Authors: Shaoning Li, Mingyu Li, Yusong Wang, Xinheng He, Nanning Zheng, Jian Zhang, Pheng-Ann Heng
Abstract: Investigating conformational landscapes of proteins is a crucial way to understand their biological functions and properties. AlphaFlow stands out as a sequence-conditioned generative model that introduces flexibility into structure prediction models by fine-tuning AlphaFold under the flow-matching framework. Despite the advantages of efficient sampling afforded by flow-matching, AlphaFlow still requires multiple runs of AlphaFold to finally generate one single conformation. Due to the heavy consumption of AlphaFold, its applicability is limited in sampling larger set of protein ensembles or the longer chains within a constrained timeframe. In this work, we propose a feature-conditioned generative model called AlphaFlow-Lit to realize efficient protein ensembles generation. In contrast to the full fine-tuning on the entire structure, we focus solely on the light-weight structure module to reconstruct the conformation. AlphaFlow-Lit performs on-par with AlphaFlow and surpasses its distilled version without pretraining, all while achieving a significant sampling acceleration of around 47 times. The advancement in efficiency showcases the potential of AlphaFlow-Lit in enabling faster and more scalable generation of protein ensembles.
Authors: Mohammed Alruqimi, Luca Di Persio
Abstract: Accurate crude oil price forecasting is crucial for various economic activities, including energy trading, risk management, and investment planning. Although deep learning models have emerged as powerful tools for crude oil price forecasting, achieving accurate forecasts remains challenging. Deep learning models' performance is heavily influenced by hyperparameters tuning, and they are expected to perform differently under various circumstances. Furthermore, price volatility is also sensitive to external factors such as world events. To address these limitations, we propose a hybrid approach combining metaheuristic optimisation and an ensemble of five popular neural network architectures used in time series forecasting. Unlike existing methods that apply metaheuristics to optimise hyperparameters within the neural network architecture, we exploit the GWO metaheuristic optimiser at four levels: feature selection, data preparation, model training, and forecast blending. The proposed approach has been evaluated for forecasting three-ahead days using real-world Brent crude oil price data, and the obtained results demonstrate that the proposed approach improves the forecasting performance measured using various benchmarks, achieving 0.000127 of MSE.
Authors: Linh Trinh, Ali Anwar, Siegfried Mercelis
Abstract: As the popularity of autonomous vehicles has grown, many standards and regulators, such as ISO, NHTSA, and Euro NCAP, require safety validation to ensure a sufficient level of safety before deploying them in the real world. Manufacturers gather a large amount of public road data for this purpose. However, the majority of these validation activities are done manually by humans. Furthermore, the data used to validate each driving feature may differ. As a result, it is essential to have an efficient data selection method that can be used flexibly and dynamically for verification and validation while also accelerating the validation process. In this paper, we present a data selection method that is practical, flexible, and efficient for assessment of autonomous vehicles. Our idea is to optimize the similarity between the metadata distribution of the selected data and a predefined metadata distribution that is expected for validation. Our experiments on the large dataset BDD100K show that our method can perform data selection tasks efficiently. These results demonstrate that our methods are highly reliable and can be used to select appropriate data for the validation of various safety functions.
Authors: Kai Guo, Zewen Liu, Zhikai Chen, Hongzhi Wen, Wei Jin, Jiliang Tang, Yi Chang
Abstract: Large Language Models (LLMs) have demonstrated remarkable performance across various natural language processing tasks. Recently, several LLMs-based pipelines have been developed to enhance learning on graphs with text attributes, showcasing promising performance. However, graphs are well-known to be susceptible to adversarial attacks and it remains unclear whether LLMs exhibit robustness in learning on graphs. To address this gap, our work aims to explore the potential of LLMs in the context of adversarial attacks on graphs. Specifically, we investigate the robustness against graph structural and textual perturbations in terms of two dimensions: LLMs-as-Enhancers and LLMs-as-Predictors. Through extensive experiments, we find that, compared to shallow models, both LLMs-as-Enhancers and LLMs-as-Predictors offer superior robustness against structural and textual attacks.Based on these findings, we carried out additional analyses to investigate the underlying causes. Furthermore, we have made our benchmark library openly available to facilitate quick and fair evaluations, and to encourage ongoing innovative research in this field.
Authors: Yuhao Ji, Chao Fang, Shaobo Ma, Haikuo Shao, Zhongfeng Wang
Abstract: Transformer models have revolutionized AI tasks, but their large size hinders real-world deployment on resource-constrained and latency-critical edge devices. While binarized Transformers offer a promising solution by significantly reducing model size, existing approaches suffer from algorithm-hardware mismatches with limited co-design exploration, leading to suboptimal performance on edge devices. Hence, we propose a co-design method for efficient end-to-end edge deployment of Transformers from three aspects: algorithm, hardware, and joint optimization. First, we propose BMT, a novel hardware-friendly binarized Transformer with optimized quantization methods and components, and we further enhance its model accuracy by leveraging the weighted ternary weight splitting training technique. Second, we develop a streaming processor mixed binarized Transformer accelerator, namely BAT, which is equipped with specialized units and scheduling pipelines for efficient inference of binarized Transformers. Finally, we co-optimize the algorithm and hardware through a design space exploration approach to achieve a global trade-off between accuracy, latency, and robustness for real-world deployments. Experimental results show our co-design achieves up to 2.14-49.37x throughput gains and 3.72-88.53x better energy efficiency over state-of-the-art Transformer accelerators, enabling efficient end-to-end edge deployment.
Authors: Yuzhu Mao, Siqi Ping, Zihao Zhao, Yang Liu, Wenbo Ding
Abstract: Large pre-trained models, such as large language models (LLMs), present significant resource challenges for fine-tuning due to their extensive parameter sizes, especially for applications in mobile systems. To address this, Low-Rank Adaptation (LoRA) has been developed to reduce resource consumption while maintaining satisfactory fine-tuning results. Despite its effectiveness, the original LoRA method faces challenges of suboptimal performance and overfitting. This paper investigates the intrinsic dimension of the matrix updates approximated by the LoRA method and reveals the performance benefits of increasing this intrinsic dimension. By employing regularization and a gradient masking method that encourages higher intrinsic dimension, the proposed method, termed Regularized and Masked LoRA (RM-LoRA), achieves superior generalization performance with the same or lower trainable parameter budget compared to the original LoRA and its latest variants across various open-source vision and language datasets.
Authors: Matt Gorbett, Hossein Shirazi, Indrakshi Ray
Abstract: Binary Neural Networks (BNNs) enable efficient deep learning by saving on storage and computational costs. However, as the size of neural networks continues to grow, meeting computational requirements remains a challenge. In this work, we propose a new form of quantization to tile neural network layers with sequences of bits to achieve sub-bit compression of binary-weighted neural networks. The method learns binary vectors (i.e. tiles) to populate each layer of a model via aggregation and reshaping operations. During inference, the method reuses a single tile per layer to represent the full tensor. We employ the approach to both fully-connected and convolutional layers, which make up the breadth of space in most neural architectures. Empirically, the approach achieves near fullprecision performance on a diverse range of architectures (CNNs, Transformers, MLPs) and tasks (classification, segmentation, and time series forecasting) with up to an 8x reduction in size compared to binary-weighted models. We provide two implementations for Tiled Bit Networks: 1) we deploy the model to a microcontroller to assess its feasibility in resource-constrained environments, and 2) a GPU-compatible inference kernel to facilitate the reuse of a single tile per layer in memory.
Authors: Kareem Amin, Alex Bie, Weiwei Kong, Alexey Kurakin, Natalia Ponomareva, Umar Syed, Andreas Terzis, Sergei Vassilvitskii
Abstract: We present an approach for generating differentially private synthetic text using large language models (LLMs), via private prediction. In the private prediction framework, we only require the output synthetic data to satisfy differential privacy guarantees. This is in contrast to approaches that train a generative model on potentially sensitive user-supplied source data and seek to ensure the model itself is safe to release. We prompt a pretrained LLM with source data, but ensure that next-token predictions are made with differential privacy guarantees. Previous work in this paradigm reported generating a small number of examples (<10) at reasonable privacy levels, an amount of data that is useful only for downstream in-context learning or prompting. In contrast, we make changes that allow us to generate thousands of high-quality synthetic data points, greatly expanding the set of potential applications. Our improvements come from an improved privacy analysis and a better private selection mechanism, which makes use of the equivalence between the softmax layer for sampling tokens in LLMs and the exponential mechanism. Furthermore, we introduce a novel use of public predictions via the sparse vector technique, in which we do not pay privacy costs for tokens that are predictable without sensitive data; we find this to be particularly effective for structured data.
Authors: Yushun Dong, Song Wang, Zhenyu Lei, Zaiyi Zheng, Jing Ma, Chen Chen, Jundong Li
Abstract: Fairness-aware graph learning has gained increasing attention in recent years. Nevertheless, there lacks a comprehensive benchmark to evaluate and compare different fairness-aware graph learning methods, which blocks practitioners from choosing appropriate ones for broader real-world applications. In this paper, we present an extensive benchmark on ten representative fairness-aware graph learning methods. Specifically, we design a systematic evaluation protocol and conduct experiments on seven real-world datasets to evaluate these methods from multiple perspectives, including group fairness, individual fairness, the balance between different fairness criteria, and computational efficiency. Our in-depth analysis reveals key insights into the strengths and limitations of existing methods. Additionally, we provide practical guidance for applying fairness-aware graph learning methods in applications. To the best of our knowledge, this work serves as an initial step towards comprehensively understanding representative fairness-aware graph learning methods to facilitate future advancements in this area.
Authors: Prithvi Poddar, Steve Paul, Souma Chowdhury
Abstract: The advent of Urban Air Mobility (UAM) presents the scope for a transformative shift in the domain of urban transportation. However, its widespread adoption and economic viability depends in part on the ability to optimally schedule the fleet of aircraft across vertiports in a UAM network, under uncertainties attributed to airspace congestion, changing weather conditions, and varying demands. This paper presents a comprehensive optimization formulation of the fleet scheduling problem, while also identifying the need for alternate solution approaches, since directly solving the resulting integer nonlinear programming problem is computationally prohibitive for daily fleet scheduling. Previous work has shown the effectiveness of using (graph) reinforcement learning (RL) approaches to train real-time executable policy models for fleet scheduling. However, such policies can often be brittle on out-of-distribution scenarios or edge cases. Moreover, training performance also deteriorates as the complexity (e.g., number of constraints) of the problem increases. To address these issues, this paper presents an imitation learning approach where the RL-based policy exploits expert demonstrations yielded by solving the exact optimization using a Genetic Algorithm. The policy model comprises Graph Neural Network (GNN) based encoders that embed the space of vertiports and aircraft, Transformer networks to encode demand, passenger fare, and transport cost profiles, and a Multi-head attention (MHA) based decoder. Expert demonstrations are used through the Generative Adversarial Imitation Learning (GAIL) algorithm. Interfaced with a UAM simulation environment involving 8 vertiports and 40 aircrafts, in terms of the daily profits earned reward, the new imitative approach achieves better mean performance and remarkable improvement in the case of unseen worst-case scenarios, compared to pure RL results.
Authors: Pinxue Zhao, Hailin Zhang, Fangcheng Fu, Xiaonan Nie, Qibin Liu, Fang Yang, Yuanbo Peng, Dian Jiao, Shuaipeng Li, Jinbao Xue, Yangyu Tao, Bin Cui
Abstract: Nowadays, Large Language Models (LLMs) have been trained using extended context lengths to foster more creative applications. However, long context training poses great challenges considering the constraint of GPU memory. It not only leads to substantial activation memory consumption during training, but also incurs considerable memory fragmentation. To facilitate long context training, existing frameworks have adopted strategies such as recomputation and various forms of parallelisms. Nevertheless, these techniques rely on redundant computation or extensive communication, resulting in low Model FLOPS Utilization (MFU). In this paper, we propose MEMO, a novel LLM training framework designed for fine-grained activation memory management. Given the quadratic scaling of computation and linear scaling of memory with sequence lengths when using FlashAttention, we offload memory-consuming activations to CPU memory after each layer's forward pass and fetch them during the backward pass. To maximize the swapping of activations without hindering computation, and to avoid exhausting limited CPU memory, we implement a token-wise activation recomputation and swapping mechanism. Furthermore, we tackle the memory fragmentation issue by employing a bi-level Mixed Integer Programming (MIP) approach, optimizing the reuse of memory across transformer layers. Empirical results demonstrate that MEMO achieves an average of 2.42x and 2.26x MFU compared to Megatron-LM and DeepSpeed, respectively. This improvement is attributed to MEMO's ability to minimize memory fragmentation, reduce recomputation and intensive communication, and circumvent the delays associated with the memory reorganization process due to fragmentation. By leveraging fine-grained activation memory management, MEMO facilitates efficient training of 7B LLM with 1 million sequence length on just 8 A800 GPUs, achieving an MFU of 52.30%.
Authors: Ziqiang Wang, Zhixiang Chi, Yanan Wu, Li Gu, Zhi Liu, Konstantinos Plataniotis, Yang Wang
Abstract: Given a model trained on source data, Test-Time Adaptation (TTA) enables adaptation and inference in test data streams with domain shifts from the source. Current methods predominantly optimize the model for each incoming test data batch using self-training loss. While these methods yield commendable results in ideal test data streams, where batches are independently and identically sampled from the target distribution, they falter under more practical test data streams that are not independent and identically distributed (non-i.i.d.). The data batches in a non-i.i.d. stream display prominent label shifts relative to each other. It leads to conflicting optimization objectives among batches during the TTA process. Given the inherent risks of adapting the source model to unpredictable test-time distributions, we reverse the adaptation process and propose a novel Distribution Alignment loss for TTA. This loss guides the distributions of test-time features back towards the source distributions, which ensures compatibility with the well-trained source model and eliminates the pitfalls associated with conflicting optimization objectives. Moreover, we devise a domain shift detection mechanism to extend the success of our proposed TTA method in the continual domain shift scenarios. Our extensive experiments validate the logic and efficacy of our method. On six benchmark datasets, we surpass existing methods in non-i.i.d. scenarios and maintain competitive performance under the ideal i.i.d. assumption.
Authors: Jakub Adamczyk, Wojciech Czech
Abstract: We revisit the effectiveness of topological descriptors for molecular graph classification and design a simple, yet strong baseline. We demonstrate that a simple approach to feature engineering - employing histogram aggregation of edge descriptors and one-hot encoding for atomic numbers and bond types - when combined with a Random Forest classifier, can establish a strong baseline for Graph Neural Networks (GNNs). The novel algorithm, Molecular Topological Profile (MOLTOP), integrates Edge Betweenness Centrality, Adjusted Rand Index and SCAN Structural Similarity score. This approach proves to be remarkably competitive when compared to modern GNNs, while also being simple, fast, low-variance and hyperparameter-free. Our approach is rigorously tested on MoleculeNet datasets using fair evaluation protocol provided by Open Graph Benchmark. We additionally show out-of-domain generation capabilities on peptide classification task from Long Range Graph Benchmark. The evaluations across eleven benchmark datasets reveal MOLTOP's strong discriminative capabilities, surpassing the $1$-WL test and even $3$-WL test for some classes of graphs. Our conclusion is that descriptor-based baselines, such as the one we propose, are still crucial for accurately assessing advancements in the GNN domain.
Authors: Liam Schramm, Abdeslam Boularias
Abstract: Diffusion models have seen tremendous success as generative architectures. Recently, they have been shown to be effective at modelling policies for offline reinforcement learning and imitation learning. We explore using diffusion as a model class for the successor state measure (SSM) of a policy. We find that enforcing the Bellman flow constraints leads to a simple Bellman update on the diffusion step distribution.
Authors: Junqi Yin, Siming Liang, Siyan Liu, Feng Bao, Hristo G. Chipilski, Dan Lu, Guannan Zhang
Abstract: The weather and climate domains are undergoing a significant transformation thanks to advances in AI-based foundation models such as FourCastNet, GraphCast, ClimaX and Pangu-Weather. While these models show considerable potential, they are not ready yet for operational use in weather forecasting or climate prediction. This is due to the lack of a data assimilation method as part of their workflow to enable the assimilation of incoming Earth system observations in real time. This limitation affects their effectiveness in predicting complex atmospheric phenomena such as tropical cyclones and atmospheric rivers. To overcome these obstacles, we introduce a generic real-time data assimilation framework and demonstrate its end-to-end performance on the Frontier supercomputer. This framework comprises two primary modules: an ensemble score filter (EnSF), which significantly outperforms the state-of-the-art data assimilation method, namely, the Local Ensemble Transform Kalman Filter (LETKF); and a vision transformer-based surrogate capable of real-time adaptation through the integration of observational data. The ViT surrogate can represent either physics-based models or AI-based foundation models. We demonstrate both the strong and weak scaling of our framework up to 1024 GPUs on the Exascale supercomputer, Frontier. Our results not only illustrate the framework's exceptional scalability on high-performance computing systems, but also demonstrate the importance of supercomputers in real-time data assimilation for weather and climate predictions. Even though the proposed framework is tested only on a benchmark surface quasi-geostrophic (SQG) turbulence system, it has the potential to be combined with existing AI-based foundation models, making it suitable for future operational implementations.
Authors: Ahmed M Salih, Yuhe Wang
Abstract: Explainable artificial intelligence (XAI) is a set of tools and algorithms that applied or embedded to machine learning models to understand and interpret the models. They are recommended especially for complex or advanced models including deep neural network because they are not interpretable from human point of view. On the other hand, simple models including linear regression are easy to implement, has less computational complexity and easy to visualize the output. The common notion in the literature that simple models including linear regression are considered as "white box" because they are more interpretable and easier to understand. This is based on the idea that linear regression models have several favorable outcomes including the effect of the features in the model and whether they affect positively or negatively toward model output. Moreover, uncertainty of the model can be measured or estimated using the confidence interval. However, we argue that this perception is not accurate and linear regression models are not easy to interpret neither easy to understand considering common XAI metrics and possible challenges might face. This includes linearity, local explanation, multicollinearity, covariates, normalization, uncertainty, features contribution and fairness. Consequently, we recommend the so-called simple models should be treated equally to complex models when it comes to explainability and interpretability.
Authors: Dilip Arumugam, Wanqiao Xu, Benjamin Van Roy
Abstract: A sequential decision-making agent balances between exploring to gain new knowledge about an environment and exploiting current knowledge to maximize immediate reward. For environments studied in the traditional literature, optimal decisions gravitate over time toward exploitation as the agent accumulates sufficient knowledge and the benefits of further exploration vanish. What if, however, the environment offers an unlimited amount of useful knowledge and there is large benefit to further exploration no matter how much the agent has learned? We offer a simple, quintessential example of such a complex environment. In this environment, rewards are unbounded and an agent can always increase the rate at which rewards accumulate by exploring to learn more. Consequently, an optimal agent forever maintains a propensity to explore.
Authors: Dilip Arumugam, Saurabh Kumar, Ramki Gummadi, Benjamin Van Roy
Abstract: A default assumption in the design of reinforcement-learning algorithms is that a decision-making agent always explores to learn optimal behavior. In sufficiently complex environments that approach the vastness and scale of the real world, however, attaining optimal performance may in fact be an entirely intractable endeavor and an agent may seldom find itself in a position to complete the requisite exploration for identifying an optimal policy. Recent work has leveraged tools from information theory to design agents that deliberately forgo optimal solutions in favor of sufficiently-satisfying or satisficing solutions, obtained through lossy compression. Notably, such agents may employ fundamentally different exploratory decisions to learn satisficing behaviors more efficiently than optimal ones that are more data intensive. While supported by a rigorous corroborating theory, the underlying algorithm relies on model-based planning, drastically limiting the compatibility of these ideas with function approximation and high-dimensional observations. In this work, we remedy this issue by extending an agent that directly represents uncertainty over the optimal value function allowing it to both bypass the need for model-based planning and to learn satisficing policies. We provide simple yet illustrative experiments that demonstrate how our algorithm enables deep reinforcement-learning agents to achieve satisficing behaviors. In keeping with previous work on this setting for multi-armed bandits, we additionally find that our algorithm is capable of synthesizing optimal behaviors, when feasible, more efficiently than its non-information-theoretic counterpart.
Authors: Zachariah Carmichael, Timothy Redgrave, Daniel Gonzalez Cedre, Walter J. Scheirer
Abstract: We combine concept-based neural networks with generative, flow-based classifiers into a novel, intrinsically explainable, exactly invertible approach to supervised learning. Prototypical neural networks, a type of concept-based neural network, represent an exciting way forward in realizing human-comprehensible machine learning without concept annotations, but a human-machine semantic gap continues to haunt current approaches. We find that reliance on indirect interpretation functions for prototypical explanations imposes a severe limit on prototypes' informative power. From this, we posit that invertibly learning prototypes as distributions over the latent space provides more robust, expressive, and interpretable modeling. We propose one such model, called ProtoFlow, by composing a normalizing flow with Gaussian mixture models. ProtoFlow (1) sets a new state-of-the-art in joint generative and predictive modeling and (2) achieves predictive performance comparable to existing prototypical neural networks while enabling richer interpretation.
Authors: Mohammed Fellaji, Fr\'ed\'eric Pennerath, Brieuc Conan-Guez, Miguel Couceiro
Abstract: The calibration of predictive distributions has been widely studied in deep learning, but the same cannot be said about the more specific epistemic uncertainty as produced by Deep Ensembles, Bayesian Deep Networks, or Evidential Deep Networks. Although measurable, this form of uncertainty is difficult to calibrate on an objective basis as it depends on the prior for which a variety of choices exist. Nevertheless, epistemic uncertainty must in all cases satisfy two formal requirements: first, it must decrease when the training dataset gets larger and, second, it must increase when the model expressiveness grows. Despite these expectations, our experimental study shows that on several reference datasets and models, measures of epistemic uncertainty violate these requirements, sometimes presenting trends completely opposite to those expected. These paradoxes between expectation and reality raise the question of the true utility of epistemic uncertainty as estimated by these models. A formal argument suggests that this disagreement is due to a poor approximation of the posterior distribution rather than to a flaw in the measure itself. Based on this observation, we propose a regularization function for deep ensembles, called conflictual loss in line with the above requirements. We emphasize its strengths by showing experimentally that it restores both requirements of epistemic uncertainty, without sacrificing either the performance or the calibration of the deep ensembles.
Authors: Wonho Bae, Junhyug Noh, Danica J. Sutherland
Abstract: The ProbCover method of Yehuda et al. is a well-motivated algorithm for active learning in low-budget regimes, which attempts to "cover" the data distribution with balls of a given radius at selected data points. We demonstrate, however, that the performance of this algorithm is extremely sensitive to the choice of this radius hyper-parameter, and that tuning it is quite difficult, with the original heuristic frequently failing. We thus introduce (and theoretically motivate) a generalized notion of "coverage," including ProbCover's objective as a special case, but also allowing smoother notions that are far more robust to hyper-parameter choice. We propose an efficient greedy method to optimize this coverage, generalizing ProbCover's algorithm; due to its close connection to kernel herding, we call it "MaxHerding." The objective can also be optimized non-greedily through a variant of $k$-medoids, clarifying the relationship to other low-budget active learning methods. In comprehensive experiments, MaxHerding surpasses existing active learning methods across multiple low-budget image classification benchmarks, and does so with less computational cost than most competitive methods.
Authors: Gavin Leech, Juan J. Vazquez, Misha Yagudin, Niclas Kupper, Laurence Aitchison
Abstract: Evaluating modern ML models is hard. The strong incentive for researchers and companies to report a state-of-the-art result on some metric often leads to questionable research practices (QRPs): bad practices which fall short of outright research fraud. We describe 43 such practices which can undermine reported results, giving examples where possible. Our list emphasises the evaluation of large language models (LLMs) on public benchmarks. We also discuss "irreproducible research practices", i.e. decisions that make it difficult or impossible for other researchers to reproduce, build on or audit previous research.
Authors: Chengzhi Lin, Shuchang Liu, Chuyuan Wang, Yongqi Liu
Abstract: Within the domain of short video recommendation, predicting users' watch time is a critical but challenging task. Prevailing deterministic solutions obtain accurate debiased statistical models, yet they neglect the intrinsic uncertainty inherent in user environments. In our observation, we found that this uncertainty could potentially limit these methods' accuracy in watch-time prediction on our online platform, despite that we have employed numerous features and complex network architectures. Consequently, we believe that a better solution is to model the conditional distribution of this uncertain watch time. In this paper, we introduce a novel estimation technique -- Conditional Quantile Estimation (CQE), which utilizes quantile regression to capture the nuanced distribution of watch time. The learned distribution accounts for the stochastic nature of users, thereby it provides a more accurate and robust estimation. In addition, we also design several strategies to enhance the quantile prediction including conditional expectation, conservative estimation, and dynamic quantile combination. We verify the effectiveness of our method through extensive offline evaluations using public datasets as well as deployment in a real-world video application with over 300 million daily active users.
Authors: Hang Chen, Collin Meese, Mark Nejad, Chien-Chung Shen
Abstract: Low-latency traffic prediction is vital for smart city traffic management. Federated Learning has emerged as a promising technique for Traffic Prediction (FLTP), offering several advantages such as privacy preservation, reduced communication overhead, improved prediction accuracy, and enhanced adaptability to changing traffic conditions. However, majority of the current FLTP frameworks lack a real-time model updating scheme, which hinders their ability to continuously incorporate new incoming traffic data and adapt effectively to the changing dynamics of traffic trends. Another concern with the existing FLTP frameworks is their reliance on the conventional FL model aggregation method, which involves assigning an identical model (i.e., the global model) to all traffic monitoring devices to predict their individual local traffic trends, thereby neglecting the non-IID characteristics of traffic data collected in different locations. Building upon these findings and harnessing insights from reinforcement learning, we propose NeighborFL, an individualized real-time federated learning scheme that introduces a haversine distance-based and error-driven, personalized local models grouping heuristic from the perspective of each individual traffic node. This approach allows NeighborFL to create location-aware and tailored prediction models for each client while fostering collaborative learning. Simulations demonstrate the effectiveness of NeighborFL, offering improved real-time prediction accuracy over three baseline models, with one experimental setting showing a 16.9% reduction in MSE value compared to a naive FL setting.
Authors: Xingzi Xu, Ali Hasan, Jie Ding, Vahid Tarokh
Abstract: Parabolic partial differential equations (PDEs) appear in many disciplines to model the evolution of various mathematical objects, such as probability flows, value functions in control theory, and derivative prices in finance. It is often necessary to compute the solutions or a function of the solutions to a parametric PDE in multiple scenarios corresponding to different parameters of this PDE. This process often requires resolving the PDEs from scratch, which is time-consuming. To better employ existing simulations for the PDEs, we propose a framework for finding solutions to parabolic PDEs across different scenarios by meta-learning an underlying base distribution. We build upon this base distribution to propose a method for computing solutions to parametric PDEs under different parameter settings. Finally, we illustrate the application of the proposed methods through extensive experiments in generative modeling, stochastic control, and finance. The empirical results suggest that the proposed approach improves generalization to solving PDEs under new parameter regimes.
Authors: Mayur Patil, Qadeer Ahmed, Shawn Midlam-Mohler
Abstract: Traffic flow prediction is a big challenge for transportation authorities as it helps in planning and developing better infrastructure. State-of-the-art models often struggle to consider the data in the best way possible, intrinsic uncertainties, and the actual physics of the traffic. In this study, we propose a novel framework to incorporate travel times between stations into a weighted adjacency matrix of a Graph Neural Network (GNN) architecture with information from traffic stations based on their data availability. To handle uncertainty, we utilized the Adaptive Conformal Prediction (ACP) method that adjusts prediction intervals based on real-time validation residuals. To validate our results, we model a microscopic traffic scenario and perform a Monte-Carlo simulation to get a travel time distribution for a Vehicle Under Test (VUT) while it is navigating the traffic scenario, and this distribution is compared against the actual data. Experiments show that the proposed model outperformed the next-best model by approximately 24% in MAE and 8% in RMSE and validation showed the simulated travel time closely matches the 95th percentile of the observed travel time value.
Authors: Kien X. Nguyen, Fengchun Qiao, Xi Peng
Abstract: We study the problem of continual test-time adaption where the goal is to adapt a source pre-trained model to a sequence of unlabelled target domains at test time. Existing methods on test-time training suffer from several limitations: (1) Mismatch between the feature extractor and classifier; (2) Interference between the main and self-supervised tasks; (3) Lack of the ability to quickly adapt to the current distribution. In light of these challenges, we propose a cascading paradigm that simultaneously updates the feature extractor and classifier at test time, mitigating the mismatch between them and enabling long-term model adaptation. The pre-training of our model is structured within a meta-learning framework, thereby minimizing the interference between the main and self-supervised tasks and encouraging fast adaptation in the presence of limited unlabelled data. Additionally, we introduce innovative evaluation metrics, average accuracy and forward transfer, to effectively measure the model's adaptation capabilities in dynamic, real-world scenarios. Extensive experiments and ablation studies demonstrate the superiority of our approach in a range of tasks including image classification, text classification, and speech recognition.
Authors: Biagio La Rosa
Abstract: Despite their impact on the society, deep neural networks are often regarded as black-box models due to their intricate structures and the absence of explanations for their decisions. This opacity poses a significant challenge to AI systems wider adoption and trustworthiness. This thesis addresses this issue by contributing to the field of eXplainable AI, focusing on enhancing the interpretability of deep neural networks. The core contributions lie in introducing novel techniques aimed at making these networks more interpretable by leveraging an analysis of their inner workings. Specifically, the contributions are threefold. Firstly, the thesis introduces designs for self-explanatory deep neural networks, such as the integration of external memory for interpretability purposes and the usage of prototype and constraint-based layers across several domains. Secondly, this research delves into novel investigations on neurons within trained deep neural networks, shedding light on overlooked phenomena related to their activation values. Lastly, the thesis conducts an analysis of the application of explanatory techniques in the field of visual analytics, exploring the maturity of their adoption and the potential of these systems to convey explanations to users effectively.
Authors: Ting-Yun Ou, Ching Chang, Wen-Chih Peng
Abstract: Understanding causal relationships between machines is crucial for fault diagnosis and optimization in manufacturing processes. Real-world datasets frequently exhibit up to 90% missing data and high dimensionality from hundreds of sensors. These datasets also include domain-specific expert knowledge and chronological order information, reflecting the recording order across different machines, which is pivotal for discerning causal relationships within the manufacturing data. However, previous methods for handling missing data in scenarios akin to real-world conditions have not been able to effectively utilize expert knowledge. Conversely, prior methods that can incorporate expert knowledge struggle with datasets that exhibit missing values. Therefore, we propose COKE to construct causal graphs in manufacturing datasets by leveraging expert knowledge and chronological order among sensors without imputing missing data. Utilizing the characteristics of the recipe, we maximize the use of samples with missing values, derive embeddings from intersections with an initial graph that incorporates expert knowledge and chronological order, and create a sensor ordering graph. The graph-generating process has been optimized by an actor-critic architecture to obtain a final graph that has a maximum reward. Experimental evaluations in diverse settings of sensor quantities and missing proportions demonstrate that our approach compared with the benchmark methods shows an average improvement of 39.9% in the F1-score. Moreover, the F1-score improvement can reach 62.6% when considering the configuration similar to real-world datasets, and 85.0% in real-world semiconductor datasets. The source code is available at https://github.com/OuTingYun/COKE.
Authors: Shenyang Huang, Farimah Poursafaei, Reihaneh Rabbany, Guillaume Rabusseau, Emanuele Rossi
Abstract: Temporal graphs have gained increasing importance due to their ability to model dynamically evolving relationships. These graphs can be represented through either a stream of edge events or a sequence of graph snapshots. Until now, the development of machine learning methods for both types has occurred largely in isolation, resulting in limited experimental comparison and theoretical crosspollination between the two. In this paper, we introduce Unified Temporal Graph (UTG), a framework that unifies snapshot-based and event-based machine learning models under a single umbrella, enabling models developed for one representation to be applied effectively to datasets of the other. We also propose a novel UTG training procedure to boost the performance of snapshot-based models in the streaming setting. We comprehensively evaluate both snapshot and event-based models across both types of temporal graphs on the temporal link prediction task. Our main findings are threefold: first, when combined with UTG training, snapshotbased models can perform competitively with event-based models such as TGN and GraphMixer even on event datasets. Second, snapshot-based models are at least an order of magnitude faster than most event-based models during inference. Third, while event-based methods such as NAT and DyGFormer outperforms snapshotbased methods on both types of temporal graphs, this is because they leverage joint neighborhood structural features thus emphasizing the potential to incorporate these features into snapshot-based models as well. These findings highlight the importance of comparing model architectures independent of the data format and suggest the potential of combining the efficiency of snapshot-based models with the performance of event-based models in the future.
Authors: Seijin Kobayashi, Simon Schug, Yassir Akram, Florian Redhardt, Johannes von Oswald, Razvan Pascanu, Guillaume Lajoie, Jo\~ao Sacramento
Abstract: Many tasks can be composed from a few independent components. This gives rise to a combinatorial explosion of possible tasks, only some of which might be encountered during training. Under what circumstances can transformers compositionally generalize from a subset of tasks to all possible combinations of tasks that share similar components? Here we study a modular multitask setting that allows us to precisely control compositional structure in the data generation process. We present evidence that transformers learning in-context struggle to generalize compositionally on this task despite being in principle expressive enough to do so. Compositional generalization becomes possible only when introducing a bottleneck that enforces an explicit separation between task inference and task execution.
Authors: Huiwei Lin
Abstract: Online continual learning (OCL) involves deep neural networks retaining knowledge from old data while adapting to new data, which is accessible only once. A critical challenge in OCL is catastrophic forgetting, reflected in reduced model performance on old data. Existing replay-based methods mitigate forgetting by replaying buffered samples from old data and learning current samples of new data. In this work, we dissect existing methods and empirically discover that learning and replaying in the same feature space is not conducive to addressing the forgetting issue. Since the learned features associated with old data are readily changed by the features related to new data due to data imbalance, leading to the forgetting problem. Based on this observation, we intuitively explore learning and replaying in different feature spaces. Learning in a feature subspace is sufficient to capture novel knowledge from new data while replaying in a larger feature space provides more feature space to maintain historical knowledge from old data. To this end, we propose a novel OCL approach called experience replay with feature subspace learning (ER-FSL). Firstly, ER-FSL divides the entire feature space into multiple subspaces, with each subspace used to learn current samples. Moreover, it introduces a subspace reuse mechanism to address situations where no blank subspaces exist. Secondly, ER-FSL replays previous samples using an accumulated space comprising all learned subspaces. Extensive experiments on three datasets demonstrate the superiority of ER-FSL over various state-of-the-art methods.
Authors: Vint Lee, Chun Deng, Leena Elzeiny, Pieter Abbeel, John Wawrzynek
Abstract: Macro placement is a vital step in digital circuit design that defines the physical location of large collections of components, known as macros, on a 2-dimensional chip. The physical layout obtained during placement determines key performance metrics of the chip, such as power consumption, area, and performance. Existing learning-based methods typically fall short because of their reliance on reinforcement learning, which is slow and limits the flexibility of the agent by casting placement as a sequential process. Instead, we use a powerful diffusion model to place all components simultaneously. To enable such models to train at scale, we propose a novel architecture for the denoising model, as well as an algorithm to generate large synthetic datasets for pre-training. We empirically show that our model can tackle the placement task, and achieve competitive performance on placement benchmarks compared to state-of-the-art methods.
Authors: Ensieh Khazaei, Alireza Esmaeilzehi, Bilal Taha, Dimitrios Hatzinakos
Abstract: In the realm of ubiquitous computing, Human Activity Recognition (HAR) is vital for the automation and intelligent identification of human actions through data from diverse sensors. However, traditional machine learning approaches by aggregating data on a central server and centralized processing are memory-intensive and raise privacy concerns. Federated Learning (FL) has emerged as a solution by training a global model collaboratively across multiple devices by exchanging their local model parameters instead of local data. However, in realistic settings, sensor data on devices is non-independently and identically distributed (Non-IID). This means that data activity recorded by most devices is sparse, and sensor data distribution for each client may be inconsistent. As a result, typical FL frameworks in heterogeneous environments suffer from slow convergence and poor performance due to deviation of the global model's objective from the global objective. Most FL methods applied to HAR are either designed for overly ideal scenarios without considering the Non-IID problem or present privacy and scalability concerns. This work addresses these challenges, proposing CDFL, an efficient federated learning framework for image-based HAR. CDFL efficiently selects a representative set of privacy-preserved images using contrastive learning and deep clustering, reduces communication overhead by selecting effective clients for global model updates, and improves global model quality by training on privacy-preserved data. Our comprehensive experiments carried out on three public datasets, namely Stanford40, PPMI, and VOC2012, demonstrate the superiority of CDFL in terms of performance, convergence rate, and bandwidth usage compared to state-of-the-art approaches.
Authors: Ayush Kaushal, Tejas Pandey, Tejas Vaidhya, Aaryan Bhagat, Irina Rish
Abstract: Post-training quantization is the leading method for addressing memory-related bottlenecks in LLM inference, but unfortunately, it suffers from significant performance degradation below 4-bit precision. An alternative approach involves training compressed models directly at a low bitwidth (e.g., binary or ternary models). However, the performance, training dynamics, and scaling trends of such models are not yet well understood. To address this issue, we train and openly release the Spectra LLM suite consisting of 54 language models ranging from 99M to 3.9B parameters, trained on 300B tokens. Spectra includes FloatLMs, post-training quantized QuantLMs (3, 4, 6, and 8 bits), and ternary LLMs (TriLMs) - our improved architecture for ternary language modeling, which significantly outperforms previously proposed ternary models of a given size (in bits), matching half-precision models at scale. For example, TriLM 3.9B is (bit-wise) smaller than the half-precision FloatLM 830M, but matches half-precision FloatLM 3.9B in commonsense reasoning and knowledge benchmarks. However, TriLM 3.9B is also as toxic and stereotyping as FloatLM 3.9B, a model six times larger in size. Additionally, TriLM 3.9B lags behind FloatLM in perplexity on validation splits and web-based corpora but performs better on less noisy datasets like Lambada and PennTreeBank. To enhance understanding of low-bitwidth models, we are releasing 500+ intermediate checkpoints of the Spectra suite at \href{https://github.com/NolanoOrg/SpectraSuite}{https://github.com/NolanoOrg/SpectraSuite}.
URLs: https://github.com/NolanoOrg/SpectraSuite, https://github.com/NolanoOrg/SpectraSuite
Authors: Mijoo Kim, Junseok Kwon
Abstract: With the rapid advancement in the performance of deep neural networks (DNNs), there has been significant interest in deploying and incorporating artificial intelligence (AI) systems into real-world scenarios. However, many DNNs lack the ability to represent uncertainty, often exhibiting excessive confidence even when making incorrect predictions. To ensure the reliability of AI systems, particularly in safety-critical cases, DNNs should transparently reflect the uncertainty in their predictions. In this paper, we investigate robust post-hoc uncertainty calibration methods for DNNs within the context of multi-class classification tasks. While previous studies have made notable progress, they still face challenges in achieving robust calibration, particularly in scenarios involving out-of-distribution (OOD). We identify that previous methods lack adaptability to individual input data and struggle to accurately estimate uncertainty when processing inputs drawn from the wild dataset. To address this issue, we introduce a novel instance-wise calibration method based on an energy model. Our method incorporates energy scores instead of softmax confidence scores, allowing for adaptive consideration of DNN uncertainty for each prediction within a logit space. In experiments, we show that the proposed method consistently maintains robust performance across the spectrum, spanning from in-distribution to OOD scenarios, when compared to other state-of-the-art methods.
Authors: Mohamad Amin Mohamadi, Zhiyuan Li, Lei Wu, Danica J. Sutherland
Abstract: We present a theoretical explanation of the ``grokking'' phenomenon, where a model generalizes long after overfitting,for the originally-studied problem of modular addition. First, we show that early in gradient descent, when the ``kernel regime'' approximately holds, no permutation-equivariant model can achieve small population error on modular addition unless it sees at least a constant fraction of all possible data points. Eventually, however, models escape the kernel regime. We show that two-layer quadratic networks that achieve zero training loss with bounded $\ell_{\infty}$ norm generalize well with substantially fewer training points, and further show such networks exist and can be found by gradient descent with small $\ell_{\infty}$ regularization. We further provide empirical evidence that these networks as well as simple Transformers, leave the kernel regime only after initially overfitting. Taken together, our results strongly support the case for grokking as a consequence of the transition from kernel-like behavior to limiting behavior of gradient descent on deep networks.
Authors: Yannis Karmim (CEDRIC - VERTIGO), Leshanshui Yang (LITIS), Rapha\"el Fournier S'Niehotta (CEDRIC - VERTIGO), Cl\'ement Chatelain (LITIS), S\'ebastien Adam (LITIS), Nicolas Thome (MLIA)
Abstract: Dynamic link prediction is a critical task in the analysis of evolving networks, with applications ranging from recommender systems to economic exchanges. However, the concept of the temporal receptive field, which refers to the temporal context that models use for making predictions, has been largely overlooked and insufficiently analyzed in existing research. In this study, we present a comprehensive analysis of the temporal receptive field in dynamic graph learning. By examining multiple datasets and models, we formalize the role of temporal receptive field and highlight their crucial influence on predictive accuracy. Our results demonstrate that appropriately chosen temporal receptive field can significantly enhance model performance, while for some models, overly large windows may introduce noise and reduce accuracy. We conduct extensive benchmarking to validate our findings, ensuring that all experiments are fully reproducible.
Authors: Roie Reshef, Kfir Y. Levy
Abstract: This paper addresses the challenge of preserving privacy in Federated Learning (FL) within centralized systems, focusing on both trusted and untrusted server scenarios. We analyze this setting within the Stochastic Convex Optimization (SCO) framework, and devise methods that ensure Differential Privacy (DP) while maintaining optimal convergence rates for homogeneous and heterogeneous data distributions. Our approach, based on a recent stochastic optimization technique, offers linear computational complexity, comparable to non-private FL methods, and reduced gradient obfuscation. This work enhances the practicality of DP in FL, balancing privacy, efficiency, and robustness in a variety of server trust environment.
Authors: Alessandro Pierro, Steven Abreu
Abstract: Modern recurrent layers are emerging as a promising path toward edge deployment of foundation models, especially in the context of large language models (LLMs). Compressing the whole input sequence in a finite-dimensional representation enables recurrent layers to model long-range dependencies while maintaining a constant inference cost for each token and a fixed memory requirement. However, the practical deployment of LLMs in resource-limited environments often requires further model compression, such as quantization and pruning. While these techniques are well-established for attention-based models, their effects on recurrent layers remain underexplored. In this preliminary work, we focus on post-training quantization for recurrent LLMs and show that Mamba models exhibit the same pattern of outlier channels observed in attention-based LLMs. We show that the reason for the difficulty of quantizing SSMs is caused by activation outliers, similar to those observed in transformer-based LLMs. We report baseline results for post-training quantization of Mamba that do not take into account the activation outliers and suggest first steps for outlier-aware quantization.
Authors: Mohamed Kissi, Mathieu Pont, Joshua A. Levine, Julien Tierny
Abstract: This paper presents a practical approach for the optimization of topological simplification, a central pre-processing step for the analysis and visualization of scalar data. Given an input scalar field f and a set of "signal" persistence pairs to maintain, our approach produces an output field g that is close to f and which optimizes (i) the cancellation of "non-signal" pairs, while (ii) preserving the "signal" pairs. In contrast to pre-existing simplification algorithms, our approach is not restricted to persistence pairs involving extrema and can thus address a larger class of topological features, in particular saddle pairs in three-dimensional scalar data. Our approach leverages recent generic persistence optimization frameworks and extends them with tailored accelerations specific to the problem of topological simplification. Extensive experiments report substantial accelerations over these frameworks, thereby making topological simplification optimization practical for real-life datasets. Our approach enables a direct visualization and analysis of the topologically simplified data, e.g., via isosurfaces of simplified topology (fewer components and handles). We apply our approach to the extraction of prominent filament structures in three-dimensional data. Specifically, we show that our pre-simplification of the data leads to practical improvements over standard topological techniques for removing filament loops. We also show how our approach can be used to repair genus defects in surface processing. Finally, we provide a C++ implementation for reproducibility purposes.
Authors: Yong-Hyun Park, Junghoon Seo, Bomseok Park, Seongsu Lee, Junghyo Jo
Abstract: Identifying the relevant input features that have a critical influence on the output results is indispensable for the development of explainable artificial intelligence (XAI). Remove-and-Retrain (ROAR) is a widely accepted approach for assessing the importance of individual pixels by measuring changes in accuracy following their removal and subsequent retraining of the modified dataset. However, we uncover notable limitations in pixel-perturbation strategies. When viewed from a geometric perspective, we discover that these metrics fail to discriminate between differences among feature attribution methods, thereby compromising the reliability of the evaluation. To address this challenge, we introduce an alternative feature-perturbation approach named Geometric Remove-and-Retrain (GOAR). Through a series of experiments with both synthetic and real datasets, we substantiate that GOAR transcends the limitations of pixel-centric metrics.
Authors: Daniel Tan, David Chanin, Aengus Lynch, Dimitrios Kanoulas, Brooks Paige, Adria Garriga-Alonso, Robert Kirk
Abstract: Steering vectors (SVs) are a new approach to efficiently adjust language model behaviour at inference time by intervening on intermediate model activations. They have shown promise in terms of improving both capabilities and model alignment. However, the reliability and generalisation properties of this approach are unknown. In this work, we rigorously investigate these properties, and show that steering vectors have substantial limitations both in- and out-of-distribution. In-distribution, steerability is highly variable across different inputs. Depending on the concept, spurious biases can substantially contribute to how effective steering is for each input, presenting a challenge for the widespread use of steering vectors. Out-of-distribution, while steering vectors often generalise well, for several concepts they are brittle to reasonable changes in the prompt, resulting in them failing to generalise well. Overall, our findings show that while steering can work well in the right circumstances, there remain many technical difficulties of applying steering vectors to guide models' behaviour at scale.
Authors: Davide Domini, Gianluca Aguzzi, Nicolas Farabegoli, Mirko Viroli, Lukas Esterle
Abstract: In recent advancements in machine learning, federated learning allows a network of distributed clients to collaboratively develop a global model without needing to share their local data. This technique aims to safeguard privacy, countering the vulnerabilities of conventional centralized learning methods. Traditional federated learning approaches often rely on a central server to coordinate model training across clients, aiming to replicate the same model uniformly across all nodes. However, these methods overlook the significance of geographical and local data variances in vast networks, potentially affecting model effectiveness and applicability. Moreover, relying on a central server might become a bottleneck in large networks, such as the ones promoted by edge computing. Our paper introduces a novel, fully-distributed federated learning strategy called proximity-based self-federated learning that enables the self-organised creation of multiple federations of clients based on their geographic proximity and data distribution without exchanging raw data. Indeed, unlike traditional algorithms, our approach encourages clients to share and adjust their models with neighbouring nodes based on geographic proximity and model accuracy. This method not only addresses the limitations posed by diverse data distributions but also enhances the model's adaptability to different regional characteristics creating specialized models for each federation. We demonstrate the efficacy of our approach through simulations on well-known datasets, showcasing its effectiveness over the conventional centralized federated learning framework.
Authors: Xingyu Zhang, Siyu Zhao, Zeen Song, Huijie Guo, Jianqi Zhang, Changwen Zheng, Wenwen Qiang
Abstract: Long-term time series forecasting is a long-standing challenge in various applications. A central issue in time series forecasting is that methods should expressively capture long-term dependency. Furthermore, time series forecasting methods should be flexible when applied to different scenarios. Although Fourier analysis offers an alternative to effectively capture reusable and periodic patterns to achieve long-term forecasting in different scenarios, existing methods often assume high-frequency components represent noise and should be discarded in time series forecasting. However, we conduct a series of motivation experiments and discover that the role of certain frequencies varies depending on the scenarios. In some scenarios, removing high-frequency components from the original time series can improve the forecasting performance, while in others scenarios, removing them is harmful to forecasting performance. Therefore, it is necessary to treat the frequencies differently according to specific scenarios. To achieve this, we first reformulate the time series forecasting problem as learning a transfer function of each frequency in the Fourier domain. Further, we design Frequency Dynamic Fusion (FreDF), which individually predicts each Fourier component, and dynamically fuses the output of different frequencies. Moreover, we provide a novel insight into the generalization ability of time series forecasting and propose the generalization bound of time series forecasting. Then we prove FreDF has a lower bound, indicating that FreDF has better generalization ability. Extensive experiments conducted on multiple benchmark datasets and ablation studies demonstrate the effectiveness of FreDF.
Authors: V\'ictor Manuel Vargas, Pedro Antonio Guti\'errez, Javier Barbero-G\'omez, C\'esar Herv\'as-Mart\'inez
Abstract: An ordinal classification problem is one in which the target variable takes values on an ordinal scale. Nowadays, there are many of these problems associated with real-world tasks where it is crucial to accurately classify the extreme classes of the ordinal structure. In this work, we propose a unimodal regularisation approach that can be applied to any loss function to improve the classification performance of the first and last classes while maintaining good performance for the remainder. The proposed methodology is tested on six datasets with different numbers of classes, and compared with other unimodal regularisation methods in the literature. In addition, performance in the extreme classes is compared using a new metric that takes into account their sensitivities. Experimental results and statistical analysis show that the proposed methodology obtains a superior average performance considering different metrics. The results for the proposed metric show that the generalised beta distribution generally improves classification performance in the extreme classes. At the same time, the other five nominal and ordinal metrics considered show that the overall performance is aligned with the performance of previous alternatives.
Authors: Christian Nauck, Rohan Gorantla, Michael Lindner, Konstantin Sch\"urholt, Antonia S. J. S. Mey, Frank Hellmann
Abstract: The geometry of a graph is encoded in dynamical processes on the graph. Many graph neural network (GNN) architectures are inspired by such dynamical systems, typically based on the graph Laplacian. Here, we introduce Dirac--Bianconi GNNs (DBGNNs), which are based on the topological Dirac equation recently proposed by Bianconi. Based on the graph Laplacian, we demonstrate that DBGNNs explore the geometry of the graph in a fundamentally different way than conventional message passing neural networks (MPNNs). While regular MPNNs propagate features diffusively, analogous to the heat equation, DBGNNs allow for coherent long-range propagation. Experimental results showcase the superior performance of DBGNNs over existing conventional MPNNs for long-range predictions of power grid stability and peptide properties. This study highlights the effectiveness of DBGNNs in capturing intricate graph dynamics, providing notable advancements in GNN architectures.
Authors: Salah Ghamizi, Aleksandar Bojchevski, Aoxiang Ma, Jun Cao
Abstract: Power grids are critical infrastructures of paramount importance to modern society and their rapid evolution and interconnections has heightened the complexity of power systems (PS) operations. Traditional methods for grid analysis struggle with the computational demands of large-scale RES and ES integration, prompting the adoption of machine learning (ML) techniques, particularly Graph Neural Networks (GNNs). GNNs have proven effective in solving the alternating current (AC) Power Flow (PF) and Optimal Power Flow (OPF) problems, crucial for operational planning. However, existing benchmarks and datasets completely ignore safety and robustness requirements in their evaluation and never consider realistic safety-critical scenarios that most impact the operations of the power grids. We present SafePowerGraph, the first simulator-agnostic, safety-oriented framework and benchmark for GNNs in PS operations. SafePowerGraph integrates multiple PF and OPF simulators and assesses GNN performance under diverse scenarios, including energy price variations and power line outages. Our extensive experiments underscore the importance of self-supervised learning and graph attention architectures for GNN robustness. We provide at https://github.com/yamizi/SafePowerGraph our open-source repository, a comprehensive leaderboard, a dataset and model zoo and expect our framework to standardize and advance research in the critical field of GNN for power systems.
Authors: Minh Hoang Nguyen, Hung Le, Svetha Venkatesh
Abstract: Modern reinforcement learning (RL) struggles to capture real-world cause-and-effect dynamics, leading to inefficient exploration due to extensive trial-and-error actions. While recent efforts to improve agent exploration have leveraged causal discovery, they often make unrealistic assumptions of causal variables in the environments. In this paper, we introduce a novel framework, Variable-Agnostic Causal Exploration for Reinforcement Learning (VACERL), incorporating causal relationships to drive exploration in RL without specifying environmental causal variables. Our approach automatically identifies crucial observation-action steps associated with key variables using attention mechanisms. Subsequently, it constructs the causal graph connecting these steps, which guides the agent towards observation-action pairs with greater causal influence on task completion. This can be leveraged to generate intrinsic rewards or establish a hierarchy of subgoals to enhance exploration efficiency. Experimental results showcase a significant improvement in agent performance in grid-world, 2d games and robotic domains, particularly in scenarios with sparse rewards and noisy actions, such as the notorious Noisy-TV environments.
Authors: Pierre Lamart, Yinan Yu, Christian Berger
Abstract: Machine Learning (ML) is continuously permeating a growing amount of application domains. Generative AI such as Large Language Models (LLMs) also sees broad adoption to process multi-modal data such as text, images, audio, and video. While the trend is to use ever-larger datasets for training, managing this data efficiently has become a significant practical challenge in the industry-double as much data is certainly not double as good. Rather the opposite is important since getting an understanding of the inherent quality and diversity of the underlying data lakes is a growing challenge for application-specific ML as well as for fine-tuning foundation models. Furthermore, information retrieval (IR) from expanding data lakes is complicated by the temporal dimension inherent in time-series data which must be considered to determine its semantic value. This study focuses on the different semantic-aware techniques to extract embeddings from mono-modal, multi-modal, and cross-modal data to enhance IR capabilities in a growing data lake. Articles were collected to summarize information about the state-of-the-art techniques focusing on applications of embedding for three different categories of data modalities.
Authors: Krist\'ofer Reynisson, Marco Schreyer, Damian Borth
Abstract: Credit card fraud has significant implications at both an individual and societal level, making effective prevention essential. Current methods rely heavily on feature engineering and labeled information, both of which have significant limitations. In this work, we present GraphGuard, a novel contrastive self-supervised graph-based framework for detecting fraudulent credit card transactions. We conduct experiments on a real-world dataset and a synthetic dataset. Our results provide a promising initial direction for exploring the effectiveness of graph-based self-supervised approaches for credit card fraud detection.
Authors: Zhaoxin Wang, Handing Wang, Cong Tian, Yaochu Jin
Abstract: Adversarial training (AT) has become an effective defense method against adversarial examples (AEs) and it is typically framed as a bi-level optimization problem. Among various AT methods, fast AT (FAT), which employs a single-step attack strategy to guide the training process, can achieve good robustness against adversarial attacks at a low cost. However, FAT methods suffer from the catastrophic overfitting problem, especially on complex tasks or with large-parameter models. In this work, we propose a FAT method termed FGSM-PCO, which mitigates catastrophic overfitting by averting the collapse of the inner optimization problem in the bi-level optimization process. FGSM-PCO generates current-stage AEs from the historical AEs and incorporates them into the training process using an adaptive mechanism. This mechanism determines an appropriate fusion ratio according to the performance of the AEs on the training model. Coupled with a loss function tailored to the training framework, FGSM-PCO can alleviate catastrophic overfitting and help the recovery of an overfitted model to effective training. We evaluate our algorithm across three models and three datasets to validate its effectiveness. Comparative empirical studies against other FAT algorithms demonstrate that our proposed method effectively addresses unresolved overfitting issues in existing algorithms.
Authors: Roberto Pagliari, Peter Hill, Po-Yu Chen, Maciej Dabrowny, Tingsheng Tan, Francois Buet-Golfouse
Abstract: In financial applications, regulations or best practices often lead to specific requirements in machine learning relating to four key pillars: fairness, privacy, interpretability and greenhouse gas emissions. These all sit in the broader context of sustainability in AI, an emerging practical AI topic. However, although these pillars have been individually addressed by past literature, none of these works have considered all the pillars. There are inherent trade-offs between each of the pillars (for example, accuracy vs fairness or accuracy vs privacy), making it even more important to consider them together. This paper outlines a new framework for Sustainable Machine Learning and proposes FPIG, a general AI pipeline that allows for these critical topics to be considered simultaneously to learn the trade-offs between the pillars better. Based on the FPIG framework, we propose a meta-learning algorithm to estimate the four key pillars given a dataset summary, model architecture, and hyperparameters before model training. This algorithm allows users to select the optimal model architecture for a given dataset and a given set of user requirements on the pillars. We illustrate the trade-offs under the FPIG model on three classical datasets and demonstrate the meta-learning approach with an example of real-world datasets and models with different interpretability, showcasing how it can aid model selection.
Authors: Xu-Hui Liu, Tian-Shuo Liu, Shengyi Jiang, Ruifeng Chen, Zhilong Zhang, Xinwei Chen, Yang Yu
Abstract: Combining offline and online reinforcement learning (RL) techniques is indeed crucial for achieving efficient and safe learning where data acquisition is expensive. Existing methods replay offline data directly in the online phase, resulting in a significant challenge of data distribution shift and subsequently causing inefficiency in online fine-tuning. To address this issue, we introduce an innovative approach, \textbf{E}nergy-guided \textbf{DI}ffusion \textbf{S}ampling (EDIS), which utilizes a diffusion model to extract prior knowledge from the offline dataset and employs energy functions to distill this knowledge for enhanced data generation in the online phase. The theoretical analysis demonstrates that EDIS exhibits reduced suboptimality compared to solely utilizing online data or directly reusing offline data. EDIS is a plug-in approach and can be combined with existing methods in offline-to-online RL setting. By implementing EDIS to off-the-shelf methods Cal-QL and IQL, we observe a notable 20% average improvement in empirical performance on MuJoCo, AntMaze, and Adroit environments. Code is available at \url{https://github.com/liuxhym/EDIS}.
Authors: Adittya Pal
Abstract: Stable states in complex systems correspond to local minima on the associated potential energy surface. Transitions between these local minima govern the dynamics of such systems. Precisely determining the transition pathways in complex and high-dimensional systems is challenging because these transitions are rare events, and isolating the relevant species in experiments is difficult. Most of the time, the system remains near a local minimum, with rare, large fluctuations leading to transitions between minima. The probability of such transitions decreases exponentially with the height of the energy barrier, making the system's dynamics highly sensitive to the calculated energy barriers. This work aims to formulate the problem of finding the minimum energy barrier between two stable states in the system's state space as a cost-minimization problem. We propose solving this problem using reinforcement learning algorithms. The exploratory nature of reinforcement learning agents enables efficient sampling and determination of the minimum energy barrier for transitions.
Authors: Mona Schirmer, Dan Zhang, Eric Nalisnick
Abstract: Distribution shifts between training and test data are all but inevitable over the lifecycle of a deployed model and lead to performance decay. Adapting the model can hopefully mitigate this drop in performance. Yet, adaptation is challenging since it must be unsupervised: we usually do not have access to any labeled data at test time. In this paper, we propose a probabilistic state-space model that can adapt a deployed model subjected to distribution drift. Our model learns the dynamics induced by distribution shifts on the last set of hidden features. Without requiring labels, we infer time-evolving class prototypes that serve as a dynamic classification head. Moreover, our approach is lightweight, modifying only the model's last linear layer. In experiments on real-world distribution shifts and synthetic corruptions, we demonstrate that our approach performs competitively with methods that require back-propagation and access to the model backbone. Our model especially excels in the case of small test batches - the most difficult setting.
Authors: Runfa Chen, Ling Wang, Yu Du, Tianrui Xue, Fuchun Sun, Jianwei Zhang, Wenbing Huang
Abstract: Learning policies for multi-entity systems in 3D environments is far more complicated against single-entity scenarios, due to the exponential expansion of the global state space as the number of entities increases. One potential solution of alleviating the exponential complexity is dividing the global space into independent local views that are invariant to transformations including translations and rotations. To this end, this paper proposes Subequivariant Hierarchical Neural Networks (SHNN) to facilitate multi-entity policy learning. In particular, SHNN first dynamically decouples the global space into local entity-level graphs via task assignment. Second, it leverages subequivariant message passing over the local entity-level graphs to devise local reference frames, remarkably compressing the representation redundancy, particularly in gravity-affected environments. Furthermore, to overcome the limitations of existing benchmarks in capturing the subtleties of multi-entity systems under the Euclidean symmetry, we propose the Multi-entity Benchmark (MEBEN), a new suite of environments tailored for exploring a wide range of multi-entity reinforcement learning. Extensive experiments demonstrate significant advancements of SHNN on the proposed benchmarks compared to existing methods. Comprehensive ablations are conducted to verify the indispensability of task assignment and subequivariance.
Authors: Ayush Prasad, Paula Harder, Qidong Yang, Prasanna Sattegeri, Daniela Szwarcman, Campbell Watson, David Rolnick
Abstract: Climate downscaling, the process of generating high-resolution climate data from low-resolution simulations, is essential for understanding and adapting to climate change at regional and local scales. Deep learning approaches have proven useful in tackling this problem. However, existing studies usually focus on training models for one specific task, location and variable, which are therefore limited in their generalizability and transferability. In this paper, we evaluate the efficacy of training deep learning downscaling models on multiple diverse climate datasets to learn more robust and transferable representations. We evaluate the effectiveness of architectures zero-shot transferability using CNNs, Fourier Neural Operators (FNOs), and vision Transformers (ViTs). We assess the spatial, variable, and product transferability of downscaling models experimentally, to understand the generalizability of these different architecture types.
Authors: Angie Boggust, Hyemin Bang, Hendrik Strobelt, Arvind Satyanarayan
Abstract: Abstraction -- the process of generalizing specific examples into broad reusable patterns -- is central to how people efficiently process and store information and apply their knowledge to new data. Promisingly, research has shown that ML models learn representations that span levels of abstraction, from specific concepts like "bolo tie" and "car tire" to more general concepts like "CEO" and "model". However, existing techniques analyze these representations in isolation, treating learned concepts as independent artifacts rather than an interconnected web of abstraction. As a result, although we can identify the concepts a model uses to produce its output, it is difficult to assess if it has learned a human-aligned abstraction of the concepts that will generalize to new data. To address this gap, we introduce abstraction alignment, a methodology to measure the agreement between a model's learned abstraction and the expected human abstraction. We quantify abstraction alignment by comparing model outputs against a human abstraction graph, such as linguistic relationships or medical disease hierarchies. In evaluation tasks interpreting image models, benchmarking language models, and analyzing medical datasets, abstraction alignment provides a deeper understanding of model behavior and dataset content, differentiating errors based on their agreement with human knowledge, expanding the verbosity of current model quality metrics, and revealing ways to improve existing human abstractions.
Authors: Yan Lin, Zeyu Zhou, Yicheng Liu, Haochen Lv, Haomin Wen, Tianyi Li, Yushuai Li, Christian S. Jensen, Shengnan Guo, Youfang Lin, Huaiyu Wan
Abstract: Spatio-temporal (ST) trajectories are sequences of timestamped locations, which enable a variety of analyses that in turn enable important real-world applications. It is common to map trajectories to vectors, called embeddings, before subsequent analyses. Thus, the qualities of embeddings are very important. Methods for pre-training embeddings, which leverage unlabeled trajectories for training universal embeddings, have shown promising applicability across different tasks, thus attracting considerable interest. However, research progress on this topic faces two key challenges: a lack of a comprehensive overview of existing methods, resulting in several related methods not being well-recognized, and the absence of a unified pipeline, complicating the development new methods and the analysis of methods. To overcome these obstacles and advance the field of pre-training of trajectory embeddings, we present UniTE, a survey and a unified pipeline for this domain. In doing so, we present a comprehensive list of existing methods for pre-training trajectory embeddings, which includes methods that either explicitly or implicitly employ pre-training techniques. Further, we present a unified and modular pipeline with publicly available underlying code, simplifying the process of constructing and evaluating methods for pre-training trajectory embeddings. Additionally, we contribute a selection of experimental results using the proposed pipeline on real-world datasets.
Authors: Wojciech Ciezobka, Joan Falco-Roget, Cemal Koba, Alessandro Crimi
Abstract: In this paper, we propose a reservoir computing-based and directed graph analysis pipeline. The goal of this pipeline is to define an efficient brain representation for connectivity in stroke data derived from magnetic resonance imaging. Ultimately, this representation is used within a directed graph convolutional architecture and investigated with explainable artificial intelligence (AI) tools. Stroke is one of the leading causes of mortality and morbidity worldwide, and it demands precise diagnostic tools for timely intervention and improved patient outcomes. Neuroimaging data, with their rich structural and functional information, provide a fertile ground for biomarker discovery. However, the complexity and variability of information flow in the brain requires advanced analysis, especially if we consider the case of disrupted networks as those given by the brain connectome of stroke patients. To address the needs given by this complex scenario we proposed an end-to-end pipeline. This pipeline begins with reservoir computing causality, to define effective connectivity of the brain. This allows directed graph network representations which have not been fully investigated so far by graph convolutional network classifiers. Indeed, the pipeline subsequently incorporates a classification module to categorize the effective connectivity (directed graphs) of brain networks of patients versus matched healthy control. The classification led to an area under the curve of 0.69 with the given heterogeneous dataset. Thanks to explainable tools, an interpretation of disrupted networks across the brain networks was possible. This elucidates the effective connectivity biomarker's contribution to stroke classification, fostering insights into disease mechanisms and treatment responses.
Authors: Nikita P. Kalinin, Simone Bombari, Hossein Zakerinia, Christoph H. Lampert
Abstract: We study the Kolmogorov-Arnold Network (KAN), recently proposed as an alternative to the classical Multilayer Perceptron (MLP), in the application for differentially private model training. Using the DP-SGD algorithm, we demonstrate that KAN can be made private in a straightforward manner and evaluated its performance across several datasets. Our results indicate that the accuracy of KAN is not only comparable with MLP but also experiences similar deterioration due to privacy constraints, making it suitable for differentially private model training.
Authors: Mizuka Komatsu
Abstract: In this study, we considered the problem of estimating epidemiological parameters based on physics-informed neural networks (PINNs). In practice, not all trajectory data corresponding to the population estimated by epidemic models can be obtained, and some observed trajectories are noisy. Learning PINNs to estimate unknown epidemiological parameters using such partial observations is challenging. Accordingly, we introduce the concept of algebraic observability into PINNs. The validity of the proposed PINN, named as an algebraically observable PINNs, in terms of estimation parameters and prediction of unobserved variables, is demonstrated through numerical experiments.
Authors: Brahim Oubaha, Claude Berrou, Xueyao Ji, Yehya Nasser, Rapha\"el Le Bidan
Abstract: Diversity is a concept of prime importance in almost all disciplines based on information processing. In telecommunications, for example, spatial, temporal, and frequency diversity, as well as redundant coding, are fundamental concepts that have enabled the design of extremely efficient systems. In machine learning, in particular with neural networks, diversity is not always a concept that is emphasized or at least clearly identified. This paper proposes a neural network architecture that builds upon various diversity principles, some of them already known, others more original. Our architecture obtains remarkable results, with a record self-supervised learning accuracy of 99. 57% in MNIST, and a top tier promising semi-supervised learning accuracy of 94.21% in CIFAR-10 using only 25 labels per class.
Authors: Kushal Chakrabarti, Mayank Baranwal
Abstract: Adaptive gradient-descent optimizers are the standard choice for training neural network models. Despite their faster convergence than gradient-descent and remarkable performance in practice, the adaptive optimizers are not as well understood as vanilla gradient-descent. A reason is that the dynamic update of the learning rate that helps in faster convergence of these methods also makes their analysis intricate. Particularly, the simple gradient-descent method converges at a linear rate for a class of optimization problems, whereas the practically faster adaptive gradient methods lack such a theoretical guarantee. The Polyak-{\L}ojasiewicz (PL) inequality is the weakest known class, for which linear convergence of gradient-descent and its momentum variants has been proved. Therefore, in this paper, we prove that AdaGrad and Adam, two well-known adaptive gradient methods, converge linearly when the cost function is smooth and satisfies the PL inequality. Our theoretical framework follows a simple and unified approach, applicable to both batch and stochastic gradients, which can potentially be utilized in analyzing linear convergence of other variants of Adam.
Authors: Mohammad-Amin Charusaie, Samira Samadi
Abstract: Learn-to-Defer is a paradigm that enables learning algorithms to work not in isolation but as a team with human experts. In this paradigm, we permit the system to defer a subset of its tasks to the expert. Although there are currently systems that follow this paradigm and are designed to optimize the accuracy of the final human-AI team, the general methodology for developing such systems under a set of constraints (e.g., algorithmic fairness, expert intervention budget, defer of anomaly, etc.) remains largely unexplored. In this paper, using a $d$-dimensional generalization to the fundamental lemma of Neyman and Pearson (d-GNP), we obtain the Bayes optimal solution for learn-to-defer systems under various constraints. Furthermore, we design a generalizable algorithm to estimate that solution and apply this algorithm to the COMPAS and ACSIncome datasets. Our algorithm shows improvements in terms of constraint violation over a set of baselines.
Authors: Mehmet Yigit Balik
Abstract: Predicting hospital length of stay (LOS) reliably is an essential need for efficient resource allocation at hospitals. Traditional predictive modeling tools frequently have difficulty acquiring sufficient and diverse data because healthcare institutions have privacy rules in place. In our study, we modeled this problem as an empirical graph where nodes are the hospitals. This modeling approach facilitates collaborative model training by modeling decentralized data sources from different hospitals without extracting sensitive data outside of hospitals. A local model is trained on a node (hospital) by aiming the generalized total variation minimization (GTVMin). Moreover, we implemented and compared two different federated learning optimization algorithms named federated stochastic gradient descent (FedSGD) and federated averaging (FedAVG). Our results show that federated learning enables accurate prediction of hospital LOS while addressing privacy concerns without extracting data outside healthcare institutions.
Authors: Maissae Haddouchi, Abdelaziz Berrado
Abstract: The interpretability of random forest (RF) models is a research topic of growing interest in the machine learning (ML) community. In the state of the art, RF is considered a powerful learning ensemble given its predictive performance, flexibility, and ease of use. Furthermore, the inner process of the RF model is understandable because it uses an intuitive and intelligible approach for building the RF decision tree ensemble. However, the RF resulting model is regarded as a "black box" because of its numerous deep decision trees. Gaining visibility over the entire process that induces the final decisions by exploring each decision tree is complicated, if not impossible. This complexity limits the acceptance and implementation of RF models in several fields of application. Several papers have tackled the interpretation of RF models. This paper aims to provide an extensive review of methods used in the literature to interpret RF resulting models. We have analyzed these methods and classified them based on different axes. Although this review is not exhaustive, it provides a taxonomy of various techniques that should guide users in choosing the most appropriate tools for interpreting RF models, depending on the interpretability aspects sought. It should also be valuable for researchers who aim to focus their work on the interpretability of RF or ML black boxes in general.
Authors: Jinxuan Xu, Hong-You Chen, Wei-Lun Chao, Yuqian Zhang
Abstract: Federated learning has recently garnered significant attention, especially within the domain of supervised learning. However, despite the abundance of unlabeled data on end-users, unsupervised learning problems such as clustering in the federated setting remain underexplored. In this paper, we investigate the federated clustering problem, with a focus on federated k-means. We outline the challenge posed by its non-convex objective and data heterogeneity in the federated framework. To tackle these challenges, we adopt a new perspective by studying the structures of local solutions in k-means and propose a one-shot algorithm called FeCA (Federated Centroid Aggregation). FeCA adaptively refines local solutions on clients, then aggregates these refined solutions to recover the global solution of the entire dataset in a single round. We empirically demonstrate the robustness of FeCA under various federated scenarios on both synthetic and real-world data. Additionally, we extend FeCA to representation learning and present DeepFeCA, which combines DeepCluster and FeCA for unsupervised feature learning in the federated setting.
Authors: Jiahong Chen, Zhilin Zhang, Lucy Li, Behzad Shahrasbi, Arjun Mishra
Abstract: Domain adversarial training has shown its effective capability for finding domain invariant feature representations and been successfully adopted for various domain adaptation tasks. However, recent advances of large models (e.g., vision transformers) and emerging of complex adaptation scenarios (e.g., DomainNet) make adversarial training being easily biased towards source domain and hardly adapted to target domain. The reason is twofold: relying on large amount of labelled data from source domain for large model training and lacking of labelled data from target domain for fine-tuning. Existing approaches widely focused on either enhancing discriminator or improving the training stability for the backbone networks. Due to unbalanced competition between the feature extractor and the discriminator during the adversarial training, existing solutions fail to function well on complex datasets. To address this issue, we proposed a novel contrastive adversarial training (CAT) approach that leverages the labeled source domain samples to reinforce and regulate the feature generation for target domain. Typically, the regulation forces the target feature distribution being similar to the source feature distribution. CAT addressed three major challenges in adversarial learning: 1) ensure the feature distributions from two domains as indistinguishable as possible for the discriminator, resulting in a more robust domain-invariant feature generation; 2) encourage target samples moving closer to the source in the feature space, reducing the requirement for generalizing classifier trained on the labeled source domain to unlabeled target domain; 3) avoid directly aligning unpaired source and target samples within mini-batch. CAT can be easily plugged into existing models and exhibits significant performance improvements.
Authors: Zhaorun Chen, Zhen Xiang, Chaowei Xiao, Dawn Song, Bo Li
Abstract: LLM agents have demonstrated remarkable performance across various applications, primarily due to their advanced capabilities in reasoning, utilizing external knowledge and tools, calling APIs, and executing actions to interact with environments. Current agents typically utilize a memory module or a retrieval-augmented generation (RAG) mechanism, retrieving past knowledge and instances with similar embeddings from knowledge bases to inform task planning and execution. However, the reliance on unverified knowledge bases raises significant concerns about their safety and trustworthiness. To uncover such vulnerabilities, we propose a novel red teaming approach AgentPoison, the first backdoor attack targeting generic and RAG-based LLM agents by poisoning their long-term memory or RAG knowledge base. In particular, we form the trigger generation process as a constrained optimization to optimize backdoor triggers by mapping the triggered instances to a unique embedding space, so as to ensure that whenever a user instruction contains the optimized backdoor trigger, the malicious demonstrations are retrieved from the poisoned memory or knowledge base with high probability. In the meantime, benign instructions without the trigger will still maintain normal performance. Unlike conventional backdoor attacks, AgentPoison requires no additional model training or fine-tuning, and the optimized backdoor trigger exhibits superior transferability, in-context coherence, and stealthiness. Extensive experiments demonstrate AgentPoison's effectiveness in attacking three types of real-world LLM agents: RAG-based autonomous driving agent, knowledge-intensive QA agent, and healthcare EHRAgent. On each agent, AgentPoison achieves an average attack success rate higher than 80% with minimal impact on benign performance (less than 1%) with a poison rate less than 0.1%.
Authors: Isadora Salles, Paola Mejia-Domenzain, Vinitra Swamy, Julian Blackwell, Tanja K\"aser
Abstract: Clustering in education, particularly in large-scale online environments like MOOCs, is essential for understanding and adapting to diverse student needs. However, the effectiveness of clustering depends on its interpretability, which becomes challenging with high-dimensional data. Existing clustering approaches often neglect individual differences in feature importance and rely on a homogenized feature set. Addressing this gap, we introduce Interpret3C (Interpretable Conditional Computation Clustering), a novel clustering pipeline that incorporates interpretable neural networks (NNs) in an unsupervised learning context. This method leverages adaptive gating in NNs to select features for each student. Then, clustering is performed using the most relevant features per student, enhancing clusters' relevance and interpretability. We use Interpret3C to analyze the behavioral clusters considering individual feature importances in a MOOC with over 5,000 students. This research contributes to the field by offering a scalable, robust clustering methodology and an educational case study that respects individual student differences and improves interpretability for high-dimensional data.
Authors: Muhao Chen, Jing Qin
Abstract: In the design of tensegrity structures, traditional form-finding methods utilize kinematic and static approaches to identify geometric configurations that achieve equilibrium. However, these methods often fall short when applied to actual physical models due to imperfections in the manufacturing of structural elements, assembly errors, and material non-linearities. In this work, we develop a deep neural network (DNN) approach to predict the geometric configurations and physical properties-such as nodal coordinates, member forces, and natural frequencies-of any tensegrity structures in equilibrium states. First, we outline the analytical governing equations for tensegrity structures, covering statics involving nodal coordinates and member forces, as well as modal information. Next, we propose a data-driven framework for training an appropriate DNN model capable of simultaneously predicting tensegrity forms and physical properties, thereby circumventing the need to solve equilibrium equations. For validation, we analyze three tensegrity structures, including a tensegrity D-bar, prism, and lander, demonstrating that our approach can identify approximation systems with relatively very small output errors. This technique is applicable to a wide range of tensegrity structures, particularly in real-world construction, and can be extended to address additional challenges in identifying structural physics information.
Authors: Santiago Arena, Antonio Quintero-Rinc\'on
Abstract: Specific Language Impairment (SLI) is a disorder that affects communication and can affect both comprehension and expression. This study focuses on effectively detecting SLI in children using transcripts of spontaneous narratives from 1063 interviews. A three-stage cascading pipeline was proposed f. In the first stage, feature extraction and dimensionality reduction of the data are performed using the Random Forest (RF) and Spearman correlation methods. In the second stage, the most predictive variables from the first stage are estimated using logistic regression, which is used in the last stage to detect SLI in children from transcripts of spontaneous narratives using a nearest neighbor classifier. The results revealed an accuracy of 97.13% in identifying SLI, highlighting aspects such as the length of the responses, the quality of their utterances, and the complexity of the language. This new approach, framed in natural language processing, offers significant benefits to the field of SLI detection by avoiding complex subjective variables and focusing on quantitative metrics directly related to the child's performance.
Authors: Mladen Popovi\'c, Maruf A. Dhali, Lambert Schomaker, Johannes van der Plicht, Kaare Lund Rasmussen, Jacopo La Nasa, Ilaria Degano, Maria Perla Colombini, Eibert Tigchelaar
Abstract: Determining the chronology of ancient handwritten manuscripts is essential for reconstructing the evolution of ideas. For the Dead Sea Scrolls, this is particularly important. However, there is an almost complete lack of date-bearing manuscripts evenly distributed across the timeline and written in similar scripts available for palaeographic comparison. Here, we present Enoch, a state-of-the-art AI-based date-prediction model, trained on the basis of new radiocarbon-dated samples of the scrolls. Enoch uses established handwriting-style descriptors and applies Bayesian ridge regression. The challenge of this study is that the number of radiocarbon-dated manuscripts is small, while current machine learning requires an abundance of training data. We show that by using combined angular and allographic writing style feature vectors and applying Bayesian ridge regression, Enoch could predict the radiocarbon-based dates from style, supported by leave-one-out validation, with varied MAEs of 27.9 to 30.7 years relative to the radiocarbon dating. Enoch was then used to estimate the dates of 135 unseen manuscripts, revealing that 79 per cent of the samples were considered 'realistic' upon palaeographic post-hoc evaluation. We present a new chronology of the scrolls. The radiocarbon ranges and Enoch's style-based predictions are often older than the traditionally assumed palaeographic estimates. In the range of 300-50 BCE, Enoch's date prediction provides an improved granularity. The study is in line with current developments in multimodal machine-learning techniques, and the methods can be used for date prediction in other partially-dated manuscript collections. This research shows how Enoch's quantitative, probability-based approach can be a tool for palaeographers and historians, re-dating ancient Jewish key texts and contributing to current debates on Jewish and Christian origins.
Authors: Aditya Makkar, Divya Makkar, Aarav Patel, Liam Hebert
Abstract: The lack of fluency in sign language remains a barrier to seamless communication for hearing and speech-impaired communities. In this work, we propose a low-cost, real-time ASL-to-speech translation glove and an exhaustive training dataset of sign language patterns. We then benchmarked this dataset with supervised learning models, such as LSTMs, GRUs and Transformers, where our best model achieved 92% accuracy. The SignSpeak dataset has 7200 samples encompassing 36 classes (A-Z, 1-10) and aims to capture realistic signing patterns by using five low-cost flex sensors to measure finger positions at each time step at 36 Hz. Our open-source dataset, models and glove designs, provide an accurate and efficient ASL translator while maintaining cost-effectiveness, establishing a framework for future work to build on.
Authors: Timothy Nguyen
Abstract: Transformer based large-language models (LLMs) display extreme proficiency with language yet a precise understanding of how they work remains elusive. One way of demystifying transformer predictions would be to describe how they depend on their context in terms of simple template functions. This paper takes a first step in this direction by considering families of functions (i.e. rules) formed out of simple N-gram based statistics of the training data. By studying how well these rulesets approximate transformer predictions, we obtain a variety of novel discoveries: a simple method to detect overfitting during training without using a holdout set, a quantitative measure of how transformers progress from learning simple to more complex statistical rules over the course of training, a model-variance criterion governing when transformer predictions tend to be described by N-gram rules, and insights into how well transformers can be approximated by N-gram rulesets in the limit where these rulesets become increasingly complex. In this latter direction, we find that for 78% of LLM next-token distributions on TinyStories, their top-1 predictions agree with those provided by our N-gram rulesets.
Authors: Zhiyuan Peng, Yuanbo Tang, Yang Li
Abstract: DNA sequences encode vital genetic and biological information, yet these unfixed-length sequences cannot serve as the input of common data mining algorithms. Hence, various representation schemes have been developed to transform DNA sequences into fixed-length numerical representations. However, these schemes face difficulties in learning high-quality representations due to the complexity and sparsity of DNA data. Additionally, DNA sequences are inherently noisy because of mutations. While several schemes have been proposed for their effectiveness, they often lack semantic structure, making it difficult for biologists to validate and leverage the results. To address these challenges, we propose \textbf{Dy-mer}, an explainable and robust DNA representation scheme based on sparse recovery. Leveraging the underlying semantic structure of DNA, we modify the traditional sparse recovery to capture recurring patterns indicative of biological functions by representing frequent K-mers as basis vectors and reconstructing each DNA sequence through simple concatenation. Experimental results demonstrate that \textbf{Dy-mer} achieves state-of-the-art performance in DNA promoter classification, yielding a remarkable \textbf{13\%} increase in accuracy. Moreover, its inherent explainability facilitates DNA clustering and motif detection, enhancing its utility in biological research.
Authors: Himanshu Aggarwal, Liza Al-Shikhley, Bertrand Thirion
Abstract: Decoding cognitive states from functional magnetic resonance imaging is central to understanding the functional organization of the brain. Within-subject decoding avoids between-subject correspondence problems but requires large sample sizes to make accurate predictions; obtaining such large sample sizes is both challenging and expensive. Here, we investigate an ensemble approach to decoding that combines the classifiers trained on data from other subjects to decode cognitive states in a new subject. We compare it with the conventional decoding approach on five different datasets and cognitive tasks. We find that it outperforms the conventional approach by up to 20% in accuracy, especially for datasets with limited per-subject data. The ensemble approach is particularly advantageous when the classifier is trained in voxel space. Furthermore, a Multi-layer Perceptron turns out to be a good default choice as an ensemble method. These results show that the pre-training strategy reduces the need for large per-subject data.
Authors: Khai Le-Duc, Ryan Zhang, Ngoc Son Nguyen, Tan-Hanh Pham, Anh Dao, Ba Hung Ngo, Anh Totti Nguyen, Truong-Son Hy
Abstract: Vision-language models have been extensively explored across a wide range of tasks, achieving satisfactory performance; however, their application in medical imaging remains underexplored. In this work, we propose a unified framework - LiteGPT - for the medical imaging. We leverage multiple pre-trained visual encoders to enrich information and enhance the performance of vision-language models. To the best of our knowledge, this is the first study to utilize vision-language models for the novel task of joint localization and classification in medical images. Besides, we are pioneers in providing baselines for disease localization in chest X-rays. Finally, we set new state-of-the-art performance in the image classification task on the well-benchmarked VinDr-CXR dataset. All code and models are publicly available online: https://github.com/leduckhai/LiteGPT
Authors: Sreetama Sarkar, Gourav Datta, Souvik Kundu, Kai Zheng, Chirayata Bhattacharyya, Peter A. Beerel
Abstract: Video tasks are compute-heavy and thus pose a challenge when deploying in real-time applications, particularly for tasks that require state-of-the-art Vision Transformers (ViTs). Several research efforts have tried to address this challenge by leveraging the fact that large portions of the video undergo very little change across frames, leading to redundant computations in frame-based video processing. In particular, some works leverage pixel or semantic differences across frames, however, this yields limited latency benefits with significantly increased memory overhead. This paper, in contrast, presents a strategy for masking regions in video frames that leverages the semantic information in images and the temporal correlation between frames to significantly reduce FLOPs and latency with little to no penalty in performance over baseline models. In particular, we demonstrate that by leveraging extracted features from previous frames, ViT backbones directly benefit from region masking, skipping up to 80% of input regions, improving FLOPs and latency by 3.14x and 1.5x. We improve memory and latency over the state-of-the-art (SOTA) by 2.3x and 1.14x, while maintaining similar detection performance. Additionally, our approach demonstrates promising results on convolutional neural networks (CNNs) and provides latency improvements over the SOTA up to 1.3x using specialized computational kernels.
Authors: Arshika Lalan, Shresth Verma, Paula Rodriguez Diaz, Panayiotis Danassis, Amrita Mahale, Kumar Madhu Sudan, Aparna Hegde, Milind Tambe, Aparna Taneja
Abstract: Harnessing the wide-spread availability of cell phones, many nonprofits have launched mobile health (mHealth) programs to deliver information via voice or text to beneficiaries in underserved communities, with maternal and infant health being a key area of such mHealth programs. Unfortunately, dwindling listenership is a major challenge, requiring targeted interventions using limited resources. This paper focuses on Kilkari, the world's largest mHealth program for maternal and child care - with over 3 million active subscribers at a time - launched by India's Ministry of Health and Family Welfare (MoHFW) and run by the non-profit ARRMAN. We present a system called CHAHAK that aims to reduce automated dropouts as well as boost engagement with the program through the strategic allocation of interventions to beneficiaries. Past work in a similar domain has focused on a much smaller scale mHealth program and used markovian restless multiarmed bandits to optimize a single limited intervention resource. However this paper demonstrates the challenges in adopting a markovian approach in Kilkari; therefore CHAHAK instead relies on non-markovian time-series restless bandits, and optimizes multiple interventions to improve listenership. We use real Kilkari data from the Odisha state in India to show CHAHAK's effectiveness in harnessing multiple interventions to boost listenership, benefiting marginalized communities. When deployed CHAHAK will assist the largest maternal mHealth program to date.
Authors: Maciej Grzenda, Marcin Luckner, Jakub Zawieska, Przemys{\l}aw Wrona
Abstract: Demand for sustainable mobility is particularly high in urban areas. Hence, there is a growing need to predict when people will decide to use different travel modes with an emphasis on environmentally friendly travel modes. As travel mode choice (TMC) is influenced by multiple factors, in a growing number of cases machine learning methods are used to predict travel mode choices given respondent and journey features. Typically, travel diaries are used to provide core relevant data. However, other features such as attributes of mode alternatives including, but not limited to travel times, and, in the case of public transport (PT), also walking distances have a major impact on whether a person decides to use a travel mode of interest. Hence, in this work, we propose an architecture of a software platform performing the data fusion combining data documenting journeys with the features calculated to summarise transport options available for these journeys, built environment and environmental factors such as weather conditions possibly influencing travel mode decisions. Furthermore, we propose various novel features, many of which we show to be among the most important for TMC prediction. We propose how stream processing engines and other Big Data systems can be used for their calculation. The data processed by the platform is used to develop machine learning models predicting travel mode choices. To validate the platform, we propose ablation studies investigating the importance of individual feature subsets calculated by it and their impact on the TMC models built with them. In our experiments, we combine survey data, GPS traces, weather and pollution time series, transport model data, and spatial data of the built environment. The growth in the accuracy of TMC models built with the additional features is up to 18.2% compared to the use of core survey data only.
Authors: Robert Spektor, Tom Friedman, Itay Or, Gil Bolotin, Shlomi Laufer
Abstract: This work presents a novel approach to monocular 6D pose estimation of surgical instruments in open surgery, addressing challenges such as object articulations, symmetries, occlusions, and lack of annotated real-world data. The method leverages synthetic data generation and domain adaptation techniques to overcome these obstacles. The proposed approach consists of three main components: (1) synthetic data generation using 3D modeling of surgical tools with articulation rigging and physically-based rendering; (2) a tailored pose estimation framework combining object detection with pose estimation and a hybrid geometric fusion strategy; and (3) a training strategy that utilizes both synthetic and real unannotated data, employing domain adaptation on real video data using automatically generated pseudo-labels. Evaluations conducted on videos of open surgery demonstrate the good performance and real-world applicability of the proposed method, highlighting its potential for integration into medical augmented reality and robotic systems. The approach eliminates the need for extensive manual annotation of real surgical data.
Authors: R{\i}za \"Oz\c{c}elik, Francesca Grisoni
Abstract: Deep learning has significantly accelerated drug discovery, with 'chemical language' processing (CLP) emerging as a prominent approach. CLP learns from molecular string representations (e.g., Simplified Molecular Input Line Entry Systems [SMILES] and Self-Referencing Embedded Strings [SELFIES]) with methods akin to natural language processing. Despite their growing importance, training predictive CLP models is far from trivial, as it involves many 'bells and whistles'. Here, we analyze the key elements of CLP training, to provide guidelines for newcomers and experts alike. Our study spans three neural network architectures, two string representations, three embedding strategies, across ten bioactivity datasets, for both classification and regression purposes. This 'hitchhiker's guide' not only underscores the importance of certain methodological choices, but it also equips researchers with practical recommendations on ideal choices, e.g., in terms of neural network architectures, molecular representations, and hyperparameter optimization.
Authors: Thomas Trask, Dr. Nicholas Lytle, Michael Boyle, Dr. David Joyner, Dr. Ahmed Mubarak
Abstract: As online courses become the norm in the higher-education landscape, investigations into student performance between students who take online vs on-campus versions of classes become necessary. While attention has been given to looking at differences in learning outcomes through comparisons of students' end performance, less attention has been given in comparing students' engagement patterns between different modalities. In this study, we analyze a heterogeneous knowledge graph consisting of students, course videos, formative assessments and their interactions to predict student performance via a Graph Convolutional Network (GCN). Using students' performance on the assessments, we attempt to determine a useful model for identifying at-risk students. We then compare the models generated between 5 on-campus and 2 fully-online MOOC-style instances of the same course. The model developed achieved a 70-90\% accuracy of predicting whether a student would pass a particular problem set based on content consumed, course instance, and modality.
Authors: Yanting Miao, William Loh, Suraj Kothawade, Pascal Poupart, Abdullah Rashwan, Yeqing Li
Abstract: Text-to-image generative models have recently attracted considerable interest, enabling the synthesis of high-quality images from textual prompts. However, these models often lack the capability to generate specific subjects from given reference images or to synthesize novel renditions under varying conditions. Methods like DreamBooth and Subject-driven Text-to-Image (SuTI) have made significant progress in this area. Yet, both approaches primarily focus on enhancing similarity to reference images and require expensive setups, often overlooking the need for efficient training and avoiding overfitting to the reference images. In this work, we present the $\lambda$-Harmonic reward function, which provides a reliable reward signal and enables early stopping for faster training and effective regularization. By combining the Bradley-Terry preference model, the $\lambda$-Harmonic reward function also provides preference labels for subject-driven generation tasks. We propose Reward Preference Optimization (RPO), which offers a simpler setup (requiring only $3\%$ of the negative samples used by DreamBooth) and fewer gradient steps for fine-tuning. Unlike most existing methods, our approach does not require training a text encoder or optimizing text embeddings and achieves text-image alignment by fine-tuning only the U-Net component. Empirically, $\lambda$-Harmonic proves to be a reliable approach for model selection in subject-driven generation tasks. Based on preference labels and early stopping validation from the $\lambda$-Harmonic reward function, our algorithm achieves a state-of-the-art CLIP-I score of 0.833 and a CLIP-T score of 0.314 on DreamBench.
Authors: Yang Cheng, Qingyuan Shu, Albert Lee, Haoran He, Ivy Zhu, Haris Suhail, Minzhang Chen, Renhe Chen, Zirui Wang, Hantao Zhang, Chih-Yao Wang, Shan-Yi Yang, Yu-Chen Hsin, Cheng-Yi Shih, Hsin-Han Lee, Ran Cheng, Sudhakar Pamarti, Xufeng Kou, Kang L. Wang
Abstract: Stochastic diffusion processes are pervasive in nature, from the seemingly erratic Brownian motion to the complex interactions of synaptically-coupled spiking neurons. Recently, drawing inspiration from Langevin dynamics, neuromorphic diffusion models were proposed and have become one of the major breakthroughs in the field of generative artificial intelligence. Unlike discriminative models that have been well developed to tackle classification or regression tasks, diffusion models as well as other generative models such as ChatGPT aim at creating content based upon contexts learned. However, the more complex algorithms of these models result in high computational costs using today's technologies, creating a bottleneck in their efficiency, and impeding further development. Here, we develop a spintronic voltage-controlled magnetoelectric memory hardware for the neuromorphic diffusion process. The in-memory computing capability of our spintronic devices goes beyond current Von Neumann architecture, where memory and computing units are separated. Together with the non-volatility of magnetic memory, we can achieve high-speed and low-cost computing, which is desirable for the increasing scale of generative models in the current era. We experimentally demonstrate that the hardware-based true random diffusion process can be implemented for image generation and achieve comparable image quality to software-based training as measured by the Frechet inception distance (FID) score, achieving ~10^3 better energy-per-bit-per-area over traditional hardware.
Authors: Hong Jun Jeon, Benjamin Van Roy
Abstract: The staggering progress of machine learning in the past decade has been a sight to behold. In retrospect, it is both remarkable and unsettling that these milestones were achievable with little to no rigorous theory to guide experimentation. Despite this fact, practitioners have been able to guide their future experimentation via observations from previous large-scale empirical investigations. However, alluding to Plato's Allegory of the cave, it is likely that the observations which form the field's notion of reality are but shadows representing fragments of that reality. In this work, we propose a theoretical framework which attempts to answer what exists outside of the cave. To the theorist, we provide a framework which is mathematically rigorous and leaves open many interesting ideas for future exploration. To the practitioner, we provide a framework whose results are very intuitive, general, and which will help form principles to guide future investigations. Concretely, we provide a theoretical framework rooted in Bayesian statistics and Shannon's information theory which is general enough to unify the analysis of many phenomena in machine learning. Our framework characterizes the performance of an optimal Bayesian learner, which considers the fundamental limits of information. Throughout this work, we derive very general theoretical results and apply them to derive insights specific to settings ranging from data which is independently and identically distributed under an unknown distribution, to data which is sequential, to data which exhibits hierarchical structure amenable to meta-learning. We conclude with a section dedicated to characterizing the performance of misspecified algorithms. These results are exciting and particularly relevant as we strive to overcome increasingly difficult machine learning challenges in this endlessly complex world.
Authors: Hadden Kim, Tamer A. Zaki
Abstract: Evolutional deep neural networks (EDNN) solve partial differential equations (PDEs) by marching the network representation of the solution fields, using the governing equations. Use of a single network to solve coupled PDEs on large domains requires a large number of network parameters and incurs a significant computational cost. We introduce coupled EDNN (C-EDNN) to solve systems of PDEs by using independent networks for each state variable, which are only coupled through the governing equations. We also introduce distributed EDNN (D-EDNN) by spatially partitioning the global domain into several elements and assigning individual EDNNs to each element to solve the local evolution of the PDE. The networks then exchange the solution and fluxes at their interfaces, similar to flux-reconstruction methods, and ensure that the PDE dynamics are accurately preserved between neighboring elements. Together C-EDNN and D-EDNN form the general class of Multi-EDNN methods. We demonstrate these methods with aid of canonical problems including linear advection, the heat equation, and the compressible Navier-Stokes equations in Couette and Taylor-Green flows.
Authors: Cagatay Isil, Hatice Ceylan Koydemir, Merve Eryilmaz, Kevin de Haan, Nir Pillar, Koray Mentesoglu, Aras Firat Unal, Yair Rivenson, Sukantha Chandrasekaran, Omai B. Garner, Aydogan Ozcan
Abstract: Gram staining has been one of the most frequently used staining protocols in microbiology for over a century, utilized across various fields, including diagnostics, food safety, and environmental monitoring. Its manual procedures make it vulnerable to staining errors and artifacts due to, e.g., operator inexperience and chemical variations. Here, we introduce virtual Gram staining of label-free bacteria using a trained deep neural network that digitally transforms darkfield images of unstained bacteria into their Gram-stained equivalents matching brightfield image contrast. After a one-time training effort, the virtual Gram staining model processes an axial stack of darkfield microscopy images of label-free bacteria (never seen before) to rapidly generate Gram staining, bypassing several chemical steps involved in the conventional staining process. We demonstrated the success of the virtual Gram staining workflow on label-free bacteria samples containing Escherichia coli and Listeria innocua by quantifying the staining accuracy of the virtual Gram staining model and comparing the chromatic and morphological features of the virtually stained bacteria against their chemically stained counterparts. This virtual bacteria staining framework effectively bypasses the traditional Gram staining protocol and its challenges, including stain standardization, operator errors, and sensitivity to chemical variations.
Authors: Naoya Sogi, Takashi Shibata, Makoto Terao
Abstract: The pre-trained vision and language (V\&L) models have substantially improved the performance of cross-modal image-text retrieval. In general, however, V\&L models have limited retrieval performance for small objects because of the rough alignment between words and the small objects in the image. In contrast, it is known that human cognition is object-centric, and we pay more attention to important objects, even if they are small. To bridge this gap between the human cognition and the V\&L model's capability, we propose a cross-modal image-text retrieval framework based on ``object-aware query perturbation.'' The proposed method generates a key feature subspace of the detected objects and perturbs the corresponding queries using this subspace to improve the object awareness in the image. In our proposed method, object-aware cross-modal image-text retrieval is possible while keeping the rich expressive power and retrieval performance of existing V\&L models without additional fine-tuning. Comprehensive experiments on four public datasets show that our method outperforms conventional algorithms.
Authors: Markus Wei{\ss}flog, Peter Protzel, Peer Neubert
Abstract: Class-incremental continual learning is an important area of research, as static deep learning methods fail to adapt to changing tasks and data distributions. In previous works, promising results were achieved using replay and compressed replay techniques. In the field of regular replay, GDumb achieved outstanding results but requires a large amount of memory. This problem can be addressed by compressed replay techniques. The goal of this work is to evaluate compressed replay in the pipeline of GDumb. We propose FETCH, a two-stage compression approach. First, the samples from the continual datastream are encoded by the early layers of a pre-trained neural network. Second, the samples are compressed before being stored in the episodic memory. Following GDumb, the remaining classification head is trained from scratch using only the decompressed samples from the reply memory. We evaluate FETCH in different scenarios and show that this approach can increase accuracy on CIFAR10 and CIFAR100. In our experiments, simple compression methods (e.g., quantization of tensors) outperform deep autoencoders. In the future, FETCH could serve as a baseline for benchmarking compressed replay learning in constrained memory scenarios.
Authors: Indranil Bandyopadhyay, Rahul Karmakar
Abstract: Sentiment analysis (SA), is an approach of natural language processing (NLP) for determining a text's emotional tone by analyzing subjective information such as views, feelings, and attitudes toward specific topics, products, services, events, or experiences. This study attempts to develop an advanced deep learning (DL) model for SA to understand global audience emotions through tweets in the context of the Olympic Games. The findings represent global attitudes around the Olympics and contribute to advancing the SA models. We have used NLP for tweet pre-processing and sophisticated DL models for arguing with SA, this research enhances the reliability and accuracy of sentiment classification. The study focuses on data selection, preprocessing, visualization, feature extraction, and model building, featuring a baseline Na\"ive Bayes (NB) model and three advanced DL models: Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and Bidirectional Encoder Representations from Transformers (BERT). The results of the experiments show that the BERT model can efficiently classify sentiments related to the Olympics, achieving the highest accuracy of 99.23%.
Authors: Kun Sun, Rong Wang
Abstract: The development of different theories of discourse structure has led to the establishment of discourse corpora based on these theories. However, the existence of discourse corpora established on different theoretical bases creates challenges when it comes to exploring them in a consistent and cohesive way. This study has as its primary focus the conversion of PDTB annotations into dependency structures. It employs refined BERT-based discourse parsers to test the validity of the dependency data derived from the PDTB-style corpora in English, Chinese, and several other languages. By converting both PDTB and RST annotations for the same texts into dependencies, this study also applies ``dependency distance'' metrics to examine the correlation between RST dependencies and PDTB dependencies in English. The results show that the PDTB dependency data is valid and that there is a strong correlation between the two types of dependency distance. This study presents a comprehensive approach for analyzing and evaluating discourse corpora by employing discourse dependencies to achieve unified analysis. By applying dependency representations, we can extract data from PDTB, RST, and SDRT corpora in a coherent and unified manner. Moreover, the cross-linguistic validation establishes the framework's generalizability beyond English. The establishment of this comprehensive dependency framework overcomes limitations of existing discourse corpora, supporting a diverse range of algorithms and facilitating further studies in computational discourse analysis and language sciences.
Authors: Finn Behrendt, Debayan Bhattacharya, Robin Mieling, Lennart Maack, Julia Kr\"uger, Roland Opfer, Alexander Schlaefer
Abstract: Unsupervised Anomaly Detection (UAD) methods rely on healthy data distributions to identify anomalies as outliers. In brain MRI, a common approach is reconstruction-based UAD, where generative models reconstruct healthy brain MRIs, and anomalies are detected as deviations between input and reconstruction. However, this method is sensitive to imperfect reconstructions, leading to false positives that impede the segmentation. To address this limitation, we construct multiple reconstructions with probabilistic diffusion models. We then analyze the resulting distribution of these reconstructions using the Mahalanobis distance to identify anomalies as outliers. By leveraging information about normal variations and covariance of individual pixels within this distribution, we effectively refine anomaly scoring, leading to improved segmentation. Our experimental results demonstrate substantial performance improvements across various data sets. Specifically, compared to relying solely on single reconstructions, our approach achieves relative improvements of 15.9%, 35.4%, 48.0%, and 4.7% in terms of AUPRC for the BRATS21, ATLAS, MSLUB and WMH data sets, respectively.
Authors: Mingqing Xiao, Qingyan Meng, Zongpeng Zhang, Di He, Zhouchen Lin
Abstract: Brain-inspired neuromorphic computing with spiking neural networks (SNNs) is a promising energy-efficient computational approach. However, successfully training SNNs in a more biologically plausible and neuromorphic-hardware-friendly way is still challenging. Most recent methods leverage spatial and temporal backpropagation (BP), not adhering to neuromorphic properties. Despite the efforts of some online training methods, tackling spatial credit assignments by alternatives with comparable performance as spatial BP remains a significant problem. In this work, we propose a novel method, online pseudo-zeroth-order (OPZO) training. Our method only requires a single forward propagation with noise injection and direct top-down signals for spatial credit assignment, avoiding spatial BP's problem of symmetric weights and separate phases for layer-by-layer forward-backward propagation. OPZO solves the large variance problem of zeroth-order methods by the pseudo-zeroth-order formulation and momentum feedback connections, while having more guarantees than random feedback. Combining online training, OPZO can pave paths to on-chip SNN training. Experiments on neuromorphic and static datasets with fully connected and convolutional networks demonstrate the effectiveness of OPZO with similar performance compared with spatial BP, as well as estimated low training costs.
Authors: Ichrak Mokhtari, Walid Bechkit, Mohamed Sami Assenine, Herv\'e Rivano
Abstract: The rapid rise of air pollution events necessitates accurate, real-time monitoring for informed mitigation strategies. Data Assimilation (DA) methods provide promising solutions, but their effectiveness hinges heavily on optimal measurement locations. This paper presents a novel approach for air quality mapping where autonomous drones, guided by a collaborative multi-agent reinforcement learning (MARL) framework, act as airborne detectives. Ditching the limitations of static sensor networks, the drones engage in a synergistic interaction, adapting their flight paths in real time to gather optimal data for Data Assimilation (DA). Our approach employs a tailored reward function with dynamic credit assignment, enabling drones to prioritize informative measurements without requiring unavailable ground truth data, making it practical for real-world deployments. Extensive experiments using a real-world dataset demonstrate that our solution achieves significantly improved pollution estimates, even with limited drone resources or limited prior knowledge of the pollution plume. Beyond air quality, this solution unlocks possibilities for tackling diverse environmental challenges like wildfire detection and management through scalable and autonomous drone cooperation.
Authors: Salma Afifi, Ishan Thakkar, Sudeep Pasricha
Abstract: Transformers have emerged as a powerful tool for natural language processing (NLP) and computer vision. Through the attention mechanism, these models have exhibited remarkable performance gains when compared to conventional approaches like recurrent neural networks (RNNs) and convolutional neural networks (CNNs). Nevertheless, transformers typically demand substantial execution time due to their extensive computations and large memory footprint. Processing in-memory (PIM) and near-memory computing (NMC) are promising solutions to accelerating transformers as they offer high compute parallelism and memory bandwidth. However, designing PIM/NMC architectures to support the complex operations and massive amounts of data that need to be moved between layers in transformer neural networks remains a challenge. We propose ARTEMIS, a mixed analog-stochastic in-DRAM accelerator for transformer models. Through employing minimal changes to the conventional DRAM arrays, ARTEMIS efficiently alleviates the costs associated with transformer model execution by supporting stochastic computing for multiplications and temporal analog accumulations using a novel in-DRAM metal-on-metal capacitor. Our analysis indicates that ARTEMIS exhibits at least 3.0x speedup, 1.8x lower energy, and 1.9x better energy efficiency compared to GPU, TPU, CPU, and state-of-the-art PIM transformer hardware accelerators.
Authors: Medina Bandic, Pablo le Henaff, Anabel Ovide, Pau Escofet, Sahar Ben Rached, Santiago Rodrigo, Hans van Someren, Sergi Abadal, Eduard Alarcon, Carmen G. Almudever, Sebastian Feld
Abstract: Application-specific quantum computers offer the most efficient means to tackle problems intractable by classical computers. Realizing these architectures necessitates a deep understanding of quantum circuit properties and their relationship to execution outcomes on quantum devices. Our study aims to perform for the first time a rigorous examination of quantum circuits by introducing graph theory-based metrics extracted from their qubit interaction graph and gate dependency graph alongside conventional parameters describing the circuit itself. This methodology facilitates a comprehensive analysis and clustering of quantum circuits. Furthermore, it uncovers a connection between parameters rooted in both qubit interaction and gate dependency graphs, and the performance metrics for quantum circuit mapping, across a range of established quantum device and mapping configurations. Among the various device configurations, we particularly emphasize modular (i.e., multi-core) quantum computing architectures due to their high potential as a viable solution for quantum device scalability. This thorough analysis will help us to: i) identify key attributes of quantum circuits that affect the quantum circuit mapping performance metrics; ii) predict the performance on a specific chip for similar circuit structures; iii) determine preferable combinations of mapping techniques and hardware setups for specific circuits; and iv) define representative benchmark sets by clustering similarly structured circuits.
Authors: Chenze Shao, Fandong Meng, Jie Zhou
Abstract: As Large Language Models (LLMs) achieve remarkable progress in language understanding and generation, their training efficiency has become a critical concern. Traditionally, LLMs are trained to predict the next token in a sequence. Despite the success of token-level training, it suffers from considerable computational costs due to the need to process an extensive number of tokens. To mitigate this issue, this paper introduces patch-level training for LLMs, which reduces the sequence length by compressing multiple tokens into a single patch. During patch-level training, we feed the language model shorter sequences of patches and train it to predict the next patch, thereby processing the majority of the training data at a significantly reduced computational cost. Following this, the model continues token-level training on the remaining training data to align with the inference mode. Experiments on a diverse range of models (370M-2.7B parameters) demonstrate that patch-level training can reduce overall computational costs to 0.5$\times$, without compromising the model performance compared to token-level training. Source code: \url{https://github.com/shaochenze/PatchTrain}.
Authors: Richard Osuala, Daniel M. Lang, Anneliese Riess, Georgios Kaissis, Zuzanna Szafranowska, Grzegorz Skorupko, Oliver Diaz, Julia A. Schnabel, Karim Lekadir
Abstract: Deep learning holds immense promise for aiding radiologists in breast cancer detection. However, achieving optimal model performance is hampered by limitations in availability and sharing of data commonly associated to patient privacy concerns. Such concerns are further exacerbated, as traditional deep learning models can inadvertently leak sensitive training information. This work addresses these challenges exploring and quantifying the utility of privacy-preserving deep learning techniques, concretely, (i) differentially private stochastic gradient descent (DP-SGD) and (ii) fully synthetic training data generated by our proposed malignancy-conditioned generative adversarial network. We assess these methods via downstream malignancy classification of mammography masses using a transformer model. Our experimental results depict that synthetic data augmentation can improve privacy-utility tradeoffs in differentially private model training. Further, model pretraining on synthetic data achieves remarkable performance, which can be further increased with DP-SGD fine-tuning across all privacy guarantees. With this first in-depth exploration of privacy-preserving deep learning in breast imaging, we address current and emerging clinical privacy requirements and pave the way towards the adoption of private high-utility deep diagnostic models. Our reproducible codebase is publicly available at https://github.com/RichardObi/mammo_dp.
Authors: Irina Jurenka, Markus Kunesch, Kevin R. McKee, Daniel Gillick, Shaojian Zhu, Sara Wiltberger, Shubham Milind Phal, Katherine Hermann, Daniel Kasenberg, Avishkar Bhoopchand, Ankit Anand, Miruna P\^islar, Stephanie Chan, Lisa Wang, Jennifer She, Parsa Mahmoudieh, Aliya Rysbek, Wei-Jen Ko, Andrea Huber, Brett Wiltshire, Gal Elidan, Roni Rabin, Jasmin Rubinovitz, Amit Pitaru, Mac McAllister, Julia Wilkowski, David Choi, Roee Engelberg, Lidan Hackmon, Adva Levin, Rachel Griffin, Michael Sears, Filip Bar, Mia Mesar, Mana Jabbour, Arslan Chaudhry, James Cohan, Sridhar Thiagarajan, Nir Levine, Ben Brown, Dilan Gorur, Svetlana Grant, Rachel Hashimoshoni, Laura Weidinger, Jieru Hu, Dawn Chen, Kuba Dolecki, Canfer Akbulut, Maxwell Bileschi, Laura Culp, Wen-Xin Dong, Nahema Marchal, Kelsie Van Deman, Hema Bajaj Misra, Michael Duah, Moran Ambar, Avi Caciularu, Sandra Lefdal, Chris Summerfield, James An, Pierre-Alexandre Kamienny, Abhinit Mohdi, Theofilos Strinopoulous, Annie Hale, Wayne Anderson, Luis C. Cobo, Niv Efron, Muktha Ananda, Shakir Mohamed, Maureen Heymans, Zoubin Ghahramani, Yossi Matias, Ben Gomes, Lila Ibrahim
Abstract: A major challenge facing the world is the provision of equitable and universal access to quality education. Recent advances in generative AI (gen AI) have created excitement about the potential of new technologies to offer a personal tutor for every learner and a teaching assistant for every teacher. The full extent of this dream, however, has not yet materialised. We argue that this is primarily due to the difficulties with verbalising pedagogical intuitions into gen AI prompts and the lack of good evaluation practices, reinforced by the challenges in defining excellent pedagogy. Here we present our work collaborating with learners and educators to translate high level principles from learning science into a pragmatic set of seven diverse educational benchmarks, spanning quantitative, qualitative, automatic and human evaluations; and to develop a new set of fine-tuning datasets to improve the pedagogical capabilities of Gemini, introducing LearnLM-Tutor. Our evaluations show that LearnLM-Tutor is consistently preferred over a prompt tuned Gemini by educators and learners on a number of pedagogical dimensions. We hope that this work can serve as a first step towards developing a comprehensive educational evaluation framework, and that this can enable rapid progress within the AI and EdTech communities towards maximising the positive impact of gen AI in education.
Authors: Christoph Minixhofer, Ond\v{r}ej Klejch, Peter Bell
Abstract: Many recently published Text-to-Speech (TTS) systems produce audio close to real speech. However, TTS evaluation needs to be revisited to make sense of the results obtained with the new architectures, approaches and datasets. We propose evaluating the quality of synthetic speech as a combination of multiple factors such as prosody, speaker identity, and intelligibility. Our approach assesses how well synthetic speech mirrors real speech by obtaining correlates of each factor and measuring their distance from both real speech datasets and noise datasets. We benchmark 35 TTS systems developed between 2008 and 2024 and show that our score computed as an unweighted average of factors strongly correlates with the human evaluations from each time period.
Authors: Amit Prasad, Bappaditya Dey, Victor Blanco, Sandip Halder
Abstract: Deep learning-based semiconductor defect inspection has gained traction in recent years, offering a powerful and versatile approach that provides high accuracy, adaptability, and efficiency in detecting and classifying nano-scale defects. However, semiconductor manufacturing processes are continually evolving, leading to the emergence of new types of defects over time. This presents a significant challenge for conventional supervised defect detectors, as they may suffer from catastrophic forgetting when trained on new defect datasets, potentially compromising performance on previously learned tasks. An alternative approach involves the constant storage of previously trained datasets alongside pre-trained model versions, which can be utilized for (re-)training from scratch or fine-tuning whenever encountering a new defect dataset. However, adhering to such a storage template is impractical in terms of size, particularly when considering High-Volume Manufacturing (HVM). Additionally, semiconductor defect datasets, especially those encompassing stochastic defects, are often limited and expensive to obtain, thus lacking sufficient representation of the entire universal set of defectivity. This work introduces a task-agnostic, meta-learning approach aimed at addressing this challenge, which enables the incremental addition of new defect classes and scales to create a more robust and generalized model for semiconductor defect inspection. We have benchmarked our approach using real resist-wafer SEM (Scanning Electron Microscopy) datasets for two process steps, ADI and AEI, demonstrating its superior performance compared to conventional supervised training methods.
Authors: Paul Fearnhead, Christopher Nemeth, Chris J. Oates, Chris Sherlock
Abstract: This book aims to provide a graduate-level introduction to advanced topics in Markov chain Monte Carlo (MCMC) algorithms, as applied broadly in the Bayesian computational context. Most, if not all of these topics (stochastic gradient MCMC, non-reversible MCMC, continuous time MCMC, and new techniques for convergence assessment) have emerged as recently as the last decade, and have driven substantial recent practical and theoretical advances in the field. A particular focus is on methods that are scalable with respect to either the amount of data, or the data dimension, motivated by the emerging high-priority application areas in machine learning and AI.
Authors: Rajat Koner, Gagan Jain, Prateek Jain, Volker Tresp, Sujoy Paul
Abstract: Vision Transformers (ViT) have emerged as the de-facto choice for numerous industry grade vision solutions. But their inference cost can be prohibitive for many settings, as they compute self-attention in each layer which suffers from quadratic computational complexity in the number of tokens. On the other hand, spatial information in images and spatio-temporal information in videos is usually sparse and redundant. In this work, we introduce LookupViT, that aims to exploit this information sparsity to reduce ViT inference cost. LookupViT provides a novel general purpose vision transformer block that operates by compressing information from higher resolution tokens to a fixed number of tokens. These few compressed tokens undergo meticulous processing, while the higher-resolution tokens are passed through computationally cheaper layers. Information sharing between these two token sets is enabled through a bidirectional cross-attention mechanism. The approach offers multiple advantages - (a) easy to implement on standard ML accelerators (GPUs/TPUs) via standard high-level operators, (b) applicable to standard ViT and its variants, thus generalizes to various tasks, (c) can handle different tokenization and attention approaches. LookupViT also offers flexibility for the compressed tokens, enabling performance-computation trade-offs in a single trained model. We show LookupViT's effectiveness on multiple domains - (a) for image-classification (ImageNet-1K and ImageNet-21K), (b) video classification (Kinetics400 and Something-Something V2), (c) image captioning (COCO-Captions) with a frozen encoder. LookupViT provides $2\times$ reduction in FLOPs while upholding or improving accuracy across these domains. In addition, LookupViT also demonstrates out-of-the-box robustness and generalization on image classification (ImageNet-C,R,A,O), improving by up to $4\%$ over ViT.
Authors: Christoph Hertrich, Leon Sering
Abstract: This paper studies the expressive power of artificial neural networks with rectified linear units. In order to study them as a model of real-valued computation, we introduce the concept of Max-Affine Arithmetic Programs and show equivalence between them and neural networks concerning natural complexity measures. We then use this result to show that two fundamental combinatorial optimization problems can be solved with polynomial-size neural networks. First, we show that for any undirected graph with $n$ nodes, there is a neural network (with fixed weights and biases) of size $\mathcal{O}(n^3)$ that takes the edge weights as input and computes the value of a minimum spanning tree of the graph. Second, we show that for any directed graph with $n$ nodes and $m$ arcs, there is a neural network of size $\mathcal{O}(m^2n^2)$ that takes the arc capacities as input and computes a maximum flow. Our results imply that these two problems can be solved with strongly polynomial time algorithms that solely use affine transformations and maxima computations, but no comparison-based branchings.
Authors: Christoph Hertrich, Amitabh Basu, Marco Di Summa, Martin Skutella
Abstract: We contribute to a better understanding of the class of functions that can be represented by a neural network with ReLU activations and a given architecture. Using techniques from mixed-integer optimization, polyhedral theory, and tropical geometry, we provide a mathematical counterbalance to the universal approximation theorems which suggest that a single hidden layer is sufficient for learning any function. In particular, we investigate whether the class of exactly representable functions strictly increases by adding more layers (with no restrictions on size). As a by-product of our investigations, we settle an old conjecture about piecewise linear functions by Wang and Sun (2005) in the affirmative. We also present upper bounds on the sizes of neural networks required to represent functions with logarithmic depth.
Authors: Jaehui Hwang, Dongyoon Han, Byeongho Heo, Song Park, Sanghyuk Chun, Jong-Seok Lee
Abstract: In recent years, many deep neural architectures have been developed for image classification. Whether they are similar or dissimilar and what factors contribute to their (dis)similarities remains curious. To address this question, we aim to design a quantitative and scalable similarity measure between neural architectures. We propose Similarity by Attack Transferability (SAT) from the observation that adversarial attack transferability contains information related to input gradients and decision boundaries widely used to understand model behaviors. We conduct a large-scale analysis on 69 state-of-the-art ImageNet classifiers using our proposed similarity function to answer the question. Moreover, we observe neural architecture-related phenomena using model similarity that model diversity can lead to better performance on model ensembles and knowledge distillation under specific conditions. Our results provide insights into why developing diverse neural architectures with distinct components is necessary.
Authors: Florian Tram\`er, Gautam Kamath, Nicholas Carlini
Abstract: The performance of differentially private machine learning can be boosted significantly by leveraging the transfer learning capabilities of non-private models pretrained on large public datasets. We critically review this approach. We primarily question whether the use of large Web-scraped datasets should be viewed as differential-privacy-preserving. We caution that publicizing these models pretrained on Web data as "private" could lead to harm and erode the public's trust in differential privacy as a meaningful definition of privacy. Beyond the privacy considerations of using public data, we further question the utility of this paradigm. We scrutinize whether existing machine learning benchmarks are appropriate for measuring the ability of pretrained models to generalize to sensitive domains, which may be poorly represented in public Web data. Finally, we notice that pretraining has been especially impactful for the largest available models -- models sufficiently large to prohibit end users running them on their own devices. Thus, deploying such models today could be a net loss for privacy, as it would require (private) data to be outsourced to a more compute-powerful third party. We conclude by discussing potential paths forward for the field of private learning, as public pretraining becomes more popular and powerful.
Authors: Lakshmi Mandal, Shalabh Bhatnagar
Abstract: We consider the problem of finding the optimal value of n in the n-step temporal difference (TD) learning algorithm. Our objective function for the optimization problem is the average root mean squared error (RMSE). We find the optimal n by resorting to a model-free optimization technique involving a one-simulation simultaneous perturbation stochastic approximation (SPSA) based procedure. Whereas SPSA is a zeroth-order continuous optimization procedure, we adapt it to the discrete optimization setting by using a random projection operator. We prove the asymptotic convergence of the recursion by showing that the sequence of n-updates obtained using zeroth-order stochastic gradient search converges almost surely to an internally chain transitive invariant set of an associated differential inclusion. This results in convergence of the discrete parameter sequence to the optimal n in n-step TD. Through experiments, we show that the optimal value of n is achieved with our SDPSA algorithm for arbitrary initial values. We further show using numerical evaluations that SDPSA outperforms the state-of-the-art discrete parameter stochastic optimization algorithm Optimal Computing Budget Allocation (OCBA) on benchmark RL tasks.
Authors: Lorenzo Basile, Nikos Karantzas, Alberto D'Onofrio, Luca Bortolussi, Alex Rodriguez, Fabio Anselmi
Abstract: Despite their impressive performance in classification tasks, neural networks are known to be vulnerable to adversarial attacks, subtle perturbations of the input data designed to deceive the model. In this work, we investigate the relation between these perturbations and the implicit bias of neural networks trained with gradient-based algorithms. To this end, we analyse the network's implicit bias through the lens of the Fourier transform. Specifically, we identify the minimal and most critical frequencies necessary for accurate classification or misclassification respectively for each input image and its adversarially perturbed version, and uncover the correlation among those. To this end, among other methods, we use a newly introduced technique capable of detecting non-linear correlations between high-dimensional datasets. Our results provide empirical evidence that the network bias in Fourier space and the target frequencies of adversarial attacks are highly correlated and suggest new potential strategies for adversarial defence.
Authors: Hyeonah Kim, Minsu Kim, Sungsoo Ahn, Jinkyoo Park
Abstract: Deep reinforcement learning (DRL) has significantly advanced the field of combinatorial optimization (CO). However, its practicality is hindered by the necessity for a large number of reward evaluations, especially in scenarios involving computationally intensive function assessments. To enhance the sample efficiency, we propose a simple but effective method, called symmetric replay training (SRT), which can be easily integrated into various DRL methods. Our method leverages high-reward samples to encourage exploration of the under-explored symmetric regions without additional online interactions - free. Through replay training, the policy is trained to maximize the likelihood of the symmetric trajectories of discovered high-rewarded samples. Experimental results demonstrate the consistent improvement of our method in sample efficiency across diverse DRL methods applied to real-world tasks, such as molecular optimization and hardware design.
Authors: Xin Mu, Yu Wang, Yehong Zhang, Jiaqi Zhang, Hui Wang, Yang Xiang, Yue Yu
Abstract: Understanding the life cycle of the machine learning (ML) model is an intriguing area of research (e.g., understanding where the model comes from, how it is trained, and how it is used). This paper focuses on a novel problem within this field, namely Model Provenance (MP), which concerns the relationship between a target model and its pre-training model and aims to determine whether a source model serves as the provenance for a target model. This is an important problem that has significant implications for ensuring the security and intellectual property of machine learning models but has not received much attention in the literature. To fill in this gap, we introduce a novel concept of Model DNA which represents the unique characteristics of a machine learning model. We utilize a data-driven and model-driven representation learning method to encode the model's training data and input-output information as a compact and comprehensive representation (i.e., DNA) of the model. Using this model DNA, we develop an efficient framework for model provenance identification, which enables us to identify whether a source model is a pre-training model of a target model. We conduct evaluations on both computer vision and natural language processing tasks using various models, datasets, and scenarios to demonstrate the effectiveness of our approach in accurately identifying model provenance.
Authors: Eran Malach
Abstract: Large language models display remarkable capabilities in logical and mathematical reasoning, allowing them to solve complex tasks. Interestingly, these abilities emerge in networks trained on the simple task of next-token prediction. In this work, we present a theoretical framework for studying auto-regressive next-token predictors. We demonstrate that even simple models such as linear next-token predictors, trained on Chain-of-Thought (CoT) data, can approximate any function efficiently computed by a Turing machine. We introduce a new complexity measure -- length complexity -- which measures the number of intermediate tokens in a CoT sequence required to approximate some target function, and analyze the interplay between length complexity and other notions of complexity. Finally, we show experimentally that simple next-token predictors, such as linear networks and shallow Multi-Layer Perceptrons (MLPs), display non-trivial performance on text generation and arithmetic tasks. Our results demonstrate that the power of today's LLMs can be attributed, to a great extent, to the auto-regressive next-token training scheme, and not necessarily to a particular choice of architecture.
Authors: Taejong Joo, Diego Klabjan
Abstract: Distribution shifts pose significant challenges for model calibration and model selection tasks in the unsupervised domain adaptation problem -- a scenario where the goal is to perform well in a distribution shifted domain without labels. In this work, we tackle difficulties coming from distribution shifts by developing a novel importance weighted group accuracy estimator. Specifically, we present a new perspective of addressing the model calibration and model selection tasks by estimating the group accuracy. Then, we formulate an optimization problem for finding an importance weight that leads to an accurate group accuracy estimation with theoretical analyses. Our extensive experiments show that our approach improves state-of-the-art performances by 22% in the model calibration task and 14% in the model selection task.
Authors: Mehrshad Saadatinia, Armin Salimi-Badr
Abstract: In this study, we leverage a deep learning-based method for the automatic diagnosis of schizophrenia using EEG brain recordings. This approach utilizes generative data augmentation, a powerful technique that enhances the accuracy of the diagnosis. To enable the utilization of time-frequency features, spectrograms were extracted from the raw signals. After exploring several neural network architectural setups, a proper convolutional neural network (CNN) was used for the initial diagnosis. Subsequently, using Wasserstein GAN with Gradient Penalty (WGAN-GP) and Variational Autoencoder (VAE), two different synthetic datasets were generated in order to augment the initial dataset and address the over-fitting issue. The augmented dataset using VAE achieved a 3.0\% improvement in accuracy reaching up to 99.0\% and yielded a lower loss value as well as a faster convergence. Finally, we addressed the lack of trust in black-box models using the Local Interpretable Model-agnostic Explanations (LIME) algorithm to determine the most important superpixels (frequencies) in the diagnosis process.
Authors: Wonho Bae, Jing Wang, Danica J. Sutherland
Abstract: Most meta-learning methods assume that the (very small) context set used to establish a new task at test time is passively provided. In some settings, however, it is feasible to actively select which points to label; the potential gain from a careful choice is substantial, but the setting requires major differences from typical active learning setups. We clarify the ways in which active meta-learning can be used to label a context set, depending on which parts of the meta-learning process use active learning. Within this framework, we propose a natural algorithm based on fitting Gaussian mixtures for selecting which points to label; though simple, the algorithm also has theoretical motivation. The proposed algorithm outperforms state-of-the-art active learning methods when used with various meta-learning algorithms across several benchmark datasets.
Authors: Daniel Marczak, Sebastian Cygert, Tomasz Trzci\'nski, Bart{\l}omiej Twardowski
Abstract: In the field of continual learning, models are designed to learn tasks one after the other. While most research has centered on supervised continual learning, there is a growing interest in unsupervised continual learning, which makes use of the vast amounts of unlabeled data. Recent studies have highlighted the strengths of unsupervised methods, particularly self-supervised learning, in providing robust representations. The improved transferability of those representations built with self-supervised methods is often associated with the role played by the multi-layer perceptron projector. In this work, we depart from this observation and reexamine the role of supervision in continual representation learning. We reckon that additional information, such as human annotations, should not deteriorate the quality of representations. Our findings show that supervised models when enhanced with a multi-layer perceptron head, can outperform self-supervised models in continual representation learning. This highlights the importance of the multi-layer perceptron projector in shaping feature transferability across a sequence of tasks in continual learning. The code is available on github: https://github.com/danielm1405/sl-vs-ssl-cl.
Authors: Seth Nabarro, Mark van der Wilk, Andrew J Davison
Abstract: We propose an approach to do learning in Gaussian factor graphs. We treat all relevant quantities (inputs, outputs, parameters, latents) as random variables in a graphical model, and view both training and prediction as inference problems with different observed nodes. Our experiments show that these problems can be efficiently solved with belief propagation (BP), whose updates are inherently local, presenting exciting opportunities for distributed and asynchronous training. Our approach can be scaled to deep networks and provides a natural means to do continual learning: use the BP-estimated parameter marginals of the current task as parameter priors for the next. On a video denoising task we demonstrate the benefit of learnable parameters over a classical factor graph approach and we show encouraging performance of deep factor graphs for continual image classification.
Authors: Xingtong Yu, Zhenghao Liu, Yuan Fang, Zemin Liu, Sihong Chen, Xinming Zhang
Abstract: Graph neural networks have emerged as a powerful tool for graph representation learning, but their performance heavily relies on abundant task-specific supervision. To reduce labeling requirement, the "pre-train, prompt" paradigms have become increasingly common. However, existing study of prompting on graphs is limited, lacking a universal treatment to appeal to different downstream tasks. In this paper, we propose GraphPrompt, a novel pre-training and prompting framework on graphs. GraphPrompt not only unifies pre-training and downstream tasks into a common task template but also employs a learnable prompt to assist a downstream task in locating the most relevant knowledge from the pre-trained model in a task-specific manner. To further enhance GraphPrompt in these two stages, we extend it into GraphPrompt+ with two major enhancements. First, we generalize several popular graph pre-training tasks beyond simple link prediction to broaden the compatibility with our task template. Second, we propose a more generalized prompt design that incorporates a series of prompt vectors within every layer of the pre-trained graph encoder, in order to capitalize on the hierarchical information across different layers beyond just the readout layer. Finally, we conduct extensive experiments on five public datasets to evaluate and analyze GraphPrompt and GraphPrompt+.
Authors: Avery Ma, Amir-massoud Farahmand, Yangchen Pan, Philip Torr, Jindong Gu
Abstract: Neural networks are susceptible to adversarial perturbations that are transferable across different models. In this paper, we introduce a novel model alignment technique aimed at improving a given source model's ability in generating transferable adversarial perturbations. During the alignment process, the parameters of the source model are fine-tuned to minimize an alignment loss. This loss measures the divergence in the predictions between the source model and another, independently trained model, referred to as the witness model. To understand the effect of model alignment, we conduct a geometric analysis of the resulting changes in the loss landscape. Extensive experiments on the ImageNet dataset, using a variety of model architectures, demonstrate that perturbations generated from aligned source models exhibit significantly higher transferability than those from the original source model.
Authors: Ching Chang, Chiao-Tung Chan, Wei-Yao Wang, Wen-Chih Peng, Tien-Fu Chen
Abstract: Multivariate time-series data in numerous real-world applications (e.g., healthcare and industry) are informative but challenging due to the lack of labels and high dimensionality. Recent studies in self-supervised learning have shown their potential in learning rich representations without relying on labels, yet they fall short in learning disentangled embeddings and addressing issues of inductive bias (e.g., transformation-invariance). To tackle these challenges, we propose TimeDRL, a generic multivariate time-series representation learning framework with disentangled dual-level embeddings. TimeDRL is characterized by three novel features: (i) disentangled derivation of timestamp-level and instance-level embeddings from patched time-series data using a [CLS] token strategy; (ii) utilization of timestamp-predictive and instance-contrastive tasks for disentangled representation learning, with the former optimizing timestamp-level embeddings with predictive loss, and the latter optimizing instance-level embeddings with contrastive loss; and (iii) avoidance of augmentation methods to eliminate inductive biases, such as transformation-invariance from cropping and masking. Comprehensive experiments on 6 time-series forecasting datasets and 5 time-series classification datasets have shown that TimeDRL consistently surpasses existing representation learning approaches, achieving an average improvement of forecasting by 58.02% in MSE and classification by 1.48% in accuracy. Furthermore, extensive ablation studies confirmed the relative contribution of each component in TimeDRL's architecture, and semi-supervised learning evaluations demonstrated its effectiveness in real-world scenarios, even with limited labeled data. The code is available at https://github.com/blacksnail789521/TimeDRL.
Authors: Ryan Greenblatt, Buck Shlegeris, Kshitij Sachan, Fabien Roger
Abstract: As large language models (LLMs) become more powerful and are deployed more autonomously, it will be increasingly important to prevent them from causing harmful outcomes. Researchers have investigated a variety of safety techniques for this purpose, e.g. using models to review the outputs of other models, or red-teaming techniques to surface subtle failure modes. However, researchers have not evaluated whether such techniques still ensure safety if the model is itself intentionally trying to subvert them. In this paper, we develop and evaluate pipelines of safety techniques ("protocols") that are robust to intentional subversion. We investigate a scenario in which we want to solve a sequence of programming problems, using access to a powerful but untrusted model (in our case, GPT-4), access to a less powerful trusted model (in our case, GPT-3.5), and limited access to high-quality trusted labor. We investigate protocols that aim to never submit solutions containing backdoors, which we operationalize here as logical errors that are not caught by test cases. We investigate a range of protocols and test each against strategies that the untrusted model could use to subvert them. One protocol is what we call trusted editing. This protocol first asks GPT-4 to write code, and then asks GPT-3.5 to rate the suspiciousness of that code. If the code is below some suspiciousness threshold, it is submitted. Otherwise, GPT-3.5 edits the solution to remove parts that seem suspicious and then submits the edited code. Another protocol is untrusted monitoring. This protocol asks GPT-4 to write code, and then asks another instance of GPT-4 whether the code is backdoored, using various techniques to prevent the GPT-4 instances from colluding. These protocols improve substantially on simple baselines.
Authors: Haz Sameen Shahgir, Xianghao Kong, Greg Ver Steeg, Yue Dong
Abstract: The widespread use of Text-to-Image (T2I) models in content generation requires careful examination of their safety, including their robustness to adversarial attacks. Despite extensive research on adversarial attacks, the reasons for their effectiveness remain underexplored. This paper presents an empirical study on adversarial attacks against T2I models, focusing on analyzing factors associated with attack success rates (ASR). We introduce a new attack objective - entity swapping using adversarial suffixes and two gradient-based attack algorithms. Human and automatic evaluations reveal the asymmetric nature of ASRs on entity swap: for example, it is easier to replace "human" with "robot" in the prompt "a human dancing in the rain." with an adversarial suffix, but the reverse replacement is significantly harder. We further propose probing metrics to establish indicative signals from the model's beliefs to the adversarial ASR. We identify conditions that result in a success probability of 60% for adversarial attacks and others where this likelihood drops below 5%.
Authors: Yichen Li, Chicheng Zhang
Abstract: We study interactive imitation learning, where a learner interactively queries a demonstrating expert for action annotations, aiming to learn a policy that has performance competitive with the expert, using as few annotations as possible. We focus on the general agnostic setting where the expert demonstration policy may not be contained in the policy class used by the learner. We propose a new oracle-efficient algorithm MFTPL-P (abbreviation for Mixed Follow the Perturbed Leader with Poisson perturbations) with provable finite-sample guarantees, under the assumption that the learner is given access to samples from some ``explorative'' distribution over states. Our guarantees hold for any policy class, which is considerably broader than prior state of the art. We further propose Bootstrap-Dagger, a more practical variant that does not require additional sample access. Empirically, MFTPL-P and Bootstrap-Dagger notably surpass online and offline imitation learning baselines in continuous control tasks.
Authors: Jing Wu, Mehrtash Harandi
Abstract: Machine unlearning has become a pivotal task to erase the influence of data from a trained model. It adheres to recent data regulation standards and enhances the privacy and security of machine learning applications. In this work, we present a new machine unlearning approach Scissorhands. Initially, Scissorhands identifies the most pertinent parameters in the given model relative to the forgetting data via connection sensitivity. By reinitializing the most influential top-k percent of these parameters, a trimmed model for erasing the influence of the forgetting data is obtained. Subsequently, Scissorhands fine-tunes the trimmed model with a gradient projection-based approach, seeking parameters that preserve information on the remaining data while discarding information related to the forgetting data. Our experimental results, conducted across image classification and image generation tasks, demonstrate that Scissorhands, showcases competitive performance when compared to existing methods. Source code is available at https://github.com/JingWu321/Scissorhands.
Authors: Hwanwoo Kim, Daniel Sanz-Alonso
Abstract: This paper proposes novel noise-free Bayesian optimization strategies that rely on a random exploration step to enhance the accuracy of Gaussian process surrogate models. The new algorithms retain the ease of implementation of the classical GP-UCB algorithm, but the additional random exploration step accelerates their convergence, nearly achieving the optimal convergence rate. Furthermore, to facilitate Bayesian inference with an intractable likelihood, we propose to utilize optimization iterates for maximum a posteriori estimation to build a Gaussian process surrogate model for the unnormalized log-posterior density. We provide bounds for the Hellinger distance between the true and the approximate posterior distributions in terms of the number of design points. We demonstrate the effectiveness of our Bayesian optimization algorithms in non-convex benchmark objective functions, in a machine learning hyperparameter tuning problem, and in a black-box engineering design problem. The effectiveness of our posterior approximation approach is demonstrated in two Bayesian inference problems for parameters of dynamical systems.
Authors: Maciej Wo{\l}czyk, Bart{\l}omiej Cupia{\l}, Mateusz Ostaszewski, Micha{\l} Bortkiewicz, Micha{\l} Zaj\k{a}c, Razvan Pascanu, {\L}ukasz Kuci\'nski, Piotr Mi{\l}o\'s
Abstract: Fine-tuning is a widespread technique that allows practitioners to transfer pre-trained capabilities, as recently showcased by the successful applications of foundation models. However, fine-tuning reinforcement learning (RL) models remains a challenge. This work conceptualizes one specific cause of poor transfer, accentuated in the RL setting by the interplay between actions and observations: forgetting of pre-trained capabilities. Namely, a model deteriorates on the state subspace of the downstream task not visited in the initial phase of fine-tuning, on which the model behaved well due to pre-training. This way, we lose the anticipated transfer benefits. We identify conditions when this problem occurs, showing that it is common and, in many cases, catastrophic. Through a detailed empirical analysis of the challenging NetHack and Montezuma's Revenge environments, we show that standard knowledge retention techniques mitigate the problem and thus allow us to take full advantage of the pre-trained capabilities. In particular, in NetHack, we achieve a new state-of-the-art for neural models, improving the previous best score from $5$K to over $10$K points in the Human Monk scenario.
Authors: Nazarii Tupitsa, Samuel Horv\'ath, Martin Tak\'a\v{c}, Eduard Gorbunov
Abstract: In Federated Learning (FL), the distributed nature and heterogeneity of client data present both opportunities and challenges. While collaboration among clients can significantly enhance the learning process, not all collaborations are beneficial; some may even be detrimental. In this study, we introduce a novel algorithm that assigns adaptive aggregation weights to clients participating in FL training, identifying those with data distributions most conducive to a specific learning objective. We demonstrate that our aggregation method converges no worse than the method that aggregates only the updates received from clients with the same data distribution. Furthermore, empirical evaluations consistently reveal that collaborations guided by our algorithm outperform traditional FL approaches. This underscores the critical role of judicious client selection and lays the foundation for more streamlined and effective FL implementations in the coming years.
Authors: Brian Yang, Huangyuan Su, Nikolaos Gkanatsios, Tsung-Wei Ke, Ayush Jain, Jeff Schneider, Katerina Fragkiadaki
Abstract: Diffusion models excel at modeling complex and multimodal trajectory distributions for decision-making and control. Reward-gradient guided denoising has been recently proposed to generate trajectories that maximize both a differentiable reward function and the likelihood under the data distribution captured by a diffusion model. Reward-gradient guided denoising requires a differentiable reward function fitted to both clean and noised samples, limiting its applicability as a general trajectory optimizer. In this paper, we propose DiffusionES, a method that combines gradient-free optimization with trajectory denoising to optimize black-box non-differentiable objectives while staying in the data manifold. Diffusion-ES samples trajectories during evolutionary search from a diffusion model and scores them using a black-box reward function. It mutates high-scoring trajectories using a truncated diffusion process that applies a small number of noising and denoising steps, allowing for much more efficient exploration of the solution space. We show that DiffusionES achieves state-of-the-art performance on nuPlan, an established closed-loop planning benchmark for autonomous driving. Diffusion-ES outperforms existing sampling-based planners, reactive deterministic or diffusion-based policies, and reward-gradient guidance. Additionally, we show that unlike prior guidance methods, our method can optimize non-differentiable language-shaped reward functions generated by few-shot LLM prompting. When guided by a human teacher that issues instructions to follow, our method can generate novel, highly complex behaviors, such as aggressive lane weaving, which are not present in the training data. This allows us to solve the hardest nuPlan scenarios which are beyond the capabilities of existing trajectory optimization methods and driving policies.
Authors: Matthew Niedoba, Dylan Green, Saeid Naderiparizi, Vasileios Lioutas, Jonathan Wilder Lavington, Xiaoxuan Liang, Yunpeng Liu, Ke Zhang, Setareh Dabiri, Adam \'Scibior, Berend Zwartsenberg, Frank Wood
Abstract: Score function estimation is the cornerstone of both training and sampling from diffusion generative models. Despite this fact, the most commonly used estimators are either biased neural network approximations or high variance Monte Carlo estimators based on the conditional score. We introduce a novel nearest neighbour score function estimator which utilizes multiple samples from the training set to dramatically decrease estimator variance. We leverage our low variance estimator in two compelling applications. Training consistency models with our estimator, we report a significant increase in both convergence speed and sample quality. In diffusion models, we show that our estimator can replace a learned network for probability-flow ODE integration, opening promising new avenues of future research.
Authors: Benjamin Bergner, Andrii Skliar, Amelie Royer, Tijmen Blankevoort, Yuki Asano, Babak Ehteshami Bejnordi
Abstract: Large language models (LLMs) have become ubiquitous in practice and are widely used for generation tasks such as translation, summarization and instruction following. However, their enormous size and reliance on autoregressive decoding increase deployment costs and complicate their use in latency-critical applications. In this work, we propose a hybrid approach that combines language models of different sizes to increase the efficiency of autoregressive decoding while maintaining high performance. Our method utilizes a pretrained frozen LLM that encodes all prompt tokens once in parallel, and uses the resulting representations to condition and guide a small language model (SLM), which then generates the response more efficiently. We investigate the combination of encoder-decoder LLMs with both encoder-decoder and decoder-only SLMs from different model families and only require fine-tuning of the SLM. Experiments with various benchmarks show substantial speedups of up to $4\times$, with minor performance penalties of $1-2\%$ for translation and summarization tasks compared to the LLM.
Authors: Tobias Christian Nauen, Sebastian Palacio, Andreas Dengel
Abstract: The quadratic complexity of the attention mechanism represents one of the biggest hurdles for processing long sequences using Transformers. Current methods, relying on sparse representations or stateful recurrence, sacrifice token-to-token interactions, which ultimately leads to compromises in performance. This paper introduces TaylorShift, a novel reformulation of the Taylor softmax that enables computing full token-to-token interactions in linear time and space. We analytically determine the crossover points where employing TaylorShift becomes more efficient than traditional attention, aligning closely with empirical measurements. Specifically, our findings demonstrate that TaylorShift enhances memory efficiency for sequences as short as 800 tokens and accelerates inference for inputs of approximately 1700 tokens and beyond. For shorter sequences, TaylorShift scales comparably with the vanilla attention. Furthermore, a classification benchmark across five tasks involving long sequences reveals no degradation in accuracy when employing Transformers equipped with TaylorShift. For reproducibility, we provide access to our code under https://github.com/tobna/TaylorShift.
Authors: Sahil Sidheekh, Pranuthi Tenali, Saurabh Mathur, Erik Blasch, Kristian Kersting, Sriraam Natarajan
Abstract: We consider the problem of late multi-modal fusion for discriminative learning. Motivated by noisy, multi-source domains that require understanding the reliability of each data source, we explore the notion of credibility in the context of multi-modal fusion. We propose a combination function that uses probabilistic circuits (PCs) to combine predictive distributions over individual modalities. We also define a probabilistic measure to evaluate the credibility of each modality via inference queries over the PC. Our experimental evaluation demonstrates that our fusion method can reliably infer credibility while maintaining competitive performance with the state-of-the-art.
Authors: Chenxi Liu, Zhenyi Wang, Tianyi Xiong, Ruibo Chen, Yihan Wu, Junfeng Guo, Heng Huang
Abstract: Few-Shot Class-Incremental Learning (FSCIL) models aim to incrementally learn new classes with scarce samples while preserving knowledge of old ones. Existing FSCIL methods usually fine-tune the entire backbone, leading to overfitting and hindering the potential to learn new classes. On the other hand, recent prompt-based CIL approaches alleviate forgetting by training prompts with sufficient data in each task. In this work, we propose a novel framework named Attention-aware Self-adaptive Prompt (ASP). ASP encourages task-invariant prompts to capture shared knowledge by reducing specific information from the attention aspect. Additionally, self-adaptive task-specific prompts in ASP provide specific information and transfer knowledge from old classes to new classes with an Information Bottleneck learning objective. In summary, ASP prevents overfitting on base task and does not require enormous data in few-shot incremental tasks. Extensive experiments on three benchmark datasets validate that ASP consistently outperforms state-of-the-art FSCIL and prompt-based CIL methods in terms of both learning new classes and mitigating forgetting.
Authors: Abhishek Ghose, Emma Thuong Nguyen
Abstract: Active learning (AL) techniques optimally utilize a labeling budget by iteratively selecting instances that are most valuable for learning. However, they lack ``prerequisite checks'', i.e., there are no prescribed criteria to pick an AL algorithm best suited for a dataset. A practitioner must pick a technique they \emph{trust} would beat random sampling, based on prior reported results, and hope that it is resilient to the many variables in their environment: dataset, labeling budget and prediction pipelines. The important questions then are: how often on average, do we expect any AL technique to reliably beat the computationally cheap and easy-to-implement strategy of random sampling? Does it at least make sense to use AL in an ``Always ON'' mode in a prediction pipeline, so that while it might not always help, it never under-performs random sampling? How much of a role does the prediction pipeline play in AL's success? We examine these questions in detail for the task of text classification using pre-trained representations, which are ubiquitous today. Our primary contribution here is a rigorous evaluation of AL techniques, old and new, across setups that vary wrt datasets, text representations and classifiers. This unlocks multiple insights around warm-up times, i.e., number of labels before gains from AL are seen, viability of an ``Always ON'' mode and the relative significance of different factors. Additionally, we release a framework for rigorous benchmarking of AL techniques for text classification.
Authors: Neil Mallinar, Austin Zane, Spencer Frei, Bin Yu
Abstract: Transfer learning is a critical part of real-world machine learning deployments and has been extensively studied in experimental works with overparameterized neural networks. However, even in the simplest setting of linear regression a notable gap still exists in the theoretical understanding of transfer learning. In-distribution research on high-dimensional linear regression has led to the identification of a phenomenon known as \textit{benign overfitting}, in which linear interpolators overfit to noisy training labels and yet still generalize well. This behavior occurs under specific conditions on the source covariance matrix and input data dimension. Therefore, it is natural to wonder how such high-dimensional linear models behave under transfer learning. We prove the first non-asymptotic excess risk bounds for benignly-overfit linear interpolators in the transfer learning setting. From our analysis, we propose a taxonomy of \textit{beneficial} and \textit{malignant} covariate shifts based on the degree of overparameterization. We follow our analysis with empirical studies that show these beneficial and malignant covariate shifts for linear interpolators on real image data, and for fully-connected neural networks in settings where the input data dimension is larger than the training sample size.
Authors: Krzysztof Kotowski, Irena Roterman, Katarzyna Stapor
Abstract: The prediction of intrinsic disorder regions has significant implications for understanding protein functions and dynamics. It can help to discover novel protein-protein interactions essential for designing new drugs and enzymes. Recently, a new generation of predictors based on protein language models (pLMs) is emerging. These algorithms reach state-of-the-art accuracy with-out calculating time-consuming multiple sequence alignments (MSAs). The article introduces the new DisorderUnetLM disorder predictor, which builds upon the idea of ProteinUnet. It uses the Attention U-Net convolutional neural network and incorporates features from the ProtTrans pLM. DisorderUnetLM achieves top results in the direct comparison with recent predictors exploiting MSAs and pLMs. Moreover, among 43 predictors from the latest CAID-2 benchmark, it ranks 1st for the Disorder-NOX subset (ROC-AUC of 0.844) and 10th for the Disorder-PDB subset (ROC-AUC of 0.924). The code and model are publicly available and fully reproducible at doi.org/10.24433/CO.7350682.v1.
Authors: Zeke Xia, Ming Hu, Dengke Yan, Xiaofei Xie, Tianlin Li, Anran Li, Junlong Zhou, Mingsong Chen
Abstract: Federated Learning (FL) as a promising distributed machine learning paradigm has been widely adopted in Artificial Intelligence of Things (AIoT) applications. However, the efficiency and inference capability of FL is seriously limited due to the presence of stragglers and data imbalance across massive AIoT devices, respectively. To address the above challenges, we present a novel asynchronous FL approach named CaBaFL, which includes a hierarchical Cache-based aggregation mechanism and a feature Balance-guided device selection strategy. CaBaFL maintains multiple intermediate models simultaneously for local training. The hierarchical cache-based aggregation mechanism enables each intermediate model to be trained on multiple devices to align the training time and mitigate the straggler issue. In specific, each intermediate model is stored in a low-level cache for local training and when it is trained by sufficient local devices, it will be stored in a high-level cache for aggregation. To address the problem of imbalanced data, the feature balance-guided device selection strategy in CaBaFL adopts the activation distribution as a metric, which enables each intermediate model to be trained across devices with totally balanced data distributions before aggregation. Experimental results show that compared with the state-of-the-art FL methods, CaBaFL achieves up to 9.26X training acceleration and 19.71\% accuracy improvements.
Authors: Yangchen Pan, Junfeng Wen, Chenjun Xiao, Philip Torr
Abstract: In traditional statistical learning, data points are usually assumed to be independently and identically distributed (i.i.d.) following an unknown probability distribution. This paper presents a contrasting viewpoint, perceiving data points as interconnected and employing a Markov reward process (MRP) for data modeling. We reformulate the typical supervised learning as an on-policy policy evaluation problem within reinforcement learning (RL), introducing a generalized temporal difference (TD) learning algorithm as a resolution. Theoretically, our analysis draws connections between the solutions of linear TD learning and ordinary least squares (OLS). We also show that under specific conditions, particularly when noises are correlated, the TD's solution proves to be a more effective estimator than OLS. Furthermore, we establish the convergence of our generalized TD algorithms under linear function approximation. Empirical studies verify our theoretical results, examine the vital design of our TD algorithm and show practical utility across various datasets, encompassing tasks such as regression and image classification with deep learning.
Authors: Fabio Massimo Zennaro, Nicholas Bishop, Joel Dyer, Yorgos Felekis, Anisoara Calinescu, Michael Wooldridge, Theodoros Damoulas
Abstract: Multi-armed bandits (MAB) and causal MABs (CMAB) are established frameworks for decision-making problems. The majority of prior work typically studies and solves individual MAB and CMAB in isolation for a given problem and associated data. However, decision-makers are often faced with multiple related problems and multi-scale observations where joint formulations are needed in order to efficiently exploit the problem structures and data dependencies. Transfer learning for CMABs addresses the situation where models are defined on identical variables, although causal connections may differ. In this work, we extend transfer learning to setups involving CMABs defined on potentially different variables, with varying degrees of granularity, and related via an abstraction map. Formally, we introduce the problem of causally abstracted MABs (CAMABs) by relying on the theory of causal abstraction in order to express a rigorous abstraction map. We propose algorithms to learn in a CAMAB, and study their regret. We illustrate the limitations and the strengths of our algorithms on a real-world scenario related to online advertising.
Authors: Saeed Damadi, Soroush Zolfaghari, Mahdi Rezaie, Jinglai Shen
Abstract: The core of a good model is in its ability to focus only on important information that reflects the basic patterns and consistencies, thus pulling out a clear, noise-free signal from the dataset. This necessitates using a simplified model defined by fewer parameters. The importance of theoretical foundations becomes clear in this context, as this paper relies on established results from the domain of advanced sparse optimization, particularly those addressing nonlinear differentiable functions. The need for such theoretical foundations is further highlighted by the trend that as computational power for training NNs increases, so does the complexity of the models in terms of a higher number of parameters. In practical scenarios, these large models are often simplified to more manageable versions with fewer parameters. Understanding why these simplified models with less number of parameters remain effective raises a crucial question. Understanding why these simplified models with fewer parameters remain effective raises an important question. This leads to the broader question of whether there is a theoretical framework that can clearly explain these empirical observations. Recent developments, such as establishing necessary conditions for the convergence of iterative hard thresholding (IHT) to a sparse local minimum (a sparse method analogous to gradient descent) are promising. The remarkable capacity of the IHT algorithm to accurately identify and learn the locations of nonzero parameters underscores its practical effectiveness and utility. This paper aims to investigate whether the theoretical prerequisites for such convergence are applicable in the realm of neural network (NN) training by providing justification for all the necessary conditions for convergence. Then, these conditions are validated by experiments on a single-layer NN, using the IRIS dataset as a testbed.
Authors: Zhenqiao Song, Yunlong Zhao, Wenxian Shi, Wengong Jin, Yang Yang, Lei Li
Abstract: Enzymes are genetically encoded biocatalysts capable of accelerating chemical reactions. How can we automatically design functional enzymes? In this paper, we propose EnzyGen, an approach to learn a unified model to design enzymes across all functional families. Our key idea is to generate an enzyme's amino acid sequence and their three-dimensional (3D) coordinates based on functionally important sites and substrates corresponding to a desired catalytic function. These sites are automatically mined from enzyme databases. EnzyGen consists of a novel interleaving network of attention and neighborhood equivariant layers, which captures both long-range correlation in an entire protein sequence and local influence from nearest amino acids in 3D space. To learn the generative model, we devise a joint training objective, including a sequence generation loss, a position prediction loss and an enzyme-substrate interaction loss. We further construct EnzyBench, a dataset with 3157 enzyme families, covering all available enzymes within the protein data bank (PDB). Experimental results show that our EnzyGen consistently achieves the best performance across all 323 testing families, surpassing the best baseline by 10.79% in terms of substrate binding affinity. These findings demonstrate EnzyGen's superior capability in designing well-folded and effective enzymes binding to specific substrates with high affinities.
Authors: Jingyang Qiao, Zhizhong Zhang, Xin Tan, Yanyun Qu, Wensheng Zhang, Zhi Han, Yuan Xie
Abstract: Parameter-efficient tunings (PETs) have demonstrated impressive performance and promising perspectives in training large models, while they are still confronted with a common problem: the trade-off between learning new content and protecting old knowledge, leading to zero-shot generalization collapse, and cross-modal hallucination. In this paper, we reformulate Adapter, LoRA, Prefix-tuning, and Prompt-tuning from the perspective of gradient projection, and firstly propose a unified framework called Parameter Efficient Gradient Projection (PEGP). We introduce orthogonal gradient projection into different PET paradigms and theoretically demonstrate that the orthogonal condition for the gradient can effectively resist forgetting even for large-scale models. It therefore modifies the gradient towards the direction that has less impact on the old feature space, with less extra memory space and training time. We extensively evaluate our method with different backbones, including ViT and CLIP, on diverse datasets, and experiments comprehensively demonstrate its efficiency in reducing forgetting in class, online class, domain, task, and multi-modality continual settings. The project page is available at https://dmcv-ecnu-pegp.github.io/.
Authors: B. N. Kausik
Abstract: Deep learning neural network models must be large enough to adapt to their problem domain, while small enough to avoid overfitting training data during gradient descent. To balance these competing demands, overprovisioned deep learning models such as transformers are trained for a single epoch on large data sets, and hence inefficient with both computing resources and training data. In response to these inefficiencies, we exploit learning theory to derive Occam Gradient Descent, an algorithm that interleaves adaptive reduction of model size to minimize generalization error, with gradient descent on model weights to minimize fitting error. In contrast, traditional gradient descent greedily minimizes fitting error without regard to generalization error. Our algorithm simultaneously descends the space of weights and topological size of any neural network without modification, and is effective in our image classification experiments in outperforming traditional gradient descent with or without post-train pruning in loss, compute and model size. Furthermore, applying our algorithm to tabular data classification we find that across a range of data sets, neural networks trained with Occam Gradient Descent outperform neural networks trained with gradient descent, as well as Random Forests, in both loss and model size.
Authors: Yasin Abbasi Yadkori, Ilja Kuzborskij, Andr\'as Gy\"orgy, Csaba Szepesv\'ari
Abstract: We explore uncertainty quantification in large language models (LLMs), with the goal to identify when uncertainty in responses given a query is large. We simultaneously consider both epistemic and aleatoric uncertainties, where the former comes from the lack of knowledge about the ground truth (such as about facts or the language), and the latter comes from irreducible randomness (such as multiple possible answers). In particular, we derive an information-theoretic metric that allows to reliably detect when only epistemic uncertainty is large, in which case the output of the model is unreliable. This condition can be computed based solely on the output of the model obtained simply by some special iterative prompting based on the previous responses. Such quantification, for instance, allows to detect hallucinations (cases when epistemic uncertainty is high) in both single- and multi-answer responses. This is in contrast to many standard uncertainty quantification strategies (such as thresholding the log-likelihood of a response) where hallucinations in the multi-answer case cannot be detected. We conduct a series of experiments which demonstrate the advantage of our formulation. Further, our investigations shed some light on how the probabilities assigned to a given output by an LLM can be amplified by iterative prompting, which might be of independent interest.
Authors: Vaneet Aggarwal, Washim Uddin Mondal, Qinbo Bai
Abstract: Reinforcement Learning (RL) serves as a versatile framework for sequential decision-making, finding applications across diverse domains such as robotics, autonomous driving, recommendation systems, supply chain optimization, biology, mechanics, and finance. The primary objective in these applications is to maximize the average reward. Real-world scenarios often necessitate adherence to specific constraints during the learning process. This monograph focuses on the exploration of various model-based and model-free approaches for Constrained RL within the context of average reward Markov Decision Processes (MDPs). The investigation commences with an examination of model-based strategies, delving into two foundational methods - optimism in the face of uncertainty and posterior sampling. Subsequently, the discussion transitions to parametrized model-free approaches, where the primal-dual policy gradient-based algorithm is explored as a solution for constrained MDPs. The monograph provides regret guarantees and analyzes constraint violation for each of the discussed setups. For the above exploration, we assume the underlying MDP to be ergodic. Further, this monograph extends its discussion to encompass results tailored for weakly communicating MDPs, thereby broadening the scope of its findings and their relevance to a wider range of practical scenarios.
Authors: Chenxu Wang, Haowei Ming, Jian He, Yao Lu, Junhong Chen
Abstract: The accurate prediction of drug molecule solubility is essential for determining their therapeutic effectiveness and safety, influencing the drug's ADME processes. Traditional solubility prediction techniques often fail to capture the complex nature of molecular tructures, leading to notable deviations between predictions and actual results. For example, the Discussion on Advanced Drug-Like Compound Structures. Lusci highlighted issues in capturing crucial cyclic structural information in molecules with ring structures. To overcome this issue, our research introduces a novel deep learning framework combining attention-based transformers, Long Short-Term Memory (LSTM) networks, and Graph Convolutional Networks (GCN), aimed at enhancing the precision of solubility predictions. Utilizing a training set of 9,943 compounds and testing on an anticancer compound dataset, our method achieved a correlation coefficient ($R^2$) of 0.59 and a Root Mean Square Error (RMSE) of 0.57, which outperforms the benchmark models' scores of 0.52 ($R^2$) and 0.61 (RMSE). Importantly, in an additional independent test, our model significantly outperformed the baseline with an RMSE of 1.05 compared to 1.28, a relative accuracy improvement of 45.9%. This research not only demonstrates the vast potential of deep learning for improving solubility prediction accuracy but also offers novel insights for drug design and selection in the future. Continued efforts will be directed towards optimizing the model architecture and extending its application to better support the drug development process, underscoring the pivotal role of deep learning in drug discovery.
Authors: Pedro Barbosa, Rosina Savisaar, Alcides Fonseca
Abstract: Black box deep learning models trained on genomic sequences excel at predicting the outcomes of different gene regulatory mechanisms. Therefore, interpreting these models may provide novel insights into the underlying biology, supporting downstream biomedical applications. Due to their complexity, interpretable surrogate models can only be built for local explanations (e.g., a single instance). However, accomplishing this requires generating a dataset in the neighborhood of the input, which must maintain syntactic similarity to the original data while introducing semantic variability in the model's predictions. This task is challenging due to the complex sequence-to-function relationship of DNA. We propose using Genetic Programming to generate datasets by evolving perturbations in sequences that contribute to their semantic diversity. Our custom, domain-guided individual representation effectively constrains syntactic similarity, and we provide two alternative fitness functions that promote diversity with no computational effort. Applied to the RNA splicing domain, our approach quickly achieves good diversity and significantly outperforms a random baseline in exploring the search space, as shown by our proof-of-concept, short RNA sequence. Furthermore, we assess its generalizability and demonstrate scalability to larger sequences, resulting in a ~30% improvement over the baseline.
Authors: Nan Chen, Merlijn Schram, Doina Bucur
Abstract: We aim to learn the functional co-response group: a group of taxa whose co-response effect (the representative characteristic of the group showing the total topological abundance of taxa) co-responds (associates well statistically) to a functional variable. Different from the state-of-the-art method, we model the soil microbial community as an ecological co-occurrence network with the taxa as nodes (weighted by their abundance) and their relationships (a combination from both spatial and functional ecological aspects) as edges (weighted by the strength of the relationships). Then, we design a method called gFlora which notably uses graph convolution over this co-occurrence network to get the co-response effect of the group, such that the network topology is also considered in the discovery process. We evaluate gFlora on two real-world soil microbiome datasets (bacteria and nematodes) and compare it with the state-of-the-art method. gFlora outperforms this on all evaluation metrics, and discovers new functional evidence for taxa which were so far under-studied. We show that the graph convolution step is crucial to taxa with relatively low abundance (thus removing the bias towards taxa with higher abundance), and the discovered bacteria of different genera are distributed in the co-occurrence network but still tightly connected among themselves, demonstrating that topologically they fill different but collaborative functional roles in the ecological community.
Authors: Ahmed K. Kadhim, Ole-Christoffer Granmo, Lei Jiao, Rishad Shafik
Abstract: The Tsetlin Machine (TM) has gained significant attention in Machine Learning (ML). By employing logical fundamentals, it facilitates pattern learning and representation, offering an alternative approach for developing comprehensible Artificial Intelligence (AI) with a specific focus on pattern classification in the form of conjunctive clauses. In the domain of Natural Language Processing (NLP), TM is utilised to construct word embedding and describe target words using clauses. To enhance the descriptive capacity of these clauses, we study the concept of Reasoning by Elimination (RbE) in clauses' formulation, which involves incorporating feature negations to provide a more comprehensive representation. In more detail, this paper employs the Tsetlin Machine Auto-Encoder (TM-AE) architecture to generate dense word vectors, aiming at capturing contextual information by extracting feature-dense vectors for a given vocabulary. Thereafter, the principle of RbE is explored to improve descriptivity and optimise the performance of the TM. Specifically, the specificity parameter s and the voting margin parameter T are leveraged to regulate feature distribution in the state space, resulting in a dense representation of information for each clause. In addition, we investigate the state spaces of TM-AE, especially for the forgotten/excluded features. Empirical investigations on artificially generated data, the IMDB dataset, and the 20 Newsgroups dataset showcase the robustness of the TM, with accuracy reaching 90.62\% for the IMDB.
Authors: Chuanhao Sun, Zhihang Yuan, Kai Xu, Luo Mai, N. Siddharth, Shuo Chen, Mahesh K. Marina
Abstract: Fourier features based positional encoding (PE) is commonly used in machine learning tasks that involve learning high-frequency features from low-dimensional inputs, such as 3D view synthesis and time series regression with neural tangent kernels. Despite their effectiveness, existing PEs require manual, empirical adjustment of crucial hyperparameters, specifically the Fourier features, tailored to each unique task. Further, PEs face challenges in efficiently learning high-frequency functions, particularly in tasks with limited data. In this paper, we introduce sinusoidal PE (SPE), designed to efficiently learn adaptive frequency features closely aligned with the true underlying function. Our experiments demonstrate that SPE, without hyperparameter tuning, consistently achieves enhanced fidelity and faster training across various tasks, including 3D view synthesis, Text-to-Speech generation, and 1D regression. SPE is implemented as a direct replacement for existing PEs. Its plug-and-play nature lets numerous tasks easily adopt and benefit from SPE.
Authors: Mikhail Andronov, Natalia Andronova, Michael Wand, J\"urgen Schmidhuber, Djork-Arn\'e Clevert
Abstract: Template-free SMILES-to-SMILES translation models for reaction prediction and single-step retrosynthesis are of interest for industrial applications in computer-aided synthesis planning systems due to their state-of-the-art accuracy. However, they suffer from slow inference speed. We present a method to accelerate inference in autoregressive SMILES generators through speculative decoding by copying query string subsequences into target strings in the right places. We apply our method to the molecular transformer implemented in Pytorch Lightning and achieve over 3X faster inference in reaction prediction and single-step retrosynthesis, with no loss in accuracy.
Authors: Samyak Jain, Ekdeep Singh Lubana, Kemal Oksuz, Tom Joy, Philip H. S. Torr, Amartya Sanyal, Puneet K. Dokania
Abstract: Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation framework that captures salient aspects of an unsafe input by modeling the interaction between the task the model is asked to perform (e.g., "design") versus the specific concepts the task is asked to be performed upon (e.g., a "cycle" vs. a "bomb"). Using this, we investigate three well-known safety fine-tuning methods -- supervised safety fine-tuning, direct preference optimization, and unlearning -- and provide significant evidence demonstrating that these methods minimally transform MLP weights to specifically align unsafe inputs into its weights' null space. This yields a clustering of inputs based on whether the model deems them safe or not. Correspondingly, when an adversarial input (e.g., a jailbreak) is provided, its activations are closer to safer samples, leading to the model processing such an input as if it were safe. We validate our findings, wherever possible, on real-world models -- specifically, Llama-2 7B and Llama-3 8B.
Authors: Zeqing Wang, Fei Cheng, Kangye Ji, Bohu Huang
Abstract: Continual learning(CL) is a useful technique to acquire dynamic knowledge continually. Although powerful cloud platforms can fully exert the ability of CL,e.g., customized recommendation systems, similar personalized requirements for edge devices are almost disregarded. This phenomenon stems from the huge resource overhead involved in training neural networks and overcoming the forgetting problem of CL. This paper focuses on these scenarios and proposes a compact algorithm called LightCL. Different from other CL methods bringing huge resource consumption to acquire generalizability among all tasks for delaying forgetting, LightCL compress the resource consumption of already generalized components in neural networks and uses a few extra resources to improve memory in other parts. We first propose two new metrics of learning plasticity and memory stability to seek generalizability during CL. Based on the discovery that lower and middle layers have more generalizability and deeper layers are opposite, we $\textit{Maintain Generalizability}$ by freezing the lower and middle layers. Then, we $\textit{Memorize Feature Patterns}$ to stabilize the feature extracting patterns of previous tasks to improve generalizability in deeper layers. In the experimental comparison, LightCL outperforms other SOTA methods in delaying forgetting and reduces at most $\textbf{6.16$\times$}$ memory footprint, proving the excellent performance of LightCL in efficiency. We also evaluate the efficiency of our method on an edge device, the Jetson Nano, which further proves our method's practical effectiveness.
Authors: Jiahao Wu, Ning Lu, Zeiyu Dai, Wenqi Fan, Shengcai Liu, Qing Li, Ke Tang
Abstract: Recently, graph condensation has emerged as a prevalent technique to improve the training efficiency for graph neural networks (GNNs). It condenses a large graph into a small one such that a GNN trained on this small synthetic graph can achieve comparable performance to a GNN trained on a large graph. However, while existing graph condensation studies mainly focus on the best trade-off between graph size and the GNNs' performance (model utility), the security issues of graph condensation have not been studied. To bridge this research gap, we propose the task of backdoor graph condensation. While graph backdoor attacks have been extensively explored, applying existing graph backdoor methods for graph condensation is not practical since they can undermine the model utility and yield low attack success rate. To alleviate these issues, we introduce two primary objectives for backdoor attacks against graph condensation: 1) the injection of triggers cannot affect the quality of condensed graphs, maintaining the utility of GNNs trained on them; and 2) the effectiveness of triggers should be preserved throughout the condensation process, achieving high attack success rate. To pursue the objectives, we devise the first backdoor attack against graph condensation, denoted as BGC. Specifically, we inject triggers during condensation and iteratively update the triggers to ensure effective attacks. Further, we propose a poisoned node selection module to minimize the influence of triggers on condensed graphs' quality. The extensive experiments demonstrate the effectiveness of our attack. BGC achieves a high attack success rate (close to 1.0) and good model utility in all cases. Furthermore, the results demonstrate our method's resilience against multiple defense methods. Finally, we conduct comprehensive studies to analyze the factors that influence the attack performance.
Authors: Naoki Nishimura, Ken Kobayashi, Kazuhide Nakata
Abstract: Coupon allocation drives customer purchases and boosts revenue. However, it presents a fundamental trade-off between exploiting the current optimal policy to maximize immediate revenue and exploring alternative policies to collect data for future policy improvement via off-policy evaluation (OPE). While online A/B testing can validate new policies, it risks compromising short-term revenue. Conversely, relying solely on an exploitative policy hinders the ability to reliably estimate and enhance future policies. To balance this trade-off, we propose a novel approach that combines a model-based revenue maximization policy and a randomized exploration policy for data collection. Our framework enables flexibly adjusting the mixture ratio between these two policies to optimize the balance between short-term revenue and future policy improvement. We formulate the problem of determining the optimal mixture ratio between a model-based revenue maximization policy and a randomized exploration policy for data collection. We empirically verified the effectiveness of the proposed mixed policy using both synthetic and real-world data. Our main contributions are: (1) Demonstrating a mixed policy combining deterministic and probabilistic policies, flexibly adjusting the data collection vs. revenue trade-off. (2) Formulating the optimal mixture ratio problem as multi-objective optimization, enabling quantitative evaluation of this trade-off. By optimizing the mixture ratio, businesses can maximize revenue while ensuring reliable future OPE and policy improvement. This framework is applicable in any context where the exploration-exploitation trade-off is relevant.
Authors: Vidya Srinivas, Malek Itani, Tuochao Chen, Emre Sefik Eskimez, Takuya Yoshioka, Shyamnath Gollakota
Abstract: Models for low-latency, streaming applications could benefit from the knowledge capacity of larger models, but edge devices cannot run these models due to resource constraints. A possible solution is to transfer hints during inference from a large model running remotely to a small model running on-device. However, this incurs a communication delay that breaks real-time requirements and does not guarantee that both models will operate on the same data at the same time. We propose knowledge boosting, a novel technique that allows a large model to operate on time-delayed input during inference, while still boosting small model performance. Using a streaming neural network that processes 8 ms chunks, we evaluate different speech separation and enhancement tasks with communication delays of up to six chunks or 48 ms. Our results show larger gains where the performance gap between the small and large models is wide, demonstrating a promising method for large-small model collaboration for low-latency applications. Code, dataset, and audio samples available at https://knowledgeboosting.cs.washington.edu/.
Authors: Jakob Weber, Markus Gurtner, Amadeus Lobe, Adrian Trachte, Andreas Kugi
Abstract: This survey provides an overview of combining Federated Learning (FL) and control to enhance adaptability, scalability, generalization, and privacy in (nonlinear) control applications. Traditional control methods rely on controller design models, but real-world scenarios often require online model retuning or learning. FL offers a distributed approach to model training, enabling collaborative learning across distributed devices while preserving data privacy. By keeping data localized, FL mitigates concerns regarding privacy and security while reducing network bandwidth requirements for communication. This survey summarizes the state-of-the-art concepts and ideas of combining FL and control. The methodical benefits are further discussed, culminating in a detailed overview of expected applications, from dynamical system modeling over controller design, focusing on adaptive control, to knowledge transfer in multi-agent decision-making systems.
Authors: Piotr Mirowski, David Warde-Farley, Mihaela Rosca, Matthew Koichi Grimes, Yana Hasson, Hyunjik Kim, M\'elanie Rey, Simon Osindero, Suman Ravuri, Shakir Mohamed
Abstract: Atmospheric states derived from reanalysis comprise a substantial portion of weather and climate simulation outputs. Many stakeholders -- such as researchers, policy makers, and insurers -- use this data to better understand the earth system and guide policy decisions. Atmospheric states have also received increased interest as machine learning approaches to weather prediction have shown promising results. A key issue for all audiences is that dense time series of these high-dimensional states comprise an enormous amount of data, precluding all but the most well resourced groups from accessing and using historical data and future projections. To address this problem, we propose a method for compressing atmospheric states using methods from the neural network literature, adapting spherical data to processing by conventional neural architectures through the use of the area-preserving HEALPix projection. We investigate two model classes for building neural compressors: the hyperprior model from the neural image compression literature and recent vector-quantised models. We show that both families of models satisfy the desiderata of small average error, a small number of high-error reconstructed pixels, faithful reproduction of extreme events such as hurricanes and heatwaves, preservation of the spectral power distribution across spatial scales. We demonstrate compression ratios in excess of 1000x, with compression and decompression at a rate of approximately one second per global atmospheric state.
Authors: Athindran Ramesh Kumar, Balaraman Ravindran, Anand Raghunathan
Abstract: Object detection in videos is an important task in computer vision for various applications such as object tracking, video summarization and video search. Although great progress has been made in improving the accuracy of object detection in recent years due to the rise of deep neural networks, the state-of-the-art algorithms are highly computationally intensive. In order to address this challenge, we make two important observations in the context of videos: (i) Objects often occupy only a small fraction of the area in each video frame, and (ii) There is a high likelihood of strong temporal correlation between consecutive frames. Based on these observations, we propose Pack and Detect (PaD), an approach to reduce the computational requirements of object detection in videos. In PaD, only selected video frames called anchor frames are processed at full size. In the frames that lie between anchor frames (inter-anchor frames), regions of interest (ROIs) are identified based on the detections in the previous frame. We propose an algorithm to pack the ROIs of each inter-anchor frame together into a reduced-size frame. The computational requirements of the detector are reduced due to the lower size of the input. In order to maintain the accuracy of object detection, the proposed algorithm expands the ROIs greedily to provide additional background around each object to the detector. PaD can use any underlying neural network architecture to process the full-size and reduced-size frames. Experiments using the ImageNet video object detection dataset indicate that PaD can potentially reduce the number of FLOPS required for a frame by $4\times$. This leads to an overall increase in throughput of $1.25\times$ on a 2.1 GHz Intel Xeon server with a NVIDIA Titan X GPU at the cost of $1.1\%$ drop in accuracy.
Authors: Kelum Gajamannage
Abstract: With the proliferation of sophisticated cameras in modern society, the demand for accurate and visually pleasing images is increasing. However, the quality of an image captured by a camera may be degraded by noise. Thus, some processing of images is required to filter out the noise without losing vital image features. Even though the current literature offers a variety of denoising methods, the fidelity and efficacy of their denoising are sometimes uncertain. Thus, here we propose a novel and computationally efficient image denoising method that is capable of producing accurate images. To preserve image smoothness, this method inputs patches partitioned from the image rather than pixels. Then, it performs denoising on the manifold underlying the patch-space rather than that in the image domain to better preserve the features across the whole image. We validate the performance of this method against benchmark image processing methods.
Authors: Bojia Zi, Minghao Chang, Jingjing Chen, Xingjun Ma, Yu-Gang Jiang
Abstract: In recent years, the abuse of a face swap technique called deepfake has raised enormous public concerns. So far, a large number of deepfake videos (known as "deepfakes") have been crafted and uploaded to the internet, calling for effective countermeasures. One promising countermeasure against deepfakes is deepfake detection. Several deepfake datasets have been released to support the training and testing of deepfake detectors, such as DeepfakeDetection and FaceForensics++. While this has greatly advanced deepfake detection, most of the real videos in these datasets are filmed with a few volunteer actors in limited scenes, and the fake videos are crafted by researchers using a few popular deepfake softwares. Detectors developed on these datasets may become less effective against real-world deepfakes on the internet. To better support detection against real-world deepfakes, in this paper, we introduce a new dataset WildDeepfake which consists of 7,314 face sequences extracted from 707 deepfake videos collected completely from the internet. WildDeepfake is a small dataset that can be used, in addition to existing datasets, to develop and test the effectiveness of deepfake detectors against real-world deepfakes. We conduct a systematic evaluation of a set of baseline detection networks on both existing and our WildDeepfake datasets, and show that WildDeepfake is indeed a more challenging dataset, where the detection performance can decrease drastically. We also propose two (eg. 2D and 3D) Attention-based Deepfake Detection Networks (ADDNets) to leverage the attention masks on real/fake faces for improved detection. We empirically verify the effectiveness of ADDNets on both existing datasets and WildDeepfake. The dataset is available at: https://github.com/OpenTAI/wild-deepfake.
Authors: Ariel Neufeld, Philipp Schmocker
Abstract: In this paper, we extend the Wiener-Ito chaos decomposition to the class of continuous semimartingales that are exponentially integrable, which includes in particular affine and some polynomial diffusion processes. By omitting the orthogonality in the expansion, we are able to show that every $p$-integrable functional of the semimartingale, for $p \in [1,\infty)$, can be represented as a sum of iterated integrals thereof. Using finitely many terms of this expansion and (possibly random) neural networks for the integrands, whose parameters are learned in a machine learning setting, we show that every financial derivative can be approximated arbitrarily well in the $L^p$-sense. In particular, for $p = 2$, we recover the optimal hedging strategy in the sense of quadratic hedging. Moreover, since the hedging strategy of the approximating option can be computed in closed form, we obtain an efficient algorithm to approximately replicate any sufficiently integrable financial derivative within short runtime.
Authors: Atefeh H. Arani, Peng Hu, Yeying Zhu
Abstract: Recent technological advancements in space, air, and ground components have made possible a new network paradigm called space-air-ground integrated network (SAGIN). Unmanned aerial vehicles (UAVs) play a key role in SAGINs. However, due to UAVs' high dynamics and complexity, real-world deployment of a SAGIN becomes a significant barrier to realizing such SAGINs. UAVs are expected to meet key performance requirements with limited maneuverability and resources with space and terrestrial components. Therefore, employing UAVs in various usage scenarios requires well-designed planning in algorithmic approaches. This paper provides an essential review and analysis of recent learning algorithms in a UAV-assisted SAGIN. We consider possible reward functions and discuss the state-of-the-art algorithms for optimizing the reward functions, including Q-learning, deep Q-learning, multi-armed bandit, particle swarm optimization, and satisfaction-based learning algorithms. Unlike other survey papers, we focus on the methodological perspective of the optimization problem, applicable to various missions on a SAGIN. We consider real-world configurations and the 2-dimensional (2D) and 3-dimensional (3D) UAV trajectories to reflect deployment cases. Our simulations suggest the 3D satisfaction-based learning algorithm outperforms other approaches in most cases. With open challenges discussed at the end, we aim to provide design and deployment guidelines for UAV-assisted SAGINs.
Authors: Florinel-Alin Croitoru, Nicolae-Catalin Ristea, Dana Dascalescu, Radu Tudor Ionescu, Fahad Shahbaz Khan, Mubarak Shah
Abstract: We propose a very fast frame-level model for anomaly detection in video, which learns to detect anomalies by distilling knowledge from multiple highly accurate object-level teacher models. To improve the fidelity of our student, we distill the low-resolution anomaly maps of the teachers by jointly applying standard and adversarial distillation, introducing an adversarial discriminator for each teacher to distinguish between target and generated anomaly maps. We conduct experiments on three benchmarks (Avenue, ShanghaiTech, UCSD Ped2), showing that our method is over 7 times faster than the fastest competing method, and between 28 and 62 times faster than object-centric models, while obtaining comparable results to recent methods. Our evaluation also indicates that our model achieves the best trade-off between speed and accuracy, due to its previously unheard-of speed of 1480 FPS. In addition, we carry out a comprehensive ablation study to justify our architectural design choices. Our code is freely available at: https://github.com/ristea/fast-aed.
Authors: Mohsen Karami (Hoda), Roohallah Alizadehsani (Hoda), Khadijeh (Hoda), Jahanian, Ahmadreza Argha, Iman Dehzangi, Hamid Alinejad-Rokny
Abstract: In recent years, Reinforcement Learning (RL) has emerged as a powerful tool for solving a wide range of problems, including decision-making and genomics. The exponential growth of raw genomic data over the past two decades has exceeded the capacity of manual analysis, leading to a growing interest in automatic data analysis and processing. RL algorithms are capable of learning from experience with minimal human supervision, making them well-suited for genomic data analysis and interpretation. One of the key benefits of using RL is the reduced cost associated with collecting labeled training data, which is required for supervised learning. While there have been numerous studies examining the applications of Machine Learning (ML) in genomics, this survey focuses exclusively on the use of RL in various genomics research fields, including gene regulatory networks (GRNs), genome assembly, and sequence alignment. We present a comprehensive technical overview of existing studies on the application of RL in genomics, highlighting the strengths and limitations of these approaches. We then discuss potential research directions that are worthy of future exploration, including the development of more sophisticated reward functions as RL heavily depends on the accuracy of the reward function, the integration of RL with other machine learning techniques, and the application of RL to new and emerging areas in genomics research. Finally, we present our findings and conclude by summarizing the current state of the field and the future outlook for RL in genomics.
Authors: Lorenzo Cazzella, Francesco Linsalata, Maurizio Magarini, Matteo Matteucci, Umberto Spagnolini
Abstract: Digital Twins (DTs) for physical wireless environments have been recently proposed as accurate virtual representations of the propagation environment that can enable multi-layer decisions at the physical communication equipment. At high-frequency bands, DTs can help to overcome the challenges emerging in high mobility conditions featuring vehicular environments. In this paper, we propose a novel data-driven workflow for the creation of the DT of a Vehicle-to-Everything (V2X) communication scenario and a multi-modal simulation framework for the generation of realistic sensor data and accurate mmWave/sub-THz wireless channels. The proposed method leverages an automotive simulation and testing framework and an accurate ray-tracing channel simulator. Simulations over an urban scenario show the achievable realistic sensor and channel modelling both at the infrastructure and at ego-vehicles. We showcase the proposed framework on the DT-aided blockage handover task for V2X link restoration, leveraging the framework's dynamic channel generation capabilities for realistic vehicular blockage simulation.
Authors: Mengxin Zheng, Jiaqi Xue, Zihao Wang, Xun Chen, Qian Lou, Lei Jiang, Xiaofeng Wang
Abstract: Self-supervised learning (SSL) is a prevalent approach for encoding data representations. Using a pre-trained SSL image encoder and subsequently training a downstream classifier, impressive performance can be achieved on various tasks with very little labeled data. The growing adoption of SSL has led to an increase in security research on SSL encoders and associated Trojan attacks. Trojan attacks embedded in SSL encoders can operate covertly, spreading across multiple users and devices. The presence of backdoor behavior in Trojaned encoders can inadvertently be inherited by downstream classifiers, making it even more difficult to detect and mitigate the threat. Although current Trojan detection methods in supervised learning can potentially safeguard SSL downstream classifiers, identifying and addressing triggers in the SSL encoder before its widespread dissemination is a challenging task. This challenge arises because downstream tasks might be unknown, dataset labels may be unavailable, and the original unlabeled training dataset might be inaccessible during Trojan detection in SSL encoders. We introduce SSL-Cleanse as a solution to identify and mitigate backdoor threats in SSL encoders. We evaluated SSL-Cleanse on various datasets using 1200 encoders, achieving an average detection success rate of 82.2% on ImageNet-100. After mitigating backdoors, on average, backdoored encoders achieve 0.3% attack success rate without great accuracy loss, proving the effectiveness of SSL-Cleanse. The source code of SSL-Cleanse is available at https://github.com/UCF-ML-Research/SSL-Cleanse.
Authors: Yunjie He, Mojtaba Nayyeri, Bo Xiong, Yuqicheng Zhu, Evgeny Kharlamov, Steffen Staab
Abstract: Answering first-order logical (FOL) queries over knowledge graphs (KG) remains a challenging task mainly due to KG incompleteness. Query embedding approaches this problem by computing the low-dimensional vector representations of entities, relations, and logical queries. KGs exhibit relational patterns such as symmetry and composition and modeling the patterns can further enhance the performance of query embedding models. However, the role of such patterns in answering FOL queries by query embedding models has not been yet studied in the literature. In this paper, we fill in this research gap and empower FOL queries reasoning with pattern inference by introducing an inductive bias that allows for learning relation patterns. To this end, we develop a novel query embedding method, RoConE, that defines query regions as geometric cones and algebraic query operators by rotations in complex space. RoConE combines the advantages of Cone as a well-specified geometric representation for query embedding, and also the rotation operator as a powerful algebraic operation for pattern inference. Our experimental results on several benchmark datasets confirm the advantage of relational patterns for enhancing logical query answering task.
Authors: Zhenqiao Song, Lei Li
Abstract: Designing protein sequences with desired biological function is crucial in biology and chemistry. Recent machine learning methods use a surrogate sequence-function model to replace the expensive wet-lab validation. How can we efficiently generate diverse and novel protein sequences with high fitness? In this paper, we propose IsEM-Pro, an approach to generate protein sequences towards a given fitness criterion. At its core, IsEM-Pro is a latent generative model, augmented by combinatorial structure features from a separately learned Markov random fields (MRFs). We develop an Monte Carlo Expectation-Maximization method (MCEM) to learn the model. During inference, sampling from its latent space enhances diversity while its MRFs features guide the exploration in high fitness regions. Experiments on eight protein sequence design tasks show that our IsEM-Pro outperforms the previous best methods by at least 55% on average fitness score and generates more diverse and novel protein sequences.
Authors: Zhan Yu, Jun Fan, Zhongjie Shi, Ding-Xuan Zhou
Abstract: In recent years, different types of distributed and parallel learning schemes have received increasing attention for their strong advantages in handling large-scale data information. In the information era, to face the big data challenges {that} stem from functional data analysis very recently, we propose a novel distributed gradient descent functional learning (DGDFL) algorithm to tackle functional data across numerous local machines (processors) in the framework of reproducing kernel Hilbert space. Based on integral operator approaches, we provide the first theoretical understanding of the DGDFL algorithm in many different aspects of the literature. On the way of understanding DGDFL, firstly, a data-based gradient descent functional learning (GDFL) algorithm associated with a single-machine model is proposed and comprehensively studied. Under mild conditions, confidence-based optimal learning rates of DGDFL are obtained without the saturation boundary on the regularity index suffered in previous works in functional regression. We further provide a semi-supervised DGDFL approach to weaken the restriction on the maximal number of local machines to ensure optimal rates. To our best knowledge, the DGDFL provides the first divide-and-conquer iterative training approach to functional learning based on data samples of intrinsically infinite-dimensional random functions (functional covariates) and enriches the methodologies for functional data analysis.
Authors: Christoph Hertrich, Yixin Tao, L\'aszl\'o A. V\'egh
Abstract: Optimal auction design is a fundamental problem in algorithmic game theory. This problem is notoriously difficult already in very simple settings. Recent work in differentiable economics showed that neural networks can efficiently learn known optimal auction mechanisms and discover interesting new ones. In an attempt to theoretically justify their empirical success, we focus on one of the first such networks, RochetNet, and a generalized version for affine maximizer auctions. We prove that they satisfy mode connectivity, i.e., locally optimal solutions are connected by a simple, piecewise linear path such that every solution on the path is almost as good as one of the two local optima. Mode connectivity has been recently investigated as an intriguing empirical and theoretically justifiable property of neural networks used for prediction problems. Our results give the first such analysis in the context of differentiable economics, where neural networks are used directly for solving non-convex optimization problems.
Authors: Caixin Kang, Yinpeng Dong, Zhengyi Wang, Shouwei Ruan, Yubo Chen, Hang Su, Xingxing Wei
Abstract: Adversarial attacks, particularly patch attacks, pose significant threats to the robustness and reliability of deep learning models. Developing reliable defenses against patch attacks is crucial for real-world applications. This paper introduces DIFFender, a novel defense framework that harnesses the capabilities of a text-guided diffusion model to combat patch attacks. Central to our approach is the discovery of the Adversarial Anomaly Perception (AAP) phenomenon, which empowers the diffusion model to detect and localize adversarial patches through the analysis of distributional discrepancies. DIFFender integrates dual tasks of patch localization and restoration within a single diffusion model framework, utilizing their close interaction to enhance defense efficacy. Moreover, DIFFender utilizes vision-language pre-training coupled with an efficient few-shot prompt-tuning algorithm, which streamlines the adaptation of the pre-trained diffusion model to defense tasks, thus eliminating the need for extensive retraining. Our comprehensive evaluation spans image classification and face recognition tasks, extending to real-world scenarios, where DIFFender shows good robustness against adversarial attacks. The versatility and generalizability of DIFFender are evident across a variety of settings, classifiers, and attack methodologies, marking an advancement in adversarial patch defense strategies.
Authors: Jiexin Wang, Yujie Zhou, Wenwen Qiang, Ying Ba, Bing Su, Ji-Rong Wen
Abstract: Human motion prediction (HMP) has emerged as a popular research topic due to its diverse applications, but it remains a challenging task due to the stochastic and aperiodic nature of future poses. Traditional methods rely on hand-crafted features and machine learning techniques, which often struggle to model the complex dynamics of human motion. Recent deep learning-based methods have achieved success by learning spatio-temporal representations of motion, but these models often overlook the reliability of motion data. Additionally, the temporal and spatial dependencies of skeleton nodes are distinct. The temporal relationship captures motion information over time, while the spatial relationship describes body structure and the relationships between different nodes. In this paper, we propose a novel spatio-temporal branching network using incremental information for HMP, which decouples the learning of temporal-domain and spatial-domain features, extracts more motion information, and achieves complementary cross-domain knowledge learning through knowledge distillation. Our approach effectively reduces noise interference and provides more expressive information for characterizing motion by separately extracting temporal and spatial features. We evaluate our approach on standard HMP benchmarks and outperform state-of-the-art methods in terms of prediction accuracy.
Authors: Maan Qraitem, Kate Saenko, Bryan A. Plummer
Abstract: Visual recognition models are prone to learning spurious correlations induced by a biased training set where certain conditions $B$ (\eg, Indoors) are over-represented in certain classes $Y$ (\eg, Big Dogs). Synthetic data from off-the-shelf large-scale generative models offers a promising direction to mitigate this issue by augmenting underrepresented subgroups in the real dataset. However, by using a mixed distribution of real and synthetic data, we introduce another source of bias due to distributional differences between synthetic and real data (\eg synthetic artifacts). As we will show, prior work's approach for using synthetic data to resolve the model's bias toward $B$ do not correct the model's bias toward the pair $(B, G)$, where $G$ denotes whether the sample is real or synthetic. Thus, the model could simply learn signals based on the pair $(B, G)$ (\eg, Synthetic Indoors) to make predictions about $Y$ (\eg, Big Dogs). To address this issue, we propose a simple, easy-to-implement, two-step training pipeline that we call From Fake to Real (FFR). The first step of FFR pre-trains a model on balanced synthetic data to learn robust representations across subgroups. In the second step, FFR fine-tunes the model on real data using ERM or common loss-based bias mitigation methods. By training on real and synthetic data separately, FFR does not expose the model to the statistical differences between real and synthetic data and thus avoids the issue of bias toward the pair $(B, G)$. Our experiments show that FFR improves worst group accuracy over the state-of-the-art by up to 20\% over three datasets. Code available: \url{https://github.com/mqraitem/From-Fake-to-Real}
Authors: Steffen Hagedorn, Marcel Hallgarten, Martin Stoll, Alexandru Condurache
Abstract: Automated driving has the potential to revolutionize personal, public, and freight mobility. Beside accurately perceiving the environment, automated vehicles must plan a safe, comfortable, and efficient motion trajectory. To promote safety and progress, many works rely on modules that predict the future motion of surrounding traffic. Modular automated driving systems commonly handle prediction and planning as sequential, separate tasks. While this accounts for the influence of surrounding traffic on the ego vehicle, it fails to anticipate the reactions of traffic participants to the ego vehicle's behavior. Recent models increasingly integrate prediction and planning in a joint or interdependent step to model bi-directional interactions. To date, a comprehensive overview of different integration principles is lacking. We systematically review state-of-the-art deep learning-based prediction and planning, and focus on integrated prediction and planning models. Different facets of the integration ranging from model architecture and model design to behavioral aspects are considered and related to each other. Moreover, we discuss the implications, strengths, and limitations of different integration principles. By pointing out research gaps, describing relevant future challenges, and highlighting trends in the research field, we identify promising directions for future research.
Authors: Nikolai K\"orber, Eduard Kromer, Andreas Siebert, Sascha Hauke, Daniel Mueller-Gritschneder, Bj\"orn Schuller
Abstract: We introduce EGIC, an enhanced generative image compression method that allows traversing the distortion-perception curve efficiently from a single model. EGIC is based on two novel building blocks: i) OASIS-C, a conditional pre-trained semantic segmentation-guided discriminator, which provides both spatially and semantically-aware gradient feedback to the generator, conditioned on the latent image distribution, and ii) Output Residual Prediction (ORP), a retrofit solution for multi-realism image compression that allows control over the synthesis process by adjusting the impact of the residual between an MSE-optimized and GAN-optimized decoder output on the GAN-based reconstruction. Together, EGIC forms a powerful codec, outperforming state-of-the-art diffusion and GAN-based methods (e.g., HiFiC, MS-ILLM, and DIRAC-100), while performing almost on par with VTM-20.0 on the distortion end. EGIC is simple to implement, very lightweight, and provides excellent interpolation characteristics, which makes it a promising candidate for practical applications targeting the low bit range.
Authors: Chengpeng Li, Zheng Yuan, Hongyi Yuan, Guanting Dong, Keming Lu, Jiancan Wu, Chuanqi Tan, Xiang Wang, Chang Zhou
Abstract: In math reasoning with large language models (LLMs), fine-tuning data augmentation by query evolution and diverse reasoning paths is empirically verified effective, profoundly narrowing the gap between open-sourced LLMs and cutting-edge proprietary LLMs. In this paper, we conduct an investigation for such data augmentation in math reasoning and are intended to answer: (1) What strategies of data augmentation are more effective; (2) What is the scaling relationship between the amount of augmented data and model performance; and (3) Can data augmentation incentivize generalization to out-of-domain mathematical reasoning tasks? To this end, we create two new dataset AugGSM8K and AugMATH, by complicating and diversifying the queries and sampling multiple reasoning paths from GSM8K and MATH. We obtained a series of LLMs called MuggleMath by fine-tuning LLaMA models on AugGSM8K and AugMATH. MuggleMath substantially achieves new state-of-the-art on GSM8K and MATH. A log-linear relationship and a segmented log-linear are presented between MuggleMath's performance and the amount of augmented data on GSM8K and MATH, respectively. We also find that it is weak in out-of-domain math reasoning generalization from AugGSM8K to MATH and from AugMATH to GSM8K, which suggests that augmenting queries that cover a broader range of subjects is more beneficial for generalization. We release our codes and augmented data in https://github.com/OFA-Sys/gsm8k-ScRel.
Authors: Nikolaos Evangelou, Dimitrios G. Giovanis, George A. Kevrekidis, Grigorios A. Pavliotis, Ioannis G. Kevrekidis
Abstract: Deriving closed-form, analytical expressions for reduced-order models, and judiciously choosing the closures leading to them, has long been the strategy of choice for studying phase- and noise-induced transitions for agent-based models (ABMs). In this paper, we propose a data-driven framework that pinpoints phase transitions for an ABM- the Desai-Zwanzig model in its mean-field limit, using a smaller number of variables than traditional closed-form models. To this end, we use the manifold learning algorithm Diffusion Maps to identify a parsimonious set of data-driven latent variables, and show that they are in one-to-one correspondence with the expected theoretical order parameter of the ABM. We then utilize a deep learning framework to obtain a conformal reparametrization of the data-driven coordinates that facilitates, in our example, the identification of a single parameter-dependent ODE in these coordinates. We identify this ODE through a residual neural network inspired by a numerical integration scheme (forward Euler). We then use the identified ODE - enabled through an odd symmetry transformation - to construct the bifurcation diagram exhibiting the phase transition.
Authors: Bowen Jiang, Zhijun Zhuang, Shreyas S. Shivakumar, Camillo J. Taylor
Abstract: This work introduces an enhanced approach to generating scene graphs by incorporating both a relationship hierarchy and commonsense knowledge. Specifically, we begin by proposing a hierarchical relation head that exploits an informative hierarchical structure. It jointly predicts the relation super-category between object pairs in an image, along with detailed relations under each super-category. Following this, we implement a robust commonsense validation pipeline that harnesses foundation models to critique the results from the scene graph prediction system, removing nonsensical predicates even with a small language-only model. Extensive experiments on Visual Genome and OpenImage V6 datasets demonstrate that the proposed modules can be seamlessly integrated as plug-and-play enhancements to existing scene graph generation algorithms. The results show significant improvements with an extensive set of reasonable predictions beyond dataset annotations. Codes are available at https://github.com/bowen-upenn/scene_graph_commonsense.
URLs: https://github.com/bowen-upenn/scene_graph_commonsense.
Authors: Chenglin Yang, Siyuan Qiao, Yuan Cao, Yu Zhang, Tao Zhu, Alan Yuille, Jiahui Yu
Abstract: Generative training has been demonstrated to be powerful for building visual-language models. However, on zero-shot discriminative benchmarks, there is still a performance gap between models trained with generative and discriminative objectives. In this paper, we aim to narrow this gap by improving the efficacy of generative training on classification tasks, without any finetuning processes or additional modules. Specifically, we focus on narrowing the gap between the generative captioner and the CLIP classifier. We begin by analysing the predictions made by the captioner and classifier and observe that the caption generation inherits the distribution bias from the language model trained with pure text modality, making it less grounded on the visual signal. To tackle this problem, we redesign the scoring objective for the captioner to alleviate the distributional bias and focus on measuring the gain of information brought by the visual inputs. We further design a generative training objective to match the evaluation objective. We name our model trained and evaluated from the novel procedures as Information Gain (IG) captioner. We pretrain the models on the public Laion-5B dataset and perform a series of discriminative evaluations. For the zero-shot classification on ImageNet, IG captioner achieves $> 18\%$ improvements over the standard captioner, achieving comparable performances with the CLIP classifier. IG captioner also demonstrated strong performance on zero-shot image-text retrieval tasks on MSCOCO and Flickr30K. We hope this paper inspires further research towards unifying generative and discriminative training procedures for visual-language models.
Authors: Ruoqi Wen, Jiahao Huang, Rongpeng Li, Guoru Ding, Zhifeng Zhao
Abstract: Autonomous Vehicles (AVs) have attracted significant attention in recent years and Reinforcement Learning (RL) has shown remarkable performance in improving the autonomy of vehicles. In that regard, the widely adopted Model-Free RL (MFRL) promises to solve decision-making tasks in connected AVs (CAVs), contingent on the readiness of a significant amount of data samples for training. Nevertheless, it might be infeasible in practice and possibly lead to learning instability. In contrast, Model-Based RL (MBRL) manifests itself in sample-efficient learning, but the asymptotic performance of MBRL might lag behind the state-of-the-art MFRL algorithms. Furthermore, most studies for CAVs are limited to the decision-making of a single AV only, thus underscoring the performance due to the absence of communications. In this study, we try to address the decision-making problem of multiple CAVs with limited communications and propose a decentralized Multi-Agent Probabilistic Ensembles with Trajectory Sampling algorithm MA-PETS. In particular, in order to better capture the uncertainty of the unknown environment, MA-PETS leverages Probabilistic Ensemble (PE) neural networks to learn from communicated samples among neighboring CAVs. Afterwards, MA-PETS capably develops Trajectory Sampling (TS)-based model-predictive control for decision-making. On this basis, we derive the multi-agent group regret bound affected by the number of agents within the communication range and mathematically validate that incorporating effective information exchange among agents into the multi-agent learning scheme contributes to reducing the group regret bound in the worst case. Finally, we empirically demonstrate the superiority of MA-PETS in terms of the sample efficiency comparable to MFBL.
Authors: Sanae Lotfi, Marc Finzi, Yilun Kuang, Tim G. J. Rudner, Micah Goldblum, Andrew Gordon Wilson
Abstract: Modern language models can contain billions of parameters, raising the question of whether they can generalize beyond the training data or simply parrot their training corpora. We provide the first non-vacuous generalization bounds for pretrained large language models (LLMs), indicating that language models are capable of discovering regularities that generalize to unseen data. In particular, we derive a compression bound that is valid for the unbounded log-likelihood loss using prediction smoothing, and we extend the bound to handle subsampling, accelerating bound computation by orders of magnitude on massive datasets. To achieve the extreme level of compression required for non-vacuous bounds, we devise SubLoRA, a simple low-dimensional nonlinear parameterization that leads to non-vacuous generalization bounds for models with nearly a billion parameters. Finally, we use our bounds to understand LLM generalization and find that larger models have better generalization bounds and are more compressible than smaller models.
Authors: Christian Huber, Alexander Waibel
Abstract: Despite recent advances, Automatic Speech Recognition (ASR) systems are still far from perfect. Typical errors include acronyms, named entities and domain-specific special words for which little or no data is available. To address the problem of recognizing these words, we propose an self-supervised continual learning approach. Given the audio of a lecture talk with corresponding slides, we bias the model towards decoding new words from the slides by using a memory-enhanced ASR model from previous work. Then, we perform inference on the talk, collecting utterances that contain detected new words into an adaptation dataset. Continual learning is then performed on this set by adapting low-rank matrix weights added to each weight matrix of the model. The whole procedure is iterated for many talks. We show that with this approach, we obtain increasing performance on the new words when they occur more frequently (more than 80% recall) while preserving the general performance of the model.
Authors: Yanran Guan, Oliver van Kaick
Abstract: Methods that use neural networks for synthesizing 3D shapes in the form of a part-based representation have been introduced over the last few years. These methods represent shapes as a graph or hierarchy of parts and enable a variety of applications such as shape sampling and reconstruction. However, current methods do not allow easily regenerating individual shape parts according to user preferences. In this paper, we investigate techniques that allow the user to generate multiple, diverse suggestions for individual parts. Specifically, we experiment with multimodal deep generative models that allow sampling diverse suggestions for shape parts and focus on models which have not been considered in previous work on shape synthesis. To provide a comparative study of these techniques, we introduce a method for synthesizing 3D shapes in a part-based representation and evaluate all the part suggestion techniques within this synthesis method. In our method, which is inspired by previous work, shapes are represented as a set of parts in the form of implicit functions which are then positioned in space to form the final shape. Synthesis in this representation is enabled by a neural network architecture based on an implicit decoder and a spatial transformer. We compare the various multimodal generative models by evaluating their performance in generating part suggestions. Our contribution is to show with qualitative and quantitative evaluations which of the new techniques for multimodal part generation perform the best and that a synthesis method based on the top-performing techniques allows the user to more finely control the parts that are generated in the 3D shapes while maintaining high shape fidelity when reconstructing shapes.
Authors: Aron Brenner, Rahman Khorramfar, Dharik Mallapragada, Saurabh Amin
Abstract: Solving large-scale capacity expansion problems (CEPs) is central to cost-effective decarbonization of regional-scale energy systems. To ensure the intended outcomes of CEPs, modeling uncertainty due to weather-dependent variable renewable energy (VRE) supply and energy demand becomes crucially important. However, the resulting stochastic optimization models are often less computationally tractable than their deterministic counterparts. Here, we propose a learning-assisted approximate solution method to tractably solve two-stage stochastic CEPs. Our method identifies low-cost planning decisions by constructing and solving a sequence of tractable temporally aggregated surrogate problems. We adopt a Bayesian optimization approach to searching the space of time series aggregation hyperparameters and compute approximate solutions that minimize costs on a validation set of supply-demand projections. Importantly, we evaluate solved planning outcomes on a held-out set of test projections. We apply our approach to generation and transmission expansion planning for a joint power-gas system spanning New England. We show that our approach yields an estimated cost savings of up to 3.8% in comparison to benchmark time series aggregation approaches.
Authors: Yanis Labrak, Adrien Bazoge, Emmanuel Morin, Pierre-Antoine Gourraud, Mickael Rouvier, Richard Dufour
Abstract: Large Language Models (LLMs) have demonstrated remarkable versatility in recent years, offering potential applications across specialized domains such as healthcare and medicine. Despite the availability of various open-source LLMs tailored for health contexts, adapting general-purpose LLMs to the medical domain presents significant challenges. In this paper, we introduce BioMistral, an open-source LLM tailored for the biomedical domain, utilizing Mistral as its foundation model and further pre-trained on PubMed Central. We conduct a comprehensive evaluation of BioMistral on a benchmark comprising 10 established medical question-answering (QA) tasks in English. We also explore lightweight models obtained through quantization and model merging approaches. Our results demonstrate BioMistral's superior performance compared to existing open-source medical models and its competitive edge against proprietary counterparts. Finally, to address the limited availability of data beyond English and to assess the multilingual generalization of medical LLMs, we automatically translated and evaluated this benchmark into 7 other languages. This marks the first large-scale multilingual evaluation of LLMs in the medical domain. Datasets, multilingual evaluation benchmarks, scripts, and all the models obtained during our experiments are freely released.
Authors: Maximilien Dreveton, Alperen G\"ozeten, Matthias Grossglauser, Patrick Thiran
Abstract: Clustering is a pivotal challenge in unsupervised machine learning and is often investigated through the lens of mixture models. The optimal error rate for recovering cluster labels in Gaussian and sub-Gaussian mixture models involves ad hoc signal-to-noise ratios. Simple iterative algorithms, such as Lloyd's algorithm, attain this optimal error rate. In this paper, we first establish a universal lower bound for the error rate in clustering any mixture model, expressed through a Chernoff divergence, a more versatile measure of model information than signal-to-noise ratios. We then demonstrate that iterative algorithms attain this lower bound in mixture models with sub-exponential tails, notably emphasizing location-scale mixtures featuring Laplace-distributed errors. Additionally, for datasets better modelled by Poisson or Negative Binomial mixtures, we study mixture models whose distributions belong to an exponential family. In such mixtures, we establish that Bregman hard clustering, a variant of Lloyd's algorithm employing a Bregman divergence, is rate optimal.
Authors: Andr\'e Ferreira, Naida Solak, Jianning Li, Philipp Dammann, Jens Kleesiek, Victor Alves, Jan Egger
Abstract: Deep Learning is the state-of-the-art technology for segmenting brain tumours. However, this requires a lot of high-quality data, which is difficult to obtain, especially in the medical field. Therefore, our solutions address this problem by using unconventional mechanisms for data augmentation. Generative adversarial networks and registration are used to massively increase the amount of available samples for training three different deep learning models for brain tumour segmentation, the first task of the BraTS2023 challenge. The first model is the standard nnU-Net, the second is the Swin UNETR and the third is the winning solution of the BraTS 2021 Challenge. The entire pipeline is built on the nnU-Net implementation, except for the generation of the synthetic data. The use of convolutional algorithms and transformers is able to fill each other's knowledge gaps. Using the new metric, our best solution achieves the dice results 0.9005, 0.8673, 0.8509 and HD95 14.940, 14.467, 17.699 (whole tumour, tumour core and enhancing tumour) in the validation set.
Authors: Alberto Bemporad
Abstract: In this paper, we propose a very efficient numerical method based on the L-BFGS-B algorithm for identifying linear and nonlinear discrete-time state-space models, possibly under $\ell_1$- and group-Lasso regularization for reducing model complexity. For the identification of linear models, we show that, compared to classical linear subspace methods, the approach often provides better results, is much more general in terms of the loss and regularization terms used (such as penalties for enforcing system stability), and is also more stable from a numerical point of view. The proposed method not only enriches the existing set of linear system identification tools but can also be applied to identifying a very broad class of parametric nonlinear state-space models, including recurrent neural networks. We illustrate the approach on synthetic and experimental datasets and apply it to solve a challenging industrial robot benchmark for nonlinear multi-input/multi-output system identification. A Python implementation of the proposed identification method is available in the package jax-sysid, available at https://github.com/bemporad/jax-sysid.
Authors: Richard Osuala, Daniel M. Lang, Preeti Verma, Smriti Joshi, Apostolia Tsirikoglou, Grzegorz Skorupko, Kaisar Kushibar, Lidia Garrucho, Walter H. L. Pinaya, Oliver Diaz, Julia A. Schnabel, Karim Lekadir
Abstract: Contrast agents in dynamic contrast enhanced magnetic resonance imaging allow to localize tumors and observe their contrast kinetics, which is essential for cancer characterization and respective treatment decision-making. However, contrast agent administration is not only associated with adverse health risks, but also restricted for patients during pregnancy, and for those with kidney malfunction, or other adverse reactions. With contrast uptake as key biomarker for lesion malignancy, cancer recurrence risk, and treatment response, it becomes pivotal to reduce the dependency on intravenous contrast agent administration. To this end, we propose a multi-conditional latent diffusion model capable of acquisition time-conditioned image synthesis of DCE-MRI temporal sequences. To evaluate medical image synthesis, we additionally propose and validate the Fr\'echet radiomics distance as an image quality measure based on biomarker variability between synthetic and real imaging data. Our results demonstrate our method's ability to generate realistic multi-sequence fat-saturated breast DCE-MRI and uncover the emerging potential of deep learning based contrast kinetics simulation. We publicly share our accessible codebase at https://github.com/RichardObi/ccnet and provide a user-friendly library for Fr\'echet radiomics distance calculation at https://pypi.org/project/frd-score.
URLs: https://github.com/RichardObi/ccnet, https://pypi.org/project/frd-score.
Authors: Ari Karchmer
Abstract: Recently, multimodal machine learning has enjoyed huge empirical success (e.g. GPT-4). Motivated to develop theoretical justification for this empirical success, Lu (NeurIPS '23, ALT '24) introduces a theory of multimodal learning, and considers possible \textit{separations} between theoretical models of multimodal and unimodal learning. In particular, Lu (ALT '24) shows a computational separation, which is relevant to \textit{worst-case} instances of the learning task. In this paper, we give a stronger \textit{average-case} computational separation, where for ``typical'' instances of the learning task, unimodal learning is computationally hard, but multimodal learning is easy. We then question how ``natural'' the average-case separation is. Would it be encountered in practice? To this end, we prove that under basic conditions, any given computational separation between average-case unimodal and multimodal learning tasks implies a corresponding cryptographic key agreement protocol. We suggest to interpret this as evidence that very strong \textit{computational} advantages of multimodal learning may arise \textit{infrequently} in practice, since they exist only for the ``pathological'' case of inherently cryptographic distributions. However, this does not apply to possible (super-polynomial) \textit{statistical} advantages.
Authors: Yannick Kirchhoff, Maximilian R. Rokuss, Saikat Roy, Balint Kovacs, Constantin Ulrich, Tassilo Wald, Maximilian Zenk, Philipp Vollmuth, Jens Kleesiek, Fabian Isensee, Klaus Maier-Hein
Abstract: Accurately segmenting thin tubular structures, such as vessels, nerves, roads or concrete cracks, is a crucial task in computer vision. Standard deep learning-based segmentation loss functions, such as Dice or Cross-Entropy, focus on volumetric overlap, often at the expense of preserving structural connectivity or topology. This can lead to segmentation errors that adversely affect downstream tasks, including flow calculation, navigation, and structural inspection. Although current topology-focused losses mark an improvement, they introduce significant computational and memory overheads. This is particularly relevant for 3D data, rendering these losses infeasible for larger volumes as well as increasingly important multi-class segmentation problems. To mitigate this, we propose a novel Skeleton Recall Loss, which effectively addresses these challenges by circumventing intensive GPU-based calculations with inexpensive CPU operations. It demonstrates overall superior performance to current state-of-the-art approaches on five public datasets for topology-preserving segmentation, while substantially reducing computational overheads by more than 90%. In doing so, we introduce the first multi-class capable loss function for thin structure segmentation, excelling in both efficiency and efficacy for topology-preservation.
Authors: Seunghoi Kim, Chen Jin, Tom Diethe, Matteo Figini, Henry F. J. Tregidgo, Asher Mullokandov, Philip Teare, Daniel C. Alexander
Abstract: Recent developments in diffusion models have advanced conditioned image generation, yet they struggle with reconstructing out-of-distribution (OOD) images, such as unseen tumors in medical images, causing "image hallucination" and risking misdiagnosis. We hypothesize such hallucinations result from local OOD regions in the conditional images. We verify that partitioning the OOD region and conducting separate image generations alleviates hallucinations in several applications. From this, we propose a training-free diffusion framework that reduces hallucination with multiple Local Diffusion processes. Our approach involves OOD estimation followed by two modules: a "branching" module generates locally both within and outside OOD regions, and a "fusion" module integrates these predictions into one. Our evaluation shows our method mitigates hallucination over baseline models quantitatively and qualitatively, reducing misdiagnosis by 40% and 25% in the real-world medical and natural image datasets, respectively. It also demonstrates compatibility with various pre-trained diffusion models.
Authors: Nico Meyer, Christian Ufrecht, Maniraman Periyasamy, Axel Plinge, Christopher Mutschler, Daniel D. Scherer, Andreas Maier
Abstract: Quantum computer simulation software is an integral tool for the research efforts in the quantum computing community. An important aspect is the efficiency of respective frameworks, especially for training variational quantum algorithms. Focusing on the widely used Qiskit software environment, we develop the qiskit-torch-module. It improves runtime performance by two orders of magnitude over comparable libraries, while facilitating low-overhead integration with existing codebases. Moreover, the framework provides advanced tools for integrating quantum neural networks with PyTorch. The pipeline is tailored for single-machine compute systems, which constitute a widely employed setup in day-to-day research efforts.
Authors: Anton Sch\"afer, Thomas Hofmann, Imanol Schlag, Tiago Pimentel
Abstract: Tokenisation is a core part of language models (LMs). It involves splitting a character sequence into subwords which are assigned arbitrary indices before being served to the LM. While typically lossless, however, this process may lead to less sample efficient LM training: as it removes character-level information, it could make it harder for LMs to generalise across similar subwords, such as now and Now. We refer to such subwords as near duplicates. In this paper, we study the impact of near duplicate subwords on LM training efficiency. First, we design an experiment that gives us an upper bound to how much we should expect a model to improve if we could perfectly generalise across near duplicates. We do this by duplicating each subword in our LM's vocabulary, creating perfectly equivalent classes of subwords. Experimentally, we find that LMs need roughly 17% more data when trained in a fully duplicated setting. Second, we investigate the impact of naturally occurring near duplicates on LMs. Here, we see that merging them considerably hurts LM performance. Therefore, although subword duplication negatively impacts LM training efficiency, naturally occurring near duplicates may not be as similar as anticipated, limiting the potential for performance improvements.
Authors: Anton Sch\"afer, Shauli Ravfogel, Thomas Hofmann, Tiago Pimentel, Imanol Schlag
Abstract: Multilinguality is crucial for extending recent advancements in language modelling to diverse linguistic communities. To maintain high performance while representing multiple languages, multilingual models ideally align representations, allowing what is learned in one language to generalise to others. Prior research has emphasised the importance of parallel data and shared vocabulary elements as key factors for such alignment. In this study, we investigate an unintuitive novel driver of cross-lingual generalisation: language imbalance. In controlled experiments on perfectly equivalent cloned languages, we observe that the existence of a predominant language during training boosts the performance of less frequent languages and leads to stronger alignment of model representations across languages. Furthermore, we find that this trend is amplified with scale: with large enough models or long enough training, we observe that bilingual training data with a 90/10 language split yields better performance on both languages than a balanced 50/50 split. Building on these insights, we design training schemes that can improve performance in all cloned languages, even without altering the training data. As we extend our analysis to real languages, we find that infrequent languages still benefit from frequent ones, yet whether language imbalance causes cross-lingual generalisation there is not conclusive.
Authors: Nico Meyer, Jakob Murauer, Alexander Popov, Christian Ufrecht, Axel Plinge, Christopher Mutschler, Daniel D. Scherer
Abstract: Reinforcement learning is a powerful framework aiming to determine optimal behavior in highly complex decision-making scenarios. This objective can be achieved using policy iteration, which requires to solve a typically large linear system of equations. We propose the variational quantum policy iteration (VarQPI) algorithm, realizing this step with a NISQ-compatible quantum-enhanced subroutine. Its scalability is supported by an analysis of the structure of generic reinforcement learning environments, laying the foundation for potential quantum advantage with utility-scale quantum computers. Furthermore, we introduce the warm-start initialization variant (WS-VarQPI) that significantly reduces resource overhead. The algorithm solves a large FrozenLake environment with an underlying 256x256-dimensional linear system, indicating its practical robustness.
Authors: Xiang Li, Shunpan Liang, Yu Lei, Chen Li, Yulei Hou, Tengfei Ma
Abstract: Medication recommendation systems are developed to recommend suitable medications tailored to specific patient. Previous researches primarily focus on learning medication representations, which have yielded notable advances. However, these methods are limited to capturing personalized patient representations due to the following primary limitations: (i) unable to capture the differences in the impact of diseases/procedures on patients across various patient health states; (ii) fail to model the direct causal relationships between medications and specific health state of patients, resulting in an inability to determine which specific disease each medication is treating. To address these limitations, we propose CausalMed, a patient health state-centric model capable of enhancing the personalization of patient representations. Specifically, CausalMed first captures the causal relationship between diseases/procedures and medications through causal discovery and evaluates their causal effects. Building upon this, CausalMed focuses on analyzing the health state of patients, capturing the dynamic differences of diseases/procedures in different health states of patients, and transforming diseases/procedures into medications on direct causal relationships. Ultimately, CausalMed integrates information from longitudinal visits to recommend medication combinations. Extensive experiments on real-world datasets show that our method learns more personalized patient representation and outperforms state-of-the-art models in accuracy and safety.
Authors: Guangyu Sun, Matias Mendieta, Aritra Dutta, Xin Li, Chen Chen
Abstract: Multi-modal transformers mark significant progress in different domains, but siloed high-quality data hinders their further improvement. To remedy this, federated learning (FL) has emerged as a promising privacy-preserving paradigm for training models without direct access to the raw data held by different clients. Despite its potential, a considerable research direction regarding the unpaired uni-modal clients and the transformer architecture in FL remains unexplored. To fill this gap, this paper explores a transfer multi-modal federated learning (MFL) scenario within the vision-language domain, where clients possess data of various modalities distributed across different datasets. We systematically evaluate the performance of existing methods when a transformer architecture is utilized and introduce a novel framework called Federated modality complementary and collaboration (FedCola) by addressing the in-modality and cross-modality gaps among clients. Through extensive experiments across various FL settings, FedCola demonstrates superior performance over previous approaches, offering new perspectives on future federated training of multi-modal transformers.
Authors: Konstantinos Vilouras, Pedro Sanchez, Alison Q. O'Neil, Sotirios A. Tsaftaris
Abstract: Localizing the exact pathological regions in a given medical scan is an important imaging problem that requires a large amount of bounding box ground truth annotations to be accurately solved. However, there exist alternative, potentially weaker, forms of supervision, such as accompanying free-text reports, which are readily available. The task of performing localization with textual guidance is commonly referred to as phrase grounding. In this work, we use a publicly available Foundation Model, namely the Latent Diffusion Model, to solve this challenging task. This choice is supported by the fact that the Latent Diffusion Model, despite being generative in nature, contains mechanisms (cross-attention) that implicitly align visual and textual features, thus leading to intermediate representations that are suitable for the task at hand. In addition, we aim to perform this task in a zero-shot manner, i.e., without any further training on target data, meaning that the model's weights remain frozen. To this end, we devise strategies to select features and also refine them via post-processing without extra learnable parameters. We compare our proposed method with state-of-the-art approaches which explicitly enforce image-text alignment in a joint embedding space via contrastive learning. Results on a popular chest X-ray benchmark indicate that our method is competitive wih SOTA on different types of pathology, and even outperforms them on average in terms of two metrics (mean IoU and AUC-ROC). Source code will be released upon acceptance.
Authors: Jinbo Wen, Ruichen Zhang, Dusit Niyato, Jiawen Kang, Hongyang Du, Yang Zhang, Zhu Han
Abstract: By integrating Artificial Intelligence (AI) with the Internet of Things (IoT), Artificial Intelligence of Things (AIoT) has revolutionized many fields. However, AIoT is facing the challenges of energy consumption and carbon emissions due to the continuous advancement of mobile technology. Fortunately, Generative AI (GAI) holds immense potential to reduce carbon emissions of AIoT due to its excellent reasoning and generation capabilities. In this article, we explore the potential of GAI for carbon emissions reduction and propose a novel GAI-enabled solution for low-carbon AIoT. Specifically, we first study the main impacts that cause carbon emissions in AIoT, and then introduce GAI techniques and their relations to carbon emissions. We then explore the application prospects of GAI in low-carbon AIoT, focusing on how GAI can reduce carbon emissions of network components. Subsequently, we propose a Large Language Model (LLM)-enabled carbon emission optimization framework, in which we design pluggable LLM and Retrieval Augmented Generation (RAG) modules to generate more accurate and reliable optimization problems. Furthermore, we utilize Generative Diffusion Models (GDMs) to identify optimal strategies for carbon emission reduction. Numerical results demonstrate the effectiveness of the proposed framework. Finally, we insightfully provide open research directions for low-carbon AIoT.
Authors: Matteo Merler, Katsiaryna Haitsiukevich, Nicola Dainese, Pekka Marttinen
Abstract: State of the art Symbolic Regression (SR) methods currently build specialized models, while the application of Large Language Models (LLMs) remains largely unexplored. In this work, we introduce the first comprehensive framework that utilizes LLMs for the task of SR. We propose In-Context Symbolic Regression (ICSR), an SR method which iteratively refines a functional form with an LLM and determines its coefficients with an external optimizer. ICSR leverages LLMs' strong mathematical prior both to propose an initial set of possible functions given the observations and to refine them based on their errors. Our findings reveal that LLMs are able to successfully find symbolic equations that fit the given data, matching or outperforming the overall performance of the best SR baselines on four popular benchmarks, while yielding simpler equations with better out of distribution generalization.
Authors: Jian Hu, Xibin Wu, Weixun Wang, Xianyu, Dehao Zhang, Yu Cao
Abstract: As large language models (LLMs) continue to grow by scaling laws, reinforcement learning from human feedback (RLHF) has gained significant attention due to its outstanding performance. However, unlike pretraining or fine-tuning a single model, scaling reinforcement learning from human feedback (RLHF) for training large language models poses coordination challenges across four models. We present OpenRLHF, an open-source framework enabling efficient RLHF scaling. Unlike existing RLHF frameworks that co-locate four models on the same GPUs, OpenRLHF re-designs scheduling for the models beyond 70B parameters using Ray, vLLM, and DeepSpeed, leveraging improved resource utilization and diverse training approaches. Integrating seamlessly with Hugging Face, OpenRLHF provides an out-of-the-box solution with optimized algorithms and launch scripts, which ensures user-friendliness. OpenRLHF implements RLHF, DPO, rejection sampling, and other alignment techniques. Empowering state-of-the-art LLM development, OpenRLHF's code is available at \url{https://github.com/OpenRLHF/OpenRLHF}.
Authors: Christoph Dann, Yishay Mansour, Mehryar Mohri, Jon Schneider, Balasubramanian Sivan
Abstract: Abernethy et al. (2011) showed that Blackwell approachability and no-regret learning are equivalent, in the sense that any algorithm that solves a specific Blackwell approachability instance can be converted to a sublinear regret algorithm for a specific no-regret learning instance, and vice versa. In this paper, we study a more fine-grained form of such reductions, and ask when this translation between problems preserves not only a sublinear rate of convergence, but also preserves the optimal rate of convergence. That is, in which cases does it suffice to find the optimal regret bound for a no-regret learning instance in order to find the optimal rate of convergence for a corresponding approachability instance? We show that the reduction of Abernethy et al. (2011) does not preserve rates: their reduction may reduce a $d$-dimensional approachability instance $I_1$ with optimal convergence rate $R_1$ to a no-regret learning instance $I_2$ with optimal regret-per-round of $R_2$, with $R_{2}/R_{1}$ arbitrarily large (in particular, it is possible that $R_1 = 0$ and $R_{2} > 0$). On the other hand, we show that it is possible to tightly reduce any approachability instance to an instance of a generalized form of regret minimization we call improper $\phi$-regret minimization (a variant of the $\phi$-regret minimization of Gordon et al. (2008) where the transformation functions may map actions outside of the action set). Finally, we characterize when linear transformations suffice to reduce improper $\phi$-regret minimization problems to standard classes of regret minimization problems in a rate preserving manner. We prove that some improper $\phi$-regret minimization instances cannot be reduced to either subclass of instance in this way, suggesting that approachability can capture some problems that cannot be phrased in the language of online learning.
Authors: Guanting Dong, Keming Lu, Chengpeng Li, Tingyu Xia, Bowen Yu, Chang Zhou, Jingren Zhou
Abstract: One core capability of large language models (LLMs) is to follow natural language instructions. However, the issue of automatically constructing high-quality training data to enhance the complex instruction-following abilities of LLMs without manual annotation remains unresolved. In this paper, we introduce AutoIF, the first scalable and reliable method for automatically generating instruction-following training data. AutoIF transforms the validation of instruction-following data quality into code verification, requiring LLMs to generate instructions, the corresponding code to check the correctness of the instruction responses, and unit test samples to verify the code's correctness. Then, execution feedback-based rejection sampling can generate data for Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) training. AutoIF achieves significant improvements across three training algorithms, SFT, Offline DPO, and Online DPO, when applied to the top open-source LLMs, Qwen2 and LLaMA3, in self-alignment and strong-to-weak distillation settings. Our code is publicly available at https://github.com/QwenLM/AutoIF.
Authors: Yuhui Jin
Abstract: The application of deep learning techniques for predicting stock market prices is a prominent and widely researched topic in the field of data science. To effectively predict market trends, it is essential to utilize a diversified dataset. In this paper, we give a graph neural network based convolutional neural network (CNN) model, that can be applied on diverse source of data, in the attempt to extract features to predict the trends of indices of \text{S}\&\text{P} 500, NASDAQ, DJI, NYSE, and RUSSEL. The experiments show that the associated models improve the performance of prediction in all indices over the baseline algorithms by about $4\% \text{ to } 15\%$, in terms of F-measure. A trading simulation is generated from predictions and gained a Sharpe ratio of over 3.
Authors: Chengpeng Li, Guanting Dong, Mingfeng Xue, Ru Peng, Xiang Wang, Dayiheng Liu
Abstract: Large language models (LLMs) have made impressive progress in handling simple math problems, yet they still struggle with more challenging and complex mathematical tasks. In this paper, we introduce a series of LLMs that employs the Decomposition of thought with code assistance and self-correction for mathematical reasoning, dubbed as DotaMath. DotaMath models tackle complex mathematical tasks by decomposing them into simpler logical subtasks, leveraging code to solve these subtasks, obtaining fine-grained feedback from the code interpreter, and engaging in self-reflection and correction. By annotating diverse interactive tool-use trajectories and employing query evolution on GSM8K and MATH datasets, we generate an instruction fine-tuning dataset called DotaMathQA with 574K query-response pairs. We train a series of base LLMs using imitation learning on DotaMathQA, resulting in DotaMath models that achieve remarkable performance compared to open-source LLMs across various in-domain and out-of-domain benchmarks. Notably, DotaMath-deepseek-7B showcases an outstanding performance of 64.8% on the competitive MATH dataset and 86.7% on GSM8K. Besides, DotaMath-deepseek-7B maintains strong competitiveness on a series of in-domain and out-of-domain benchmarks (Avg. 80.1%). Looking forward, we anticipate that the DotaMath paradigm will open new pathways for addressing intricate mathematical problems. Our code is publicly available at https://github.com/ChengpengLi1003/DotaMath.
Authors: Yang Liu, Weixing Chen, Yongjie Bai, Jingzhou Luo, Xinshuai Song, Kaixuan Jiang, Zhida Li, Ganlong Zhao, Junyi Lin, Guanbin Li, Wen Gao, Liang Lin
Abstract: Embodied Artificial Intelligence (Embodied AI) is crucial for achieving Artificial General Intelligence (AGI) and serves as a foundation for various applications that bridge cyberspace and the physical world. Recently, the emergence of Multi-modal Large Models (MLMs) and World Models (WMs) have attracted significant attention due to their remarkable perception, interaction, and reasoning capabilities, making them a promising architecture for the brain of embodied agents. However, there is no comprehensive survey for Embodied AI in the era of MLMs. In this survey, we give a comprehensive exploration of the latest advancements in Embodied AI. Our analysis firstly navigates through the forefront of representative works of embodied robots and simulators, to fully understand the research focuses and their limitations. Then, we analyze four main research targets: 1) embodied perception, 2) embodied interaction, 3) embodied agent, and 4) sim-to-real adaptation, covering the state-of-the-art methods, essential paradigms, and comprehensive datasets. Additionally, we explore the complexities of MLMs in virtual and real embodied agents, highlighting their significance in facilitating interactions in dynamic digital and physical environments. Finally, we summarize the challenges and limitations of embodied AI and discuss their potential future directions. We hope this survey will serve as a foundational reference for the research community and inspire continued innovation. The associated project can be found at https://github.com/HCPLab-SYSU/Embodied_AI_Paper_List.
URLs: https://github.com/HCPLab-SYSU/Embodied_AI_Paper_List.
Authors: Jase Clarkson, Wenkai Xu, Mihai Cucuringu, Gesine Reinert
Abstract: Conformal prediction is a non-parametric technique for constructing prediction intervals or sets from arbitrary predictive models under the assumption that the data is exchangeable. It is popular as it comes with theoretical guarantees on the marginal coverage of the prediction sets and the split conformal prediction variant has a very low computational cost compared to model training. We study the robustness of split conformal prediction in a data contamination setting, where we assume a small fraction of the calibration scores are drawn from a different distribution than the bulk. We quantify the impact of the corrupted data on the coverage and efficiency of the constructed sets when evaluated on "clean" test points, and verify our results with numerical experiments. Moreover, we propose an adjustment in the classification setting which we call Contamination Robust Conformal Prediction, and verify the efficacy of our approach using both synthetic and real datasets.
Authors: Liang Zeng, Liangjun Zhong, Liang Zhao, Tianwen Wei, Liu Yang, Jujie He, Cheng Cheng, Rui Hu, Yang Liu, Shuicheng Yan, Han Fang, Yahui Zhou
Abstract: In this paper, we investigate the underlying factors that potentially enhance the mathematical reasoning capabilities of large language models (LLMs). We argue that the data scaling law for math reasoning capabilities in modern LLMs is far from being saturated, highlighting how the model's quality improves with increases in data quantity. To support this claim, we introduce the Skywork-Math model series, supervised fine-tuned (SFT) on common 7B LLMs using our proposed 2.5M-instance Skywork-MathQA dataset. Skywork-Math 7B has achieved impressive accuracies of 51.2% on the competition-level MATH benchmark and 83.9% on the GSM8K benchmark using only SFT data, outperforming an early version of GPT-4 on MATH. The superior performance of Skywork-Math models contributes to our novel two-stage data synthesis and model SFT pipelines, which include three different augmentation methods and a diverse seed problem set, ensuring both the quantity and quality of Skywork-MathQA dataset across varying difficulty levels. Most importantly, we provide several practical takeaways to enhance math reasoning abilities in LLMs for both research and industry applications.
Authors: Yunjie He, Daniel Hernandez, Mojtaba Nayyeri, Bo Xiong, Yuqicheng Zhu, Evgeny Kharlamov, Steffen Staab
Abstract: Query embedding approaches answer complex logical queries over incomplete knowledge graphs (KGs) by computing and operating on low-dimensional vector representations of entities, relations, and queries. However, current query embedding models heavily rely on excessively parameterized neural networks and cannot explain the knowledge learned from the graph. We propose a novel query embedding method, AConE, which explains the knowledge learned from the graph in the form of SROI^{-} description logic axioms while being more parameter-efficient than most existing approaches. AConE associates queries to a SROI^{-} description logic concept. Every SROI^{-} concept is embedded as a cone in complex vector space, and each SROI^{-} relation is embedded as a transformation that rotates and scales cones. We show theoretically that AConE can learn SROI^{-} axioms, and defines an algebra whose operations correspond one to one to SROI^{-} description logic concept constructs. Our empirical study on multiple query datasets shows that AConE achieves superior results over previous baselines with fewer parameters. Notably on the WN18RR dataset, AConE achieves significant improvement over baseline models. We provide comprehensive analyses showing that the capability to represent axioms positively impacts the results of query answering.
Authors: Seunghee Han, Byeong Gwan Lee, Dae Woon Lim, Jihan Kim
Abstract: Recently, metal-organic frameworks (MOFs) have demonstrated their potential as solid-state electrolytes in proton exchange membrane fuel cells. However, the number of MOFs reported to exhibit proton conductivity remains limited, and the mechanisms underlying this phenomenon are not fully elucidated, complicating the design of proton-conductive MOFs. In response, we developed a comprehensive database of proton-conductive MOFs and applied machine learning techniques to predict their proton conductivity. Our approach included the construction of both descriptor-based and transformer-based models. Notably, the transformer-based transfer learning (Freeze) model performed the best with a mean absolute error (MAE) of 0.91, suggesting that the proton conductivity of MOFs can be estimated within one order of magnitude using this model. Additionally, we employed feature importance and principal component analysis to explore the factors influencing proton conductivity. The insights gained from our database and machine learning model are expected to facilitate the targeted design of proton-conductive MOFs.
Authors: Kalliopi Basioti, Mohamed A. Abdelsalam, Federico Fancellu, Vladimir Pavlovic, Afsaneh Fazly
Abstract: Controllable Image Captioning (CIC) aims at generating natural language descriptions for an image, conditioned on information provided by end users, e.g., regions, entities or events of interest. However, available image-language datasets mainly contain captions that describe the entirety of an image, making them ineffective for training CIC models that can potentially attend to any subset of regions or relationships. To tackle this challenge, we propose a novel, fully automatic method to sample additional focused and visually grounded captions using a unified structured semantic representation built on top of the existing set of captions associated with an image. We leverage Abstract Meaning Representation (AMR), a cross-lingual graph-based semantic formalism, to encode all possible spatio-semantic relations between entities, beyond the typical spatial-relations-only focus of current methods. We use this Structured Semantic Augmentation (SSA) framework to augment existing image-caption datasets with the grounded controlled captions, increasing their spatial and semantic diversity and focal coverage. We then develop a new model, CIC-BART-SSA, specifically tailored for the CIC task, that sources its control signals from SSA-diversified datasets. We empirically show that, compared to SOTA CIC models, CIC-BART-SSA generates captions that are superior in diversity and text quality, are competitive in controllability, and, importantly, minimize the gap between broad and highly focused controlled captioning performance by efficiently generalizing to the challenging highly focused scenarios. Code is available at https://github.com/SamsungLabs/CIC-BART-SSA.
Authors: Ziang Zhang, Guangzhi Chen, Youlong Weng, Shunchuan Yang, Zhiyu Jia, Jingxuan Chen
Abstract: Frequency-modulated continuous-wave (FMCW) radar plays a pivotal role in the field of remote sensing. The increasing degree of FMCW radar deployment has increased the mutual interference, which weakens the detection capabilities of radars and threatens reliability and safety of systems. In this paper, a novel FMCW radar interference mitigation (RIM) method, termed as RIMformer, is proposed by using an end-to-end Transformer-based structure. In the RIMformer, a dual multi-head self-attention mechanism is proposed to capture the correlations among the distinct distance elements of intermediate frequency (IF) signals. Additionally, an improved convolutional block is integrated to harness the power of convolution for extracting local features. The architecture is designed to process time-domain IF signals in an end-to-end manner, thereby avoiding the need for additional manual data processing steps. The improved decoder structure ensures the parallelization of the network to increase its computational efficiency. Simulation and measurement experiments are carried out to validate the accuracy and effectiveness of the proposed method. The results show that the proposed RIMformer can effectively mitigate interference and restore the target signals.
Authors: Julien Hauret, Malo Olivier, Thomas Joubaud, Christophe Langrenne, Sarah Poir\'ee, V\'eronique Zimpfer, \'Eric Bavu
Abstract: Vibravox is a dataset compliant with the General Data Protection Regulation (GDPR) containing audio recordings using five different body-conduction audio sensors : two in-ear microphones, two bone conduction vibration pickups and a laryngophone. The data set also includes audio data from an airborne microphone used as a reference. The Vibravox corpus contains 38 hours of speech samples and physiological sounds recorded by 188 participants under different acoustic conditions imposed by an high order ambisonics 3D spatializer. Annotations about the recording conditions and linguistic transcriptions are also included in the corpus. We conducted a series of experiments on various speech-related tasks, including speech recognition, speech enhancement and speaker verification. These experiments were carried out using state-of-the-art models to evaluate and compare their performances on signals captured by the different audio sensors offered by the Vibravox dataset, with the aim of gaining a better grasp of their individual characteristics.