained QNNs. The transition from trainability to untrainability in each of these contexts is governed by a single parameter we call the "degrees of freedom" of the network architecture. We thus end by proposing a formal definition for the "trainability" of a given QNN architecture using this experimentally accessible quantity.
Authors: Jane Castleman, Aleksandra Korolova
Abstract: Recently, Meta has shifted towards AI-mediated ad targeting mechanisms that do not require advertisers to provide detailed targeting criteria, likely driven by excitement over AI capabilities as well as new data privacy policies and targeting changes agreed upon in civil rights settlements. At the same time, Meta has touted their ad preference controls as an effective mechanism for users to control the ads they see. Furthermore, Meta markets their targeting explanations as a transparency tool that allows users to understand why they saw certain ads and inform actions to control future ads. Our study evaluates the effectiveness of Meta's "See less" ad control and the actionability of ad targeting explanations following the shift to AI-mediated targeting. We conduct a large-scale study, randomly assigning participants to mark "See less" to Body Weight Control or Parenting topics, and collecting the ads and targeting explanations Meta shows to participants before and after the intervention. We find that utilizing the "See less" ad control for the topics we study does not significantly reduce the number of ads shown by Meta on these topics, and that the control is less effective for some users whose demographics are correlated with the topic. Furthermore, we find that the majority of ad targeting explanations for local ads made no reference to location-specific targeting criteria, and did not inform users why ads related to the topics they marked to "See less" of continued to be delivered. We hypothesize that the poor effectiveness of controls and lack of actionability in explanations are the result of the shift to AI-mediated targeting, for which explainability and transparency tools have not yet been developed. Our work thus provides evidence for the need of new methods for transparency and user control, suitable and reflective of increasingly complex AI-mediated ad delivery systems.
Authors: Junwon Lee, Jaekwon Im, Dabin Kim, Juhan Nam
Abstract: Foley sound synthesis is crucial for multimedia production, enhancing user experience by synchronizing audio and video both temporally and semantically. Recent studies on automating this labor-intensive process through video-to-sound generation face significant challenges. Systems lacking explicit temporal features suffer from poor controllability and alignment, while timestamp-based models require costly and subjective human annotation. We propose Video-Foley, a video-to-sound system using Root Mean Square (RMS) as a temporal event condition with semantic timbre prompts (audio or text). RMS, a frame-level intensity envelope feature closely related to audio semantics, ensures high controllability and synchronization. The annotation-free self-supervised learning framework consists of two stages, Video2RMS and RMS2Sound, incorporating novel ideas including RMS discretization and RMS-ControlNet with a pretrained text-to-audio model. Our extensive evaluation shows that Video-Foley achieves state-of-the-art performance in audio-visual alignment and controllability for sound timing, intensity, timbre, and nuance. Code, model weights, and demonstrations are available on the accompanying website. (https://jnwnlee.github.io/video-foley-demo)
Authors: Jinendra Malekar, Mohammed E. Elbtity, Ramtin Zand Co
Abstract: The advent of 1-bit large language models (LLMs) has attracted considerable attention and opened up new research opportunities. However, 1-bit LLMs only improve a fraction of models by applying extreme quantization to the projection layers while leaving attention heads unchanged. Therefore, to avoid fundamentally wrong choices of goals in future research, it is crucial to understand the actual improvements in computation and memory usage that 1-bit LLMs can deliver. In this work, we present an adaptation of Amdahl's Law tailored for the 1-bit LLM context, which illustrates how partial improvements in 1-bit LLMs impact overall model performance. Through extensive experiments, we uncover key nuances across different model architectures and hardware configurations, offering a roadmap for future research in the era of 1-bit LLMs.
Authors: Baihan Lin
Abstract: Understanding how the brain represents and processes information is crucial for advancing neuroscience and artificial intelligence. Representational similarity analysis (RSA) has been instrumental in characterizing neural representations, but traditional RSA relies solely on geometric properties, overlooking crucial topological information. This thesis introduces Topological RSA (tRSA), a novel framework combining geometric and topological properties of neural representations. tRSA applies nonlinear monotonic transforms to representational dissimilarities, emphasizing local topology while retaining intermediate-scale geometry. The resulting geo-topological matrices enable model comparisons robust to noise and individual idiosyncrasies. This thesis introduces several key methodological advances: (1) Topological RSA (tRSA) for identifying computational signatures and testing topological hypotheses; (2) Adaptive Geo-Topological Dependence Measure (AGTDM) for detecting complex multivariate relationships; (3) Procrustes-aligned Multidimensional Scaling (pMDS) for revealing neural computation stages; (4) Temporal Topological Data Analysis (tTDA) for uncovering developmental trajectories; and (5) Single-cell Topological Simplicial Analysis (scTSA) for characterizing cell population complexity. Through analyses of neural recordings, biological data, and neural network simulations, this thesis demonstrates the power and versatility of these methods in understanding brains, computational models, and complex biological systems. They not only offer robust approaches for adjudicating among competing models but also reveal novel theoretical insights into the nature of neural computation. This work lays the foundation for future investigations at the intersection of topology, neuroscience, and time series analysis, paving the way for more nuanced understanding of brain function and dysfunction.
Authors: James Tavernor, Yara El-Tawil, Emily Mower Provost
Abstract: Emotion expression and perception are nuanced, complex, and highly subjective processes. When multiple annotators label emotional data, the resulting labels contain high variability. Most speech emotion recognition tasks address this by averaging annotator labels as ground truth. However, this process omits the nuance of emotion and inter-annotator variability, which are important signals to capture. Previous work has attempted to learn distributions to capture emotion variability, but these methods also lose information about the individual annotators. We address these limitations by learning to predict individual annotators and by introducing a novel method to create distributions from continuous model outputs that permit the learning of emotion distributions during model training. We show that this combined approach can result in emotion distributions that are more accurate than those seen in prior work, in both within- and cross-corpus settings.
Authors: Neil Ashton, Charles Mockett, Marian Fuchs, Louis Fliessbach, Hendrik Hetmann, Thilo Knacke, Norbert Schonwald, Vangelis Skaperdas, Grigoris Fotiadis, Astrid Walle, Burkhard Hupertz, Danielle Maddix
Abstract: Machine Learning (ML) has the potential to revolutionise the field of automotive aerodynamics, enabling split-second flow predictions early in the design process. However, the lack of open-source training data for realistic road cars, using high-fidelity CFD methods, represents a barrier to their development. To address this, a high-fidelity open-source (CC-BY-SA) public dataset for automotive aerodynamics has been generated, based on 500 parametrically morphed variants of the widely-used DrivAer notchback generic vehicle. Mesh generation and scale-resolving CFD was executed using consistent and validated automatic workflows representative of the industrial state-of-the-art. Geometries and rich aerodynamic data are published in open-source formats. To our knowledge, this is the first large, public-domain dataset for complex automotive configurations generated using high-fidelity CFD.
Authors: Tong Xu, Armeen Taeb, Simge K\"u\c{c}\"ukyavuz, Ali Shojaie
Abstract: This paper studies the problem of learning Bayesian networks from continuous observational data, generated according to a linear Gaussian structural equation model. We consider an $\ell_0$-penalized maximum likelihood estimator for this problem which is known to have favorable statistical properties but is computationally challenging to solve, especially for medium-sized Bayesian networks. We propose a new coordinate descent algorithm to approximate this estimator and prove several remarkable properties of our procedure: the algorithm converges to a coordinate-wise minimum, and despite the non-convexity of the loss function, as the sample size tends to infinity, the objective value of the coordinate descent solution converges to the optimal objective value of the $\ell_0$-penalized maximum likelihood estimator. Finite-sample optimality and statistical consistency guarantees are also established. To the best of our knowledge, our proposal is the first coordinate descent procedure endowed with optimality and statistical guarantees in the context of learning Bayesian networks. Numerical experiments on synthetic and real data demonstrate that our coordinate descent method can obtain near-optimal solutions while being scalable.
Authors: Anton Klenitskiy, Anna Volodkevich, Anton Pembek, Alexey Vasilev
Abstract: Sequential recommender systems are an important and demanded area of research. Such systems aim to use the order of interactions in a user's history to predict future interactions. The premise is that the order of interactions and sequential patterns play an essential role. Therefore, it is crucial to use datasets that exhibit a sequential structure to evaluate sequential recommenders properly. We apply several methods based on the random shuffling of the user's sequence of interactions to assess the strength of sequential structure across 15 datasets, frequently used for sequential recommender systems evaluation in recent research papers presented at top-tier conferences. As shuffling explicitly breaks sequential dependencies inherent in datasets, we estimate the strength of sequential patterns by comparing metrics for shuffled and original versions of the dataset. Our findings show that several popular datasets have a rather weak sequential structure.
Authors: Subin Sahayam, John Michael Sujay Zakkam, Yoga Sri Varshan V, Umarani Jayaraman
Abstract: Brain tumors in magnetic resonance imaging (MR) are difficult, time-consuming, and prone to human error. These challenges can be resolved by developing automatic brain tumor segmentation methods from MR images. Various deep-learning models based on the U-Net have been proposed for the task. These deep-learning models are trained on a dataset of tumor images and then used for segmenting the masks. Mini-batch training is a widely used method in deep learning for training. However, one of the significant challenges associated with this approach is that if the training dataset has under-represented samples or samples with complex latent representations, the model may not generalize well to these samples. The issue leads to skewed learning of the data, where the model learns to fit towards the majority representations while underestimating the under-represented samples. The proposed dynamic batch training method addresses the challenges posed by under-represented data points, data points with complex latent representation, and imbalances within the class, where some samples may be harder to learn than others. Poor performance of such samples can be identified only after the completion of the training, leading to the wastage of computational resources. Also, training easy samples after each epoch is an inefficient utilization of computation resources. To overcome these challenges, the proposed method identifies hard samples and trains such samples for more iterations compared to easier samples on the BraTS2020 dataset. Additionally, the samples trained multiple times are identified and it provides a way to identify hard samples in the BraTS2020 dataset. The comparison of the proposed training approach with U-Net and other models in the literature highlights the capabilities of the proposed training approach.
Authors: Wangjiaxuan Xin, Kanlun Wang, Zhe Fu, Lina Zhou
Abstract: Content moderation is a widely used strategy to prevent the dissemination of irregular information on social media platforms. Despite extensive research on developing automated models to support decision-making in content moderation, there remains a notable scarcity of studies that integrate the rules of online communities into content moderation. This study addresses this gap by proposing a community rule-based content moderation framework that directly integrates community rules into the moderation of user-generated content. Our experiment results with datasets collected from two domains demonstrate the superior performance of models based on the framework to baseline models across all evaluation metrics. In particular, incorporating community rules substantially enhances model performance in content moderation. The findings of this research have significant research and practical implications for improving the effectiveness and generalizability of content moderation models in online communities.
Authors: Raphael Poulain, Hamed Fayyaz, Rahmatollah Beheshti
Abstract: Large Language Models (LLMs) have emerged as promising solutions for a variety of medical and clinical decision support applications. However, LLMs are often subject to different types of biases, which can lead to unfair treatment of individuals, worsening health disparities, and reducing trust in AI-augmented medical tools. Aiming to address this important issue, in this study, we present a new model alignment approach for aligning LLMs using a preference optimization method within a knowledge distillation framework. Prior to presenting our proposed method, we first use an evaluation framework to conduct a comprehensive (largest to our knowledge) empirical evaluation to reveal the type and nature of existing biases in LLMs used for medical applications. We then offer a bias mitigation technique to reduce the unfair patterns in LLM outputs across different subgroups identified by the protected attributes. We show that our mitigation method is effective in significantly reducing observed biased patterns. Our code is publicly available at \url{https://github.com/healthylaife/FairAlignmentLLM}.
Authors: Hanieh Rashidpour, Hossein Bahramgiri
Abstract: With the emergence of new technologies and a growing number of wireless networks, we face the problem of radio spectrum shortages. As a result, identifying the wireless channel spectrum to exploit the channel's idle state while also boosting network security is a pivotal issue. Detecting and classifying protocols in the MAC sublayer enables Cognitive Radio users to improve spectrum utilization and minimize potential interference. In this paper, we classify the Wi-Fi and Bluetooth protocols, which are the most widely used MAC sublayer protocols in the ISM radio band. With the advent of various wireless technologies, especially in the 2.4 GHz frequency band, the ISM frequency spectrum has become crowded and high-traffic, which faces a lack of spectrum resources and user interference. Therefore, identifying and classifying protocols is an effective and useful method. Leveraging machine learning and deep learning techniques, known for their advanced classification capabilities, we apply Support Vector Machine and K-Nearest Neighbors algorithms, which are machine learning algorithms, to classify protocols into three classes: Wi-Fi, Wi-Fi Beacon, and Bluetooth. To capture the signals, we use the USRP N210 Software Defined Radio device and sample the real data in the indoor environment in different conditions of the presence and absence of transmitters and receivers for these two protocols. By assembling this dataset and studying the time and frequency features of the protocols, we extract the frame width and the silence gap between the two frames as time features and the PAPR of each frame as a power feature. By comparing the output of the protocols classification in different conditions and also adding Gaussian noise, it was found that the samples in the nonlinear SVM method with RBF and KNN functions have the best performance, with 97.83% and 98.12% classification accuracy, respectively.
Authors: Wentao Gao, Jiuyong Li, Debo Cheng, Lin Liu, Jixue Liu, Thuc Duy Le, Xiaojing Du, Xiongren Chen, Yanchang Zhao, Yun Chen
Abstract: Global Climate Models (GCMs) are crucial for predicting future climate changes by simulating the Earth systems. However, GCM outputs exhibit systematic biases due to model uncertainties, parameterization simplifications, and inadequate representation of complex climate phenomena. Traditional bias correction methods, which rely on historical observation data and statistical techniques, often neglect unobserved confounders, leading to biased results. This paper proposes a novel bias correction approach to utilize both GCM and observational data to learn a factor model that captures multi-cause latent confounders. Inspired by recent advances in causality based time series deconfounding, our method first constructs a factor model to learn latent confounders from historical data and then applies them to enhance the bias correction process using advanced time series forecasting models. The experimental results demonstrate significant improvements in the accuracy of precipitation outputs. By addressing unobserved confounders, our approach offers a robust and theoretically grounded solution for climate model bias correction.
Authors: Xiaopeng Yang, Weicheng Gao, Xiaodong Qu, Zeyu Ma, Hao Zhang
Abstract: With the help of micro-Doppler signature, ultra-wideband (UWB) through-the-wall radar (TWR) enables the reconstruction of range and velocity information of limb nodes to accurately identify indoor human activities. However, existing methods are usually trained and validated directly using range-time maps (RTM) and Doppler-time maps (DTM), which have high feature redundancy and poor generalization ability. In order to solve this problem, this paper proposes a human activity micro-Doppler signature representation method based on joint Boulic-sinusoidal pendulum motion model. In detail, this paper presents a simplified joint Boulic-sinusoidal pendulum human motion model by taking head, torso, both hands and feet into consideration improved from Boulic-Thalmann kinematic model. The paper also calculates the minimum number of key points needed to describe the Doppler and micro-Doppler information sufficiently. Both numerical simulations and experiments are conducted to verify the effectiveness. The results demonstrate that the proposed number of key points of micro-Doppler signature can precisely represent the indoor human limb node motion characteristics, and substantially improve the generalization capability of the existing methods for different testers.
Authors: Aishik Nagar, Yutong Liu, Andy T. Liu, Viktor Schlegel, Vijay Prakash Dwivedi, Arun-Kumar Kaliya-Perumal, Guna Pratheep Kalanchiam, Yili Tang, Robby T. Tan
Abstract: Medical abstractive summarization faces the challenge of balancing faithfulness and informativeness. Current methods often sacrifice key information for faithfulness or introduce confabulations when prioritizing informativeness. While recent advancements in techniques like in-context learning (ICL) and fine-tuning have improved medical summarization, they often overlook crucial aspects such as faithfulness and informativeness without considering advanced methods like model reasoning and self-improvement. Moreover, the field lacks a unified benchmark, hindering systematic evaluation due to varied metrics and datasets. This paper addresses these gaps by presenting a comprehensive benchmark of six advanced abstractive summarization methods across three diverse datasets using five standardized metrics. Building on these findings, we propose uMedSum, a modular hybrid summarization framework that introduces novel approaches for sequential confabulation removal followed by key missing information addition, ensuring both faithfulness and informativeness. Our work improves upon previous GPT-4-based state-of-the-art (SOTA) medical summarization methods, significantly outperforming them in both quantitative metrics and qualitative domain expert evaluations. Notably, we achieve an average relative performance improvement of 11.8% in reference-free metrics over the previous SOTA. Doctors prefer uMedSum's summaries 6 times more than previous SOTA in difficult cases where there are chances of confabulations or missing information. These results highlight uMedSum's effectiveness and generalizability across various datasets and metrics, marking a significant advancement in medical summarization.
Authors: Yile Chen, Weiming Huang, Kaiqi Zhao, Yue Jiang, Gao Cong
Abstract: The proliferation of geospatial data in urban and territorial environments has significantly facilitated the development of geospatial artificial intelligence (GeoAI) across various urban applications. Given the vast yet inherently sparse labeled nature of geospatial data, there is a critical need for techniques that can effectively leverage such data without heavy reliance on labeled datasets. This requirement aligns with the principles of self-supervised learning (SSL), which has attracted increasing attention for its adoption in geospatial data. This paper conducts a comprehensive and up-to-date survey of SSL techniques applied to or developed for three primary data (geometric) types prevalent in geospatial vector data: points, polylines, and polygons. We systematically categorize various SSL techniques into predictive and contrastive methods, discussing their application with respect to each data type in enhancing generalization across various downstream tasks. Furthermore, we review the emerging trends of SSL for GeoAI, and several task-specific SSL techniques. Finally, we discuss several key challenges in the current research and outline promising directions for future investigation. By presenting a structured analysis of relevant studies, this paper aims to inspire continued advancements in the integration of SSL with GeoAI, encouraging innovative methods to harnessing the power of geospatial data.
Authors: Jooyoung Lee, Se Yoon Jeong, Munchurl Kim
Abstract: Unlike fixed- or variable-rate image coding, progressive image coding (PIC) aims to compress various qualities of images into a single bitstream, increasing the versatility of bitstream utilization and providing high compression efficiency compared to simulcast compression. Research on neural network (NN)-based PIC is in its early stages, mainly focusing on applying varying quantization step sizes to the transformed latent representations in a hierarchical manner. These approaches are designed to compress only the progressively added information as the quality improves, considering that a wider quantization interval for lower-quality compression includes multiple narrower sub-intervals for higher-quality compression. However, the existing methods are based on handcrafted quantization hierarchies, resulting in sub-optimal compression efficiency. In this paper, we propose an NN-based progressive coding method that firstly utilizes learned quantization step sizes via learning for each quantization layer. We also incorporate selective compression with which only the essential representation components are compressed for each quantization layer. We demonstrate that our method achieves significantly higher coding efficiency than the existing approaches with decreased decoding time and reduced model size.
Authors: Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song
Abstract: In this work, we improved the analysis of the running time of SparseGPT [Frantar, Alistarh ICML 2023] from $O(d^{3})$ to $O(d^{\omega} + d^{2+a+o(1)} + d^{1+\omega(1,1,a)-a})$ for any $a \in [0, 1]$, where $\omega$ is the exponent of matrix multiplication. In particular, for the current $\omega \approx 2.371$ [Alman, Duan, Williams, Xu, Xu, Zhou 2024], our running times boil down to $O(d^{2.53})$. This running time is due to the analysis of the lazy update behavior in iterative maintenance problems, such as [Deng, Song, Weinstein 2022, Brand, Song, Zhou ICML 2024].
Authors: Wuchao Li, Rui Huang, Haijun Zhao, Chi Liu, Kai Zheng, Qi Liu, Na Mou, Guorui Zhou, Defu Lian, Yang Song, Wentian Bao, Enyun Yu, Wenwu Ou
Abstract: Sequential Recommendation (SR) plays a pivotal role in recommender systems by tailoring recommendations to user preferences based on their non-stationary historical interactions. Achieving high-quality performance in SR requires attention to both item representation and diversity. However, designing an SR method that simultaneously optimizes these merits remains a long-standing challenge. In this study, we address this issue by integrating recent generative Diffusion Models (DM) into SR. DM has demonstrated utility in representation learning and diverse image generation. Nevertheless, a straightforward combination of SR and DM leads to sub-optimal performance due to discrepancies in learning objectives (recommendation vs. noise reconstruction) and the respective learning spaces (non-stationary vs. stationary). To overcome this, we propose a novel framework called DimeRec (\textbf{Di}ffusion with \textbf{m}ulti-interest \textbf{e}nhanced \textbf{Rec}ommender). DimeRec synergistically combines a guidance extraction module (GEM) and a generative diffusion aggregation module (DAM). The GEM extracts crucial stationary guidance signals from the user's non-stationary interaction history, while the DAM employs a generative diffusion process conditioned on GEM's outputs to reconstruct and generate consistent recommendations. Our numerical experiments demonstrate that DimeRec significantly outperforms established baseline methods across three publicly available datasets. Furthermore, we have successfully deployed DimeRec on a large-scale short video recommendation platform, serving hundreds of millions of users. Live A/B testing confirms that our method improves both users' time spent and result diversification.
Authors: Juno Kim, Tai Nakamaki, Taiji Suzuki
Abstract: In-context learning (ICL) of large language models has proven to be a surprisingly effective method of learning a new task from only a few demonstrative examples. In this paper, we study the efficacy of ICL from the viewpoint of statistical learning theory. We develop approximation and generalization error bounds for a transformer composed of a deep neural network and one linear attention layer, pretrained on nonparametric regression tasks sampled from general function spaces including the Besov space and piecewise $\gamma$-smooth class. We show that sufficiently trained transformers can achieve -- and even improve upon -- the minimax optimal estimation risk in context by encoding the most relevant basis representations during pretraining. Our analysis extends to high-dimensional or sequential data and distinguishes the \emph{pretraining} and \emph{in-context} generalization gaps. Furthermore, we establish information-theoretic lower bounds for meta-learners w.r.t. both the number of tasks and in-context examples. These findings shed light on the roles of task diversity and representation learning for ICL.
Authors: Stefanos Bakirtzis, Cagkan Yapar, Marco Fiore, Jie Zhang, Ian Wassell
Abstract: The efficient deployment and operation of any wireless communication ecosystem rely on knowledge of the received signal quality over the target coverage area. This knowledge is typically acquired through radio propagation solvers, which however suffer from intrinsic and well-known performance limitations. This article provides a primer on how integrating deep learning and conventional propagation modeling techniques can enhance multiple vital facets of wireless network operation, and yield benefits in terms of efficiency and reliability. By highlighting the pivotal role that the deep learning-based radio propagation models will assume in next-generation wireless networks, we aspire to propel further research in this direction and foster their adoption in additional applications.
Authors: Yuxuan Du, Min-Hsiu Hsieh, Dacheng Tao
Abstract: The vast and complicated large-qubit state space forbids us to comprehensively capture the dynamics of modern quantum computers via classical simulations or quantum tomography. However, recent progress in quantum learning theory invokes a crucial question: given a quantum circuit containing d tunable RZ gates and G-d Clifford gates, can a learner perform purely classical inference to efficiently predict its linear properties using new classical inputs, after learning from data obtained by incoherently measuring states generated by the same circuit but with different classical inputs? In this work, we prove that the sample complexity scaling linearly in d is necessary and sufficient to achieve a small prediction error, while the corresponding computational complexity may scale exponentially in d. Building upon these derived complexity bounds, we further harness the concept of classical shadow and truncated trigonometric expansion to devise a kernel-based learning model capable of trading off prediction error and computational complexity, transitioning from exponential to polynomial scaling in many practical settings. Our results advance two crucial realms in quantum computation: the exploration of quantum algorithms with practical utilities and learning-based quantum system certification. We conduct numerical simulations to validate our proposals across diverse scenarios, encompassing quantum information processing protocols, Hamiltonian simulation, and variational quantum algorithms up to 60 qubits.
Authors: Ludovico Boratto, Francesco Fabbri, Gianni Fenu, Mirko Marras, Giacomo Medda
Abstract: Recent developments in recommendation have harnessed the collaborative power of graph neural networks (GNNs) in learning users' preferences from user-item networks. Despite emerging regulations addressing fairness of automated systems, unfairness issues in graph collaborative filtering remain underexplored, especially from the consumer's perspective. Despite numerous contributions on consumer unfairness, only a few of these works have delved into GNNs. A notable gap exists in the formalization of the latest mitigation algorithms, as well as in their effectiveness and reliability on cutting-edge models. This paper serves as a solid response to recent research highlighting unfairness issues in graph collaborative filtering by reproducing one of the latest mitigation methods. The reproduced technique adjusts the system fairness level by learning a fair graph augmentation. Under an experimental setup based on 11 GNNs, 5 non-GNN models, and 5 real-world networks across diverse domains, our investigation reveals that fair graph augmentation is consistently effective on high-utility models and large datasets. Experiments on the transferability of the fair augmented graph open new issues for future recommendation studies. Source code: https://github.com/jackmedda/FA4GCF.
Authors: Zhihao Gu, Zi Xu
Abstract: The minimax excess risk optimization (MERO) problem is a new variation of the traditional distributionally robust optimization (DRO) problem, which achieves uniformly low regret across all test distributions under suitable conditions. In this paper, we propose a zeroth-order stochastic mirror descent (ZO-SMD) algorithm available for both smooth and non-smooth MERO to estimate the minimal risk of each distrbution, and finally solve MERO as (non-)smooth stochastic convex-concave (linear) minimax optimization problems. The proposed algorithm is proved to converge at optimal convergence rates of $\mathcal{O}\left(1/\sqrt{t}\right)$ on the estimate of $R_i^*$ and $\mathcal{O}\left(1/\sqrt{t}\right)$ on the optimization error of both smooth and non-smooth MERO. Numerical results show the efficiency of the proposed algorithm.
Authors: C\'eline Hocquette, Andrew Cropper
Abstract: We introduce a novel approach to program synthesis that decomposes complex functional tasks into simpler relational synthesis sub-tasks. We demonstrate the effectiveness of our approach using an off-the-shelf inductive logic programming (ILP) system on three challenging datasets. Our results show that (i) a relational representation can outperform a functional one, and (ii) an off-the-shelf ILP system with a relational encoding can outperform domain-specific approaches.
Authors: Yichu Xu, Xin-Chun Li, Le Gan, De-Chuan Zhan
Abstract: Merging models becomes a fundamental procedure in some applications that consider model efficiency and robustness. The training randomness or Non-I.I.D. data poses a huge challenge for averaging-based model fusion. Previous research efforts focus on element-wise regularization or neural permutations to enhance model averaging while overlooking weight scope variations among models, which can significantly affect merging effectiveness. In this paper, we reveal variations in weight scope under different training conditions, shedding light on its influence on model merging. Fortunately, the parameters in each layer basically follow the Gaussian distribution, which inspires a novel and simple regularization approach named Weight Scope Alignment (WSA). It contains two key components: 1) leveraging a target weight scope to guide the model training process for ensuring weight scope matching in the subsequent model merging. 2) fusing the weight scope of two or more models into a unified one for multi-stage model fusion. We extend the WSA regularization to two different scenarios, including Mode Connectivity and Federated Learning. Abundant experimental studies validate the effectiveness of our approach.
Authors: Aishik Nagar, Viktor Schlegel, Thanh-Tung Nguyen, Hao Li, Yuping Wu, Kuluhan Binici, Stefan Winkler
Abstract: Large Language Models (LLMs) are increasingly adopted for applications in healthcare, reaching the performance of domain experts on tasks such as question answering and document summarisation. Despite their success on these tasks, it is unclear how well LLMs perform on tasks that are traditionally pursued in the biomedical domain, such as structured information extration. To breach this gap, in this paper, we systematically benchmark LLM performance in Medical Classification and Named Entity Recognition (NER) tasks. We aim to disentangle the contribution of different factors to the performance, particularly the impact of LLMs' task knowledge and reasoning capabilities, their (parametric) domain knowledge, and addition of external knowledge. To this end we evaluate various open LLMs -- including BioMistral and Llama-2 models -- on a diverse set of biomedical datasets, using standard prompting, Chain-of-Thought (CoT) and Self-Consistency based reasoning as well as Retrieval-Augmented Generation (RAG) with PubMed and Wikipedia corpora. Counter-intuitively, our results reveal that standard prompting consistently outperforms more complex techniques across both tasks, laying bare the limitations in the current application of CoT, self-consistency and RAG in the biomedical domain. Our findings suggest that advanced prompting methods developed for knowledge- or reasoning-intensive tasks, such as CoT or RAG, are not easily portable to biomedical tasks where precise structured outputs are required. This highlights the need for more effective integration of external knowledge and reasoning mechanisms in LLMs to enhance their performance in real-world biomedical applications.
Authors: Yusuke Sakai, Adam Nohejl, Jiangnan Hang, Hidetaka Kamigaito, Taro Watanabe
Abstract: The natural language understanding (NLU) performance of large language models (LLMs) has been evaluated across various tasks and datasets. The existing evaluation methods, however, do not take into account the variance in scores due to differences in prompts, which leads to unfair evaluation and comparison of NLU performance. Moreover, evaluation designed for specific prompts is inappropriate for instruction tuning, which aims to perform well with any prompt. It is therefore necessary to find a way to measure NLU performance in a fair manner, considering score variance between different instruction templates. In this study, we provide English and Japanese cross-lingual datasets for evaluating the NLU performance of LLMs, which include multiple instruction templates for fair evaluation of each task, along with regular expressions to constrain the output format. Furthermore, we propose the Sharpe score as an evaluation metric that takes into account the variance in scores between templates. Comprehensive analysis of English and Japanese LLMs reveals that the high variance among templates has a significant impact on the fair evaluation of LLMs.
Authors: Stijn van Esch, Fabio Bonassi, Thomas B. Sch\"on
Abstract: In this report we investigate the use of the Tustin neural network architecture (Tustin-Net) for the identification of a physical rotary inverse pendulum. This physics-based architecture is of particular interest as it builds on the known relationship between velocities and positions. We here aim at discussing the advantages, limitations and performance of Tustin-Nets compared to first-principles grey-box models on a real physical apparatus, showing how, with a standard training procedure, the former can hardly achieve the same accuracy as the latter. To address this limitation, we present a training strategy based on transfer learning that yields Tustin-Nets that are competitive with the first-principles model, without requiring extensive knowledge of the setup as the latter.
Authors: Fabrizio Maturo, Annamaria Porreca
Abstract: The advent of big data has raised significant challenges in analysing high-dimensional datasets across various domains such as medicine, ecology, and economics. Functional Data Analysis (FDA) has proven to be a robust framework for addressing these challenges, enabling the transformation of high-dimensional data into functional forms that capture intricate temporal and spatial patterns. However, despite advancements in functional classification methods and very high performance demonstrated by combining FDA and ensemble methods, a critical gap persists in the literature concerning the transparency and interpretability of black-box models, e.g. Functional Random Forests (FRF). In response to this need, this paper introduces a novel suite of explainability tools to illuminate the inner mechanisms of FRF. We propose using Functional Partial Dependence Plots (FPDPs), Functional Principal Component (FPC) Probability Heatmaps, various model-specific and model-agnostic FPCs' importance metrics, and the FPC Internal-External Importance and Explained Variance Bubble Plot. These tools collectively enhance the transparency of FRF models by providing a detailed analysis of how individual FPCs contribute to model predictions. By applying these methods to an ECG dataset, we demonstrate the effectiveness of these tools in revealing critical patterns and improving the explainability of FRF.
Authors: Gaia Grosso, Marco Letizia
Abstract: In this work, we address the question of how to enhance signal-agnostic searches by leveraging multiple testing strategies. Specifically, we consider hypothesis tests relying on machine learning, where model selection can introduce a bias towards specific families of new physics signals. We show that it is beneficial to combine different tests, characterised by distinct choices of hyperparameters, and that performances comparable to the best available test are generally achieved while providing a more uniform response to various types of anomalies. Focusing on the New Physics Learning Machine, a methodology to perform a signal-agnostic likelihood-ratio test, we explore a number of approaches to multiple testing, such as combining p-values and aggregating test statistics.
Authors: Yansel Gonzalez Tejeda, Helmut A. Mayer
Abstract: In this tutorial, we present a compact and holistic discussion of Deep Learning with a focus on Convolutional Neural Networks (CNNs) and supervised regression. While there are numerous books and articles on the individual topics we cover, comprehensive and detailed tutorials that address Deep Learning from a foundational yet rigorous and accessible perspective are rare. Most resources on CNNs are either too advanced, focusing on cutting-edge architectures, or too narrow, addressing only specific applications like image classification.This tutorial not only summarizes the most relevant concepts but also provides an in-depth exploration of each, offering a complete yet agile set of ideas. Moreover, we highlight the powerful synergy between learning theory, statistic, and machine learning, which together underpin the Deep Learning and CNN frameworks. We aim for this tutorial to serve as an optimal resource for students, professors, and anyone interested in understanding the foundations of Deep Learning. Upon acceptance we will provide an accompanying repository under \href{https://github.com/neoglez/deep-learning-tutorial}{https://github.com/neoglez/deep-learning-tutorial} Keywords: Tutorial, Deep Learning, Convolutional Neural Networks, Machine Learning.
URLs: https://github.com/neoglez/deep-learning-tutorial, https://github.com/neoglez/deep-learning-tutorial
Authors: Steffen Limmer, Steffen Udluft, Clemens Otte
Abstract: The analysis of variance (ANOVA) decomposition offers a systematic method to understand the interaction effects that contribute to a specific decision output. In this paper we introduce Neural-ANOVA, an approach to decompose neural networks into glassbox models using the ANOVA decomposition. Our approach formulates a learning problem, which enables rapid and closed-form evaluation of integrals over subspaces that appear in the calculation of the ANOVA decomposition. Finally, we conduct numerical experiments to illustrate the advantages of enhanced interpretability and model validation by a decomposition of the learned interaction effects.
Authors: Dimitris Stripelis, Zijian Hu, Jipeng Zhang, Zhaozhuo Xu, Alay Shah, Han Jin, Yuhang Yao, Salman Avestimehr, Chaoyang He
Abstract: With the rapid growth of Large Language Models (LLMs) across various domains, numerous new LLMs have emerged, each possessing domain-specific expertise. This proliferation has highlighted the need for quick, high-quality, and cost-effective LLM query response methods. Yet, no single LLM exists to efficiently balance this trilemma. Some models are powerful but extremely costly, while others are fast and inexpensive but qualitatively inferior. To address this challenge, we present PolyRouter, a non-monolithic LLM querying system that seamlessly integrates various LLM experts into a single query interface and dynamically routes incoming queries to the most high-performant expert based on query's requirements. Through extensive experiments, we demonstrate that when compared to standalone expert models, PolyRouter improves query efficiency by up to 40%, and leads to significant cost reductions of up to 30%, while maintaining or enhancing model performance by up to 10%.
Authors: Karmvir Singh Phogat, Sai Akhil Puranam, Sridhar Dasaratha, Chetan Harsha, Shashishekar Ramakrishna
Abstract: Recent research has shown that smaller language models can acquire substantial reasoning abilities when fine-tuned with reasoning exemplars crafted by a significantly larger teacher model. We explore this paradigm for the financial domain, focusing on the challenge of answering questions that require multi-hop numerical reasoning over financial texts. We assess the performance of several smaller models that have been fine-tuned to generate programs that encode the required financial reasoning and calculations. Our findings demonstrate that these fine-tuned smaller models approach the performance of the teacher model. To provide a granular analysis of model performance, we propose an approach to investigate the specific student model capabilities that are enhanced by fine-tuning. Our empirical analysis indicates that fine-tuning refines the student models ability to express and apply the required financial concepts along with adapting the entity extraction for the specific data format. In addition, we hypothesize and demonstrate that comparable financial reasoning capability can be induced using relatively smaller datasets.
Authors: Chuhan Wang, Lixing Zhu, Xuehu Zhu
Abstract: For distributed computing with Byzantine machines under Privacy Protection (PP) constraints, this paper develops a robust PP distributed quasi-Newton estimation, which only requires the node machines to transmit five vectors to the central processor with high asymptotic relative efficiency. Compared with the gradient descent strategy which requires more rounds of transmission and the Newton iteration strategy which requires the entire Hessian matrix to be transmitted, the novel quasi-Newton iteration has advantages in reducing privacy budgeting and transmission cost. Moreover, our PP algorithm does not depend on the boundedness of gradients and second-order derivatives. When gradients and second-order derivatives follow sub-exponential distributions, we offer a mechanism that can ensure PP with a sufficiently high probability. Furthermore, this novel estimator can achieve the optimal convergence rate and the asymptotic normality. The numerical studies on synthetic and real data sets evaluate the performance of the proposed algorithm.
Authors: Apoorva Karagappa, Pawandeep Kaur Betz, Jonas Gilg, Moritz Zeumer, Andreas Gerndt, Bernhard Preim
Abstract: As the world increasingly relies on mathematical models for forecasts in different areas, effective communication of uncertainty in time series predictions is important for informed decision making. This study explores how users estimate probabilistic uncertainty in time series predictions under different variants of line charts depicting uncertainty. It examines the role of individual characteristics and the influence of user-reported metrics on uncertainty estimations. By addressing these aspects, this paper aims to enhance the understanding of uncertainty visualization and for improving communication in time series forecast visualizations and the design of prediction data dashboards.As the world increasingly relies on mathematical models for forecasts in different areas, effective communication of uncertainty in time series predictions is important for informed decision making. This study explores how users estimate probabilistic uncertainty in time series predictions under different variants of line charts depicting uncertainty. It examines the role of individual characteristics and the influence of user-reported metrics on uncertainty estimations. By addressing these aspects, this paper aims to enhance the understanding of uncertainty visualization and for improving communication in time series forecast visualizations and the design of prediction data dashboards.
Authors: Hugo Resende, Eduardo B. Neto, Fabio A. M. Cappabianco, Alvaro L. Fazenda, Fabio A. Faria
Abstract: Conserving tropical forests is highly relevant socially and ecologically because of their critical role in the global ecosystem. However, the ongoing deforestation and degradation affect millions of hectares each year, necessitating government or private initiatives to ensure effective forest monitoring. In April 2019, a project based on Citizen Science and Machine Learning models called ForestEyes (FE) was launched with the aim of providing supplementary data to assist experts from government and non-profit organizations in their deforestation monitoring efforts. Recent research has shown that labeling FE project volunteers/citizen scientists helps tailor machine learning models. In this sense, we adopt the FE project to create different sampling strategies based on the wisdom of crowds to select the most suitable samples from the training set to learn an SVM technique and obtain better classification results in deforestation detection tasks. In our experiments, we can show that our strategy based on user entropy-increasing achieved the best classification results in the deforestation detection task when compared with the random sampling strategies, as well as, reducing the convergence time of the SVM technique.
Authors: Cameron Musco, Christopher Musco, Lucas Rosenblatt, Apoorv Vikram Singh
Abstract: We study the problem of approximately recovering a probability distribution given noisy measurements of its Chebyshev polynomial moments. We sharpen prior work, proving that accurate recovery in the Wasserstein distance is possible with more noise than previously known. As a main application, our result yields a simple "linear query" algorithm for constructing a differentially private synthetic data distribution with Wasserstein-1 error $\tilde{O}(1/n)$ based on a dataset of $n$ points in $[-1,1]$. This bound is optimal up to log factors and matches a recent breakthrough of Boedihardjo, Strohmer, and Vershynin [Probab. Theory. Rel., 2024], which uses a more complex "superregular random walk" method to beat an $O(1/\sqrt{n})$ accuracy barrier inherent to earlier approaches. We illustrate a second application of our new moment-based recovery bound in numerical linear algebra: by improving an approach of Braverman, Krishnan, and Musco [STOC 2022], our result yields a faster algorithm for estimating the spectral density of a symmetric matrix up to small error in the Wasserstein distance.
Authors: Fahad Shamshad, Muzammal Naseer, Karthik Nandakumar
Abstract: Deep learning-based face recognition (FR) systems pose significant privacy risks by tracking users without their consent. While adversarial attacks can protect privacy, they often produce visible artifacts compromising user experience. To mitigate this issue, recent facial privacy protection approaches advocate embedding adversarial noise into the natural looking makeup styles. However, these methods require training on large-scale makeup datasets that are not always readily available. In addition, these approaches also suffer from dataset bias. For instance, training on makeup data that predominantly contains female faces could compromise protection efficacy for male faces. To handle these issues, we propose a test-time optimization approach that solely optimizes an untrained neural network to transfer makeup style from a reference to a source image in an adversarial manner. We introduce two key modules: a correspondence module that aligns regions between reference and source images in latent space, and a decoder with conditional makeup layers. The untrained decoder, optimized via carefully designed structural and makeup consistency losses, generates a protected image that resembles the source but incorporates adversarial makeup to deceive FR models. As our approach does not rely on training with makeup face datasets, it avoids potential male/female dataset biases while providing effective protection. We further extend the proposed approach to videos by leveraging on temporal correlations. Experiments on benchmark datasets demonstrate superior performance in face verification and identification tasks and effectiveness against commercial FR systems. Our code and models will be available at https://github.com/fahadshamshad/deep-facial-privacy-prior
URLs: https://github.com/fahadshamshad/deep-facial-privacy-prior
Authors: Mahdi Kazemi, Aftab Hussain, Md Rafiqul Islam Rabin, Mohammad Amin Alipour, Sen Lin
Abstract: This work investigates the application of Machine Unlearning (MU) for mitigating the impact of trojans embedded in conventional large language models of natural language (Text-LLMs) and large language models of code (Code-LLMs) We propose a novel unlearning approach, LYA, that leverages both gradient ascent and elastic weight consolidation, a Fisher Information Matrix (FIM) based regularization technique, to unlearn trojans from poisoned models. We compare the effectiveness of LYA against conventional techniques like fine-tuning, retraining, and vanilla gradient ascent. The subject models we investigate are BERT and CodeBERT, for sentiment analysis and code defect detection tasks, respectively. Our findings demonstrate that the combination of gradient ascent and FIM-based regularization, as done in LYA, outperforms existing methods in removing the trojan's influence from the poisoned model, while preserving its original functionality. To the best of our knowledge, this is the first work that compares and contrasts MU of trojans in LLMs, in the NL and Coding domain.
Authors: Longbiao Cheng, Ashutosh Pandey, Buye Xu, Tobi Delbruck, Shih-Chii Liu
Abstract: This paper introduces a new Dynamic Gated Recurrent Neural Network (DG-RNN) for compute-efficient speech enhancement models running on resource-constrained hardware platforms. It leverages the slow evolution characteristic of RNN hidden states over steps, and updates only a selected set of neurons at each step by adding a newly proposed select gate to the RNN model. This select gate allows the computation cost of the conventional RNN to be reduced during network inference. As a realization of the DG-RNN, we further propose the Dynamic Gated Recurrent Unit (D-GRU) which does not require additional parameters. Test results obtained from several state-of-the-art compute-efficient RNN-based speech enhancement architectures using the DNS challenge dataset, show that the D-GRU based model variants maintain similar speech intelligibility and quality metrics comparable to the baseline GRU based models even with an average 50% reduction in GRU computes.
Authors: Aydin Abadi
Abstract: Time-Lock Puzzles (TLPs) have been developed to securely transmit sensitive information into the future without relying on a trusted third party. Multi-instance TLP is a scalable variant of TLP that enables a server to efficiently find solutions to different puzzles provided by a client at once. Nevertheless, existing multi-instance TLPs lack support for (verifiable) homomorphic computation. To address this limitation, we introduce the "Multi-Instance partially Homomorphic TLP" (MH-TLP), a multi-instance TLP supporting efficient verifiable homomorphic linear combinations of puzzles belonging to a client. It ensures anyone can verify the correctness of computations and solutions. Building on MH-TLP, we further propose the "Multi-instance Multi-client verifiable partially Homomorphic TLP" (MMH-TLP). It not only supports all the features of MH-TLP but also allows for verifiable homomorphic linear combinations of puzzles from different clients. Our schemes refrain from using asymmetric-key cryptography for verification and, unlike most homomorphic TLPs, do not require a trusted third party. A comprehensive cost analysis demonstrates that our schemes scale linearly with the number of clients and puzzles.
Authors: Parvin Malekzadeh, Zissis Poulos, Jacky Chen, Zeyu Wang, Konstantinos N. Plataniotis
Abstract: Recent advancements in Distributional Reinforcement Learning (DRL) for modeling loss distributions have shown promise in developing hedging strategies in derivatives markets. A common approach in DRL involves learning the quantiles of loss distributions at specified levels using Quantile Regression (QR). This method is particularly effective in option hedging due to its direct quantile-based risk assessment, such as Value at Risk (VaR) and Conditional Value at Risk (CVaR). However, these risk measures depend on the accurate estimation of extreme quantiles in the loss distribution's tail, which can be imprecise in QR-based DRL due to the rarity and extremity of tail data, as highlighted in the literature. To address this issue, we propose EXtreme DRL (EX-DRL), which enhances extreme quantile prediction by modeling the tail of the loss distribution with a Generalized Pareto Distribution (GPD). This method introduces supplementary data to mitigate the scarcity of extreme quantile observations, thereby improving estimation accuracy through QR. Comprehensive experiments on gamma hedging options demonstrate that EX-DRL improves existing QR-based models by providing more precise estimates of extreme quantiles, thereby improving the computation and reliability of risk metrics for complex financial risk management.
Authors: Yuyan Zhang, Derya Soydaner, Lisa Ko{\ss}mann, Fatemeh Behrad, Johan Wagemans
Abstract: The human brain has an inherent ability to fill in gaps to perceive figures as complete wholes, even when parts are missing or fragmented. This phenomenon is known as Closure in psychology, one of the Gestalt laws of perceptual organization, explaining how the human brain interprets visual stimuli. Given the importance of Closure for human object recognition, we investigate whether neural networks rely on a similar mechanism. Exploring this crucial human visual skill in neural networks has the potential to highlight their comparability to humans. Recent studies have examined the Closure effect in neural networks. However, they typically focus on a limited selection of Convolutional Neural Networks (CNNs) and have not reached a consensus on their capability to perform Closure. To address these gaps, we present a systematic framework for investigating the Closure principle in neural networks. We introduce well-curated datasets designed to test for Closure effects, including both modal and amodal completion. We then conduct experiments on various CNNs employing different measurements. Our comprehensive analysis reveals that VGG16 and DenseNet-121 exhibit the Closure effect, while other CNNs show variable results. We interpret these findings by blending insights from psychology and neural network research, offering a unique perspective that enhances transparency in understanding neural networks. Our code and dataset will be made available on GitHub.
Authors: Nishan Gunawardena, Gough Yumu Lui, Jeewani Anupama Ginige, Bahman Javadi
Abstract: A significant limitation of current smartphone-based eye-tracking algorithms is their low accuracy when applied to video-type visual stimuli, as they are typically trained on static images. Also, the increasing demand for real-time interactive applications like games, VR, and AR on smartphones requires overcoming the limitations posed by resource constraints such as limited computational power, battery life, and network bandwidth. Therefore, we developed two new smartphone eye-tracking techniques for video-type visuals by combining Convolutional Neural Networks (CNN) with two different Recurrent Neural Networks (RNN), namely Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU). Our CNN+LSTM and CNN+GRU models achieved an average Root Mean Square Error of 0.955cm and 1.091cm, respectively. To address the computational constraints of smartphones, we developed an edge intelligence architecture to enhance the performance of smartphone-based eye tracking. We applied various optimisation methods like quantisation and pruning to deep learning models for better energy, CPU, and memory usage on edge devices, focusing on real-time processing. Using model quantisation, the model inference time in the CNN+LSTM and CNN+GRU models was reduced by 21.72% and 19.50%, respectively, on edge devices.
Authors: Palak Handa, Manas Dhir, Amirreza Mahbod, Florian Schwarzhans, Ramona Woitek, Nidhi Goel, Deepak Gunjan
Abstract: Computer-based analysis of Wireless Capsule Endoscopy (WCE) is crucial. However, a medically annotated WCE dataset for training and evaluation of automatic classification, detection, and segmentation of bleeding and non-bleeding frames is currently lacking. The present work focused on development of a medically annotated WCE dataset called WCEbleedGen for automatic classification, detection, and segmentation of bleeding and non-bleeding frames. It comprises 2,618 WCE bleeding and non-bleeding frames which were collected from various internet resources and existing WCE datasets. A comprehensive benchmarking and evaluation of the developed dataset was done using nine classification-based, three detection-based, and three segmentation-based deep learning models. The dataset is of high-quality, is class-balanced and contains single and multiple bleeding sites. Overall, our standard benchmark results show that Visual Geometric Group (VGG) 19, You Only Look Once version 8 nano (YOLOv8n), and Link network (Linknet) performed best in automatic classification, detection, and segmentation-based evaluations, respectively. Automatic bleeding diagnosis is crucial for WCE video interpretations. This diverse dataset will aid in developing of real-time, multi-task learning-based innovative solutions for automatic bleeding diagnosis in WCE. The dataset and code are publicly available at https://zenodo.org/records/10156571 and https://github.com/misahub2023/Benchmarking-Codes-of-the-WCEBleedGen-dataset.
URLs: https://zenodo.org/records/10156571, https://github.com/misahub2023/Benchmarking-Codes-of-the-WCEBleedGen-dataset.
Authors: Manuele Rusci, Francesco Paci, Marco Fariselli, Eric Flamand, Tinne Tuytelaars
Abstract: This paper proposes a self-learning framework to incrementally train (fine-tune) a personalized Keyword Spotting (KWS) model after the deployment on ultra-low power smart audio sensors. We address the fundamental problem of the absence of labeled training data by assigning pseudo-labels to the new recorded audio frames based on a similarity score with respect to few user recordings. By experimenting with multiple KWS models with a number of parameters up to 0.5M on two public datasets, we show an accuracy improvement of up to +19.2% and +16.0% vs. the initial models pretrained on a large set of generic keywords. The labeling task is demonstrated on a sensor system composed of a low-power microphone and an energy-efficient Microcontroller (MCU). By efficiently exploiting the heterogeneous processing engines of the MCU, the always-on labeling task runs in real-time with an average power cost of up to 8.2 mW. On the same platform, we estimate an energy cost for on-device training 10x lower than the labeling energy if sampling a new utterance every 5 s or 16.4 s with a DS-CNN-S or a DS-CNN-M model. Our empirical result paves the way to self-adaptive personalized KWS sensors at the extreme edge.
Authors: Douwe J. Spaanderman (Department of Radiology and Nuclear Medicine, Erasmus MC Cancer Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands), Matthew Marzetti (Department of Medical Physics, Leeds Teaching Hospitals NHS Trust, UK, Leeds Biomedical Research Centre, University of Leeds, UK), Xinyi Wan (Department of Radiology and Nuclear Medicine, Erasmus MC Cancer Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands), Andrew F. Scarsbrook (Department of Radiology, Leeds Teaching Hospitals NHS Trust, UK, Leeds Institute of Medical Research, University of Leeds, UK), Philip Robinson (Department of Radiology, Leeds Teaching Hospitals NHS Trust, UK), Edwin H. G. Oei (Department of Radiology and Nuclear Medicine, Erasmus MC Cancer Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands), Jacob J. Visser (Department of Radiology and Nuclear Medicine, Erasmus MC Cancer Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands), Robert Hemke (Department of Radiology and Nuclear Medicine, Amsterdam UMC, Amsterdam, the Netherlands), Kirsten van Langevelde (Department of Radiology, Leiden University Medical Center, Leiden, the Netherlands), David F. Hanff (Department of Radiology and Nuclear Medicine, Erasmus MC Cancer Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands), Geert J. L. H. van Leenders (Department of Pathology, Erasmus MC Cancer Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands), Cornelis Verhoef (Department of Surgical Oncology, Erasmus MC Cancer Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands), Dirk J. Gru\"uhagen (Department of Surgical Oncology, Erasmus MC Cancer Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands), Wiro J. Niessen (Department of Radiology and Nuclear Medicine, Erasmus MC Cancer Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands, Faculty of Medical Sciences, University of Groningen, Groningen, the Netherlands), Stefan Klein (Department of Radiology and Nuclear Medicine, Erasmus MC Cancer Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands), Martijn P. A. Starmans (Department of Radiology and Nuclear Medicine, Erasmus MC Cancer Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands)
Abstract: Soft-tissue and bone tumours (STBT) are rare, diagnostically challenging lesions with variable clinical behaviours and treatment approaches. This systematic review provides an overview of Artificial Intelligence (AI) methods using radiological imaging for diagnosis and prognosis of these tumours, highlighting challenges in clinical translation, and evaluating study alignment with the Checklist for AI in Medical Imaging (CLAIM) and the FUTURE-AI international consensus guidelines for trustworthy and deployable AI to promote the clinical translation of AI methods. The review covered literature from several bibliographic databases, including papers published before 17/07/2024. Original research in peer-reviewed journals focused on radiology-based AI for diagnosing or prognosing primary STBT was included. Exclusion criteria were animal, cadaveric, or laboratory studies, and non-English papers. Abstracts were screened by two of three independent reviewers for eligibility. Eligible papers were assessed against guidelines by one of three independent reviewers. The search identified 15,015 abstracts, from which 325 articles were included for evaluation. Most studies performed moderately on CLAIM, averaging a score of 28.9$\pm$7.5 out of 53, but poorly on FUTURE-AI, averaging 5.1$\pm$2.1 out of 30. Imaging-AI tools for STBT remain at the proof-of-concept stage, indicating significant room for improvement. Future efforts by AI developers should focus on design (e.g. define unmet clinical need, intended clinical setting and how AI would be integrated in clinical workflow), development (e.g. build on previous work, explainability), evaluation (e.g. evaluating and addressing biases, evaluating AI against best practices), and data reproducibility and availability (making documented code and data publicly available). Following these recommendations could improve clinical translation of AI methods.
Authors: Yuyang Deng, Fuli Qiao, Mehrdad Mahdavi
Abstract: Stochastic compositional minimax problems are prevalent in machine learning, yet there are only limited established on the convergence of this class of problems. In this paper, we propose a formal definition of the stochastic compositional minimax problem, which involves optimizing a minimax loss with a compositional structure either in primal , dual, or both primal and dual variables. We introduce a simple yet effective algorithm, stochastically Corrected stOchastic gradient Descent Ascent (CODA), which is a descent ascent type algorithm with compositional correction steps, and establish its convergence rate in aforementioned three settings. In the presence of the compositional structure in primal, the objective function typically becomes nonconvex in primal due to function composition. Thus, we consider the nonconvex-strongly-concave and nonconvex-concave settings and show that CODA can efficiently converge to a stationary point. In the case of composition on the dual, the objective function becomes nonconcave in the dual variable, and we demonstrate convergence in the strongly-convex-nonconcave and convex-nonconcave setting. In the case of composition on both variables, the primal and dual variables may lose convexity and concavity, respectively. Therefore, we anaylze the convergence in weakly-convex-weakly-concave setting. We also give a variance reduction version algorithm, CODA+, which achieves the best known rate on nonconvex-strongly-concave and nonconvex-concave compositional minimax problem. This work initiates the theoretical study of the stochastic compositional minimax problem on various settings and may inform modern machine learning scenarios such as domain adaptation or robust model-agnostic meta-learning.
Authors: Sayed Mohammad Vakilzadeh Hatefi, Maximilian Dreyer, Reduan Achtibat, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
Abstract: To solve ever more complex problems, Deep Neural Networks are scaled to billions of parameters, leading to huge computational costs. An effective approach to reduce computational requirements and increase efficiency is to prune unnecessary components of these often over-parameterized networks. Previous work has shown that attribution methods from the field of eXplainable AI serve as effective means to extract and prune the least relevant network components in a few-shot fashion. We extend the current state by proposing to explicitly optimize hyperparameters of attribution methods for the task of pruning, and further include transformer-based networks in our analysis. Our approach yields higher model compression rates of large transformer- and convolutional architectures (VGG, ResNet, ViT) compared to previous works, while still attaining high performance on ImageNet classification tasks. Here, our experiments indicate that transformers have a higher degree of over-parameterization compared to convolutional neural networks. Code is available at $\href{https://github.com/erfanhatefi/Pruning-by-eXplaining-in-PyTorch}{\text{this https link}}$.
URLs: https://github.com/erfanhatefi/Pruning-by-eXplaining-in-PyTorch
Authors: Jamba Team, Barak Lenz, Alan Arazi, Amir Bergman, Avshalom Manevich, Barak Peleg, Ben Aviram, Chen Almagor, Clara Fridman, Dan Padnos, Daniel Gissin, Daniel Jannai, Dor Muhlgay, Dor Zimberg, Edden M Gerber, Elad Dolev, Eran Krakovsky, Erez Safahi, Erez Schwartz, Gal Cohen, Gal Shachaf, Haim Rozenblum, Hofit Bata, Ido Blass, Inbal Magar, Itay Dalmedigos, Jhonathan Osin, Julie Fadlon, Maria Rozman, Matan Danos, Michael Gokhman, Mor Zusman, Naama Gidron, Nir Ratner, Noam Gat, Noam Rozen, Oded Fried, Ohad Leshno, Omer Antverg, Omri Abend, Opher Lieber, Or Dagan, Orit Cohavi, Raz Alon, Ro'i Belson, Roi Cohen, Rom Gilad, Roman Glozman, Shahar Lev, Shaked Meirom, Tal Delbari, Tal Ness, Tomer Asida, Tom Ben Gal, Tom Braude, Uriya Pumerantz, Yehoshua Cohen, Yonatan Belinkov, Yuval Globerson, Yuval Peleg Levy, Yoav Shoham
Abstract: We present Jamba-1.5, new instruction-tuned large language models based on our Jamba architecture. Jamba is a hybrid Transformer-Mamba mixture of experts architecture, providing high throughput and low memory usage across context lengths, while retaining the same or better quality as Transformer models. We release two model sizes: Jamba-1.5-Large, with 94B active parameters, and Jamba-1.5-Mini, with 12B active parameters. Both models are fine-tuned for a variety of conversational and instruction-following capabilties, and have an effective context length of 256K tokens, the largest amongst open-weight models. To support cost-effective inference, we introduce ExpertsInt8, a novel quantization technique that allows fitting Jamba-1.5-Large on a machine with 8 80GB GPUs when processing 256K-token contexts without loss of quality. When evaluated on a battery of academic and chatbot benchmarks, Jamba-1.5 models achieve excellent results while providing high throughput and outperforming other open-weight models on long-context benchmarks. The model weights for both sizes are publicly available under the Jamba Open Model License and we release ExpertsInt8 as open source.
Authors: Haojun Shi, Suyu Ye, Xinyu Fang, Chuanyang Jin, Layla Isik, Yen-Ling Kuo, Tianmin Shu
Abstract: Understanding people's social interactions in complex real-world scenarios often relies on intricate mental reasoning. To truly understand how and why people interact with one another, we must infer the underlying mental states that give rise to the social interactions, i.e., Theory of Mind reasoning in multi-agent interactions. Additionally, social interactions are often multi-modal -- we can watch people's actions, hear their conversations, and/or read about their past behaviors. For AI systems to successfully and safely interact with people in real-world environments, they also need to understand people's mental states as well as their inferences about each other's mental states based on multi-modal information about their interactions. For this, we introduce MuMA-ToM, a Multi-modal Multi-Agent Theory of Mind benchmark. MuMA-ToM is the first multi-modal Theory of Mind benchmark that evaluates mental reasoning in embodied multi-agent interactions. In MuMA-ToM, we provide video and text descriptions of people's multi-modal behavior in realistic household environments. Based on the context, we then ask questions about people's goals, beliefs, and beliefs about others' goals. We validated MuMA-ToM in a human experiment and provided a human baseline. We also proposed a novel multi-modal, multi-agent ToM model, LIMP (Language model-based Inverse Multi-agent Planning). Our experimental results show that LIMP significantly outperforms state-of-the-art methods, including large multi-modal models (e.g., GPT-4o, Gemini-1.5 Pro) and a recent multi-modal ToM model, BIP-ALM.
Authors: Xiaohan Wang, Xiaoyan Yang, Yuqi Zhu, Yue Shen, Jian Wang, Peng Wei, Lei Liang, Jinjie Gu, Huajun Chen, Ningyu Zhang
Abstract: Large Language Models (LLMs) like GPT-4, MedPaLM-2, and Med-Gemini achieve performance competitively with human experts across various medical benchmarks. However, they still face challenges in making professional diagnoses akin to physicians, particularly in efficiently gathering patient information and reasoning the final diagnosis. To this end, we introduce the RuleAlign framework, designed to align LLMs with specific diagnostic rules. We develop a medical dialogue dataset comprising rule-based communications between patients and physicians and design an alignment learning approach through preference learning. Experimental results demonstrate the effectiveness of the proposed approach. We hope that our work can serve as an inspiration for exploring the potential of LLMs as AI physicians.
Authors: Avrim Blum, Kevin Stangl
Abstract: Multiple fairness constraints have been proposed in the literature, motivated by a range of concerns about how demographic groups might be treated unfairly by machine learning classifiers. In this work we consider a different motivation; learning from biased training data. We posit several ways in which training data may be biased, including having a more noisy or negatively biased labeling process on members of a disadvantaged group, or a decreased prevalence of positive or negative examples from the disadvantaged group, or both. Given such biased training data, Empirical Risk Minimization (ERM) may produce a classifier that not only is biased but also has suboptimal accuracy on the true data distribution. We examine the ability of fairness-constrained ERM to correct this problem. In particular, we find that the Equal Opportunity fairness constraint (Hardt, Price, and Srebro 2016) combined with ERM will provably recover the Bayes Optimal Classifier under a range of bias models. We also consider other recovery methods including reweighting the training data, Equalized Odds, and Demographic Parity. These theoretical results provide additional motivation for considering fairness interventions even if an actor cares primarily about accuracy.
Authors: Mehmet Yama\c{c}, Mert Duman, \.Ilke Adal{\i}o\u{g}lu, Serkan Kiranyaz, Moncef Gabbouj
Abstract: This paper proposes a low-cost and highly accurate ECG-monitoring system intended for personalized early arrhythmia detection for wearable mobile sensors. Earlier supervised approaches for personalized ECG monitoring require both abnormal and normal heartbeats for the training of the dedicated classifier. However, in a real-world scenario where the personalized algorithm is embedded in a wearable device, such training data is not available for healthy people with no cardiac disorder history. In this study, (i) we propose a null space analysis on the healthy signal space obtained via sparse dictionary learning, and investigate how a simple null space projection or alternatively regularized least squares-based classification methods can reduce the computational complexity, without sacrificing the detection accuracy, when compared to sparse representation-based classification. (ii) Then we introduce a sparse representation-based domain adaptation technique in order to project other existing users' abnormal and normal signals onto the new user's signal space, enabling us to train the dedicated classifier without having any abnormal heartbeat of the new user. Therefore, zero-shot learning can be achieved without the need for synthetic abnormal heartbeat generation. An extensive set of experiments performed on the benchmark MIT-BIH ECG dataset shows that when this domain adaptation-based training data generator is used with a simple 1-D CNN classifier, the method outperforms the prior work by a significant margin. (iii) Then, by combining (i) and (ii), we propose an ensemble classifier that further improves the performance. This approach for zero-shot arrhythmia detection achieves an average accuracy level of 98.2% and an F1-Score of 92.8%. Finally, a personalized energy-efficient ECG monitoring scheme is proposed using the above-mentioned innovations.
Authors: Hudson Kaleb Dy, Chelsea Yeh, Hanna Kaitlin Dy, Phillip Schodinger
Abstract: This project describes the application of the technologies of Machine Learning and Internet-of-Things to assess the lower limb strength of individuals undergoing rehabilitation or therapy. Specifically, it seeks to measure and assess the progress of individuals by sensors attached to chairs and processing the data through Google GPU Tensorflow CoLab. Pressure sensors are attached to various locations on a chair, including but not limited to the seating area, backrest, hand rests, and legs. Sensor data from the individual performing both sit-to-stand transition and stand-to-sit transition provides a time series dataset regarding the pressure distribution and vibratory motion on the chair. The dataset and timing information can then be fed into a machine learning model to estimate the relative strength and weakness during various phases of the movement.
Authors: Junyoung Byun, Yujin Choi, Jaewook Lee
Abstract: This study aims to alleviate the trade-off between utility and privacy of differentially private clustering. Existing works focus on simple methods, which show poor performance for non-convex clusters. To fit complex cluster distributions, we propose sophisticated dynamical processing inspired by Morse theory, with which we hierarchically connect the Gaussian sub-clusters obtained through existing methods. Our theoretical results imply that the proposed dynamical processing introduces little to no additional privacy loss. Experiments show that our framework can improve the clustering performance of existing methods at the same privacy level.
Authors: Max Klabunde, Tobias Schumacher, Markus Strohmaier, Florian Lemmerich
Abstract: Measuring similarity of neural networks to understand and improve their behavior has become an issue of great importance and research interest. In this survey, we provide a comprehensive overview of two complementary perspectives of measuring neural network similarity: (i) representational similarity, which considers how activations of intermediate layers differ, and (ii) functional similarity, which considers how models differ in their outputs. In addition to providing detailed descriptions of existing measures, we summarize and discuss results on the properties of and relationships between these measures, and point to open research problems. We hope our work lays a foundation for more systematic research on the properties and applicability of similarity measures for neural network models.
Authors: William Toner, Amos Storkey
Abstract: Training neural network classifiers on datasets with label noise poses a risk of overfitting them to the noisy labels. To address this issue, researchers have explored alternative loss functions that aim to be more robust. The `forward-correction' is a popular approach wherein the model outputs are noised before being evaluated against noisy data. When the true noise model is known, applying the forward-correction guarantees consistency of the learning algorithm. While providing some benefit, the correction is insufficient to prevent overfitting to finite noisy datasets. In this work, we propose an approach to tackling overfitting caused by label noise. We observe that the presence of label noise implies a lower bound on the noisy generalised risk. Motivated by this observation, we propose imposing a lower bound on the training loss to mitigate overfitting. Our main contribution is providing theoretical insights that allow us to approximate the lower bound given only an estimate of the average noise rate. We empirically demonstrate that using this bound significantly enhances robustness in various settings, with virtually no additional computational cost.
Authors: Yikuan Li, Chengsheng Mao, Kaixuan Huang, Hanyin Wang, Zheng Yu, Mengdi Wang, Yuan Luo
Abstract: Scarcity of health care resources could result in the unavoidable consequence of rationing. For example, ventilators are often limited in supply, especially during public health emergencies or in resource-constrained health care settings, such as amid the pandemic of COVID-19. Currently, there is no universally accepted standard for health care resource allocation protocols, resulting in different governments prioritizing patients based on various criteria and heuristic-based protocols. In this study, we investigate the use of reinforcement learning for critical care resource allocation policy optimization to fairly and effectively ration resources. We propose a transformer-based deep Q-network to integrate the disease progression of individual patients and the interaction effects among patients during the critical care resource allocation. We aim to improve both fairness of allocation and overall patient outcomes. Our experiments demonstrate that our method significantly reduces excess deaths and achieves a more equitable distribution under different levels of ventilator shortage, when compared to existing severity-based and comorbidity-based methods in use by different governments. Our source code is included in the supplement and will be released on Github upon publication.
Authors: Samiul Alam, Tuo Zhang, Tiantian Feng, Hui Shen, Zhichao Cao, Dong Zhao, JeongGil Ko, Kiran Somasundaram, Shrikanth S. Narayanan, Salman Avestimehr, Mi Zhang
Abstract: There is a significant relevance of federated learning (FL) in the realm of Artificial Intelligence of Things (AIoT). However, most existing FL works do not use datasets collected from authentic IoT devices and thus do not capture unique modalities and inherent challenges of IoT data. To fill this critical gap, in this work, we introduce FedAIoT, an FL benchmark for AIoT. FedAIoT includes eight datasets collected from a wide range of IoT devices. These datasets cover unique IoT modalities and target representative applications of AIoT. FedAIoT also includes a unified end-to-end FL framework for AIoT that simplifies benchmarking the performance of the datasets. Our benchmark results shed light on the opportunities and challenges of FL for AIoT. We hope FedAIoT could serve as an invaluable resource to foster advancements in the important field of FL for AIoT. The repository of FedAIoT is maintained at https://github.com/AIoT-MLSys-Lab/FedAIoT.
Authors: Freek Holvoet, Katrien Antonio, Roel Henckaerts
Abstract: Insurers usually turn to generalized linear models for modeling claim frequency and severity data. Due to their success in other fields, machine learning techniques are gaining popularity within the actuarial toolbox. Our paper contributes to the literature on frequency-severity insurance pricing with machine learning via deep learning structures. We present a benchmark study on four insurance data sets with frequency and severity targets in the presence of multiple types of input features. We compare in detail the performance of: a generalized linear model on binned input data, a gradient-boosted tree model, a feed-forward neural network (FFNN), and the combined actuarial neural network (CANN). The CANNs combine a baseline prediction established with a GLM and GBM, respectively, with a neural network correction. We explain the data preprocessing steps with specific focus on the multiple types of input features typically present in tabular insurance data sets, such as postal codes, numeric and categorical covariates. Autoencoders are used to embed the categorical variables into the neural network, and we explore their potential advantages in a frequency-severity setting. Model performance is evaluated not only on out-of-sample deviance but also using statistical and calibration performance criteria and managerial tools to get more nuanced insights. Finally, we construct global surrogate models for the neural nets' frequency and severity models. These surrogates enable the translation of the essential insights captured by the FFNNs or CANNs to GLMs. As such, a technical tariff table results that can easily be deployed in practice.
Authors: Shengkun Zhu, Jinshan Zeng, Sheng Wang, Yuan Sun, Zhiyong Peng
Abstract: Personalized federated learning (PFL) is an approach proposed to address the issue of poor convergence on heterogeneous data. However, most existing PFL frameworks require strong assumptions for convergence. In this paper, we propose an alternating direction method of multipliers (ADMM) for training PFL models with Moreau envelope (FLAME), which achieves a sublinear convergence rate, relying on the relatively weak assumption of gradient Lipschitz continuity. Moreover, due to the gradient-free nature of ADMM, FLAME alleviates the need for hyperparameter tuning, particularly in avoiding the adjustment of the learning rate when training the global model. In addition, we propose a biased client selection strategy to expedite the convergence of training of PFL models. Our theoretical analysis establishes the global convergence under both unbiased and biased client selection strategies. Our experiments validate that FLAME, when trained on heterogeneous data, outperforms state-of-the-art methods in terms of model performance. Regarding communication efficiency, it exhibits an average speedup of 3.75x compared to the baselines. Furthermore, experimental results validate that the biased client selection strategy speeds up the convergence of both personalized and global models.
Authors: Zhilin Zhao, Longbing Cao, Yixuan Zhang, Kun-Yu Lin, Wei-Shi Zheng
Abstract: Out-of-distribution (OOD) detection is essential in identifying test samples that deviate from the in-distribution (ID) data upon which a standard network is trained, ensuring network robustness and reliability. This paper introduces OOD knowledge distillation, a pioneering learning framework applicable whether or not training ID data is available, given a standard network. This framework harnesses unknown OOD-sensitive knowledge from the standard network to craft a certain binary classifier adept at distinguishing between ID and OOD samples. To accomplish this, we introduce Confidence Amendment (CA), an innovative methodology that transforms an OOD sample into an ID one while progressively amending prediction confidence derived from the standard network. This approach enables the simultaneous synthesis of both ID and OOD samples, each accompanied by an adjusted prediction confidence, thereby facilitating the training of a binary classifier sensitive to OOD. Theoretical analysis provides bounds on the generalization error of the binary classifier, demonstrating the pivotal role of confidence amendment in enhancing OOD sensitivity. Extensive experiments spanning various datasets and network architectures confirm the efficacy of the proposed method in detecting OOD samples.
Authors: Bahram Yaghooti, Netanel Raviv, Bruno Sinopoli
Abstract: Feature extraction and selection at the presence of nonlinear dependencies among the data is a fundamental challenge in unsupervised learning. We propose using a Gram-Schmidt (GS) type orthogonalization process over function spaces to detect and map out such dependencies. Specifically, by applying the GS process over some family of functions, we construct a series of covariance matrices that can either be used to identify new large-variance directions, or to remove those dependencies from known directions. In the former case, we provide information-theoretic guarantees in terms of entropy reduction. In the latter, we provide precise conditions by which the chosen function family eliminates existing redundancy in the data. Each approach provides both a feature extraction and a feature selection algorithm. Our feature extraction methods are linear, and can be seen as natural generalization of principal component analysis (PCA). We provide experimental results for synthetic and real-world benchmark datasets which show superior performance over state-of-the-art (linear) feature extraction and selection algorithms. Surprisingly, our linear feature extraction algorithms are comparable and often outperform several important nonlinear feature extraction methods such as autoencoders, kernel PCA, and UMAP. Furthermore, one of our feature selection algorithms strictly generalizes a recent Fourier-based feature selection mechanism (Heidari et al., IEEE Transactions on Information Theory, 2022), yet at significantly reduced complexity.
Authors: Taeyoung Kim, Hongseok Yang
Abstract: The recent theoretical analysis of deep neural networks in their infinite-width limits has deepened our understanding of initialisation, feature learning, and training of those networks, and brought new practical techniques for finding appropriate hyperparameters, learning network weights, and performing inference. In this paper, we broaden this line of research by showing that this infinite-width analysis can be extended to the Jacobian of a deep neural network. We show that a multilayer perceptron (MLP) and its Jacobian at initialisation jointly converge to a Gaussian process (GP) as the widths of the MLP's hidden layers go to infinity and characterise this GP. We also prove that in the infinite-width limit, the evolution of the MLP under the so-called robust training (i.e., training with a regulariser on the Jacobian) is described by a linear first-order ordinary differential equation that is determined by a variant of the Neural Tangent Kernel. We experimentally show the relevance of our theoretical claims to wide finite networks, and empirically analyse the properties of kernel regression solution to obtain an insight into Jacobian regularisation.
Authors: Jingyao Li, Pengguang Chen, Bin Xia, Hong Xu, Jiaya Jia
Abstract: Large Language Models (LLMs) have showcased impressive capabilities in handling straightforward programming tasks. However, their performance tends to falter when confronted with more challenging programming problems. We observe that conventional models often generate solutions as monolithic code blocks, restricting their effectiveness in tackling intricate questions. To overcome this limitation, we present Modular-of-Thought Coder (MoTCoder). We introduce a pioneering framework for MoT instruction tuning, designed to promote the decomposition of tasks into logical sub-tasks and sub-modules. Our investigations reveal that, through the cultivation and utilization of sub-modules, MoTCoder significantly improves both the modularity and correctness of the generated solutions, leading to substantial relative pass@1 improvements of 12.9% on APPS and 9.43% on CodeContests. Our codes are available at https://github.com/dvlab-research/MoTCoder.
Authors: Marius-Constantin Dinu, Claudiu Leoveanu-Condrei, Markus Holzleitner, Werner Zellinger, Sepp Hochreiter
Abstract: We introduce SymbolicAI, a versatile and modular framework employing a logic-based approach to concept learning and flow management in generative processes. SymbolicAI enables the seamless integration of generative models with a diverse range of solvers by treating large language models (LLMs) as semantic parsers that execute tasks based on both natural and formal language instructions, thus bridging the gap between symbolic reasoning and generative AI. We leverage probabilistic programming principles to tackle complex tasks, and utilize differentiable and classical programming paradigms with their respective strengths. The framework introduces a set of polymorphic, compositional, and self-referential operations for multi-modal data that connects multi-step generative processes and aligns their outputs with user objectives in complex workflows. As a result, we can transition between the capabilities of various foundation models with in-context learning capabilities and specialized, fine-tuned models or solvers proficient in addressing specific problems. Through these operations based on in-context learning our framework enables the creation and evaluation of explainable computational graphs. Finally, we introduce a quality measure and its empirical score for evaluating these computational graphs, and propose a benchmark that compares various state-of-the-art LLMs across a set of complex workflows. We refer to the empirical score as the "Vector Embedding for Relational Trajectory Evaluation through Cross-similarity", or VERTEX score for short. The framework codebase and benchmark are linked below.
Authors: Tiansheng Huang, Sihao Hu, Ling Liu
Abstract: The new paradigm of finetuning-as-a-service introduces a new attack surface for Large Language Models (LLMs): a few harmful data uploaded by users can easily trick the finetuning to produce an alignment-broken model. We conduct an empirical analysis and uncover a \textit{harmful embedding drift} phenomenon, showing a probable cause of the alignment-broken effect. Inspired by our findings, we propose Vaccine, a perturbation-aware alignment technique to mitigate the security risk of users finetuning. The core idea of Vaccine is to produce invariant hidden embeddings by progressively adding crafted perturbation to them in the alignment phase. This enables the embeddings to withstand harmful perturbation from un-sanitized user data in the finetuning phase. Our results on open source mainstream LLMs (e.g., Llama2, Opt, Vicuna) demonstrate that Vaccine can boost the robustness of alignment against harmful prompts induced embedding drift while reserving reasoning ability towards benign prompts. Our code is available at \url{https://github.com/git-disl/Vaccine}.
Authors: Yoonho Lee, Michelle S. Lam, Helena Vasconcelos, Michael S. Bernstein, Chelsea Finn
Abstract: The standard way to teach models is by feeding them lots of data. However, this approach often teaches models incorrect ideas because they pick up on misleading signals in the data. To prevent such misconceptions, we must necessarily provide additional information beyond the training data. Prior methods incorporate additional instance-level supervision, such as labels for misleading features or additional labels for debiased data. However, such strategies require a large amount of labeler effort. We hypothesize that people are good at providing textual feedback at the concept level, a capability that existing teaching frameworks do not leverage. We propose Clarify, a novel interface and method for interactively correcting model misconceptions. Through Clarify, users need only provide a short text description of a model's consistent failure patterns. Then, in an entirely automated way, we use such descriptions to improve the training process. Clarify is the first end-to-end system for user model correction. Our user studies show that non-expert users can successfully describe model misconceptions via Clarify, leading to increased worst-case performance in two datasets. We additionally conduct a case study on a large-scale image dataset, ImageNet, using Clarify to find and rectify 31 novel hard subpopulations.
Authors: Yichuan Mo, Yuji Wang, Zeming Wei, Yisen Wang
Abstract: While Large Language Models (LLMs) have achieved tremendous success in various applications, they are also susceptible to jailbreak attacks. Several primary defense strategies have been proposed to protect LLMs from producing harmful information, mostly with a particular focus on harmful content filtering or heuristical defensive prompt designs. However, how to achieve intrinsic robustness through the prompts remains an open problem. In this paper, motivated by adversarial training paradigms for achieving reliable robustness, we propose an approach named Prompt Adversarial Tuning (PAT) that trains a prompt control attached to the user prompt as a guard prefix. To achieve our defense goal whilst maintaining natural performance, we optimize the control prompt with both adversarial and benign prompts. Comprehensive experiments show that our method is effective against both grey-box and black-box attacks, reducing the success rate of advanced attacks to nearly 0 while maintaining the model's utility on the benign task. The proposed defense strategy incurs only negligible computational overhead, charting a new perspective for future explorations in LLM security. Our code is available at https://github.com/rain152/PAT.
Authors: Woo Kyung Kim, Minjong Yoo, Honguk Woo
Abstract: Skill-based reinforcement learning (RL) approaches have shown considerable promise, especially in solving long-horizon tasks via hierarchical structures. These skills, learned task-agnostically from offline datasets, can accelerate the policy learning process for new tasks. Yet, the application of these skills in different domains remains restricted due to their inherent dependency on the datasets, which poses a challenge when attempting to learn a skill-based policy via RL for a target domain different from the datasets' domains. In this paper, we present a novel offline skill learning framework DuSkill which employs a guided Diffusion model to generate versatile skills extended from the limited skills in datasets, thereby enhancing the robustness of policy learning for tasks in different domains. Specifically, we devise a guided diffusion-based skill decoder in conjunction with the hierarchical encoding to disentangle the skill embedding space into two distinct representations, one for encapsulating domain-invariant behaviors and the other for delineating the factors that induce domain variations in the behaviors. Our DuSkill framework enhances the diversity of skills learned offline, thus enabling to accelerate the learning procedure of high-level policies for different domains. Through experiments, we show that DuSkill outperforms other skill-based imitation learning and RL algorithms for several long-horizon tasks, demonstrating its benefits in few-shot imitation and online RL.
Authors: Hang Gao, Jiaguo Yuan, Jiangmeng Li, Peng Qiao, Fengge Wu, Changwen Zheng, Huaping Liu
Abstract: Graph Neural Networks (GNNs) have garnered widespread attention for their potential to address the challenges posed by graph representation learning, which face complex graph-structured data across various domains. However, due to the inherent complexity and interconnectedness of graphs, accurately annotating graph data for training GNNs is extremely challenging. To address this issue, we have introduced Partial Label Learning (PLL) into graph representation learning. PLL is a critical weakly supervised learning problem where each training instance is associated with a set of candidate labels, including the ground-truth label and the additional interfering labels. PLL allows annotators to make errors, which reduces the difficulty of data labeling. Subsequently, we propose a novel graph representation learning method that enables GNN models to effectively learn discriminative information within the context of PLL. Our approach utilizes potential cause extraction to obtain graph data that holds causal relationships with the labels. By conducting auxiliary training based on the extracted graph data, our model can effectively eliminate the interfering information in the PLL scenario. We support the rationale behind our method with a series of theoretical analyses. Moreover, we conduct extensive evaluations and ablation studies on multiple datasets, demonstrating the superiority of our proposed method.
Authors: Payel Das, Subhajit Chaudhury, Elliot Nelson, Igor Melnyk, Sarath Swaminathan, Sihui Dai, Aur\'elie Lozano, Georgios Kollias, Vijil Chenthamarakshan, Ji\v{r}\'i, Navr\'atil, Soham Dan, Pin-Yu Chen
Abstract: Efficient and accurate updating of knowledge stored in Large Language Models (LLMs) is one of the most pressing research challenges today. This paper presents Larimar - a novel, brain-inspired architecture for enhancing LLMs with a distributed episodic memory. Larimar's memory allows for dynamic, one-shot updates of knowledge without the need for computationally expensive re-training or fine-tuning. Experimental results on multiple fact editing benchmarks demonstrate that Larimar attains accuracy comparable to most competitive baselines, even in the challenging sequential editing setup, but also excels in speed - yielding speed-ups of 8-10x depending on the base LLM - as well as flexibility due to the proposed architecture being simple, LLM-agnostic, and hence general. We further provide mechanisms for selective fact forgetting, information leakage prevention, and input context length generalization with Larimar and show their effectiveness. Our code is available at https://github.com/IBM/larimar
Authors: Arsham Gholamzadeh Khoee, Yinan Yu, Robert Feldt
Abstract: Deep neural networks (DNNs) have revolutionized artificial intelligence but often lack performance when faced with out-of-distribution (OOD) data, a common scenario due to the inevitable domain shifts in real-world applications. This limitation stems from the common assumption that training and testing data share the same distribution--an assumption frequently violated in practice. Despite their effectiveness with large amounts of data and computational power, DNNs struggle with distributional shifts and limited labeled data, leading to overfitting and poor generalization across various tasks and domains. Meta-learning presents a promising approach by employing algorithms that acquire transferable knowledge across various tasks for fast adaptation, eliminating the need to learn each task from scratch. This survey paper delves into the realm of meta-learning with a focus on its contribution to domain generalization. We first clarify the concept of meta-learning for domain generalization and introduce a novel taxonomy based on the feature extraction strategy and the classifier learning methodology, offering a granular view of methodologies. Additionally, we present a decision graph to assist readers in navigating the taxonomy based on data availability and domain shifts, enabling them to select and develop a proper model tailored to their specific problem requirements. Through an exhaustive review of existing methods and underlying theories, we map out the fundamentals of the field. Our survey provides practical insights and an informed discussion on promising research directions.
Authors: Ruqian Zhang, Yijiao Zhang, Annie Qu, Zhongyi Zhu, Juan Shen
Abstract: The popularity of transfer learning stems from the fact that it can borrow information from useful auxiliary datasets. Existing statistical transfer learning methods usually adopt a global similarity measure between the source data and the target data, which may lead to inefficiency when only partial information is shared. In this paper, we propose a novel Bayesian transfer learning method named ``CONCERT'' to allow robust partial information transfer for high-dimensional data analysis. A conditional spike-and-slab prior is introduced in the joint distribution of target and source parameters for information transfer. By incorporating covariate-specific priors, we can characterize partial similarities and integrate source information collaboratively to improve the performance on the target. In contrast to existing work, the CONCERT is a one-step procedure, which achieves variable selection and information transfer simultaneously. We establish variable selection consistency, as well as estimation and prediction error bounds for CONCERT. Our theory demonstrates the covariate-specific benefit of transfer learning. To ensure that our algorithm is scalable, we adopt the variational Bayes framework to facilitate implementation. Extensive experiments and two real data applications showcase the validity and advantage of CONCERT over existing cutting-edge transfer learning methods.
Authors: Amin Aminifar, Baichuan Huang, Azra Abtahi, Amir Aminifar
Abstract: The human brain performs tasks with an outstanding energy efficiency, i.e., with approximately 20 Watts. The state-of-the-art Artificial/Deep Neural Networks (ANN/DNN), on the other hand, have recently been shown to consume massive amounts of energy. The training of these ANNs/DNNs is done almost exclusively based on the back-propagation algorithm, which is known to be biologically implausible. This has led to a new generation of forward-only techniques, including the Forward-Forward algorithm. In this paper, we propose a lightweight inference scheme specifically designed for DNNs trained using the Forward-Forward algorithm. We have evaluated our proposed lightweight inference scheme in the case of the MNIST and CIFAR datasets, as well as two real-world applications, namely, epileptic seizure detection and cardiac arrhythmia classification using wearable technologies, where complexity overheads/energy consumption is a major constraint, and demonstrate its relevance. Our code is available at https://github.com/AminAminifar/LightFF.
Authors: Xiongxiao Xu, Canyu Chen, Yueqing Liang, Baixiang Huang, Guangji Bai, Liang Zhao, Kai Shu
Abstract: Despite significant progress in time series forecasting, existing forecasters often overlook the heterogeneity between long-range and short-range time series, leading to performance degradation in practical applications. In this work, we highlight the need of distinct objectives tailored to different ranges. We point out that time series can be decomposed into global patterns and local variations, which should be addressed separately in long- and short-range time series. To meet the objectives, we propose a multi-scale hybrid Mamba-Transformer experts model State Space Transformer (SST). SST leverages Mamba as an expert to extract global patterns in coarse-grained long-range time series, and Local Window Transformer (LWT), the other expert to focus on capturing local variations in fine-grained short-range time series. With an input-dependent mechanism, State Space Model (SSM)-based Mamba is able to selectively retain long-term patterns and filter out fluctuations, while LWT employs a local window to enhance locality-awareness capability, thus effectively capturing local variations. To adaptively integrate the global patterns and local variations, a long-short router dynamically adjusts contributions of the two experts. SST achieves superior performance with scaling linearly $O(L)$ on time series length $L$. The comprehensive experiments demonstrate the SST can achieve SOTA results in long-short range time series forecasting while maintaining low memory footprint and computational cost. The code of SST is available at https://github.com/XiongxiaoXu/SST.
Authors: Yuxuan Chen, Rongpeng Li, Xiaoxue Yu, Zhifeng Zhao, Honggang Zhang
Abstract: Optimizing the deployment of large language models (LLMs) in edge computing environments is critical for enhancing privacy and computational efficiency. Toward efficient wireless LLM inference in edge computing, this study comprehensively analyzes the impact of different splitting points in mainstream open-source LLMs. On this basis, this study introduces a framework taking inspiration from model-based reinforcement learning (MBRL) to determine the optimal splitting point across the edge and user equipment (UE). By incorporating a reward surrogate model, our approach significantly reduces the computational cost of frequent performance evaluations. Extensive simulations demonstrate that this method effectively balances inference performance and computational load under varying network conditions, providing a robust solution for LLM deployment in decentralized settings.
Authors: Duanyu Li, Huijun Wu, Min Xie, Xugang Wu, Zhenwei Wu, Wenzhe Zhang
Abstract: Graph neural network (GNN) models play a pivotal role in numerous tasks involving graph-related data analysis. Despite their efficacy, similar to other deep learning models, GNNs are susceptible to adversarial attacks. Even minor perturbations in graph data can induce substantial alterations in model predictions. While existing research has explored various adversarial defense techniques for GNNs, the challenge of defending against adversarial attacks on real-world scale graph data remains largely unresolved. On one hand, methods reliant on graph purification and preprocessing tend to excessively emphasize local graph information, leading to sub-optimal defensive outcomes. On the other hand, approaches rooted in graph structure learning entail significant time overheads, rendering them impractical for large-scale graphs. In this paper, we propose a new defense method named Talos, which enhances the global, rather than local, homophily of graphs as a defense. Experiments show that the proposed approach notably outperforms state-of-the-art defense approaches, while imposing little computational overhead.
Authors: Jingyao Li, Han Shi, Xin Jiang, Zhenguo Li, Hong Xu, Jiaya Jia
Abstract: The capacity of Large Language Models (LLMs) to comprehend and reason over long contexts is pivotal for advancements in diverse fields. Yet, they still stuggle with capturing long-distance dependencies within sequences to deeply understand semantics. To address this issue, we introduce Query-aware Inference for LLMs (Q-LLM), a system designed to process extensive sequences akin to human cognition. By focusing on memory data relevant to a given query, Q-LLM can accurately capture pertinent information within a fixed window size and provide precise answers to queries. It doesn't require extra training and can be seamlessly integrated with any LLMs. Q-LLM using LLaMA3 (QuickLLaMA) can read Harry Potter within 30s and accurately answer the questions. On widely recognized benchmarks, Q-LLM improved by 7.17% compared to the current state-of-the-art on LLaMA3, and by 3.26% on Mistral on the $\infty$-bench. In the Needle-in-a-Haystack and BABILong task, Q-LLM improved upon the current SOTA by 7.0% and 6.1%. Our code can be found in https://github.com/dvlab-research/Q-LLM.
Authors: Guy Bar-Shalom, Yam Eitan, Fabrizio Frasca, Haggai Maron
Abstract: Subgraph Graph Neural Networks (Subgraph GNNs) enhance the expressivity of message-passing GNNs by representing graphs as sets of subgraphs. They have shown impressive performance on several tasks, but their complexity limits applications to larger graphs. Previous approaches suggested processing only subsets of subgraphs, selected either randomly or via learnable sampling. However, they make suboptimal subgraph selections or can only cope with very small subset sizes, inevitably incurring performance degradation. This paper introduces a new Subgraph GNNs framework to address these issues. We employ a graph coarsening function to cluster nodes into super-nodes with induced connectivity. The product between the coarsened and the original graph reveals an implicit structure whereby subgraphs are associated with specific sets of nodes. By running generalized message-passing on such graph product, our method effectively implements an efficient, yet powerful Subgraph GNN. Controlling the coarsening function enables meaningful selection of any number of subgraphs while, contrary to previous methods, being fully compatible with standard training techniques. Notably, we discover that the resulting node feature tensor exhibits new, unexplored permutation symmetries. We leverage this structure, characterize the associated linear equivariant layers and incorporate them into the layers of our Subgraph GNN architecture. Extensive experiments on multiple graph learning benchmarks demonstrate that our method is significantly more flexible than previous approaches, as it can seamlessly handle any number of subgraphs, while consistently outperforming baseline approaches.
Authors: Elena Tomasi, Gabriele Franch, Marco Cristoforetti
Abstract: Downscaling techniques are one of the most prominent applications of Deep Learning (DL) in Earth System Modeling. A robust DL downscaling model can generate high-resolution fields from coarse-scale numerical model simulations, saving the timely and resourceful applications of regional/local models. Additionally, generative DL models have the potential to provide uncertainty information, by generating ensemble-like scenario pools, a task that is computationally prohibitive for traditional numerical simulations. In this study, we apply a Latent Diffusion Model (LDM) to downscale ERA5 data over Italy up to a resolution of 2 km. The high-resolution target data consists of 2-m temperature and 10-m horizontal wind components from a dynamical downscaling performed with COSMO_CLM. Our goal is to demonstrate that recent advancements in generative modeling enable DL to deliver results comparable to those of numerical dynamical models, given the same input data, preserving the realism of fine-scale features and flow characteristics. A selection of predictors from ERA5 is used as input to the LDM, and a residual approach against a reference UNET is leveraged in applying the LDM. The performance of the generative LDM is compared with reference baselines of increasing complexity: quadratic interpolation of ERA5, a UNET, and a Generative Adversarial Network (GAN) built on the same reference UNET. Results highlight the improvements introduced by the LDM architecture and the residual approach over these baselines. The models are evaluated on a yearly test dataset, assessing the models' performance through deterministic metrics, spatial distribution of errors, and reconstruction of frequency and power spectra distributions.
Authors: Weiqin Chen, Mark S. Squillante, Chai Wah Wu, Santiago Paternain
Abstract: We devise a control-theoretic reinforcement learning approach to support direct learning of the optimal policy. We establish various theoretical properties of our approach, such as convergence and optimality of our control-theoretic operator, a new control-policy-parameter gradient ascent theorem, and a specific gradient ascent algorithm based on this theorem. As a representative example, we adapt our approach to a particular control-theoretic framework and empirically evaluate its performance on several classical reinforcement learning tasks, demonstrating significant improvements in solution quality, sample complexity, and running time of our control-theoretic approach over state-of-the-art baseline methods.
Authors: Ryoichi Ishizuka, Takashi Imai, Kaoru Kawamoto
Abstract: In this paper, we propose a novel method of model-based time series clustering with mixtures of general state space models (MSSMs). Each component of MSSMs is associated with each cluster. An advantage of the proposed method is that it enables the use of time series models appropriate to the specific time series. This not only improves clustering and prediction accuracy but also enhances the interpretability of the estimated parameters. The parameters of the MSSMs are estimated using stochastic variational inference, a subtype of variational inference. The proposed method estimates the latent variables of an arbitrary state space model by using neural networks with a normalizing flow as a variational estimator. The number of clusters can be estimated using the Bayesian information criterion. In addition, to prevent MSSMs from converging to the local optimum, we propose several optimization tricks, including an additional penalty term called entropy annealing. To our best knowledge, the proposed method is the first computationally feasible one for time series clustering based on general (possibly nonlinear, non-Gaussian) state space models. Experiments on simulated datasets show that the proposed method is effective for clustering, parameter estimation, and estimating the number of clusters.
Authors: Sahel Vahedi Noori, Bin Hu, Geir Dullerud, Peter Seiler
Abstract: This paper derives a complete set of quadratic constraints (QCs) for the repeated ReLU. The complete set of QCs is described by a collection of matrix copositivity conditions. We also show that only two functions satisfy all QCs in our complete set: the repeated ReLU and flipped ReLU. Thus our complete set of QCs bounds the repeated ReLU as tight as possible up to the sign invariance inherent in quadratic forms. We derive a similar complete set of incremental QCs for repeated ReLU, which can potentially lead to less conservative Lipschitz bounds for ReLU networks than the standard LipSDP approach. The basic constructions are also used to derive the complete sets of QCs for other piecewise linear activation functions such as leaky ReLU, MaxMin, and HouseHolder. Finally, we illustrate the use of the complete set of QCs to assess stability and performance for recurrent neural networks with ReLU activation functions. We rely on a standard copositivity relaxation to formulate the stability/performance condition as a semidefinite program. Simple examples are provided to illustrate that the complete sets of QCs and incremental QCs can yield less conservative bounds than existing sets.
Authors: Ze Yu Zhang, Arun Verma, Finale Doshi-Velez, Bryan Kian Hsiang Low
Abstract: Large language models (LLMs) are widely used in decision-making, but their reliability, especially in critical tasks like healthcare, is not well-established. Therefore, understanding how LLMs reason and make decisions is crucial for their safe deployment. This paper investigates how the uncertainty of responses generated by LLMs relates to the information provided in the input prompt. Leveraging the insight that LLMs learn to infer latent concepts during pretraining, we propose a prompt-response concept model that explains how LLMs generate responses and helps understand the relationship between prompts and response uncertainty. We show that the uncertainty decreases as the prompt's informativeness increases, similar to epistemic uncertainty. Our detailed experimental results on real datasets validate our proposed model.
Authors: Abhay Sheshadri, Aidan Ewart, Phillip Guo, Aengus Lynch, Cindy Wu, Vivek Hebbar, Henry Sleight, Asa Cooper Stickland, Ethan Perez, Dylan Hadfield-Menell, Stephen Casper
Abstract: Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful text from models that were fine-tuned to be harmless. Recent work on red-teaming, model editing, and interpretability suggests that this challenge stems from how (adversarial) fine-tuning largely serves to suppress rather than remove undesirable capabilities from LLMs. Prior work has introduced latent adversarial training (LAT) as a way to improve robustness to broad classes of failures. These prior works have considered untargeted latent space attacks where the adversary perturbs latent activations to maximize loss on examples of desirable behavior. Untargeted LAT can provide a generic type of robustness but does not leverage information about specific failure modes. Here, we experiment with targeted LAT where the adversary seeks to minimize loss on a specific competing task. We find that it can augment a wide variety of state-of-the-art methods. First, we use targeted LAT to improve robustness to jailbreaks, outperforming a strong R2D2 baseline with orders of magnitude less compute. Second, we use it to more effectively remove backdoors with no knowledge of the trigger. Finally, we use it to more effectively unlearn knowledge for specific undesirable tasks in a way that is also more robust to re-learning. Overall, our results suggest that targeted LAT can be an effective tool for defending against harmful behaviors from LLMs.
Authors: Zachary Rabin, Jim Davis, Benjamin Lewis, Matthew Scherreik
Abstract: Overfitting describes a machine learning phenomenon where the model fits too closely to the training data, resulting in poor generalization. While this occurrence is thoroughly documented for many forms of supervised learning, it is not well examined in the context of unsupervised learning. In this work we examine the nature of overfitting in unsupervised contrastive learning. We show that overfitting can indeed occur and the mechanism behind overfitting.
Authors: Juseung Yun, Yi Hu, Jinhyung Kim, Jongseong Jang, Soonyoung Lee
Abstract: Recent advancements in digital pathology have led to the development of numerous foundational models that utilize self-supervised learning on patches extracted from gigapixel whole slide images (WSIs). While this approach leverages vast amounts of unlabeled data, we have discovered a significant issue: features extracted from these self-supervised models tend to cluster by individual WSIs, a phenomenon we term WSI-specific feature collapse. This problem can potentially limit the model's generalization ability and performance on various downstream tasks. To address this issue, we introduce EXAONEPath, a novel foundational model trained on patches that have undergone stain normalization. Stain normalization helps reduce color variability arising from different laboratories and scanners, enabling the model to learn more consistent features. EXAONEPath is trained using 285,153,903 patches extracted from a total of 34,795 WSIs. Our experiments demonstrate that EXAONEPath significantly mitigates the feature collapse problem, indicating that the model has learned more generalized features rather than overfitting to individual WSI characteristics. We compared EXAONEPath with state-of-the-art models across six downstream task datasets, and our results show that EXAONEPath achieves superior performance relative to the number of WSIs used and the model's parameter count. This suggests that the application of stain normalization has substantially improved the model's efficiency and generalization capabilities.
Authors: Ruifeng Li, Mingqian Li, Wei Liu, Hongyang Chen
Abstract: Effective molecular representation learning is crucial for advancing molecular property prediction and drug design. Mainstream molecular representation learning approaches are based on Graph Neural Networks (GNNs). However, these approaches struggle with three significant challenges: insufficient annotations, molecular diversity, and architectural limitations such as over-squashing, which leads to the loss of critical structural details. To address these challenges, we introduce a new class of GNNs that integrates the Kolmogorov-Arnold Networks (KANs), known for their robust data-fitting capabilities and high accuracy in small-scale AI + Science tasks. By incorporating KANs into GNNs, our model enhances the representation of molecular structures. We further advance this approach with a variant called SwallowKAN (SKAN), which employs adaptive Radial Basis Functions (RBFs) as the core of the non-linear neurons. This innovation improves both computational efficiency and adaptability to diverse molecular structures. Building on the strengths of SKAN, we propose a new class of GNNs, GNN-SKAN, and its augmented variant, GNN-SKAN+, which incorporates a SKAN-based classifier to further boost performance. To our knowledge, this is the first work to integrate KANs into GNN architectures tailored for molecular representation learning. Experiments across 6 classification datasets, 6 regression datasets, and 4 few-shot learning datasets demonstrate that our approach achieves new state-of-the-art performance in terms of accuracy and computational cost.
Authors: Haohao Qu, Liangbo Ning, Rui An, Wenqi Fan, Tyler Derr, Hui Liu, Xin Xu, Qing Li
Abstract: As one of the most representative DL techniques, Transformer architecture has empowered numerous advanced models, especially the large language models (LLMs) that comprise billions of parameters, becoming a cornerstone in deep learning. Despite the impressive achievements, Transformers still face inherent limitations, particularly the time-consuming inference resulting from the quadratic computation complexity of attention calculation. Recently, a novel architecture named Mamba, drawing inspiration from classical state space models (SSMs), has emerged as a promising alternative for building foundation models, delivering comparable modeling abilities to Transformers while preserving near-linear scalability concerning sequence length. This has sparked an increasing number of studies actively exploring Mamba's potential to achieve impressive performance across diverse domains. Given such rapid evolution, there is a critical need for a systematic review that consolidates existing Mamba-empowered models, offering a comprehensive understanding of this emerging model architecture. In this survey, we therefore conduct an in-depth investigation of recent Mamba-associated studies, covering three main aspects: the advancements of Mamba-based models, the techniques of adapting Mamba to diverse data, and the applications where Mamba can excel. Specifically, we first review the foundational knowledge of various representative deep learning models and the details of Mamba-1&2 as preliminaries. Then, to showcase the significance of Mamba for AI, we comprehensively review the related studies focusing on Mamba models' architecture design, data adaptability, and applications. Finally, we present a discussion of current limitations and explore various promising research directions to provide deeper insights for future investigations.
Authors: Khanh Nguyen, Huy Hoang Nguyen, Egor Panfilov, Aleksei Tiulpin
Abstract: Osteoarthritis (OA) is the most common musculoskeletal disease, which has no cure. Knee OA (KOA) is one of the highest causes of disability worldwide, and it costs billions of United States dollars to the global community. Prediction of KOA progression has been of high interest to the community for years, as it can advance treatment development through more efficient clinical trials and improve patient outcomes through more efficient healthcare utilization. Existing approaches for predicting KOA, however, are predominantly static, i.e. consider data from a single time point to predict progression many years into the future, and knee level, i.e. consider progression in a single joint only. Due to these and related reasons, these methods fail to deliver the level of predictive performance, which is sufficient to result in cost savings and better patient outcomes. Collecting extensive data from all patients on a regular basis could address the issue, but it is limited by the high cost at a population level. In this work, we propose to go beyond static prediction models in OA, and bring a novel Active Sensing (AS) approach, designed to dynamically follow up patients with the objective of maximizing the number of informative data acquisitions, while minimizing their total cost over a period of time. Our approach is based on Reinforcement Learning (RL), and it leverages a novel reward function designed specifically for AS of disease progression in more than one part of a human body. Our method is end-to-end, relies on multi-modal Deep Learning, and requires no human input at inference time. Throughout an exhaustive experimental evaluation, we show that using RL can provide a higher monetary benefit when compared to state-of-the-art baselines.
Authors: Luyao Tang, Yuxuan Yuan, Chaoqi Chen, Xinghao Ding, Yue Huang
Abstract: Despite the considerable advancements achieved by deep neural networks, their performance tends to degenerate when the test environment diverges from the training ones. Domain generalization (DG) solves this issue by learning representations independent of domain-related information, thus facilitating extrapolation to unseen environments. Existing approaches typically focus on formulating tailored training objectives to extract shared features from the source data. However, the disjointed training and testing procedures may compromise robustness, particularly in the face of unforeseen variations during deployment. In this paper, we propose a novel and holistic framework based on causality, named InPer, designed to enhance model generalization by incorporating causal intervention during training and causal perturbation during testing. Specifically, during the training phase, we employ entropy-based causal intervention (EnIn) to refine the selection of causal variables. To identify samples with anti-interference causal variables from the target domain, we propose a novel metric, homeostatic score, through causal perturbation (HoPer) to construct a prototype classifier in test time. Experimental results across multiple cross-domain tasks confirm the efficacy of InPer.
Authors: Weijie Xia, Gao Peng, Chenguang Wang, Peter Palensky, Eric Pauwels, Pedro P. Vergara
Abstract: Electricity Consumption Profiles (ECPs) are crucial for operating and planning power distribution systems, especially with the increasing numbers of various low-carbon technologies such as solar panels and electric vehicles. Traditional ECP modeling methods typically assume the availability of sufficient ECP data. However, in practice, the accessibility of ECP data is limited due to privacy issues or the absence of metering devices. Few-shot learning (FSL) has emerged as a promising solution for ECP modeling in data-scarce scenarios. Nevertheless, standard FSL methods, such as those used for images, are unsuitable for ECP modeling because (1) these methods usually assume several source domains with sufficient data and several target domains. However, in the context of ECP modeling, there may be thousands of source domains with a moderate amount of data and thousands of target domains. (2) Standard FSL methods usually involve cumbersome knowledge transfer mechanisms, such as pre-training and fine-tuning, whereas ECP modeling requires more lightweight methods. (3) Deep learning models often lack explainability, hindering their application in industry. This paper proposes a novel FSL method that exploits Transformers and Gaussian Mixture Models (GMMs) for ECP modeling to address the above-described issues. Results show that our method can accurately restore the complex ECP distribution with a minimal amount of ECP data (e.g., only 1.6\% of the complete domain dataset) while it outperforms state-of-the-art time series modeling methods, maintaining the advantages of being both lightweight and interpretable. The project is open-sourced at https://github.com/xiaweijie1996/TransformerEM-GMM.git.
URLs: https://github.com/xiaweijie1996/TransformerEM-GMM.git.
Authors: Subrat Prasad Panda, Blaise Genest, Arvind Easwaran, Ponnuthurai Nagaratnam Suganthan
Abstract: Decision Trees (DTs) constitute one of the major highly non-linear AI models, valued, e.g., for their efficiency on tabular data. Learning accurate DTs is, however, complicated, especially for oblique DTs, and does take a significant training time. Further, DTs suffer from overfitting, e.g., they proverbially "do not generalize" in regression tasks. Recently, some works proposed ways to make (oblique) DTs differentiable. This enables highly efficient gradient-descent algorithms to be used to learn DTs. It also enables generalizing capabilities by learning regressors at the leaves simultaneously with the decisions in the tree. Prior approaches to making DTs differentiable rely either on probabilistic approximations at the tree's internal nodes (soft DTs) or on approximations in gradient computation at the internal node (quantized gradient descent). In this work, we propose DTSemNet, a novel semantically equivalent and invertible encoding for (hard, oblique) DTs as Neural Networks (NNs), that uses standard vanilla gradient descent. Experiments across various classification and regression benchmarks show that oblique DTs learned using DTSemNet are more accurate than oblique DTs of similar size learned using state-of-the-art techniques. Further, DT training time is significantly reduced. We also experimentally demonstrate that DTSemNet can learn DT policies as efficiently as NN policies in the Reinforcement Learning (RL) setup with physical inputs (dimensions $\leq32$). The code is available at {\color{blue}\textit{\url{https://github.com/CPS-research-group/dtsemnet}}}.
Authors: Gus Kristiansen, Mark Sandler, Andrey Zhmoginov, Nolan Miller, Anirudh Goyal, Jihwan Lee, Max Vladymyrov
Abstract: In modern deep learning, the models are learned by applying gradient updates using an optimizer, which transforms the updates based on various statistics. Optimizers are often hand-designed and tuning their hyperparameters is a big part of the training process. Learned optimizers have shown some initial promise, but are generally unsuccessful as a general optimization mechanism applicable to every problem. In this work we explore a different direction: instead of learning general optimizers, we instead specialize them to a specific training environment. We propose a novel optimizer technique that learns a layer-specific linear combination of update directions provided by a set of base optimizers, effectively adapting its strategy to the specific model and dataset. When evaluated on image classification tasks, this specialized optimizer significantly outperforms both traditional off-the-shelf methods such as Adam, as well as existing general learned optimizers. Moreover, it demonstrates robust generalization with respect to model initialization, evaluating on unseen datasets, and training durations beyond its meta-training horizon.
Authors: Tanya Liyaqat, Tanvir Ahmad, Chandni Saxena
Abstract: Molecular Property Prediction (MPP) plays a pivotal role across diverse domains, spanning drug discovery, material science, and environmental chemistry. Fueled by the exponential growth of chemical data and the evolution of artificial intelligence, recent years have witnessed remarkable strides in MPP. However, the multifaceted nature of molecular data, such as molecular structures, SMILES notation, and molecular images, continues to pose a fundamental challenge in its effective representation. To address this, representation learning techniques are instrumental as they acquire informative and interpretable representations of molecular data. This article explores recent AI/-based approaches in MPP, focusing on both single and multiple modality representation techniques. It provides an overview of various molecule representations and encoding schemes, categorizes MPP methods by their use of modalities, and outlines datasets and tools available for feature generation. The article also analyzes the performance of recent methods and suggests future research directions to advance the field of MPP.
Authors: Jie Wang, Rui Gao, Yao Xie
Abstract: Despite the growing prevalence of artificial neural networks in real-world applications, their vulnerability to adversarial attacks remains a significant concern, which motivates us to investigate the robustness of machine learning models. While various heuristics aim to optimize the distributionally robust risk using the $\infty$-Wasserstein metric, such a notion of robustness frequently encounters computation intractability. To tackle the computational challenge, we develop a novel approach to adversarial training that integrates $\phi$-divergence regularization into the distributionally robust risk function. This regularization brings a notable improvement in computation compared with the original formulation. We develop stochastic gradient methods with biased oracles to solve this problem efficiently, achieving the near-optimal sample complexity. Moreover, we establish its regularization effects and demonstrate it is asymptotic equivalence to a regularized empirical risk minimization framework, by considering various scaling regimes of the regularization parameter and robustness level. These regimes yield gradient norm regularization, variance regularization, or a smoothed gradient norm regularization that interpolates between these extremes. We numerically validate our proposed method in supervised learning, reinforcement learning, and contextual learning and showcase its state-of-the-art performance against various adversarial attacks.
Authors: Samuel Chevalier, Duncan Starkenburg, Krishnamurthy Dvijotham
Abstract: In the field of formal verification, Neural Networks (NNs) are typically reformulated into equivalent mathematical programs which are optimized over. To overcome the inherent non-convexity of these reformulations, convex relaxations of nonlinear activation functions are typically utilized. Common relaxations (i.e., static linear cuts) of "S-shaped" activation functions, however, can be overly loose, slowing down the overall verification process. In this paper, we derive tuneable hyperplanes which upper and lower bound the sigmoid activation function. When tuned in the dual space, these affine bounds smoothly rotate around the nonlinear manifold of the sigmoid activation function. This approach, termed $\alpha$-sig, allows us to tractably incorporate the tightest possible, element-wise convex relaxation of the sigmoid activation function into a formal verification framework. We embed these relaxations inside of large verification tasks and compare their performance to LiRPA and $\alpha$-CROWN, a state-of-the-art verification duo.
Authors: Manos Kirtas, Konstantinos Tsampazis, Loukia Avramelou, Nikolaos Passalis, Anastasios Tefas
Abstract: Utilizing deep learning models to learn part-based representations holds significant potential for interpretable-by-design approaches, as these models incorporate latent causes obtained from feature representations through simple addition. However, training a part-based learning model presents challenges, particularly in enforcing non-negative constraints on the model's parameters, which can result in training difficulties such as instability and convergence issues. Moreover, applying such approaches in Deep Reinforcement Learning (RL) is even more demanding due to the inherent instabilities that impact many optimization methods. In this paper, we propose a non-negative training approach for actor models in RL, enabling the extraction of part-based representations that enhance interpretability while adhering to non-negative constraints. To this end, we employ a non-negative initialization technique, as well as a modified sign-preserving training method, which can ensure better gradient flow compared to existing approaches. We demonstrate the effectiveness of the proposed approach using the well-known Cartpole benchmark.
Authors: Hao Tu, Scott Moura, Yebin Wang, Huazhen Fang
Abstract: Mathematical modeling of lithium-ion batteries (LiBs) is a primary challenge in advanced battery management. This paper proposes two new frameworks to integrate physics-based models with machine learning to achieve high-precision modeling for LiBs. The frameworks are characterized by informing the machine learning model of the state information of the physical model, enabling a deep integration between physics and machine learning. Based on the frameworks, a series of hybrid models are constructed, through combining an electrochemical model and an equivalent circuit model, respectively, with a feedforward neural network. The hybrid models are relatively parsimonious in structure and can provide considerable voltage predictive accuracy under a broad range of C-rates, as shown by extensive simulations and experiments. The study further expands to conduct aging-aware hybrid modeling, leading to the design of a hybrid model conscious of the state-of-health to make prediction. The experiments show that the model has high voltage predictive accuracy throughout a LiB's cycle life.
Authors: Carlos Garc\'ia Meixide, Marcos Matabuena, Louis Abraham, Michael R. Kosorok
Abstract: Survival analysis is a fundamental area of focus in biomedical research, particularly in the context of personalized medicine. This prominence is due to the increasing prevalence of large and high-dimensional datasets, such as omics and medical image data. However, the literature on non-linear regression algorithms and variable selection techniques for interval-censoring is either limited or non-existent, particularly in the context of neural networks. Our objective is to introduce a novel predictive framework tailored for interval-censored regression tasks, rooted in Accelerated Failure Time (AFT) models. Our strategy comprises two key components: i) a variable selection phase leveraging recent advances on sparse neural network architectures, ii) a regression model targeting prediction of the interval-censored response. To assess the performance of our novel algorithm, we conducted a comprehensive evaluation through both numerical experiments and real-world applications that encompass scenarios related to diabetes and physical activity. Our results outperform traditional AFT algorithms, particularly in scenarios featuring non-linear relationships.
Authors: I. J. Arnquist, F. T. Avignone III, A. S. Barabash, C. J. Barton, K. H. Bhimani, E. Blalock, B. Bos, M. Busch, M. Buuck, T. S. Caldwell, Y -D. Chan, C. D. Christofferson, P. -H. Chu, M. L. Clark, C. Cuesta, J. A. Detwiler, Yu. Efremenko, S. R. Elliott, G. K. Giovanetti, M. P. Green, J. Gruszko, I. S. Guinn, V. E. Guiseppe, C. R. Haufe, R. Henning, D. Hervas Aguilar, E. W. Hoppe, A. Hostiuc, M. F. Kidd, I. Kim, R. T. Kouzes, T. E. Lannen V, A. Li, J. M. Lopez-Castano, E. L. Martin, R. D. Martin, R. Massarczyk, S. J. Meijer, T. K. Oli, G. Othman, L. S. Paudel, W. Pettus, A. W. P. Poon, D. C. Radford, A. L. Reine, K. Rielage, N. W. Ruof, D. C. Schaper, D. Tedeschi, R. L. Varner, S. Vasilyev, J. F. Wilkerson, C. Wiseman, W. Xu, C. -H. Yu
Abstract: The Majorana Demonstrator is a leading experiment searching for neutrinoless double-beta decay with high purity germanium detectors (HPGe). Machine learning provides a new way to maximize the amount of information provided by these detectors, but the data-driven nature makes it less interpretable compared to traditional analysis. An interpretability study reveals the machine's decision-making logic, allowing us to learn from the machine to feedback to the traditional analysis. In this work, we have presented the first machine learning analysis of the data from the Majorana Demonstrator; this is also the first interpretable machine learning analysis of any germanium detector experiment. Two gradient boosted decision tree models are trained to learn from the data, and a game-theory-based model interpretability study is conducted to understand the origin of the classification power. By learning from data, this analysis recognizes the correlations among reconstruction parameters to further enhance the background rejection performance. By learning from the machine, this analysis reveals the importance of new background categories to reciprocally benefit the standard Majorana analysis. This model is highly compatible with next-generation germanium detector experiments like LEGEND since it can be simultaneously trained on a large number of detectors.
Authors: Ljupcho Milosheski, Gregor Cerar, Bla\v{z} Bertalani\v{c}, Carolina Fortuna, Mihael Mohor\v{c}i\v{c}
Abstract: In recent years, much work has been done on processing of wireless spectrum data involving machine learning techniques in domain-related problems for cognitive radio networks, such as anomaly detection, modulation classification, technology classification and device fingerprinting. Most of the solutions are based on labeled data, created in a controlled manner and processed with supervised learning approaches. However, spectrum data measured in real-world environment is highly nondeterministic, making its labeling a laborious and expensive process, requiring domain expertise, thus being one of the main drawbacks of using supervised learning approaches in this domain. In this paper, we investigate the use of self-supervised learning (SSL) for exploring spectrum activities in a real-world unlabeled data. In particular, we compare the performance of two SSL models, one based on a reference DeepCluster architecture and one adapted for spectrum activity identification and clustering, and a baseline model based on K-means clustering algorithm. We show that SSL models achieve superior performance regarding the quality of extracted features and clustering performance. With SSL models we achieve reduction of the feature vectors size by two orders of magnitude, while improving the performance by a factor of 2 to 2.5 across the evaluation metrics, supported by visual assessment. Additionally we show that adaptation of the reference SSL architecture to the domain data provides reduction of model complexity by one order of magnitude, while preserving or even improving the clustering performance.
Authors: Manuel V. Loureiro, Steven Derby, Tri Kurniawan Wijaya
Abstract: Topic models aim to reveal latent structures within a corpus of text, typically through the use of term-frequency statistics over bag-of-words representations from documents. In recent years, conceptual entities -- interpretable, language-independent features linked to external knowledge resources -- have been used in place of word-level tokens, as words typically require extensive language processing with a minimal assurance of interpretability. However, current literature is limited when it comes to exploring purely entity-driven neural topic modeling. For instance, despite the advantages of using entities for eliciting thematic structure, it is unclear whether current techniques are compatible with these sparsely organised, information-dense conceptual units. In this work, we explore entity-based neural topic modeling and propose a novel topic clustering approach using bimodal vector representations of entities. Concretely, we extract these latent representations from large language models and graph neural networks trained on a knowledge base of symbolic relations, in order to derive the most salient aspects of these conceptual units. Analysis of coherency metrics confirms that our approach is better suited to working with entities in comparison to state-of-the-art models, particularly when using graph-based embeddings trained on a knowledge base.
Authors: Pascal Jutras-Dub\'e, Mohammad B. Al-Khasawneh, Zhichao Yang, Javier Bas, Fabian Bastin, Cinzia Cirillo
Abstract: Population synthesis involves generating synthetic yet realistic representations of a target population of micro-agents for behavioral modeling and simulation. Traditional methods, often reliant on target population samples, such as census data or travel surveys, face limitations due to high costs and small sample sizes, particularly at smaller geographical scales. We propose a novel framework based on copulas to generate synthetic data for target populations where only empirical marginal distributions are known. This method utilizes samples from different populations with similar marginal dependencies, introduces a spatial component into population synthesis, and considers various information sources for more realistic generators. Concretely, the process involves normalizing the data and treating it as realizations of a given copula, and then training a generative model before incorporating the information on the marginals of the target population. Utilizing American Community Survey data, we assess our framework's performance through standardized root mean squared error (SRMSE) and so-called sampled zeros. We focus on its capacity to transfer a model learned from one population to another. Our experiments include transfer tests between regions at the same geographical level as well as to lower geographical levels, hence evaluating the framework's adaptability in varied spatial contexts. We compare Bayesian Networks, Variational Autoencoders, and Generative Adversarial Networks, both individually and combined with our copula framework. Results show that the copula enhances machine learning methods in matching the marginals of the reference data. Furthermore, it consistently surpasses Iterative Proportional Fitting in terms of SRMSE in the transferability experiments, while introducing unique observations not found in the original training sample.
Authors: Rachith Aiyappa, Jisun An, Haewoon Kwak, Yong-Yeol Ahn
Abstract: ChatGPT, the first large language model (LLM) with mass adoption, has demonstrated remarkable performance in numerous natural language tasks. Despite its evident usefulness, evaluating ChatGPT's performance in diverse problem domains remains challenging due to the closed nature of the model and its continuous updates via Reinforcement Learning from Human Feedback (RLHF). We highlight the issue of data contamination in ChatGPT evaluations, with a case study of the task of stance detection. We discuss the challenge of preventing data contamination and ensuring fair model evaluation in the age of closed and continuously trained models.
Authors: Haoran Liu, Peng Li, Ming-Zhe Liu, Kai-Ming Wang, Zhuo Zuo, Bing-Qi Liu
Abstract: This study utilized the Tempotron, a robust classifier based on a third-generation neural network model, for pulse shape discrimination. By eliminating the need for manual feature extraction, the Tempotron model can process pulse signals directly, generating discrimination results based on prior knowledge. The study performed experiments using GPU acceleration, resulting in over 500 times faster compared to the CPU-based model, and investigated the impact of noise augmentation on the Tempotron performance. Experimental results substantiated that Tempotron serves as a formidable classifier, adept at accomplishing high discrimination accuracy on both AmBe and time-of-flight PuBe datasets. Furthermore, analyzing the neural activity of Tempotron during training shed light on its learning characteristics and aided in selecting its hyperparameters. Moreover, the study addressed the constraints and potential avenues for future development in utilizing the Tempotron for pulse shape discrimination. The dataset used in this study and the GPU-based Tempotron are publicly available on GitHub at https://github.com/HaoranLiu507/TempotronGPU.
Authors: Sasila Ilandarideva, Anatoli Juditsky, Guanghui Lan, Tianjiao Li
Abstract: We consider a class of stochastic smooth convex optimization problems under rather general assumptions on the noise in the stochastic gradient observation. As opposed to the classical problem setting in which the variance of noise is assumed to be uniformly bounded, herein we assume that the variance of stochastic gradients is related to the "sub-optimality" of the approximate solutions delivered by the algorithm. Such problems naturally arise in a variety of applications, in particular, in the well-known generalized linear regression problem in statistics. However, to the best of our knowledge, none of the existing stochastic approximation algorithms for solving this class of problems attain optimality in terms of the dependence on accuracy, problem parameters, and mini-batch size. We discuss two non-Euclidean accelerated stochastic approximation routines--stochastic accelerated gradient descent (SAGD) and stochastic gradient extrapolation (SGE)--which carry a particular duality relationship. We show that both SAGD and SGE, under appropriate conditions, achieve the optimal convergence rate, attaining the optimal iteration and sample complexities simultaneously. However, corresponding assumptions for the SGE algorithm are more general; they allow, for instance, for efficient application of the SGE to statistical estimation problems under heavy tail noises and discontinuous score functions. We also discuss the application of the SGE to problems satisfying quadratic growth conditions, and show how it can be used to recover sparse solutions. Finally, we report on some simulation experiments to illustrate numerical performance of our proposed algorithms in high-dimensional settings.
Authors: Daniil Lisus, Johann Laconte, Keenan Burnett, Ziyu Zhang, Timothy D. Barfoot
Abstract: This paper presents a novel deep-learning-based approach to improve localizing radar measurements against lidar maps. This radar-lidar localization leverages the benefits of both sensors; radar is resilient against adverse weather, while lidar produces high-quality maps in clear conditions. However, owing in part to the unique artefacts present in radar measurements, radar-lidar localization has struggled to achieve comparable performance to lidar-lidar systems, preventing it from being viable for autonomous driving. This work builds on ICP-based radar-lidar localization by including a learned preprocessing step that weights radar points based on high-level scan information. To train the weight-generating network, we present a novel, stand-alone, open-source differentiable ICP library. The learned weights facilitate ICP by filtering out harmful radar points related to artefacts, noise, and even vehicles on the road. Combining an analytical approach with a learned weight reduces overall localization errors and improves convergence in radar-lidar ICP results run on real-world autonomous driving data. Our code base is publicly available to facilitate reproducibility and extensions.
Authors: Elena Shushkevich, Long Mai, Manuel V. Loureiro, Steven Derby, Tri Kurniawan Wijaya
Abstract: The proliferation of news media outlets has increased the demand for intelligent systems capable of detecting redundant information in news articles in order to enhance user experience. However, the heterogeneous nature of news can lead to spurious findings in these systems: Simple heuristics such as whether a pair of news are both about politics can provide strong but deceptive downstream performance. Segmenting news similarity datasets into topics improves the training of these models by forcing them to learn how to distinguish salient characteristics under more narrow domains. However, this requires the existence of topic-specific datasets, which are currently lacking. In this article, we propose a novel dataset of similar news, SPICED, which includes seven topics: Crime & Law, Culture & Entertainment, Disasters & Accidents, Economy & Business, Politics & Conflicts, Science & Technology, and Sports. Futhermore, we present four different levels of complexity, specifically designed for news similarity detection task. We benchmarked the created datasets using MinHash, BERT, SBERT, and SimCSE models.
Authors: Jiakai Wang, Xianglong Liu, Jin Hu, Donghua Wang, Siyang Wu, Tingsong Jiang, Yuanfang Guo, Aishan Liu, Jiantao Zhou
Abstract: Deep neural networks (DNNs) have demonstrated high vulnerability to adversarial examples, raising broad security concerns about their applications. Besides the attacks in the digital world, the practical implications of adversarial examples in the physical world present significant challenges and safety concerns. However, current research on physical adversarial examples (PAEs) lacks a comprehensive understanding of their unique characteristics, leading to limited significance and understanding. In this paper, we address this gap by thoroughly examining the characteristics of PAEs within a practical workflow encompassing training, manufacturing, and re-sampling processes. By analyzing the links between physical adversarial attacks, we identify manufacturing and re-sampling as the primary sources of distinct attributes and particularities in PAEs. Leveraging this knowledge, we develop a comprehensive analysis and classification framework for PAEs based on their specific characteristics, covering over 100 studies on physical-world adversarial examples. Furthermore, we investigate defense strategies against PAEs and identify open challenges and opportunities for future research. We aim to provide a fresh, thorough, and systematic understanding of PAEs, thereby promoting the development of robust adversarial learning and its application in open-world scenarios to provide the community with a continuously updated list of physical world adversarial sample resources, including papers, code, \etc, within the proposed framework
Authors: Georgia Papacharalampous, Hristos Tyralis, Nikolaos Doulamis, Anastasios Doulamis
Abstract: Merging satellite and gauge data with machine learning produces high-resolution precipitation datasets, but uncertainty estimates are often missing. We addressed the gap of how to optimally provide such estimates by benchmarking six algorithms, mostly novel even for the more general task of quantifying predictive uncertainty in spatial prediction settings. On 15 years of monthly data from over the contiguous United States (CONUS), we compared quantile regression (QR), quantile regression forests (QRF), generalized random forests (GRF), gradient boosting machines (GBM), light gradient boosting machine (LightGBM), and quantile regression neural networks (QRNN). Their ability to issue predictive precipitation quantiles at nine quantile levels (0.025, 0.050, 0.100, 0.250, 0.500, 0.750, 0.900, 0.950, 0.975), approximating the full probability distribution, was evaluated using quantile scoring functions and the quantile scoring rule. Predictors at a site were nearby values from two satellite precipitation retrievals, namely PERSIANN (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks) and IMERG (Integrated Multi-satellitE Retrievals), and the site's elevation. The dependent variable was the monthly mean gauge precipitation. With respect to QR, LightGBM showed improved performance in terms of the quantile scoring rule by 11.10%, also surpassing QRF (7.96%), GRF (7.44%), GBM (4.64%) and QRNN (1.73%). Notably, LightGBM outperformed all random forest variants, the current standard in spatial prediction with machine learning. To conclude, we propose a suite of machine learning algorithms for estimating uncertainty in spatial data prediction, supported with a formal evaluation framework based on scoring functions and scoring rules.
Authors: Jeongwhan Choi, Hyowon Wi, Chaejeong Lee, Sung-Bae Cho, Dongha Lee, Noseong Park
Abstract: Contrastive learning (CL) has emerged as a promising technique for improving recommender systems, addressing the challenge of data sparsity by using self-supervised signals from raw data. Integration of CL with graph convolutional network (GCN)-based collaborative filterings (CFs) has been explored in recommender systems. However, current CL-based recommendation models heavily rely on low-pass filters and graph augmentations. In this paper, inspired by the reaction-diffusion equation, we propose a novel CL method for recommender systems called the reaction-diffusion graph contrastive learning model (RDGCL). We design our own GCN for CF based on the equations of diffusion, i.e., low-pass filter, and reaction, i.e., high-pass filter. Our proposed CL-based training occurs between reaction and diffusion-based embeddings, so there is no need for graph augmentations. Experimental evaluation on 5 benchmark datasets demonstrates that our proposed method outperforms state-of-the-art CL-based recommendation models. By enhancing recommendation accuracy and diversity, our method brings an advancement in CL for recommender systems.
Authors: Philipp Schoenegger, Peter S. Park, Ezra Karger, Sean Trott, Philip E. Tetlock
Abstract: Large language models (LLMs) match and sometimes exceeding human performance in many domains. This study explores the potential of LLMs to augment human judgement in a forecasting task. We evaluate the effect on human forecasters of two LLM assistants: one designed to provide high-quality ("superforecasting") advice, and the other designed to be overconfident and base-rate neglecting, thus providing noisy forecasting advice. We compare participants using these assistants to a control group that received a less advanced model that did not provide numerical predictions or engaged in explicit discussion of predictions. Participants (N = 991) answered a set of six forecasting questions and had the option to consult their assigned LLM assistant throughout. Our preregistered analyses show that interacting with each of our frontier LLM assistants significantly enhances prediction accuracy by between 24 percent and 28 percent compared to the control group. Exploratory analyses showed a pronounced outlier effect in one forecasting item, without which we find that the superforecasting assistant increased accuracy by 41 percent, compared with 29 percent for the noisy assistant. We further examine whether LLM forecasting augmentation disproportionately benefits less skilled forecasters, degrades the wisdom-of-the-crowd by reducing prediction diversity, or varies in effectiveness with question difficulty. Our data do not consistently support these hypotheses. Our results suggest that access to a frontier LLM assistant, even a noisy one, can be a helpful decision aid in cognitively demanding tasks compared to a less powerful model that does not provide specific forecasting advice. However, the effects of outliers suggest that further research into the robustness of this pattern is needed.
Authors: Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, J\"urgen Schmidhuber
Abstract: Various human-designed prompt engineering techniques have been proposed to improve problem solvers based on Large Language Models (LLMs), yielding many disparate code bases. We unify these approaches by describing LLM-based agents as computational graphs. The nodes implement functions to process multimodal data or query LLMs, and the edges describe the information flow between operations. Graphs can be recursively combined into larger composite graphs representing hierarchies of inter-agent collaboration (where edges connect operations of different agents). Our novel automatic graph optimizers (1) refine node-level LLM prompts (node optimization) and (2) improve agent orchestration by changing graph connectivity (edge optimization). Experiments demonstrate that our framework can be used to efficiently develop, integrate, and automatically improve various LLM agents. The code can be found at https://github.com/metauto-ai/gptswarm.
Authors: Xianshi Su, Munan Li, Runze Ma, Jialong Li, Tongbang Jiang, Hao Long
Abstract: Dynamic graphs are extensively employed for detecting anomalous behavior in nodes within the Internet of Things (IoT). Graph generative models are often used to address the issue of imbalanced node categories in dynamic graphs. Neverthe less, the constraints it faces include the monotonicity of adjacency relationships, the difficulty in constructing multi-dimensional features for nodes, and the lack of a method for end-to-end generation of multiple categories of nodes. In this paper, we propose a novel graph generation model, called CGGM, specifically for generating samples belonging to the minority class. The framework consists two core module: a conditional graph generation module and a graph-based anomaly detection module. The generative module adapts to the sparsity of the matrix by downsampling a noise adjacency matrix, and incorporates a multi-dimensional feature encoder based on multi-head self-attention to capture latent dependencies among features. Additionally, a latent space constraint is combined with the distribution distance to approximate the latent distribution of real data. The graph-based anomaly detection module utilizes the generated balanced dataset to predict the node behaviors. Extensive experiments have shown that CGGM outperforms the state-of-the-art methods in terms of accuracy and divergence. The results also demonstrate CGGM can generated diverse data categories, that enhancing the performance of multi-category classification task.
Authors: Maksim Kuprashevich, Grigorii Alekseenko, Irina Tolstykh
Abstract: Multimodal Large Language Models (MLLMs) have recently gained immense popularity. Powerful commercial models like ChatGPT-4V and Gemini, as well as open-source ones such as LLaVA, are essentially general-purpose models and are applied to solve a wide variety of tasks, including those in computer vision. These neural networks possess such strong general knowledge and reasoning abilities that they have proven capable of working even on tasks for which they were not specifically trained. We compared the capabilities of the most powerful MLLMs to date: ShareGPT4V, ChatGPT, LLaVA-Next in a specialized task of age and gender estimation with our state-of-the-art specialized model, MiVOLO. We also updated MiVOLO and provide details and new metrics in this article. This comparison has yielded some interesting results and insights about the strengths and weaknesses of the participating models. Furthermore, we attempted various ways to fine-tune the ShareGPT4V model for this specific task, aiming to achieve state-of-the-art results in this particular challenge. Although such a model would not be practical in production, as it is incredibly expensive compared to a specialized model like MiVOLO, it could be very useful in some tasks, like data annotation.
Authors: Stephen Casper, Lennart Schulze, Oam Patel, Dylan Hadfield-Menell
Abstract: Despite extensive diagnostics and debugging by developers, AI systems sometimes exhibit harmful unintended behaviors. Finding and fixing these is challenging because the attack surface is so large -- it is not tractable to exhaustively search for inputs that may elicit harmful behaviors. Red-teaming and adversarial training (AT) are commonly used to improve robustness, however, they empirically struggle to fix failure modes that differ from the attacks used during training. In this work, we utilize latent adversarial training (LAT) to defend against vulnerabilities without leveraging knowledge of what they are or using inputs that elicit them. LAT makes use of the compressed, abstract, and structured latent representations of concepts that the network actually uses for prediction. Here, we use it to defend against failure modes without examples that elicit them. Specifically, we use LAT to remove trojans and defend against held-out classes of adversarial attacks. We show in image classification, text classification, and text generation tasks that LAT usually improves both robustness to novel attacks and performance on clean data relative to AT. This suggests that LAT can be a promising tool for defending against failure modes that are not explicitly identified by developers.
Authors: Zezhi Wang, Jin Zhu, Peng Chen, Huiyang Peng, Xiaoke Zhang, Anran Wang, Junxian Zhu, Xueqin Wang
Abstract: Applying iterative solvers on sparsity-constrained optimization (SCO) requires tedious mathematical deduction and careful programming/debugging that hinders these solvers' broad impact. In the paper, the library skscope is introduced to overcome such an obstacle. With skscope, users can solve the SCO by just programming the objective function. The convenience of skscope is demonstrated through two examples in the paper, where sparse linear regression and trend filtering are addressed with just four lines of code. More importantly, skscope's efficient implementation allows state-of-the-art solvers to quickly attain the sparse solution regardless of the high dimensionality of parameter space. Numerical experiments reveal the available solvers in skscope can achieve up to 80x speedup on the competing relaxation solutions obtained via the benchmarked convex solver. skscope is published on the Python Package Index (PyPI) and Conda, and its source code is available at: https://github.com/abess-team/skscope.
Authors: Tunazzina Islam, Dan Goldwasser
Abstract: The widespread use of social media has led to a surge in popularity for automated methods of analyzing public opinion. Supervised methods are adept at text categorization, yet the dynamic nature of social media discussions poses a continual challenge for these techniques due to the constant shifting of the focus. On the other hand, traditional unsupervised methods for extracting themes from public discourse, such as topic modeling, often reveal overarching patterns that might not capture specific nuances. Consequently, a significant portion of research into social media discourse still depends on labor-intensive manual coding techniques and a human-in-the-loop approach, which are both time-consuming and costly. In this work, we study the problem of discovering arguments associated with a specific theme. We propose a generic LLMs-in-the-Loop strategy that leverages the advanced capabilities of Large Language Models (LLMs) to extract latent arguments from social media messaging. To demonstrate our approach, we apply our framework to contentious topics. We use two publicly available datasets: (1) the climate campaigns dataset of 14k Facebook ads with 25 themes and (2) the COVID-19 vaccine campaigns dataset of 9k Facebook ads with 14 themes. Additionally, we design a downstream task as stance prediction by leveraging talking points in climate debates. Furthermore, we analyze demographic targeting and the adaptation of messaging based on real-world events.
Authors: Jayaram Raghuram, George Kesidis, David J. Miller
Abstract: Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of such attacks. The poisoning is usually in the form of a (seemingly innocuous) trigger word or phrase inserted into a very small fraction of the fine-tuning samples from a target class. Such backdoor attacks can: alter response sentiment, violate censorship, over-refuse (invoke censorship for legitimate queries), inject false content, or trigger nonsense responses (hallucinations). In this work we investigate the efficacy of instruction fine-tuning backdoor attacks as attack "hyperparameters" are varied under a variety of scenarios, considering: the trigger location in the poisoned examples; robustness to change in the trigger location, partial triggers, and synonym substitutions at test time; attack transfer from one (fine-tuning) domain to a related test domain; and clean-label vs. dirty-label poisoning. Based on our observations, we propose and evaluate two defenses against these attacks: i) a \textit{during-fine-tuning defense} based on word-frequency counts that assumes the (possibly poisoned) fine-tuning dataset is available and identifies the backdoor trigger tokens; and ii) a \textit{post-fine-tuning defense} based on downstream clean fine-tuning of the backdoored LLM with a small defense dataset. Finally, we provide a brief survey of related work on backdoor attacks and defenses.
Authors: Lechen Feng, Yuan-Hua Ni, Xuebo Zhang
Abstract: A $\mathcal{H}_2$-guaranteed decentralized linear-quadratic optimal control with convex parameterization and convex-bounded uncertainty is studied in this paper, where several sparsity promoting functions are added, respectively, into the $\mathcal{H}_2$ cost to penalize the number of communication links among decentralized controllers. Then, the sparse feedback gain is investigated to minimize the modified $\mathcal{H}_2$ cost together with the stability guarantee, and the corresponding main results are of three parts. First, the weighted-$\ell_1$ sparsity promoting function is of concern, and a two-timescale algorithm is developed based on the BSUM (Block Successive Upper-bound Minimization) framework and a primal-dual splitting approach. Second, the optimization problem induced by piecewise quadratic sparsity penalty is investigated, which exhibits an accelerated convergence rate. Third, the nonconvex sparse optimization problem with $\ell_0$-penalty is studied, which can be approximated by successive coordinatewise convex optimization problems.
Authors: Jerry Yao-Chieh Hu, Weimin Wu, Zhao Song, Han Liu
Abstract: We investigate the statistical and computational limits of latent \textbf{Di}ffusion \textbf{T}ransformers (\textbf{DiT}s) under the low-dimensional linear latent space assumption. Statistically, we study the universal approximation and sample complexity of the DiTs score function, as well as the distribution recovery property of the initial data. Specifically, under mild data assumptions, we derive an approximation error bound for the score network of latent DiTs, which is sub-linear in the latent space dimension. Additionally, we derive the corresponding sample complexity bound and show that the data distribution generated from the estimated score function converges toward a proximate area of the original one. Computationally, we characterize the hardness of both forward inference and backward computation of latent DiTs, assuming the Strong Exponential Time Hypothesis (SETH). For forward inference, we identify efficient criteria for all possible latent DiTs inference algorithms and showcase our theory by pushing the efficiency toward almost-linear time inference. For backward computation, we leverage the low-rank structure within the gradient computation of DiTs training for possible algorithmic speedup. Specifically, we show that such speedup achieves almost-linear time latent DiTs training by casting the DiTs gradient as a series of chained low-rank approximations with bounded error. Under the low-dimensional assumption, we show that the convergence rate and the computational efficiency are both dominated by the dimension of the subspace, suggesting that latent DiTs have the potential to bypass the challenges associated with the high dimensionality of initial data.
Authors: Milan Ganai, Sicun Gao, Sylvia Herbert
Abstract: Recent literature has proposed approaches that learn control policies with high performance while maintaining safety guarantees. Synthesizing Hamilton-Jacobi (HJ) reachable sets has become an effective tool for verifying safety and supervising the training of reinforcement learning-based control policies for complex, high-dimensional systems. Previously, HJ reachability was restricted to verifying low-dimensional dynamical systems primarily because the computational complexity of the dynamic programming approach it relied on grows exponentially with the number of system states. In recent years, a litany of proposed methods addresses this limitation by computing the reachability value function simultaneously with learning control policies to scale HJ reachability analysis while still maintaining a reliable estimate of the true reachable set. These HJ reachability approximations are used to improve the safety, and even reward performance, of learned control policies and can solve challenging tasks such as those with dynamic obstacles and/or with lidar-based or vision-based observations. In this survey paper, we review the recent developments in the field of HJ reachability estimation in reinforcement learning that would provide a foundational basis for further research into reliability in high-dimensional systems.
Authors: Yixin Liu, Pengfei Liu, Arman Cohan
Abstract: Direct Preference Optimization (DPO) has become a widely used training method for the instruction fine-tuning of large language models (LLMs). In this work, we explore an under-investigated aspect of DPO - its dependency on the reference model or policy. Such reference policies, typically instantiated as the model to be further fine-tuned, are important since they can impose an upper limit on DPO's effectiveness. Therefore, we address three related research questions in this work. First, we explore the optimal strength of the KL divergence constraint in DPO, which penalizes deviations from the reference policy, and find that DPO is sensitive to this strength. Next, we examine the necessity of the KL-constraint from the reference policies in DPO by providing both theoretical and empirical comparisons between DPO and related learning objectives, demonstrating DPO's superiority in this controlled setting. Additionally, we investigate whether DPO benefits from stronger reference policies, finding that a stronger reference policy can lead to improved performance, but only when it is similar to the model being fine-tuned. Our findings highlight the confounding role of reference policies in DPO and offer insights for best practices, while also identifying open research questions for future studies.
Authors: Claudius Kienle, Benjamin Alt, Onur Celik, Philipp Becker, Darko Katic, Rainer J\"akel, Gerhard Neumann
Abstract: High-level robot skills represent an increasingly popular paradigm in robot programming. However, configuring the skills' parameters for a specific task remains a manual and time-consuming endeavor. Existing approaches for learning or optimizing these parameters often require numerous real-world executions or do not work in dynamic environments. To address these challenges, we propose MuTT, a novel encoder-decoder transformer architecture designed to predict environment-aware executions of robot skills by integrating vision, trajectory, and robot skill parameters. Notably, we pioneer the fusion of vision and trajectory, introducing a novel trajectory projection. Furthermore, we illustrate MuTT's efficacy as a predictor when combined with a model-based robot skill optimizer. This approach facilitates the optimization of robot skill parameters for the current environment, without the need for real-world executions during optimization. Designed for compatibility with any representation of robot skills, MuTT demonstrates its versatility across three comprehensive experiments, showcasing superior performance across two different skill representations.
Authors: Sparsh Gupta, Debanjan Konar, Vaneet Aggarwal
Abstract: Non-local operations play a crucial role in computer vision enabling the capture of long-range dependencies through weighted sums of features across the input, surpassing the constraints of traditional convolution operations that focus solely on local neighborhoods. Non-local operations typically require computing pairwise relationships between all elements in a set, leading to quadratic complexity in terms of time and memory. Due to the high computational and memory demands, scaling non-local neural networks to large-scale problems can be challenging. This article introduces a hybrid quantum-classical scalable non-local neural network, referred to as Quantum Non-Local Neural Network (QNL-Net), to enhance pattern recognition. The proposed QNL-Net relies on inherent quantum parallelism to allow the simultaneous processing of a large number of input features enabling more efficient computations in quantum-enhanced feature space and involving pairwise relationships through quantum entanglement. We benchmark our proposed QNL-Net with other quantum counterparts to binary classification with datasets MNIST and CIFAR-10. The simulation findings showcase our QNL-Net achieves cutting-edge accuracy levels in binary image classification among quantum classifiers while utilizing fewer qubits.
Authors: Jiang Hao, Xiao Jin, Hu Xiaoguang, Chen Tianyou, Zhao Jiajia
Abstract: Diffusion models (DMs) are regarded as one of the most advanced generative models today, yet recent studies suggest that they are vulnerable to backdoor attacks, which establish hidden associations between particular input patterns and model behaviors, compromising model integrity by causing undesirable actions with manipulated inputs. This vulnerability poses substantial risks, including reputational damage to model owners and the dissemination of harmful content. To mitigate the threat of backdoor attacks, there have been some investigations on backdoor detection and model repair. However, previous work fails to reliably purify the models backdoored by state-of-the-art attack methods, rendering the field much underexplored. To bridge this gap, we introduce Diff-Cleanse, a novel two-stage backdoor defense framework specifically designed for DMs. The first stage employs a novel trigger inversion technique to reconstruct the trigger and detect the backdoor, and the second stage utilizes a structural pruning method to eliminate the backdoor. We evaluate our framework on hundreds of DMs that are attacked by three existing backdoor attack methods with a wide range of hyperparameter settings. Extensive experiments demonstrate that Diff-Cleanse achieves nearly 100\% detection accuracy and effectively mitigates backdoor impacts, preserving the model's benign performance with minimal compromise. Our code is avaliable at https://github.com/shymuel/diff-cleanse.
Authors: Mobina Mansoori, Sajjad Shahabodini, Jamshid Abouei, Konstantinos N. Plataniotis, Arash Mohammadi
Abstract: Polyp segmentation plays a crucial role in the early detection and diagnosis of colorectal cancer. However, obtaining accurate segmentations often requires labor-intensive annotations and specialized models. Recently, Meta AI Research released a general Segment Anything Model 2 (SAM 2), which has demonstrated promising performance in several segmentation tasks. In this work, we evaluate the performance of SAM 2 in segmenting polyps under various prompted settings. We hope this report will provide insights to advance the field of polyp segmentation and promote more interesting work in the future. This project is publicly available at https://github.com/ sajjad-sh33/Polyp-SAM-2.
URLs: https://github.com/
Authors: Jiahui Jin, Yifan Song, Dong Kan, Haojia Zhu, Xiangguo Sun, Zhicheng Li, Xigang Sun, Jinghui Zhang
Abstract: Urban region representation is crucial for various urban downstream tasks. However, despite the proliferation of methods and their success, acquiring general urban region knowledge and adapting to different tasks remains challenging. Previous work often neglects the spatial structures and functional layouts between entities, limiting their ability to capture transferable knowledge across regions. Further, these methods struggle to adapt effectively to specific downstream tasks, as they do not adequately address the unique features and relationships required for different downstream tasks. In this paper, we propose a $\textbf{G}$raph-based $\textbf{U}$rban $\textbf{R}$egion $\textbf{P}$re-training and $\textbf{P}$rompting framework ($\textbf{GURPP}$) for region representation learning. Specifically, we first construct an urban region graph that integrates detailed spatial entity data for more effective urban region representation. Then, we develop a subgraph-centric urban region pre-training model to capture the heterogeneous and transferable patterns of interactions among entities. To further enhance the adaptability of these embeddings to different tasks, we design two graph-based prompting methods to incorporate explicit/hidden task knowledge. Extensive experiments on various urban region prediction tasks and different cities demonstrate the superior performance of our GURPP framework. We wil release code and data upon paper notification.
Authors: Nayely V\'elez-Cruz, Manfred D. Laubichler
Abstract: The ubiquity of multiscale interactions in complex systems is well-recognized, with development and heredity serving as a prime example of how processes at different temporal scales influence one another. This work introduces a novel multiscale state-space model to explore the dynamic interplay between systems interacting across different time scales, with feedback between each scale. We propose a Bayesian learning framework to estimate unknown states by learning the unknown process noise covariances within this multiscale model. We develop a Particle Gibbs with Ancestor Sampling (PGAS) algorithm for inference and demonstrate through simulations the efficacy of our approach.
Authors: Cho Yang
Abstract: CycleGAN was trained on SynthRAD Grand Challenge Dataset using the single-epoch modification (SEM) method proposed in this paper which is referred to as (CycleGAN-single) compared to the usual method of training CycleGAN on around 200 epochs (CycleGAN-multi). Model performance were evaluated qualitatively and quantitatively with quantitative performance metrics like PSNR, SSIM, MAE and MSE. The consideration of both quantitative and qualitative performance when evaluating a model is unique to certain image-to-image translation tasks like medical imaging of patient data as detailed in this paper. Also, this paper shows that good quantitative performance does not always imply good qualitative performance and the converse is also not always True (i.e. good qualitative performance does not always imply good quantitative performance). This paper also proposes a lightweight model called FQGA (Fast Paired Image-to-Image Translation Quarter-Generator Adversary) which has 1/4 the number of parameters compared to CycleGAN (when comparing their Generator Models). FQGA outperforms CycleGAN qualitatively and quantitatively even only after training on 20 epochs. Finally, using SEM method on FQGA allowed it to again outperform CycleGAN both quantitatively and qualitatively. These performance gains even with fewer model parameters and fewer epochs (which will result in time and computational savings) may also be applicable to other image-to-image translation tasks in Machine Learning apart from the Medical image-translation task discussed in this paper between Cone Beam Computed Tomography (CBCT) and Computed Tomography (CT) images.
Authors: Yaoze Zhang, Yuming Zhang, Yu Zhao, Yue Zhang, Feiyu Zhu
Abstract: Knowledge distillation is widely applied in various fundamental vision models to enhance the performance of compact models. Existing knowledge distillation methods focus on designing different distillation targets to acquire knowledge from teacher models. However, these methods often overlook the efficient utilization of distilled information, crudely coupling different types of information, making it difficult to explain how the knowledge from the teacher network aids the student network in learning. This paper proposes a novel knowledge distillation framework, Local Attention Knowledge Distillation (LAKD), which more efficiently utilizes the distilled information from teacher networks, achieving higher interpretability and competitive performance. The framework establishes an independent interactive training mechanism through a separation-decoupling mechanism and non-directional activation mapping. LAKD decouples the teacher's features and facilitates progressive interaction training from simple to complex. Specifically, the student network is divided into local modules with independent gradients to decouple the knowledge transferred from the teacher. The non-directional activation mapping helps the student network integrate knowledge from different local modules by learning coarse-grained feature knowledge. We conducted experiments on the CIFAR-10, CIFAR-100, and ImageNet datasets, and the results show that our LAKD method significantly outperforms existing methods, consistently achieving state-of-the-art performance across different datasets.
Authors: Alireza Ghazavi Khorasgani, Mahtab Mirmohseni, Ahmed Elzanaty
Abstract: This paper characterizes the optimal capacity-distortion (C-D) tradeoff in an optical point-to-point (P2P) system with single-input single-output for communication and single-input multiple-output for sensing (SISO-COM and SIMO-SEN) within an integrated sensing and communication (ISAC) framework. We consider the optimal rate-distortion (R-D) region and explore several inner (IB) and outer (OB) bounds. We introduce practical, asymptotically optimal maximum a posteriori (MAP) and maximum likelihood estimators (MLE) for target distance, addressing nonlinear measurement-to-state relationships and non-conjugate priors. As the number of sensing antennas increases, these estimators converge to the Bayesian Cram\'er-Rao bound (BCRB). We also establish that the achievable rate-CRB (AR-CRB) serves as an OB for the optimal C-D region, valid for both unbiased estimators and asymptotically large numbers of receive antennas. To clarify that the input distribution determines the tradeoff across the Pareto boundary of the C-D region, we propose two algorithms: \textit{i}) an iterative Blahut-Arimoto algorithm (BAA)-type method, and \textit{ii}) a memory-efficient closed-form (CF) approach. The CF approach includes a CF optimal distribution for high optical signal-to-noise ratio (O-SNR) conditions. Additionally, we adapt and refine the Deterministic-Random Tradeoff (DRT) to this optical ISAC context.