Authors: Shuyue Wang, Wenjun Zhou, Han drk-m-s Jiang, Shuo Wang, Ren Zheng
Abstract: TREB, a novel tabular imputation framework utilizing BERT, introduces a groundbreaking approach for handling missing values in tabular data. Unlike traditional methods that often overlook the specific demands of imputation, TREB leverages the robust capabilities of BERT to address this critical task. While many BERT-based approaches for tabular data have emerged, they frequently under-utilize the language model's full potential. To rectify this, TREB employs a BERT-based model fine-tuned specifically for the task of imputing real-valued continuous numbers in tabular datasets. The paper comprehensively addresses the unique challenges posed by tabular data imputation, emphasizing the importance of context-based interconnections. The effectiveness of TREB is validated through rigorous evaluation using the California Housing dataset. The results demonstrate its ability to preserve feature interrelationships and accurately impute missing values. Moreover, the authors shed light on the computational efficiency and environmental impact of TREB, quantifying the floating-point operations (FLOPs) and carbon footprint associated with its training and deployment.
Authors: Akeem Temitope Otapo, Alice Othmani, Ghazaleh Khodabandelou, Zuheng Ming
Abstract: The integration of Artificial Intelligence (AI) and the Internet of Medical Things (IoMT) in healthcare, through Machine Learning (ML) and Deep Learning (DL) techniques, has advanced the prediction and diagnosis of chronic diseases. AI-driven models such as XGBoost, Random Forest, CNNs, and LSTM RNNs have achieved over 98\% accuracy in predicting heart disease, chronic kidney disease (CKD), Alzheimer's disease, and lung cancer, using datasets from platforms like Kaggle, UCI, private institutions, and real-time IoMT sources. However, challenges persist due to variations in data quality, patient demographics, and formats from different hospitals and research sources. The incorporation of IoMT data, which is vast and heterogeneous, adds complexities in ensuring interoperability and security to protect patient privacy. AI models often struggle with overfitting, performing well in controlled environments but less effectively in real-world clinical settings. Moreover, multi-morbidity scenarios especially for rare diseases like dementia, stroke, and cancers remain insufficiently addressed. Future research should focus on data standardization and advanced preprocessing techniques to improve data quality and interoperability. Transfer learning and ensemble methods are crucial for improving model generalizability across clinical settings. Additionally, the exploration of disease interactions and the development of predictive models for chronic illness intersections is needed. Creating standardized frameworks and open-source tools for integrating federated learning, blockchain, and differential privacy into IoMT systems will also ensure robust data privacy and security.
Authors: Rick White
Abstract: This paper proposes a novel approach to word embeddings in Transformer models by utilizing spinors from geometric algebra. Spinors offer a rich mathematical framework capable of capturing complex relationships and transformations in high-dimensional spaces. By encoding words as spinors, we aim to enhance the expressiveness and robustness of language representations. We present the theoretical foundations of spinors, detail their integration into Transformer architectures, and discuss potential advantages and challenges.
Authors: Guancheng Wan, Zewen Liu, Max S. Y. Lau, B. Aditya Prakash, Wei Jin
Abstract: Effective epidemic forecasting is critical for public health strategies and efficient medical resource allocation, especially in the face of rapidly spreading infectious diseases. However, existing deep-learning methods often overlook the dynamic nature of epidemics and fail to account for the specific mechanisms of disease transmission. In response to these challenges, we introduce an innovative end-to-end framework called Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graph (EARTH) in this paper. To learn continuous and regional disease transmission patterns, we first propose EANO, which seamlessly integrates the neural ODE approach with the epidemic mechanism, considering the complex spatial spread process during epidemic evolution. Additionally, we introduce GLTG to model global infection trends and leverage these signals to guide local transmission dynamically. To accommodate both the global coherence of epidemic trends and the local nuances of epidemic transmission patterns, we build a cross-attention approach to fuse the most meaningful information for forecasting. Through the smooth synergy of both components, EARTH offers a more robust and flexible approach to understanding and predicting the spread of infectious diseases. Extensive experiments show EARTH superior performance in forecasting real-world epidemics compared to state-of-the-art methods. The code will be available at https://github.com/Emory-Melody/EpiLearn.
Authors: Federico Fontana, Romeo Lanzino, Anxhelo Diko, Gian Luca Foresti, Luigi Cinque
Abstract: This paper works on Binary Neural Networks (BNNs), a promising avenue for efficient deep learning, offering significant reductions in computational overhead and memory footprint to full precision networks. However, the challenge of energy-intensive training and the drop in performance have been persistent issues. Tackling the challenge, prior works focus primarily on task-related inference optimization. Unlike prior works, this study offers an innovative methodology integrating BNNs with cyclic precision training, introducing the CycleBNN. This approach is designed to enhance training efficiency while minimizing the loss in performance. By dynamically adjusting precision in cycles, we achieve a convenient trade-off between training efficiency and model performance. This emphasizes the potential of our method in energy-constrained training scenarios, where data is collected onboard and paves the way for sustainable and efficient deep learning architectures. To gather insights on CycleBNN's efficiency, we conduct experiments on ImageNet, CIFAR-10, and PASCAL-VOC, obtaining competitive performances while using 96.09\% less operations during training on ImageNet, 88.88\% on CIFAR-10 and 96.09\% on PASCAL-VOC. Finally, CycleBNN offers a path towards faster, more accessible training of efficient networks, accelerating the development of practical applications. The PyTorch code is available at \url{https://github.com/fedeloper/CycleBNN/}
Authors: Haoran Li, Zhennan Jiang, Yuhui Chen, Dongbin Zhao
Abstract: With high-dimensional state spaces, visual reinforcement learning (RL) faces significant challenges in exploitation and exploration, resulting in low sample efficiency and training stability. As a time-efficient diffusion model, although consistency models have been validated in online state-based RL, it is still an open question whether it can be extended to visual RL. In this paper, we investigate the impact of non-stationary distribution and the actor-critic framework on consistency policy in online RL, and find that consistency policy was unstable during the training, especially in visual RL with the high-dimensional state space. To this end, we suggest sample-based entropy regularization to stabilize the policy training, and propose a consistency policy with prioritized proximal experience regularization (CP3ER) to improve sample efficiency. CP3ER achieves new state-of-the-art (SOTA) performance in 21 tasks across DeepMind control suite and Meta-world. To our knowledge, CP3ER is the first method to apply diffusion/consistency models to visual RL and demonstrates the potential of consistency models in visual RL. More visualization results are available at https://jzndd.github.io/CP3ER-Page/.
Authors: Chen Chen, Yuxin He, Hao Wang, Jingjing Chen, Qin Luo
Abstract: Train delays can propagate rapidly throughout the Urban Rail Transit (URT) network under networked operation conditions, posing significant challenges to operational departments. Accurately predicting passenger travel choices under train delays can provide interpretable insights into the redistribution of passenger flow, offering crucial decision support for emergency response and service recovery. However, the diversity of travel choices due to passenger heterogeneity and the sparsity of delay events leads to issues of data sparsity and sample imbalance in the travel choices dataset under metro delays. It is challenging to model this problem using traditional machine learning approaches, which typically rely on large, balanced datasets. Given the strengths of large language models (LLMs) in text processing, understanding, and their capabilities in small-sample and even zero-shot learning, this paper proposes a novel Passenger Travel Choice prediction framework under metro delays with the Large Language Model (DelayPTC-LLM). The well-designed prompting engineering is developed to guide the LLM in making and rationalizing predictions about travel choices, taking into account passenger heterogeneity and features of the delay events. Utilizing real-world data from Shenzhen Metro, including Automated Fare Collection (AFC) data and detailed delay logs, a comparative analysis of DelayPTC-LLM with traditional prediction models demonstrates the superior capability of LLMs in handling complex, sparse datasets commonly encountered under disruption of transportation systems. The results validate the advantages of DelayPTC-LLM in terms of predictive accuracy and its potential to provide actionable insights for big traffic data.
Authors: Jizu Huang, Rukang You, Tao Zhou
Abstract: Multi-scale deep neural networks (MscaleDNNs) with downing-scaling mapping have demonstrated superiority over traditional DNNs in approximating target functions characterized by high frequency features. However, the performance of MscaleDNNs heavily depends on the parameters in the downing-scaling mapping, which limits their broader application. In this work, we establish a fitting error bound to explain why MscaleDNNs are advantageous for approximating high frequency functions. Building on this insight, we construct a hybrid feature embedding to enhance the accuracy and robustness of the downing-scaling mapping. To reduce the dependency of MscaleDNNs on parameters in the downing-scaling mapping, we propose frequency-adaptive MscaleDNNs, which adaptively adjust these parameters based on a posterior error estimate that captures the frequency information of the fitted functions. Numerical examples, including wave propagation and the propagation of a localized solution of the schr$\ddot{\text{o}}$dinger equation with a smooth potential near the semi-classical limit, are presented. These examples demonstrate that the frequency-adaptive MscaleDNNs improve accuracy by two to three orders of magnitude compared to standard MscaleDNNs.
Authors: Zheng Zhang, Hossein Amiri, Dazhou Yu, Yuntong Hu, Liang Zhao, Andreas Zufle
Abstract: Semantic trajectories, which enrich spatial-temporal data with textual information such as trip purposes or location activities, are key for identifying outlier behaviors critical to healthcare, social security, and urban planning. Traditional outlier detection relies on heuristic rules, which requires domain knowledge and limits its ability to identify unseen outliers. Besides, there lacks a comprehensive approach that can jointly consider multi-modal data across spatial, temporal, and textual dimensions. Addressing the need for a domain-agnostic model, we propose the Transferable Outlier Detection for Human Semantic Trajectories (TOD4Traj) framework.TOD4Traj first introduces a modality feature unification module to align diverse data feature representations, enabling the integration of multi-modal information and enhancing transferability across different datasets. A contrastive learning module is further pro-posed for identifying regular mobility patterns both temporally and across populations, allowing for a joint detection of outliers based on individual consistency and group majority patterns. Our experimental results have shown TOD4Traj's superior performance over existing models, demonstrating its effectiveness and adaptability in detecting human trajectory outliers across various datasets.
Authors: Jiang Wang, Haibin Wei, Xiaowei Xu, Jiacheng Shi, Jian Nie, Longzhi Du, Taixu Jiang
Abstract: On-demand Food Delivery (OFD) services have become very common around the world. For example, on the Ele.me platform, users place more than 15 million food orders every day. Predicting the Real-time Pressure Signal (RPS) is crucial for OFD services, as it is primarily used to measure the current status of pressure on the logistics system. When RPS rises, the pressure increases, and the platform needs to quickly take measures to prevent the logistics system from being overloaded. Usually, the average delivery time for all orders within a business district is used to represent RPS. Existing research on OFD services primarily focuses on predicting the delivery time of orders, while relatively less attention has been given to the study of the RPS. Previous research directly applies general models such as DeepFM, RNN, and GNN for prediction, but fails to adequately utilize the unique temporal and spatial characteristics of OFD services, and faces issues with insufficient sensitivity during sudden severe weather conditions or peak periods. To address these problems, this paper proposes a new method based on Spatio-Temporal Transformer and Memory Network (STTM). Specifically, we use a novel Spatio-Temporal Transformer structure to learn logistics features across temporal and spatial dimensions and encode the historical information of a business district and its neighbors, thereby learning both temporal and spatial information. Additionally, a Memory Network is employed to increase sensitivity to abnormal events. Experimental results on the real-world dataset show that STTM significantly outperforms previous methods in both offline experiments and the online A/B test, demonstrating the effectiveness of this method.
Authors: Hannes Thurnherr, Kaspar Riesen
Abstract: Recently, the transformer architecture has enabled substantial progress in many areas of pattern recognition and machine learning. However, as with other neural network models, there is currently no general method available to explain their inner workings. The present paper represents a first step towards this direction. We utilize \textit{Transformer Compiler for RASP} (Tracr) to generate a large dataset of pairs of transformer weights and corresponding RASP programs. Based on this dataset, we then build and train a model, with the aim of recovering the RASP code from the compiled model. We demonstrate that the simple form of Tracr compiled transformer weights is interpretable for such a decompiler model. In an empirical evaluation, our model achieves exact reproductions on more than 30\% of the test objects, while the remaining 70\% can generally be reproduced with only few errors. Additionally, more than 70\% of the programs, produced by our model, are functionally equivalent to the ground truth, and therefore a valid decompilation of the Tracr compiled transformer weights.
Authors: Kaushik Roy, Akila Dissanayake, Brendan Tidd, Peyman Moghadam
Abstract: Lifelong imitation learning for manipulation tasks poses significant challenges due to distribution shifts that occur in incremental learning steps. Existing methods often focus on unsupervised skill discovery to construct an ever-growing skill library or distillation from multiple policies, which can lead to scalability issues as diverse manipulation tasks are continually introduced and may fail to ensure a consistent latent space throughout the learning process, leading to catastrophic forgetting of previously learned skills. In this paper, we introduce M2Distill, a multi-modal distillation-based method for lifelong imitation learning focusing on preserving consistent latent space across vision, language, and action distributions throughout the learning process. By regulating the shifts in latent representations across different modalities from previous to current steps, and reducing discrepancies in Gaussian Mixture Model (GMM) policies between consecutive learning steps, we ensure that the learned policy retains its ability to perform previously learned tasks while seamlessly integrating new skills. Extensive evaluations on the LIBERO lifelong imitation learning benchmark suites, including LIBERO-OBJECT, LIBERO-GOAL, and LIBERO-SPATIAL, demonstrate that our method consistently outperforms prior state-of-the-art methods across all evaluated metrics.
Authors: Anestis Kaimakamidis, Ioannis Mademlis, Ioannis Pitas
Abstract: A novel Learning-by-Education Node Community framework (LENC) for Collaborative Knowledge Distillation (CKD) is presented, which facilitates continual collective learning through effective knowledge exchanges among diverse deployed Deep Neural Network (DNN) peer nodes. These DNNs dynamically and autonomously adopt either the role of a student, seeking knowledge, or that of a teacher, imparting knowledge, fostering a collaborative learning environment. The proposed framework enables efficient knowledge transfer among participating DNN nodes as needed, while enhancing their learning capabilities and promoting their collaboration. LENC addresses the challenges of handling diverse training data distributions and the limitations of individual DNN node learning abilities. It ensures the exploitation of the best available teacher knowledge upon learning a new task and protects the DNN nodes from catastrophic forgetting. Additionally, it innovates by enabling collaborative multitask knowledge distillation, while addressing the problem of task-agnostic continual learning, as DNN nodes have no information on task boundaries. Experimental evaluation on a proof-of-concept implementation demonstrates the LENC framework's functionalities and benefits across multiple DNN learning and inference scenarios. The conducted experiments showcase its ability to gradually maximize the average test accuracy of the community of interacting DNN nodes in image classification problems, by appropriately leveraging the collective knowledge of all node peers. The LENC framework achieves state-of-the-art performance in on-line unlabelled CKD.
Authors: Giannis Daras, Hyungjin Chung, Chieh-Hsin Lai, Yuki Mitsufuji, Jong Chul Ye, Peyman Milanfar, Alexandros G. Dimakis, Mauricio Delbracio
Abstract: Diffusion models have become increasingly popular for generative modeling due to their ability to generate high-quality samples. This has unlocked exciting new possibilities for solving inverse problems, especially in image restoration and reconstruction, by treating diffusion models as unsupervised priors. This survey provides a comprehensive overview of methods that utilize pre-trained diffusion models to solve inverse problems without requiring further training. We introduce taxonomies to categorize these methods based on both the problems they address and the techniques they employ. We analyze the connections between different approaches, offering insights into their practical implementation and highlighting important considerations. We further discuss specific challenges and potential solutions associated with using latent diffusion models for inverse problems. This work aims to be a valuable resource for those interested in learning about the intersection of diffusion models and inverse problems.
Authors: Sunil Kumar, Ted Sandler, Paulina Varshavskaya
Abstract: Fine-tuning modern computer vision models requires accurately labeled data for which the ground truth may not exist, but a set of multiple labels can be obtained from labelers of variable accuracy. We tie the notion of label quality to confidence in labeler accuracy and show that, when prior estimates of labeler accuracy are available, using a simple naive-Bayes model to estimate the true labels allows us to label more data on a fixed budget without compromising label or fine-tuning quality. We present experiments on a dataset of industrial images that demonstrates that our method, called Ground Truth Extension (GTX), enables fine-tuning ML models using fewer human labels.
Authors: Pradyumna Elavarthi, Anca Ralescu, Mark D. Johnson, Charles J. Prestigiacomo
Abstract: Intracranial aneurysms (IAs) that rupture result in significant morbidity and mortality. While traditional risk models such as the PHASES score are useful in clinical decision making, machine learning (ML) models offer the potential to provide more accuracy. In this study, we compared the performance of four different machine learning algorithms Random Forest (RF), XGBoost (XGB), Support Vector Machine (SVM), and Multi Layer Perceptron (MLP) on clinical and radiographic features to predict rupture status of intracranial aneurysms. Among the models, RF achieved the highest accuracy (85%) with balanced precision and recall, while MLP had the lowest overall performance (accuracy of 63%). Fractal dimension ranked as the most important feature for model performance across all models.
Authors: Ji Liu, Jiaxiang Ren, Ruoming Jin, Zijie Zhang, Yang Zhou, Patrick Valduriez, Dejing Dou
Abstract: As a promising paradigm to collaboratively train models with decentralized data, Federated Learning (FL) can be exploited to fine-tune Large Language Models (LLMs). While LLMs correspond to huge size, the scale of the training data significantly increases, which leads to tremendous amounts of computation and communication costs. The training data is generally non-Independent and Identically Distributed (non-IID), which requires adaptive data processing within each device. Although Low Rank Adaptation (LoRA) can significantly reduce the scale of parameters to update in the fine-tuning process, it still takes unaffordable time to transfer the low-rank parameters of all the layers in LLMs. In this paper, we propose a Fisher Information-based Efficient Curriculum Federated Learning framework (FibecFed) with two novel methods, i.e., adaptive federated curriculum learning and efficient sparse parameter update. First, we propose a fisher information-based method to adaptively sample data within each device to improve the effectiveness of the FL fine-tuning process. Second, we dynamically select the proper layers for global aggregation and sparse parameters for local update with LoRA so as to improve the efficiency of the FL fine-tuning process. Extensive experimental results based on 10 datasets demonstrate that FibecFed yields excellent performance (up to 45.35% in terms of accuracy) and superb fine-tuning speed (up to 98.61% faster) compared with 17 baseline approaches).
Authors: Rossen Nenov, Daniel Haider, Peter Balazs
Abstract: Maintaining numerical stability in machine learning models is crucial for their reliability and performance. One approach to maintain stability of a network layer is to integrate the condition number of the weight matrix as a regularizing term into the optimization algorithm. However, due to its discontinuous nature and lack of differentiability the condition number is not suitable for a gradient descent approach. This paper introduces a novel regularizer that is provably differentiable almost everywhere and promotes matrices with low condition numbers. In particular, we derive a formula for the gradient of this regularizer which can be easily implemented and integrated into existing optimization algorithms. We show the advantages of this approach for noisy classification and denoising of MNIST images.
Authors: Tyler Ingebrand, Adam J. Thorpe, Somdatta Goswami, Krishna Kumar, Ufuk Topcu
Abstract: We present Basis-to-Basis (B2B) operator learning, a novel approach for learning operators on Hilbert spaces of functions based on the foundational ideas of function encoders. We decompose the task of learning operators into two parts: learning sets of basis functions for both the input and output spaces, and learning a potentially nonlinear mapping between the coefficients of the basis functions. B2B operator learning circumvents many challenges of prior works, such as requiring data to be at fixed locations, by leveraging classic techniques such as least-squares to compute the coefficients. It is especially potent for linear operators, where we compute a mapping between bases as a single matrix transformation with a closed form solution. Furthermore, with minimal modifications and using the deep theoretical connections between function encoders and functional analysis, we derive operator learning algorithms that are directly analogous to eigen-decomposition and singular value decomposition. We empirically validate B2B operator learning on six benchmark operator learning tasks, and show that it demonstrates a two-orders-of-magnitude improvement in accuracy over existing approaches on several benchmark tasks.
Authors: Sarthak Pati, Szymon Mazurek, Spyridon Bakas
Abstract: Generative Artificial Intelligence (GenAI) is a field of AI that creates new data samples from existing ones. It utilizing deep learning to overcome the scarcity and regulatory constraints of healthcare data by generating new data points that integrate seamlessly with original datasets. This paper explores the background and motivation for GenAI, and introduces the Generally Nuanced Deep Learning Framework for Synthesis (GaNDLF-Synth) to address a significant gap in the literature and move towards democratizing the implementation and assessment of image synthesis tasks in healthcare. GaNDLF-Synth describes a unified abstraction for various synthesis algorithms, including autoencoders, generative adversarial networks, and diffusion models. Leveraging the GANDLF-core framework, it supports diverse data modalities and distributed computing, ensuring scalability and reproducibility through extensive unit testing. The aim of GaNDLF-Synth is to lower the entry barrier for GenAI, and make it more accessible and extensible by the wider scientific community.
Authors: Yejin Lee, Anna Sun, Basil Hosmer, Bilge Acun, Can Balioglu, Changhan Wang, Charles David Hernandez, Christian Puhrsch, Daniel Haziza, Driss Guessous, Francisco Massa, Jacob Kahn, Jeffrey Wan, Jeremy Reizenstein, Jiaqi Zhai, Joe Isaacson, Joel Schlosser, Juan Pino, Kaushik Ram Sadagopan, Leonid Shamis, Linjian Ma, Min-Jae Hwang, Mingda Chen, Mostafa Elhoushi, Pedro Rodriguez, Ram Pasunuru, Scott Yih, Sravya Popuri, Xing Liu, Carole-Jean Wu
Abstract: Generative artificial intelligence (AI) technology is revolutionizing the computing industry. Not only its applications have broadened to various sectors but also poses new system design and optimization opportunities. The technology is capable of understanding and responding in multiple modalities. However, the advanced capability currently comes with significant system resource demands. To sustainably scale generative AI capabilities to billions of users in the world, inference must be fast and efficient. This paper pinpoints key system design and optimization opportunities by characterizing a family of emerging multi-modal generation models on real systems. Auto-regressive token generation is a critical latency performance bottleneck, typically dominated by GPU idle time. In addition to memory-intensive attention across the generative AI models, linear operations constitute significant inference latency due to the feed forward networks in Transformer-based models. We demonstrate that state-of-the-art optimization levers, spanning from applications to system software and hardware, set a 3.88x better baseline.
Authors: Md Rejwanur Rahman, Adrian Rodriguez-Marek, Nina Stark, Grace Massey, Carl Friedrichs, Kelly M. Dorgan
Abstract: The geotechnical evaluation of seabed sediments is important for engineering projects and naval applications, offering valuable insights into sediment properties, behavior, and strength. Obtaining high-quality seabed samples can be a challenging task, making in-situ testing an essential part of site characterization. Free Fall Penetrometers (FFP) have emerged as robust tools for rapidly profiling seabed surface sediments, even in energetic nearshore or estuarine conditions and shallow as well as deep depths. While methods for interpretation of traditional offshore Cone Penetration Testing (CPT) data are well-established, their adaptation to FFP data is still an area of research. In this study, we introduce an innovative approach that utilizes machine learning algorithms to create a sediment behavior classification system based on portable free fall penetrometer (PFFP) data. The proposed model leverages PFFP measurements obtained from locations such as Sequim Bay (Washington), the Potomac River, and the York River (Virginia). The result shows 91.1\% accuracy in the class prediction, with the classes representing cohesionless sediment with little to no plasticity, cohesionless sediment with some plasticity, cohesive sediment with low plasticity, and cohesive sediment with high plasticity. The model prediction not only provides the predicted class but also yields an estimate of inherent uncertainty associated with the prediction, which can provide valuable insight about different sediment behaviors. These uncertainties typically range from very low to very high, with lower uncertainties being more common, but they can increase significantly dpending on variations in sediment composition, environmental conditions, and operational techniques. By quantifying uncertainty, the model offers a more comprehensive and informed approach to sediment classification.
Authors: Qiang Ye
Abstract: Accelerated training algorithms, such as adaptive learning rates and various normalization methods, are widely used but not fully understood. When regularization is introduced, standard optimizers like adaptive learning rates may not perform effectively. This raises the need for alternative regularization approaches and the question of how to properly combine regularization with preconditioning. In this paper, we address these challenges using the theory of preconditioning as follows: (1) We explain how preconditioning with AdaGrad, RMSProp, and Adam accelerates training; (2) We explore the interaction between regularization and preconditioning, outlining different options for selecting the variables for regularization, and in particular we discuss how to implement that for the gradient regularization; and (3) We demonstrate how normalization methods accelerate training by improving Hessian conditioning, and discuss how this perspective can lead to new preconditioning training algorithms. Our findings offer a unified mathematical framework for understanding various acceleration techniques and deriving appropriate regularization schemes.
Authors: Tomas Ortega, Hamid Jafarkhani
Abstract: Recent advances in federated learning have shown that asynchronous variants can be faster and more scalable than their synchronous counterparts. However, their design does not include quantization, which is necessary in practice to deal with the communication bottleneck. To bridge this gap, we develop a novel algorithm, Quantized Asynchronous Federated Learning (QAFeL), which introduces a hidden-state quantization scheme to avoid the error propagation caused by direct quantization. QAFeL also includes a buffer to aggregate client updates, ensuring scalability and compatibility with techniques such as secure aggregation. Furthermore, we prove that QAFeL achieves an $\mathcal{O}(1/\sqrt{T})$ ergodic convergence rate for stochastic gradient descent on non-convex objectives, which is the optimal order of complexity, without requiring bounded gradients or uniform client arrivals. We also prove that the cross-term error between staleness and quantization only affects the higher-order error terms. We validate our theoretical findings on standard benchmarks.
Authors: Qianwen Xing, Chang Yu, Sining Huang, Qi Zheng, Xingyu Mu, Mengying Sun
Abstract: In contemporary economic society, credit scores are crucial for every participant. A robust credit evaluation system is essential for the profitability of core businesses such as credit cards, loans, and investments for commercial banks and the financial sector. This paper combines high-performance models like XGBoost and LightGBM, already widely used in modern banking systems, with the powerful TabNet model. We have developed a potent model capable of accurately determining credit score levels by integrating Random Forest, XGBoost, and TabNet, and through the stacking technique in ensemble modeling. This approach surpasses the limitations of single models and significantly advances the precise credit score prediction. In the following sections, we will explain the techniques we used and thoroughly validate our approach by comprehensively comparing a series of metrics such as Precision, Recall, F1, and AUC. By integrating Random Forest, XGBoost, and with the TabNet deep learning architecture, these models complement each other, demonstrating exceptionally strong overall performance.
Authors: Shashank Subramanian, Ermal Rrapaj, Peter Harrington, Smeet Chheda, Steven Farrell, Brian Austin, Samuel Williams, Nicholas Wright, Wahid Bhimji
Abstract: Generative AI, in particular large transformer models, are increasingly driving HPC system design in science and industry. We analyze performance characteristics of such transformer models and discuss their sensitivity to the transformer type, parallelization strategy, and HPC system features (accelerators and interconnects). We utilize a performance model that allows us to explore this complex design space and highlight its key components. We find that different transformer types demand different parallelism and system characteristics at different training regimes. Large Language Models are performant with 3D parallelism and amplify network needs only at pre-training scales with reduced dependence on accelerator capacity and bandwidth. On the other hand, long-sequence transformers, representative of scientific foundation models, place a more uniform dependence on network and capacity with necessary 4D parallelism. Our analysis emphasizes the need for closer performance modeling of different transformer types keeping system features in mind and demonstrates a path towards this. Our code is available as open-source.
Authors: Xuefeng Du, Reshmi Ghosh, Robert Sim, Ahmed Salem, Vitor Carvalho, Emily Lawton, Yixuan Li, Jack W. Stokes
Abstract: Vision-language models (VLMs) are essential for contextual understanding of both visual and textual information. However, their vulnerability to adversarially manipulated inputs presents significant risks, leading to compromised outputs and raising concerns about the reliability in VLM-integrated applications. Detecting these malicious prompts is thus crucial for maintaining trust in VLM generations. A major challenge in developing a safeguarding prompt classifier is the lack of a large amount of labeled benign and malicious data. To address the issue, we introduce VLMGuard, a novel learning framework that leverages the unlabeled user prompts in the wild for malicious prompt detection. These unlabeled prompts, which naturally arise when VLMs are deployed in the open world, consist of both benign and malicious information. To harness the unlabeled data, we present an automated maliciousness estimation score for distinguishing between benign and malicious samples within this unlabeled mixture, thereby enabling the training of a binary prompt classifier on top. Notably, our framework does not require extra human annotations, offering strong flexibility and practicality for real-world applications. Extensive experiment shows VLMGuard achieves superior detection results, significantly outperforming state-of-the-art methods. Disclaimer: This paper may contain offensive examples; reader discretion is advised.
Authors: Chenqing Hua, Yong Liu, Dinghuai Zhang, Odin Zhang, Sitao Luan, Kevin K. Yang, Guy Wolf, Doina Precup, Shuangjia Zheng
Abstract: Enzyme design is a critical area in biotechnology, with applications ranging from drug development to synthetic biology. Traditional methods for enzyme function prediction or protein binding pocket design often fall short in capturing the dynamic and complex nature of enzyme-substrate interactions, particularly in catalytic processes. To address the challenges, we introduce EnzymeFlow, a generative model that employs flow matching with hierarchical pre-training and enzyme-reaction co-evolution to generate catalytic pockets for specific substrates and catalytic reactions. Additionally, we introduce a large-scale, curated, and validated dataset of enzyme-reaction pairs, specifically designed for the catalytic pocket generation task, comprising a total of $328,192$ pairs. By incorporating evolutionary dynamics and reaction-specific adaptations, EnzymeFlow becomes a powerful model for designing enzyme pockets, which is capable of catalyzing a wide range of biochemical reactions. Experiments on the new dataset demonstrate the model's effectiveness in designing high-quality, functional enzyme catalytic pockets, paving the way for advancements in enzyme engineering and synthetic biology. We provide EnzymeFlow code at https://github.com/WillHua127/EnzymeFlow with notebook demonstration at https://github.com/WillHua127/EnzymeFlow/blob/main/enzymeflow_demo.ipynb.
URLs: https://github.com/WillHua127/EnzymeFlow, https://github.com/WillHua127/EnzymeFlow/blob/main/enzymeflow_demo.ipynb.
Authors: Gabriel Franco, Mark Crovella
Abstract: Many papers have shown that attention heads work in conjunction with each other to perform complex tasks. It's frequently assumed that communication between attention heads is via the addition of specific features to token residuals. In this work we seek to isolate and identify the features used to effect communication and coordination among attention heads in GPT-2 small. Our key leverage on the problem is to show that these features are very often sparsely coded in the singular vectors of attention head matrices. We characterize the dimensionality and occurrence of these signals across the attention heads in GPT-2 small when used for the Indirect Object Identification (IOI) task. The sparse encoding of signals, as provided by attention head singular vectors, allows for efficient separation of signals from the residual background and straightforward identification of communication paths between attention heads. We explore the effectiveness of this approach by tracing portions of the circuits used in the IOI task. Our traces reveal considerable detail not present in previous studies, shedding light on the nature of redundant paths present in GPT-2. And our traces go beyond previous work by identifying features used to communicate between attention heads when performing IOI.
Authors: Carles Domingo-Enrich
Abstract: Stochastic optimal control (SOC) aims to direct the behavior of noisy systems and has widespread applications in science, engineering, and artificial intelligence. In particular, reward fine-tuning of diffusion and flow matching models and sampling from unnormalized methods can be recast as SOC problems. A recent work has introduced Adjoint Matching (Domingo-Enrich et al., 2024), a loss function for SOC problems that vastly outperforms existing loss functions in the reward fine-tuning setup. The goal of this work is to clarify the connections between all the existing (and some new) SOC loss functions. Namely, we show that SOC loss functions can be grouped into classes that share the same gradient in expectation, which means that their optimization landscape is the same; they only differ in their gradient variance. We perform simple SOC experiments to understand the strengths and weaknesses of different loss functions.
Authors: Hao Liu, Zecheng Zhang, Wenjing Liao, Hayden Schaeffer
Abstract: Neural scaling laws play a pivotal role in the performance of deep neural networks and have been observed in a wide range of tasks. However, a complete theoretical framework for understanding these scaling laws remains underdeveloped. In this paper, we explore the neural scaling laws for deep operator networks, which involve learning mappings between function spaces, with a focus on the Chen and Chen style architecture. These approaches, which include the popular Deep Operator Network (DeepONet), approximate the output functions using a linear combination of learnable basis functions and coefficients that depend on the input functions. We establish a theoretical framework to quantify the neural scaling laws by analyzing its approximation and generalization errors. We articulate the relationship between the approximation and generalization errors of deep operator networks and key factors such as network model size and training data size. Moreover, we address cases where input functions exhibit low-dimensional structures, allowing us to derive tighter error bounds. These results also hold for deep ReLU networks and other similar structures. Our results offer a partial explanation of the neural scaling laws in operator learning and provide a theoretical foundation for their applications.
Authors: Prasenjit Maji, Amit Kumar Mondal, Hemanta Kumar Mondal, Saraju P. Mohanty
Abstract: The rapid advancements in artificial intelligence (AI) have revolutionized smart healthcare, driving innovations in wearable technologies, continuous monitoring devices, and intelligent diagnostic systems. However, security, explainability, robustness, and performance optimization challenges remain critical barriers to widespread adoption in clinical environments. This research presents an innovative algorithmic method using the Adaptive Feature Evaluator (AFE) algorithm to improve feature selection in healthcare datasets and overcome problems. AFE integrating Genetic Algorithms (GA), Explainable Artificial Intelligence (XAI), and Permutation Combination Techniques (PCT), the algorithm optimizes Clinical Decision Support Systems (CDSS), thereby enhancing predictive accuracy and interpretability. The proposed method is validated across three diverse healthcare datasets using six distinct machine learning algorithms, demonstrating its robustness and superiority over conventional feature selection techniques. The results underscore the transformative potential of AFE in smart healthcare, enabling personalized and transparent patient care. Notably, the AFE algorithm, when combined with a Multi-layer Perceptron (MLP), achieved an accuracy of up to 98.5%, highlighting its capability to improve clinical decision-making processes in real-world healthcare applications.
Authors: Hongjun Wang, Jiyuan Chen, Tong Pan, Zheng Dong, Lingyu Zhang, Renhe Jiang, Xuan Song
Abstract: Recent advancements in Spatiotemporal Graph Neural Networks (ST-GNNs) and Transformers have demonstrated promising potential for traffic forecasting by effectively capturing both temporal and spatial correlations. The generalization ability of spatiotemporal models has received considerable attention in recent scholarly discourse. However, no substantive datasets specifically addressing traffic out-of-distribution (OOD) scenarios have been proposed. Existing ST-OOD methods are either constrained to testing on extant data or necessitate manual modifications to the dataset. Consequently, the generalization capacity of current spatiotemporal models in OOD scenarios remains largely underexplored. In this paper, we investigate state-of-the-art models using newly proposed traffic OOD benchmarks and, surprisingly, find that these models experience a significant decline in performance. Through meticulous analysis, we attribute this decline to the models' inability to adapt to previously unobserved spatial relationships. To address this challenge, we propose a novel Mixture of Experts (MoE) framework, which learns a set of graph generators (i.e., graphons) during training and adaptively combines them to generate new graphs based on novel environmental conditions to handle spatial distribution shifts during testing. We further extend this concept to the Transformer architecture, achieving substantial improvements. Our method is both parsimonious and efficacious, and can be seamlessly integrated into any spatiotemporal model, outperforming current state-of-the-art approaches in addressing spatial dynamics.
Authors: Yuhao Liu, James Doss-Gollin, Guha Balakrishnan, Ashok Veeraraghavan
Abstract: Understanding local risks from extreme rainfall, such as flooding, requires both long records (to sample rare events) and high-resolution products (to assess localized hazards). Unfortunately, there is a dearth of long-record and high-resolution products that can be used to understand local risk and precipitation science. In this paper, we present a novel generative diffusion model that downscales (super-resolves) globally available Climate Prediction Center (CPC) gauge-based precipitation products and ERA5 reanalysis data to generate kilometer-scale precipitation estimates. Downscaling gauge-based precipitation from 55 km to 1 km while recovering extreme rainfall signals poses significant challenges. To enforce our model (named WassDiff) to produce well-calibrated precipitation intensity values, we introduce a Wasserstein Distance Regularization (WDR) term for the score-matching training objective in the diffusion denoising process. We show that WDR greatly enhances the model's ability to capture extreme values compared to diffusion without WDR. Extensive evaluation shows that WassDiff has better reconstruction accuracy and bias scores than conventional score-based diffusion models. Case studies of extreme weather phenomena, like tropical storms and cold fronts, demonstrate WassDiff's ability to produce appropriate spatial patterns while capturing extremes. Such downscaling capability enables the generation of extensive km-scale precipitation datasets from existing historical global gauge records and current gauge measurements in areas without high-resolution radar.
Authors: Hongjun Wang, Jiyuan Chen, Tong Pan, Zheng Dong, Lingyu Zhang, Renhe Jiang, Xuan Song
Abstract: Traffic forecasting is a cornerstone of smart city management, enabling efficient resource allocation and transportation planning. Deep learning, with its ability to capture complex nonlinear patterns in spatiotemporal (ST) data, has emerged as a powerful tool for traffic forecasting. While graph neural networks (GCNs) and transformer-based models have shown promise, their computational demands often hinder their application to real-world road networks, particularly those with large-scale spatiotemporal interactions. To address these challenges, we propose a novel spatiotemporal graph transformer (STGformer) architecture. STGformer effectively balances the strengths of GCNs and Transformers, enabling efficient modeling of both global and local traffic patterns while maintaining a manageable computational footprint. Unlike traditional approaches that require multiple attention layers, STG attention block captures high-order spatiotemporal interactions in a single layer, significantly reducing computational cost. In particular, STGformer achieves a 100x speedup and a 99.8\% reduction in GPU memory usage compared to STAEformer during batch inference on a California road graph with 8,600 sensors. We evaluate STGformer on the LargeST benchmark and demonstrate its superiority over state-of-the-art Transformer-based methods such as PDFormer and STAEformer, which underline STGformer's potential to revolutionize traffic forecasting by overcoming the computational and memory limitations of existing approaches, making it a promising foundation for future spatiotemporal modeling tasks.
Authors: Mengyuan Chen, Junyu Gao, Changsheng Xu
Abstract: Evidential Deep Learning (EDL) is an emerging method for uncertainty estimation that provides reliable predictive uncertainty in a single forward pass, attracting significant attention. Grounded in subjective logic, EDL derives Dirichlet concentration parameters from neural networks to construct a Dirichlet probability density function (PDF), modeling the distribution of class probabilities. Despite its success, EDL incorporates several nonessential settings: In model construction, (1) a commonly ignored prior weight parameter is fixed to the number of classes, while its value actually impacts the balance between the proportion of evidence and its magnitude in deriving predictive scores. In model optimization, (2) the empirical risk features a variance-minimizing optimization term that biases the PDF towards a Dirac delta function, potentially exacerbating overconfidence. (3) Additionally, the structural risk typically includes a KL-divergence-minimizing regularization, whose optimization direction extends beyond the intended purpose and contradicts common sense, diminishing the information carried by the evidence magnitude. Therefore, we propose Re-EDL, a simplified yet more effective variant of EDL, by relaxing the nonessential settings and retaining the essential one, namely, the adoption of projected probability from subjective logic. Specifically, Re-EDL treats the prior weight as an adjustable hyperparameter rather than a fixed scalar, and directly optimizes the expectation of the Dirichlet PDF provided by deprecating both the variance-minimizing optimization term and the divergence regularization term. Extensive experiments and state-of-the-art performance validate the effectiveness of our method. The source code is available at https://github.com/MengyuanChen21/Re-EDL.
Authors: Yooseok Lim, Sujee Lee
Abstract: This study develops a method to automatically count exercise repetitions by analyzing IMU signals, with a focus on a universal exercise repetition counting task that counts all types of exercise movements, including novel exercises not seen during training, using a single model. A key challenge in developing such a model is handling the considerable variation in peak patterns across different types of exercises. Since peak patterns can vary significantly between different exercises as well as between individuals performing the same exercise, the model needs to learn a complex embedding space of sensor data to generalize effectively. To address this challenge, we propose a repetition counting technique utilizing a deep metric-based few-shot learning approach, designed to handle both existing and novel exercises. By redefining the counting task as a few-shot classification problem, the method is capable of detecting peak repetition patterns in exercises not seen during training. The approach employs a Siamese network with triplet loss, optimizing the embedding space to distinguish between peak and non-peak frames. The proposed framework is composed of three main phases: standard classification training, few-shot training, and fine-tuning for novel exercises, followed by post-processing to refine the final repetition counts. Evaluation results demonstrate the effectiveness of the proposed approach, showing an 86.8% probability of accurately counting ten or more repetitions within a single set across 28 different exercises. This performance highlights the model's ability to generalize across various exercise types, including those not present in the training data. Such robustness and adaptability make the system a strong candidate for real-time implementation in fitness and healthcare applications.
Authors: Chanhui Lee, Dae-Woong Jeong, Sung Moon Ko, Sumin Lee, Hyunseung Kim, Soorin Yim, Sehui Han, Sungwoong Kim, Sungbin Lim
Abstract: Molecules have a number of distinct properties whose importance and application vary. Often, in reality, labels for some properties are hard to achieve despite their practical importance. A common solution to such data scarcity is to use models of good generalization with transfer learning. This involves domain experts for designing source and target tasks whose features are shared. However, this approach has limitations: i). Difficulty in accurate design of source-target task pairs due to the large number of tasks, and ii). corresponding computational burden verifying many trials and errors of transfer learning design, thereby iii). constraining the potential of foundation modeling of multi-task molecular property prediction. We address the limitations of the manual design of transfer learning via data-driven bi-level optimization. The proposed method enables scalable multi-task transfer learning for molecular property prediction by automatically obtaining the optimal transfer ratios. Empirically, the proposed method improved the prediction performance of 40 molecular properties and accelerated training convergence.
Authors: Lexiang Hu, Yisen Wang, Zhouchen Lin
Abstract: Kolmogorov-Arnold Networks (KANs) have seen great success in scientific domains thanks to spline activation functions, becoming an alternative to Multi-Layer Perceptrons (MLPs). However, spline functions may not respect symmetry in tasks, which is crucial prior knowledge in machine learning. Previously, equivariant networks embed symmetry into their architectures, achieving better performance in specific applications. Among these, Equivariant Multi-Layer Perceptrons (EMLP) introduce arbitrary matrix group equivariance into MLPs, providing a general framework for constructing equivariant networks layer by layer. In this paper, we propose Equivariant Kolmogorov-Arnold Networks (EKAN), a method for incorporating matrix group equivariance into KANs, aiming to broaden their applicability to more fields. First, we construct gated spline basis functions, which form the EKAN layer together with equivariant linear weights. We then define a lift layer to align the input space of EKAN with the feature space of the dataset, thereby building the entire EKAN architecture. Compared with baseline models, EKAN achieves higher accuracy with smaller datasets or fewer parameters on symmetry-related tasks, such as particle scattering and the three-body problem, often reducing test MSE by several orders of magnitude. Even in non-symbolic formula scenarios, such as top quark tagging with three jet constituents, EKAN achieves comparable results with EMLP using only $26\%$ of the parameters, while KANs do not outperform MLPs as expected.
Authors: Tai D. Nguyen, Long H. Pham, Jun Sun
Abstract: Large Language Models (LLMs) require frequent updates to correct errors and keep pace with continuously evolving knowledge in a timely and effective manner. Recent research in it model editing has highlighted the challenges in balancing generalization and locality, especially in the context of lifelong model editing. We discover that inserting knowledge directly into the model often causes conflicts and potentially disrupts other unrelated pre-trained knowledge. To address this problem, we introduce UniAdapt, a universal adapter for knowledge calibration. Inspired by the Mixture of Experts architecture and Retrieval-Augmented Generation, UniAdapt is designed with a vector-assisted router that is responsible for routing inputs to appropriate experts. The router maintains a vector store, including multiple shards, to construct routing vectors based on semantic similarity search results. UniAdapt is fully model-agnostic and designed for seamless plug-and-play integration. Experimental results show that UniAdapt outperforms existing lifelong model editors and achieves exceptional results in most metrics.
Authors: Siyi He
Abstract: Traditional reinforcement learning often struggles to generate diverse, high-reward solutions, especially in domains like drug design and black-box function optimization. Markov Chain Monte Carlo (MCMC) methods provide an alternative method of RL in candidate selection but suffer from high computational costs and limited candidate diversity exploration capabilities. In response, GFlowNet, a novel neural network architecture, was introduced to model complex system dynamics and generate diverse high-reward trajectories. To further enhance this approach, this paper proposes improvements to GFlowNet by introducing a new loss function and refining the training objective associated with sub-GFlowNet. These enhancements aim to integrate entropy and leverage network structure characteristics, improving both candidate diversity and computational efficiency. We demonstrated the superiority of the refined GFlowNet over traditional methods by empirical results from hypergrid experiments and molecule synthesis tasks. The findings underscore the effectiveness of incorporating entropy and exploiting network structure properties in solution generation in molecule synthesis as well as diverse experimental designs.
Authors: Michael Vollenweider, Manuel Sch\"urch, Chiara Rohrer, Gabriele Gut, Michael Krauthammer, Andreas Wicki
Abstract: Precision medicine offers the potential to tailor treatment decisions to individual patients, yet it faces significant challenges due to the complex biases in clinical observational data and the high-dimensional nature of biological data. This study models various types of treatment assignment biases using mutual information and investigates their impact on machine learning (ML) models for counterfactual prediction and biomarker identification. Unlike traditional counterfactual benchmarks that rely on fixed treatment policies, our work focuses on modeling different characteristics of the underlying observational treatment policy in distinct clinical settings. We validate our approach through experiments on toy datasets, semi-synthetic tumor cancer genome atlas (TCGA) data, and real-world biological outcomes from drug and CRISPR screens. By incorporating empirical biological mechanisms, we create a more realistic benchmark that reflects the complexities of real-world data. Our analysis reveals that different biases lead to varying model performances, with some biases, especially those unrelated to outcome mechanisms, having minimal effect on prediction accuracy. This highlights the crucial need to account for specific biases in clinical observational data in counterfactual ML model development, ultimately enhancing the personalization of treatment decisions in precision medicine.
Authors: Mushir Akhtar, M. Tanveer, Mohd. Arshad
Abstract: Random vector functional link (RVFL), a variant of single-layer feedforward neural network (SLFN), has garnered significant attention due to its lower computational cost and robustness to overfitting. Despite its advantages, the RVFL network's reliance on the square error loss function makes it highly sensitive to outliers and noise, leading to degraded model performance in real-world applications. To remedy it, we propose the incorporation of the HawkEye loss (H-loss) function into the RVFL framework. The H-loss function features nice mathematical properties, including smoothness and boundedness, while simultaneously incorporating an insensitive zone. Each characteristic brings its own advantages: 1) Boundedness limits the impact of extreme errors, enhancing robustness against outliers; 2) Smoothness facilitates the use of gradient-based optimization algorithms, ensuring stable and efficient convergence; and 3) The insensitive zone mitigates the effect of minor discrepancies and noise. Leveraging the H-loss function, we embed it into the RVFL framework and develop a novel robust RVFL model termed H-RVFL. Notably, this work addresses a significant gap, as no bounded loss function has been incorporated into RVFL to date. The non-convex optimization of the proposed H-RVFL is effectively addressed by the Nesterov accelerated gradient (NAG) algorithm, whose computational complexity is also discussed. The proposed H-RVFL model's effectiveness is validated through extensive experiments on $40$ benchmark datasets from UCI and KEEL repositories, with and without label noise. The results highlight significant improvements in robustness and efficiency, establishing the H-RVFL model as a powerful tool for applications in noisy and outlier-prone environments.
Authors: Hamed Behzadi-Khormouji, Jos\'e Oramas
Abstract: Model Interpretation aims at the extraction of insights from the internals of a trained model. A common approach to address this task is the characterization of relevant features internally encoded in the model that are critical for its proper operation. Despite recent progress of these methods, they come with the weakness of being computationally expensive due to the dense evaluation of datasets that they require. As a consequence, research on the design of these methods have focused on smaller data subsets which may led to reduced insights. To address these computational costs, we propose a coreset-based interpretation framework that utilizes coreset selection methods to sample a representative subset of the large dataset for the interpretation task. Towards this goal, we propose a similarity-based evaluation protocol to assess the robustness of model interpretation methods towards the amount data they take as input. Experiments considering several interpretation methods, DNN models, and coreset selection methods show the effectiveness of the proposed framework.
Authors: Francisco N. F. Q. Simoes, Mehdi Dastani, Thijs van Ommen
Abstract: To effectively study complex causal systems, it is often useful to construct representations that simplify parts of the system by discarding irrelevant details while preserving key features. The Information Bottleneck (IB) method is a widely used approach in representation learning that compresses random variables while retaining information about a target variable. Traditional methods like IB are purely statistical and ignore underlying causal structures, making them ill-suited for causal tasks. We propose the Causal Information Bottleneck (CIB), a causal extension of the IB, which compresses a set of chosen variables while maintaining causal control over a target variable. This method produces representations which are causally interpretable, and which can be used when reasoning about interventions. We present experimental results demonstrating that the learned representations accurately capture causality as intended.
Authors: Kristian Schwethelm, Johannes Kaiser, Jonas Kuntzer, Mehmet Yigitsoy, Daniel Rueckert, Georgios Kaissis
Abstract: Active learning (AL) is a widely used technique for optimizing data labeling in machine learning by iteratively selecting, labeling, and training on the most informative data. However, its integration with formal privacy-preserving methods, particularly differential privacy (DP), remains largely underexplored. While some works have explored differentially private AL for specialized scenarios like online learning, the fundamental challenge of combining AL with DP in standard learning settings has remained unaddressed, severely limiting AL's applicability in privacy-sensitive domains. This work addresses this gap by introducing differentially private active learning (DP-AL) for standard learning settings. We demonstrate that naively integrating DP-SGD training into AL presents substantial challenges in privacy budget allocation and data utilization. To overcome these challenges, we propose step amplification, which leverages individual sampling probabilities in batch creation to maximize data point participation in training steps, thus optimizing data utilization. Additionally, we investigate the effectiveness of various acquisition functions for data selection under privacy constraints, revealing that many commonly used functions become impractical. Our experiments on vision and natural language processing tasks show that DP-AL can improve performance for specific datasets and model architectures. However, our findings also highlight the limitations of AL in privacy-constrained environments, emphasizing the trade-offs between privacy, model accuracy, and data selection accuracy.
Authors: V\'ictor Sabanza-Gil, Riccardo Barbano, Daniel Pacheco Guti\'errez, Jeremy S. Luterbacher, Jos\'e Miguel Hern\'andez-Lobato, Philippe Schwaller, Lo\"ic Roch
Abstract: Multi-fidelity Bayesian Optimization (MFBO) is a promising framework to speed up materials and molecular discovery as sources of information of different accuracies are at hand at increasing cost. Despite its potential use in chemical tasks, there is a lack of systematic evaluation of the many parameters playing a role in MFBO. In this work, we provide guidelines and recommendations to decide when to use MFBO in experimental settings. We investigate MFBO methods applied to molecules and materials problems. First, we test two different families of acquisition functions in two synthetic problems and study the effect of the informativeness and cost of the approximate function. We use our implementation and guidelines to benchmark three real discovery problems and compare them against their single-fidelity counterparts. Our results may help guide future efforts to implement MFBO as a routine tool in the chemical sciences.
Authors: Jie Cheng, Ruixi Qiao, Gang Xiong, Qinghai Miao, Yingwei Ma, Binhua Li, Yongbin Li, Yisheng Lv
Abstract: A significant aspiration of offline reinforcement learning (RL) is to develop a generalist agent with high capabilities from large and heterogeneous datasets. However, prior approaches that scale offline RL either rely heavily on expert trajectories or struggle to generalize to diverse unseen tasks. Inspired by the excellent generalization of world model in conditional video generation, we explore the potential of image observation-based world model for scaling offline RL and enhancing generalization on novel tasks. In this paper, we introduce JOWA: Jointly-Optimized World-Action model, an offline model-based RL agent pretrained on multiple Atari games to learn general-purpose representation and decision-making ability. Our method jointly optimizes a world-action model through shared transformer backbone, which stabilize temporal difference learning with large models during pretraining. Moreover, we propose an provably efficient and parallelizable planning algorithm to compensate for the Q-value estimation error and thus search out better policies. Experimental results indicate that our largest agent, with 150 million parameters, achieves 78.9% human-level performance on pretrained games using only 10% subsampled offline data, outperforming existing state-of-the-art large-scale offline RL baselines by 31.6% on averange. Furthermore, JOWA scales favorably with model capacity and can sample-efficiently transfer to novel games using only 5k offline fine-tuning data corresponding to about 4 trajectories per game, which demonstrates superior generalization of JOWA. We will release codes at https://github.com/CJReinforce/JOWA.
Authors: Liangzu Peng, Juan Elenter, Joshua Agterberg, Alejandro Ribeiro, Ren\'e Vidal
Abstract: The goal of continual learning (CL) is to train a model that can solve multiple tasks presented sequentially. Recent CL approaches have achieved strong performance by leveraging large pre-trained models that generalize well to downstream tasks. However, such methods lack theoretical guarantees, making them prone to unexpected failures. Conversely, principled CL approaches often fail to achieve competitive performance. In this work, we bridge this gap between theory and practice by integrating an empirically strong approach (RanPAC) into a principled framework, Ideal Continual Learner (ICL), designed to prevent forgetting. Specifically, we lift pre-trained features into a higher dimensional space and formulate an over-parametrized minimum-norm least-squares problem. We find that the lifted features are highly ill-conditioned, potentially leading to large training errors (numerical instability) and increased generalization errors (double descent). We address these challenges by continually truncating the singular value decomposition (SVD) of the lifted features. Our approach, termed ICL-TSVD, is stable with respect to the choice of hyperparameters, can handle hundreds of tasks, and outperforms state-of-the-art CL methods on multiple datasets. Importantly, our method satisfies a recurrence relation throughout its continual learning process, which allows us to prove it maintains small training and generalization errors by appropriately truncating a fraction of SVD factors. This results in a stable continual learning method with strong empirical performance and theoretical guarantees.
Authors: Maria Khodorchenko, Nikolay Butakov, Maxim Zuev, Denis Nasonov
Abstract: In this work, we present an AutoTM 2.0 framework for optimizing additively regularized topic models. Comparing to the previous version, this version includes such valuable improvements as novel optimization pipeline, LLM-based quality metrics and distributed mode. AutoTM 2.0 is a comfort tool for specialists as well as non-specialists to work with text documents to conduct exploratory data analysis or to perform clustering task on interpretable set of features. Quality evaluation is based on specially developed metrics such as coherence and gpt-4-based approaches. Researchers and practitioners can easily integrate new optimization algorithms and adapt novel metrics to enhance modeling quality and extend their experiments. We show that AutoTM 2.0 achieves better performance compared to the previous AutoTM by providing results on 5 datasets with different features and in two different languages.
Authors: Max Wasserman, Gonzalo Mateos
Abstract: Large-scale latent variable models require expressive continuous distributions that support efficient sampling and low-variance differentiation, achievable through the reparameterization trick. The Kumaraswamy (KS) distribution is both expressive and supports the reparameterization trick with a simple closed-form inverse CDF. Yet, its adoption remains limited. We identify and resolve numerical instabilities in the inverse CDF and log-pdf, exposing issues in libraries like PyTorch and TensorFlow. We then introduce simple and scalable latent variable models based on the KS, improving exploration-exploitation trade-offs in contextual multi-armed bandits and enhancing uncertainty quantification for link prediction with graph neural networks. Our results support the stabilized KS distribution as a core component in scalable variational models for bounded latent variables.
Authors: Quan Nguyen, Nishant A. Mehta, Crist\'obal Guzm\'an
Abstract: The minimax sample complexity of group distributionally robust optimization (GDRO) has been determined up to a $\log(K)$ factor, for $K$ the number of groups. In this work, we venture beyond the minimax perspective via a novel notion of sparsity that we dub $(\lambda, \beta)$-sparsity. In short, this condition means that at any parameter $\theta$, there is a set of at most $\beta$ groups whose risks at $\theta$ all are at least $\lambda$ larger than the risks of the other groups. To find an $\epsilon$-optimal $\theta$, we show via a novel algorithm and analysis that the $\epsilon$-dependent term in the sample complexity can swap a linear dependence on $K$ for a linear dependence on the potentially much smaller $\beta$. This improvement leverages recent progress in sleeping bandits, showing a fundamental connection between the two-player zero-sum game optimization framework for GDRO and per-action regret bounds in sleeping bandits. The aforementioned result assumes having a particular $\lambda$ as input. Perhaps surprisingly, we next show an adaptive algorithm which, up to log factors, gets sample complexity that adapts to the best $(\lambda, \beta)$-sparsity condition that holds. Finally, for a particular input $\lambda$, we also show how to get a dimension-free sample complexity result.
Authors: Jing Luo, Huiyuan Wang, Weiran Huang
Abstract: Large Language Models (LLMs) based on the pre-trained fine-tuning paradigm have become pivotal in solving natural language processing tasks, consistently achieving state-of-the-art performance. Nevertheless, the theoretical understanding of how model complexity influences fine-tuning performance remains challenging and has not been well explored yet. In this paper, we focus on autoregressive LLMs and propose to employ Hidden Markov Models (HMMs) to model them. Based on the HMM modeling, we investigate the relationship between model complexity and the generalization capability in downstream tasks. Specifically, we consider a popular tuning paradigm for downstream tasks, head tuning, where all pre-trained parameters are frozen and only individual heads are trained atop pre-trained LLMs. Our theoretical analysis reveals that the risk initially increases and then decreases with rising model complexity, showcasing a "double descent" phenomenon. In this case, the initial "descent" is degenerate, signifying that the "sweet spot" where bias and variance are balanced occurs when the model size is zero. Obtaining the presented in this study conclusion confronts several challenges, primarily revolving around effectively modeling autoregressive LLMs and downstream tasks, as well as conducting a comprehensive risk analysis for multivariate regression. Our research is substantiated by experiments conducted on data generated from HMMs, which provided empirical support and alignment with our theoretical insights.
Authors: Vihang Patil, Markus Hofmarcher, Elisabeth Rumetshofer, Sepp Hochreiter
Abstract: Learning agents with reinforcement learning is difficult when dealing with long trajectories that involve a large number of states. To address these learning problems effectively, the number of states can be reduced by abstract representations that cluster states. In principle, deep reinforcement learning can find abstract states, but end-to-end learning is unstable. We propose contrastive abstraction learning to find abstract states, where we assume that successive states in a trajectory belong to the same abstract state. Such abstract states may be basic locations, achieved subgoals, inventory, or health conditions. Contrastive abstraction learning first constructs clusters of state representations by contrastive learning and then applies modern Hopfield networks to determine the abstract states. The first phase of contrastive abstraction learning is self-supervised learning, where contrastive learning forces states with sequential proximity to have similar representations. The second phase uses modern Hopfield networks to map similar state representations to the same fixed point, i.e.\ to an abstract state. The level of abstraction can be adjusted by determining the number of fixed points of the modern Hopfield network. Furthermore, \textit{contrastive abstraction learning} does not require rewards and facilitates efficient reinforcement learning for a wide range of downstream tasks. Our experiments demonstrate the effectiveness of contrastive abstraction learning for reinforcement learning.
Authors: Pingbang Hu, Mahito Sugiyama
Abstract: We propose a novel and interpretable data augmentation method based on energy-based modeling and principles from information geometry. Unlike black-box generative models, which rely on deep neural networks, our approach replaces these non-interpretable transformations with explicit, theoretically grounded ones, ensuring interpretability and strong guarantees such as energy minimization. Central to our method is the introduction of the backward projection algorithm, which reverses dimension reduction to generate new data. Empirical results demonstrate that our method achieves competitive performance with black-box generative models while offering greater transparency and interpretability.
Authors: Vahid Shahverdi, Giovanni Luca Marchetti, Kathl\'en Kohn
Abstract: We study convolutional neural networks with monomial activation functions. Specifically, we prove that their parameterization map is regular and is an isomorphism almost everywhere, up to rescaling the filters. By leveraging on tools from algebraic geometry, we explore the geometric properties of the image in function space of this map -- typically referred to as neuromanifold. In particular, we compute the dimension and the degree of the neuromanifold, which measure the expressivity of the model, and describe its singularities. Moreover, for a generic large dataset, we derive an explicit formula that quantifies the number of critical points arising in the optimization of a regression loss.
Authors: Beatriz Feliciano, Rita Costa, Jean Alves, Javier Li\'ebana, Diogo Duarte, Pedro Bizarro
Abstract: Analyzing and finding anomalies in multi-dimensional datasets is a cumbersome but vital task across different domains. In the context of financial fraud detection, analysts must quickly identify suspicious activity among transactional data. This is an iterative process made of complex exploratory tasks such as recognizing patterns, grouping, and comparing. To mitigate the information overload inherent to these steps, we present a tool combining automated information highlights, Large Language Model generated textual insights, and visual analytics, facilitating exploration at different levels of detail. We perform a segmentation of the data per analysis area and visually represent each one, making use of automated visual cues to signal which require more attention. Upon user selection of an area, our system provides textual and graphical summaries. The text, acting as a link between the high-level and detailed views of the chosen segment, allows for a quick understanding of relevant details. A thorough exploration of the data comprising the selection can be done through graphical representations. The feedback gathered in a study performed with seven domain experts suggests our tool effectively supports and guides exploratory analysis, easing the identification of suspicious information.
Authors: Tommaso Ferracci, Leonie Tabea Goldmann, Anton Hinel, Francesco Sanna Passino
Abstract: Synthetic data generation has been proven successful in improving model performance and robustness in the context of scarce or low-quality data. Using the data valuation framework to statistically identify beneficial and detrimental observations, we introduce a novel augmentation pipeline that generates only high-value training points based on hardness characterization. We first demonstrate via benchmarks on real data that Shapley-based data valuation methods perform comparably with learning-based methods in hardness characterisation tasks, while offering significant theoretical and computational advantages. Then, we show that synthetic data generators trained on the hardest points outperform non-targeted data augmentation on simulated data and on a large scale credit default prediction task. In particular, our approach improves the quality of out-of-sample predictions and it is computationally more efficient compared to non-targeted methods.
Authors: Manh Khoi Duong, Stefan Conrad
Abstract: The reason behind the unfair outcomes of AI is often rooted in biased datasets. Therefore, this work presents a framework for addressing fairness by debiasing datasets containing a (non-)binary protected attribute. The framework proposes a combinatorial optimization problem where heuristics such as genetic algorithms can be used to solve for the stated fairness objectives. The framework addresses this by finding a data subset that minimizes a certain discrimination measure. Depending on a user-defined setting, the framework enables different use cases, such as data removal, the addition of synthetic data, or exclusive use of synthetic data. The exclusive use of synthetic data in particular enhances the framework's ability to preserve privacy while optimizing for fairness. In a comprehensive evaluation, we demonstrate that under our framework, genetic algorithms can effectively yield fairer datasets compared to the original data. In contrast to prior work, the framework exhibits a high degree of flexibility as it is metric- and task-agnostic, can be applied to both binary or non-binary protected attributes, and demonstrates efficient runtime.
Authors: Zhenyi Zhang, Tiejun Li, Peijie Zhou
Abstract: Reconstructing dynamics using samples from sparsely time-resolved snapshots is an important problem in both natural sciences and machine learning. Here, we introduce a new deep learning approach for solving regularized unbalanced optimal transport (RUOT) and inferring continuous unbalanced stochastic dynamics from observed snapshots. Based on the RUOT form, our method models these dynamics without requiring prior knowledge of growth and death processes or additional information, allowing them to be learnt directly from data. Theoretically, we explore the connections between the RUOT and Schr\"odinger bridge problem and discuss the key challenges and potential solutions. The effectiveness of our method is demonstrated with a synthetic gene regulatory network. Compared with other methods, our approach accurately identifies growth and transition patterns, eliminates false transitions, and constructs the Waddington developmental landscape.
Authors: Xingzhou Lou, Dong Yan, Wei Shen, Yuzi Yan, Jian Xie, Junge Zhang
Abstract: Reward models (RM) play a critical role in aligning generations of large language models (LLM) to human expectations. However, prevailing RMs fail to capture the stochasticity within human preferences and cannot effectively evaluate the reliability of reward predictions. To address these issues, we propose Uncertain-aware RM (URM) and Uncertain-aware RM Ensemble (URME) to incorporate and manage uncertainty in reward modeling. URM can model the distribution of disentangled attributes within human preferences, while URME quantifies uncertainty through discrepancies in the ensemble, thereby identifying potential lack of knowledge during reward evaluation. Experiment results indicate that the proposed URM achieves state-of-the-art performance compared to models with the same size, demonstrating the effectiveness of modeling uncertainty within human preferences. Furthermore, empirical results show that through uncertainty quantification, URM and URME can identify unreliable predictions to improve the quality of reward evaluations.
Authors: Stefano Calzavara, Lorenzo Cazzaro, Massimo Vettori
Abstract: We present Timber, the first white-box poisoning attack targeting decision trees. Timber is based on a greedy attack strategy leveraging sub-tree retraining to efficiently estimate the damage performed by poisoning a given training instance. The attack relies on a tree annotation procedure which enables sorting training instances so that they are processed in increasing order of computational cost of sub-tree retraining. This sorting yields a variant of Timber supporting an early stopping criterion designed to make poisoning attacks more efficient and feasible on larger datasets. We also discuss an extension of Timber to traditional random forest models, which is useful because decision trees are normally combined into ensembles to improve their predictive power. Our experimental evaluation on public datasets shows that our attacks outperform existing baselines in terms of effectiveness, efficiency or both. Moreover, we show that two representative defenses can mitigate the effect of our attacks, but fail at effectively thwarting them.
Authors: Bo Liu, Mao Ye, Peter Stone, Qiang Liu
Abstract: A fundamental challenge in continual learning is to balance the trade-off between learning new tasks and remembering the previously acquired knowledge. Gradient Episodic Memory (GEM) achieves this balance by utilizing a subset of past training samples to restrict the update direction of the model parameters. In this work, we start by analyzing an often overlooked hyper-parameter in GEM, the memory strength, which boosts the empirical performance by further constraining the update direction. We show that memory strength is effective mainly because it improves GEM's generalization ability and therefore leads to a more favorable trade-off. By this finding, we propose two approaches that more flexibly constrain the update direction. Our methods are able to achieve uniformly better Pareto Frontiers of remembering old and learning new knowledge than using memory strength. We further propose a computationally efficient method to approximately solve the optimization problem with more constraints.
Authors: Amy Ancelotti, Claudia Liason
Abstract: This paper reviews the applications of Graph Neural Networks (GNNs), Graph Convolutional Networks (GCNs), and Convolutional Neural Networks (CNNs) in blockchain technology. As the complexity and adoption of blockchain networks continue to grow, traditional analytical methods are proving inadequate in capturing the intricate relationships and dynamic behaviors of decentralized systems. To address these limitations, deep learning models such as GNNs, GCNs, and CNNs offer robust solutions by leveraging the unique graph-based and temporal structures inherent in blockchain architectures. GNNs and GCNs, in particular, excel in modeling the relational data of blockchain nodes and transactions, making them ideal for applications such as fraud detection, transaction verification, and smart contract analysis. Meanwhile, CNNs can be adapted to analyze blockchain data when represented as structured matrices, revealing hidden temporal and spatial patterns in transaction flows. This paper explores how these models enhance the efficiency, security, and scalability of both linear blockchains and Directed Acyclic Graph (DAG)-based systems, providing a comprehensive overview of their strengths and future research directions. By integrating advanced neural network techniques, we aim to demonstrate the potential of these models in revolutionizing blockchain analytics, paving the way for more sophisticated decentralized applications and improved network performance.
Authors: Sharmishtha Dutta, Alex Gittens, Mohammed J. Zaki, Charu C. Aggarwal
Abstract: Knowledge graph (KG) completion aims to identify additional facts that can be inferred from the existing facts in the KG. Recent developments in this field have explored this task in the inductive setting, where at test time one sees entities that were not present during training; the most performant models in the inductive setting have employed path encoding modules in addition to standard subgraph encoding modules. This work similarly focuses on KG completion in the inductive setting, without the explicit use of path encodings, which can be time-consuming and introduces several hyperparameters that require costly hyperparameter optimization. Our approach uses a Transformer-based subgraph encoding module only; we introduce connection-biased attention and entity role embeddings into the subgraph encoding module to eliminate the need for an expensive and time-consuming path encoding module. Evaluations on standard inductive KG completion benchmark datasets demonstrate that our Connection-Biased Link Prediction (CBLiP) model has superior performance to models that do not use path information. Compared to models that utilize path information, CBLiP shows competitive or superior performance while being faster. Additionally, to show that the effectiveness of connection-biased attention and entity role embeddings also holds in the transductive setting, we compare CBLiP's performance on the relation prediction task in the transductive setting.
Authors: Yixin Liu, Arielle Carr, Lichao Sun
Abstract: The perturbation analysis of linear solvers applied to systems arising broadly in machine learning settings -- for instance, when using linear regression models -- establishes an important perspective when reframing these analyses through the lens of a data poisoning attack. By analyzing solvers' responses to such attacks, this work aims to contribute to the development of more robust linear solvers and provide insights into poisoning attacks on linear solvers. In particular, we investigate how the errors in the input data will affect the fitting error and accuracy of the solution from a linear system-solving algorithm under perturbations common in adversarial attacks. We propose data perturbation through two distinct knowledge levels, developing a poisoning optimization and studying two methods of perturbation: Label-guided Perturbation (LP) and Unconditioning Perturbation (UP). Existing works mainly focus on deriving the worst-case perturbation bound from a theoretical perspective, and the analysis is often limited to specific kinds of linear system solvers. Under the circumstance that the data is intentionally perturbed -- as is the case with data poisoning -- we seek to understand how different kinds of solvers react to these perturbations, identifying those algorithms most impacted by different types of adversarial attacks.
Authors: Pablo Rodriguez-Grasa, Robert Farzan-Rodriguez, Gabriele Novelli, Yue Ban, Mikel Sanz
Abstract: A practical application of quantum machine learning in real-world scenarios in the short term remains elusive, despite significant theoretical efforts. Image classification, a common task for classical models, has been used to benchmark quantum algorithms with simple datasets, but only few studies have tackled complex real-data classification challenges. In this work, we address such a gap by focusing on the classification of satellite images, a task of particular interest to the earth observation (EO) industry. We first preprocess the selected intrincate dataset by reducing its dimensionality. Subsequently, we employ neural quantum kernels (NQKs)- embedding quantum kernels (EQKs) constructed from trained quantum neural networks (QNNs)- to classify images which include solar panels. We explore both $1$-to-$n$ and $n$-to-$n$ NQKs. In the former, parameters from a single-qubit QNN's training construct an $n$-qubit EQK achieving a mean test accuracy over 86% with three features. In the latter, we iteratively train an $n$-qubit QNN to ensure scalability, using the resultant architecture to directly form an $n$-qubit EQK. In this case, a test accuracy over 88% is obtained for three features and 8 qubits. Additionally, we show that the results are robust against a suboptimal training of the QNN.
Authors: Diego Vallarino
Abstract: This paper examines the impact of fiscal incentives on industrial investment in Uruguay from 1974 to 2010. Using a mixed-method approach that combines econometric models with machine learning techniques, the study investigates both the short-term and long-term effects of fiscal benefits on industrial investment. The results confirm the significant role of fiscal incentives in driving long-term industrial growth, while also highlighting the importance of a stable macroeconomic environment, public investment, and access to credit. Machine learning models provide additional insights into nonlinear interactions between fiscal benefits and other macroeconomic factors, such as exchange rates, emphasizing the need for tailored fiscal policies. The findings have important policy implications, suggesting that fiscal incentives, when combined with broader economic reforms, can effectively promote industrial development in emerging economies.
Authors: Irene Weber
Abstract: Current chatbot development platforms and frameworks facilitate setting up the language and dialog part of chatbots, while connecting it to backend services and business functions requires substantial manual coding effort and programming skills. This paper proposes an approach to overcome this situation. It proposes an architecture with a chatbot as frontend using an IoT (Internet of Things) platform as a middleware for connections to backend services. Specifically, it elaborates and demonstrates how to combine a chatbot developed on the open source development platform Rasa with the open source platform Node-RED, allowing low-code or no-code development of a transactional conversational user interface from frontend to backend.
Authors: Eleonora Lopez, Aurelio Uncini, Danilo Comminiello
Abstract: Emotion recognition is essential across numerous fields, including medical applications and brain-computer interface (BCI). Emotional responses include behavioral reactions, such as tone of voice and body movement, and changes in physiological signals, such as the electroencephalogram (EEG). The latter are involuntary, thus they provide a reliable input for identifying emotions, in contrast to the former which individuals can consciously control. These signals reveal true emotional states without intentional alteration, thus increasing the accuracy of emotion recognition models. However, multimodal deep learning methods from physiological signals have not been significantly investigated. In this paper, we introduce PHemoNet, a fully hypercomplex network for multimodal emotion recognition from physiological signals. In detail, the architecture comprises modality-specific encoders and a fusion module. Both encoders and fusion modules are defined in the hypercomplex domain through parameterized hypercomplex multiplications (PHMs) that can capture latent relations between the different dimensions of each modality and between the modalities themselves. The proposed method outperforms current state-of-the-art models on the MAHNOB-HCI dataset in classifying valence and arousal using electroencephalograms (EEGs) and peripheral physiological signals. The code for this work is available at https://github.com/ispamm/MHyEEG.
Authors: Yang An, Yuhao Tong, Weikai Wang, Steven W. Su
Abstract: The present study introduces an innovative approach to the synthesis of Electroencephalogram (EEG) signals by integrating diffusion models with reinforcement learning. This integration addresses key challenges associated with traditional EEG data acquisition, including participant burden, privacy concerns, and the financial costs of obtaining high-fidelity clinical data. Our methodology enhances the generation of EEG signals with detailed temporal and spectral features, enriching the authenticity and diversity of synthetic datasets. The uniqueness of our approach lies in its capacity to concurrently model time-domain characteristics, such as waveform morphology, and frequency-domain features, including rhythmic brainwave patterns, within a cohesive generative framework. This is executed through the reinforcement learning model's autonomous selection of parameter update strategies, which steers the diffusion process to accurately reflect the complex dynamics inherent in EEG signals. We validate the efficacy of our approach using both the BCI Competition IV 2a dataset and a proprietary dataset, each collected under stringent experimental conditions. Our results indicate that the method preserves participant privacy by generating synthetic data that lacks biometric identifiers and concurrently improves the efficiency of model training by minimizing reliance on large annotated datasets. This research offers dual contributions: firstly, it advances EEG research by providing a novel tool for data augmentation and the advancement of machine learning algorithms; secondly, it enhances brain-computer interface technologies by offering a robust solution for training models on diverse and representative EEG datasets. Collectively, this study establishes a foundation for future investigations in neurological care and the development of tailored treatment protocols in neurorehabilitation.
Authors: Zhongqi Yang, Iman Azimi, Salar Jafarlou, Sina Labbaf, Brenda Nguyen, Hana Qureshi, Christopher Marcotullio, Jessica L. Borelli, Nikil Dutt, Amir M. Rahmani
Abstract: The adverse effects of loneliness on both physical and mental well-being are profound. Although previous research has utilized mobile sensing techniques to detect mental health issues, few studies have utilized state-of-the-art wearable devices to forecast loneliness and estimate the physiological manifestations of loneliness and its predictive nature. The primary objective of this study is to examine the feasibility of forecasting loneliness by employing wearable devices, such as smart rings and watches, to monitor early physiological indicators of loneliness. Furthermore, smartphones are employed to capture initial behavioral signs of loneliness. To accomplish this, we employed personalized machine learning techniques, leveraging a comprehensive dataset comprising physiological and behavioral information obtained during our study involving the monitoring of college students. Through the development of personalized models, we achieved a notable accuracy of 0.82 and an F-1 score of 0.82 in forecasting loneliness levels seven days in advance. Additionally, the application of Shapley values facilitated model explainability. The wealth of data provided by this study, coupled with the forecasting methodology employed, possesses the potential to augment interventions and facilitate the early identification of loneliness within populations at risk.
Authors: Nikhil Raghav, Avisek Gupta, Md Sahidullah, Swagatam Das
Abstract: Spectral clustering has proven effective in grouping speech representations for speaker diarization tasks, although post-processing the affinity matrix remains difficult due to the need for careful tuning before constructing the Laplacian. In this study, we present a novel pruning algorithm to create a sparse affinity matrix called \emph{spectral clustering on p-neighborhood retained affinity matrix} (SC-pNA). Our method improves on node-specific fixed neighbor selection by allowing a variable number of neighbors, eliminating the need for external tuning data as the pruning parameters are derived directly from the affinity matrix. SC-pNA does so by identifying two clusters in every row of the initial affinity matrix, and retains only the top $p\%$ similarity scores from the cluster containing larger similarities. Spectral clustering is performed subsequently, with the number of clusters determined as the maximum eigengap. Experimental results on the challenging DIHARD-III dataset highlight the superiority of SC-pNA, which is also computationally more efficient than existing auto-tuning approaches.
Authors: Sahar Arshad, Nikhar Azhar, Sana Sajid, Seemab Latif, Rabia Latif
Abstract: In the modern economic landscape, integrating financial services with Financial Technology (FinTech) has become essential, particularly in stock trend analysis. This study addresses the gap in comprehending financial dynamics across diverse global economies by creating a structured financial dataset and proposing a cross-lingual Natural Language-based Financial Forecasting (NLFF) pipeline for comprehensive financial analysis. Utilizing sentiment analysis, Named Entity Recognition (NER), and semantic textual similarity, we conducted an analytical examination of news articles to extract, map, and visualize financial event timelines, uncovering the correlation between news events and stock market trends. Our method demonstrated a meaningful correlation between stock price movements and cross-linguistic news sentiments, validated by processing two-year cross-lingual news data on two prominent sectors of the Pakistan Stock Exchange. This study offers significant insights into key events, ensuring a substantial decision margin for investors through effective visualization and providing optimal investment opportunities.
Authors: Ramya Chandrasekar, Md Rakibul Hasan, Shreya Ghosh, Tom Gedeon, Md Zakir Hossain
Abstract: Anxiety is a common mental health condition characterised by excessive worry, fear and apprehension about everyday situations. Even with significant progress over the past few years, predicting anxiety from electroencephalographic (EEG) signals, specifically using error-related negativity (ERN), still remains challenging. Following the PRISMA protocol, this paper systematically reviews 54 research papers on using EEG and ERN markers for anxiety detection published in the last 10 years (2013 -- 2023). Our analysis highlights the wide usage of traditional machine learning, such as support vector machines and random forests, as well as deep learning models, such as convolutional neural networks and recurrent neural networks across different data types. Our analysis reveals that the development of a robust and generic anxiety prediction method still needs to address real-world challenges, such as task-specific setup, feature selection and computational modelling. We conclude this review by offering potential future direction for non-invasive, objective anxiety diagnostics, deployed across diverse populations and anxiety sub-types.
Authors: Adrian Pekar
Abstract: This paper presents a novel approach to compressing IP flow records using deep learning techniques, specifically autoencoders. Our method aims to significantly reduce data volume while maintaining the utility of the compressed data for downstream analysis tasks. We demonstrate the effectiveness of our approach through extensive experiments on a large-scale, real-world network traffic dataset. The proposed autoencoder-based compression achieves a 3.28x reduction in data size while preserving 99.20% accuracy in a multi-class traffic classification task, compared to 99.77% accuracy with uncompressed data. This marginal decrease in performance is offset by substantial gains in storage efficiency and potential improvements in processing speed. Our method shows particular promise in distinguishing between various modern application protocols, including encrypted traffic from popular services. The implications of this work extend to more efficient network monitoring, real-time analysis in resource-constrained environments, and scalable network management solutions.
Authors: Anna Povey, Katherine Povey
Abstract: This paper introduces FeruzaSpeech, a read speech corpus of the Uzbek language, containing transcripts in both Cyrillic and Latin alphabets, freely available for academic research purposes. This corpus includes 60 hours of high-quality recordings from a single native female speaker from Tashkent, Uzbekistan. These recordings consist of short excerpts from a book and BBC News. This paper discusses the enhancement of the Word Error Rates (WERs) on CommonVoice 16.1's Uzbek data, Uzbek Speech Corpus data, and FeruzaSpeech data upon integrating FeruzaSpeech.
Authors: Alexandre D\'efossez, Laurent Mazar\'e, Manu Orsini, Am\'elie Royer, Patrick P\'erez, Herv\'e J\'egou, Edouard Grave, Neil Zeghidour
Abstract: We introduce Moshi, a speech-text foundation model and full-duplex spoken dialogue framework. Current systems for spoken dialogue rely on pipelines of independent components, namely voice activity detection, speech recognition, textual dialogue and text-to-speech. Such frameworks cannot emulate the experience of real conversations. First, their complexity induces a latency of several seconds between interactions. Second, text being the intermediate modality for dialogue, non-linguistic information that modifies meaning -- such as emotion or non-speech sounds -- is lost in the interaction. Finally, they rely on a segmentation into speaker turns, which does not take into account overlapping speech, interruptions and interjections. Moshi solves these independent issues altogether by casting spoken dialogue as speech-to-speech generation. Starting from a text language model backbone, Moshi generates speech as tokens from the residual quantizer of a neural audio codec, while modeling separately its own speech and that of the user into parallel streams. This allows for the removal of explicit speaker turns, and the modeling of arbitrary conversational dynamics. We moreover extend the hierarchical semantic-to-acoustic token generation of previous work to first predict time-aligned text tokens as a prefix to audio tokens. Not only this ``Inner Monologue'' method significantly improves the linguistic quality of generated speech, but we also illustrate how it can provide streaming speech recognition and text-to-speech. Our resulting model is the first real-time full-duplex spoken large language model, with a theoretical latency of 160ms, 200ms in practice, and is available at https://github.com/kyutai-labs/moshi.
Authors: Yujin Oh, Sangjoon Park, Xiang Li, Wang Yi, Jonathan Paly, Jason Efstathiou, Annie Chan, Jun Won Kim, Hwa Kyung Byun, Ik Jae Lee, Jaeho Cho, Chan Woo Wee, Peng Shu, Peilong Wang, Nathan Yu, Jason Holmes, Jong Chul Ye, Quanzheng Li, Wei Liu, Woong Sub Koom, Jin Sung Kim, Kyungsang Kim
Abstract: Clinical experts employ diverse philosophies and strategies in patient care, influenced by regional patient populations. However, existing medical artificial intelligence (AI) models are often trained on data distributions that disproportionately reflect highly prevalent patterns, reinforcing biases and overlooking the diverse expertise of clinicians. To overcome this limitation, we introduce the Mixture of Multicenter Experts (MoME) approach. This method strategically integrates specialized expertise from diverse clinical strategies, enhancing the AI model's ability to generalize and adapt across multiple medical centers. The MoME-based multimodal target volume delineation model, trained with few-shot samples including images and clinical notes from each medical center, outperformed baseline methods in prostate cancer radiotherapy target delineation. The advantages of MoME were most pronounced when data characteristics varied across centers or when data availability was limited, demonstrating its potential for broader clinical applications.Therefore, the MoME framework enables the deployment of AI-based target volume delineation models in resource-constrained medical facilities by adapting to specific preferences of each medical center only using a few sample data, without the need for data sharing between institutions. Expanding the number of multicenter experts within the MoME framework will significantly enhance the generalizability, while also improving the usability and adaptability of clinical AI applications in the field of precision radiation oncology.
Authors: Arman Afrasiyabi, Erica Busch, Rahul Singh, Dhananjay Bhaskar, Laurent Caplette, Nicholas Turk-Browne, Smita Krishnaswamy
Abstract: In this work, we explore the decoding of mental imagery from subjects using their fMRI measurements. In order to achieve this decoding, we first created a mapping between a subject's fMRI signals elicited by the videos the subjects watched. This mapping associates the high dimensional fMRI activation states with visual imagery. Next, we prompted the subjects textually, primarily with emotion labels which had no direct reference to visual objects. Then to decode visual imagery that may have been in a person's mind's eye, we align a latent representation of these fMRI measurements with a corresponding video-fMRI based on textual labels given to the videos themselves. This alignment has the effect of overlapping the video fMRI embedding with the text-prompted fMRI embedding, thus allowing us to use our fMRI-to-video mapping to decode. Additionally, we enhance an existing fMRI dataset, initially consisting of data from five subjects, by including recordings from three more subjects gathered by our team. We demonstrate the efficacy of our model on this augmented dataset both in accurately creating a mapping, as well as in plausibly decoding mental imagery.
Authors: Carl E. J. Brodzinski
Abstract: This paper surveys the landscape of security and data attacks on machine unlearning, with a focus on financial and e-commerce applications. We discuss key privacy threats such as Membership Inference Attacks and Data Reconstruction Attacks, where adversaries attempt to infer or reconstruct data that should have been removed. In addition, we explore security attacks including Machine Unlearning Data Poisoning, Unlearning Request Attacks, and Machine Unlearning Jailbreak Attacks, which target the underlying mechanisms of unlearning to manipulate or corrupt the model. To mitigate these risks, various defense strategies are examined, including differential privacy, robust cryptographic guarantees, and Zero-Knowledge Proofs (ZKPs), offering verifiable and tamper-proof unlearning mechanisms. These approaches are essential for safeguarding data integrity and privacy in high-stakes financial and e-commerce contexts, where compromised models can lead to fraud, data leaks, and reputational damage. This survey highlights the need for continued research and innovation in secure machine unlearning, as well as the importance of developing strong defenses against evolving attack vectors.
Authors: Chaohui Xu, Qi Cui, Jinxin Dong, Weiyang He, Chip-Hong Chang
Abstract: Illegitimate reproduction, distribution and derivation of Deep Neural Network (DNN) models can inflict economic loss, reputation damage and even privacy infringement. Passive DNN intellectual property (IP) protection methods such as watermarking and fingerprinting attempt to prove the ownership upon IP violation, but they are often too late to stop catastrophic damage of IP abuse and too feeble against strong adversaries. In this paper, we propose IDEA, an Inverse Domain Expert Adaptation based proactive DNN IP protection method featuring active authorization and source traceability. IDEA generalizes active authorization as an inverse problem of domain adaptation. The multi-adaptive optimization is solved by a mixture-of-experts model with one real and two fake experts. The real expert re-optimizes the source model to correctly classify test images with a unique model user key steganographically embedded. The fake experts are trained to output random prediction on test images without or with incorrect user key embedded by minimizing their mutual information (MI) with the real expert. The MoE model is knowledge distilled into a unified protected model to avoid leaking the expert model features by maximizing their MI with additional multi-layer attention and contrastive representation loss optimization. IDEA not only prevents unauthorized users without the valid key to access the functional model, but also enable the model owner to validate the deployed model and trace the source of IP infringement. We extensively evaluate IDEA on five datasets and four DNN models to demonstrate its effectiveness in authorization control, culprit tracing success rate, and robustness against various attacks.
Authors: Arvid Lepsien, Marco Pegoraro, Frederik Fonger, Dominic Langhammer, Milda Aleknonyt\.e-Resch, Agnes Koschmider
Abstract: Various kinds of uncertainty can occur in event logs, e.g., due to flawed recording, data quality issues, or the use of probabilistic models for activity recognition. Stochastically known event logs make these uncertainties transparent by encoding multiple possible realizations for events. However, the number of realizations encoded by a stochastically known log grows exponentially with its size, making exhaustive exploration infeasible even for moderately sized event logs. Thus, considering only the top-K most probable realizations has been proposed in the literature. In this paper, we implement an efficient algorithm to calculate a top-K realization ranking of an event log under event independence within O(Kn), where n is the number of uncertain events in the log. This algorithm is used to investigate the benefit of top-K rankings over top-1 interpretations of stochastically known event logs. Specifically, we analyze the usefulness of top-K rankings against different properties of the input data. We show that the benefit of a top-K ranking depends on the length of the input event log and the distribution of the event probabilities. The results highlight the potential of top-K rankings to enhance uncertainty-aware process mining techniques.
Authors: Xinyuan Zheng, Orren Ravid, Robert A. J. Barry, Yoojean Kim, Qian Wang, Young-geun Kim, Xi Zhu, Xiaofu He
Abstract: Autism spectrum disorders (ASDs) are developmental conditions characterized by restricted interests and difficulties in communication. The complexity of ASD has resulted in a deficiency of objective diagnostic biomarkers. Deep learning methods have gained recognition for addressing these challenges in neuroimaging analysis, but finding and interpreting such diagnostic biomarkers are still challenging computationally. We propose an ASD feature reduction pipeline using resting-state fMRI (rs-fMRI). We used Ncuts parcellations and Power atlas to extract functional connectivity data, resulting in over 30 thousand features. Then the pipeline further compresses the connectivities into 5 latent Gaussian distributions, providing is a low-dimensional representation of the data, using a denoising variational autoencoder (DVAE). To test the method, we employed the extracted latent features from the DVAE to classify ASD using traditional classifiers such as support vector machine (SVM) on a large multi-site dataset. The 95% confidence interval for the prediction accuracy of the SVM is [0.63, 0.76] after site harmonization using the extracted latent distributions. Without using DVAE, the prediction accuracy is 0.70, which falls within the interval. This implies that the model successfully encodes the diagnostic information in rs-fMRI data to 5 Gaussian distributions (10 features) without sacrificing prediction performance. The runtime for training the DVAE and obtaining classification results from its extracted latent features (37 minutes) was 7 times shorter compared to training classifiers directly on the raw connectivity matrices (5-6 hours). Our findings also suggest that the Power atlas provides more effective brain connectivity insights for diagnosing ASD than Ncuts parcellations. The encoded features can be used for the help of diagnosis and interpretation of the disease.
Authors: Pepijn de Reus, Kyra Dresen, Ana Oprescu, Kristina Irion, Ans Kolk
Abstract: The digital era has raised many societal challenges, including ICT's rising energy consumption and protecting privacy of personal data processing. This paper considers both aspects in relation to machine learning accuracy in an interdisciplinary exploration. We first present a method to measure the effects of privacy-enhancing techniques on data utility and energy consumption. The environmental-privacy-accuracy trade-offs are discovered through an experimental set-up. We subsequently take a storytelling approach to translate these technical findings to experts in non-ICT fields. We draft two examples for a governmental and auditing setting to contextualise our results. Ultimately, users face the task of optimising their data processing operations in a trade-off between energy, privacy, and accuracy considerations where the impact of their decisions is context-sensitive.
Authors: Daan Caljon, Jente Van Belle, Jeroen Berrevoets, Wouter Verbeke
Abstract: In Influence Maximization (IM), the objective is to -- given a budget -- select the optimal set of entities in a network to target with a treatment so as to maximize the total effect. For instance, in marketing, the objective is to target the set of customers that maximizes the total response rate, resulting from both direct treatment effects on targeted customers and indirect, spillover, effects that follow from targeting these customers. Recently, new methods to estimate treatment effects in the presence of network interference have been proposed. However, the issue of how to leverage these models to make better treatment allocation decisions has been largely overlooked. Traditionally, in Uplift Modeling (UM), entities are ranked according to estimated treatment effect, and the top entities are allocated treatment. Since, in a network context, entities influence each other, the UM ranking approach will be suboptimal. The problem of finding the optimal treatment allocation in a network setting is combinatorial and generally has to be solved heuristically. To fill the gap between IM and UM, we propose OTAPI: Optimizing Treatment Allocation in the Presence of Interference to find solutions to the IM problem using treatment effect estimates. OTAPI consists of two steps. First, a causal estimator is trained to predict treatment effects in a network setting. Second, this estimator is leveraged to identify an optimal treatment allocation by integrating it into classic IM algorithms. We demonstrate that this novel method outperforms classic IM and UM approaches on both synthetic and semi-synthetic datasets.
Authors: Hang Liu, Anna Scaglione
Abstract: Shuffled linear regression (SLR) seeks to estimate latent features through a linear transformation, complicated by unknown permutations in the measurement dimensions. This problem extends traditional least-squares (LS) and Least Absolute Shrinkage and Selection Operator (LASSO) approaches by jointly estimating the permutation, resulting in shuffled LS and shuffled LASSO formulations. Existing methods, constrained by the combinatorial complexity of permutation recovery, often address small-scale cases with limited measurements. In contrast, we focus on large-scale SLR, particularly suited for environments with abundant measurement samples. We propose a spectral matching method that efficiently resolves permutations by aligning spectral components of the measurement and feature covariances. Rigorous theoretical analyses demonstrate that our method achieves accurate estimates in both shuffled LS and shuffled LASSO settings, given a sufficient number of samples. Furthermore, we extend our approach to address simultaneous pose and correspondence estimation in image registration tasks. Experiments on synthetic datasets and real-world image registration scenarios show that our method outperforms existing algorithms in both estimation accuracy and registration performance.
Authors: Wenyue Hua, Mengting Wan, Shashank Vadrevu, Ryan Nadel, Yongfeng Zhang, Chi Wang
Abstract: Agents, as user-centric tools, are increasingly deployed for human task delegation, assisting with a broad spectrum of requests by generating thoughts, engaging with user proxies, and producing action plans. However, agents based on large language models (LLMs) often face substantial planning latency due to two primary factors: the efficiency limitations of the underlying LLMs due to their large size and high demand, and the structural complexity of the agents due to the extensive generation of intermediate thoughts to produce the final output. Given that inefficiency in service provision can undermine the value of automation for users, this paper presents a human-centered efficient agent planning method -- Interactive Speculative Planning -- aiming at enhancing the efficiency of agent planning through both system design and human-AI interaction. Our approach advocates for the co-design of the agent system and user interface, underscoring the importance of an agent system that can fluidly manage user interactions and interruptions. By integrating human interruptions as a fundamental component of the system, we not only make it more user-centric but also expedite the entire process by leveraging human-in-the-loop interactions to provide accurate intermediate steps. Code and data will be released.
Authors: Oytun Demirbilek, Tingying Peng, Alaa Bessadok
Abstract: A morphological brain graph depicting a connectional fingerprint is of paramount importance for charting brain dysconnectivity patterns. Such data often has missing observations due to various reasons such as time-consuming and incomplete neuroimage processing pipelines. Thus, predicting a target brain graph from a source graph is crucial for better diagnosing neurological disorders with minimal data acquisition resources. Many brain graph generative models were proposed for promising results, yet they are mostly based on generative adversarial networks (GAN), which could suffer from mode collapse and require large training datasets. Recent developments in diffusion models address these problems by offering essential properties such as a stable training objective and easy scalability. However, applying a diffusion process to graph edges fails to maintain the topological symmetry of the brain connectivity matrices. To meet these challenges, we propose the Graph Residual Noise Learner Network (Grenol-Net), the first graph diffusion model for predicting a target graph from a source graph.
Authors: Alan Papalia, Yulun Tian, David M. Rosen, Jonathan P. How, John J. Leonard
Abstract: This paper presents an overview of the Burer-Monteiro method (BM), a technique that has been applied to solve robot perception problems to certifiable optimality in real-time. BM is often used to solve semidefinite programming relaxations, which can be used to perform global optimization for non-convex perception problems. Specifically, BM leverages the low-rank structure of typical semidefinite programs to dramatically reduce the computational cost of performing optimization. This paper discusses BM in certifiable perception, with three main objectives: (i) to consolidate information from the literature into a unified presentation, (ii) to elucidate the role of the linear independence constraint qualification (LICQ), a concept not yet well-covered in certifiable perception literature, and (iii) to share practical considerations that are discussed among practitioners but not thoroughly covered in the literature. Our general aim is to offer a practical primer for applying BM towards certifiable perception.
Authors: Krzywda Maciej, {\L}ukasik Szymon, Gandomi H. Amir
Abstract: The present study covers an approach to neural architecture search (NAS) using Cartesian genetic programming (CGP) for the design and optimization of Convolutional Neural Networks (CNNs). In designing artificial neural networks, one crucial aspect of the innovative approach is suggesting a novel neural architecture. Currently used architectures have mostly been developed manually by human experts, which is a time-consuming and error-prone process. In this work, we use pure Genetic Programming Approach to design CNNs, which employs only one genetic operation, i.e., mutation. In the course of preliminary experiments, our methodology yields promising results.
Authors: Nicholas Rober, Jonathan P. How
Abstract: Neural networks (NNs) are becoming increasingly popular in the design of control pipelines for autonomous systems. However, since the performance of NNs can degrade in the presence of out-of-distribution data or adversarial attacks, systems that have NNs in their control pipelines, i.e., neural feedback loops (NFLs), need safety assurances before they can be applied in safety-critical situations. Reachability analysis offers a solution to this problem by calculating reachable sets that bound the possible future states of an NFL and can be checked against dangerous regions of the state space to verify that the system does not violate safety constraints. Since exact reachable sets are generally intractable to calculate, reachable set over approximations (RSOAs) are typically used. The problem with RSOAs is that they can be overly conservative, making it difficult to verify the satisfaction of safety constraints, especially over long time horizons or for highly nonlinear NN control policies. Refinement strategies such as partitioning or symbolic propagation are typically used to limit the conservativeness of RSOAs, but these approaches come with a high computational cost and often can only be used to verify safety for simple reachability problems. This paper presents Constraint-Aware Refinement for Verification (CARV): an efficient refinement strategy that reduces the conservativeness of RSOAs by explicitly using the safety constraints on the NFL to refine RSOAs only where necessary. We demonstrate that CARV can verify the safety of an NFL where other approaches either fail or take up to 60x longer and 40x the memory.
Authors: Divya Patel, Pathik Patel, Ankush Chander, Sourish Dasgupta, Tanmoy Chakraborty
Abstract: Large Language Models (LLMs) have succeeded considerably in In-Context-Learning (ICL) based summarization. However, saliency is subject to the users' specific preference histories. Hence, we need reliable In-Context Personalization Learning (ICPL) capabilities within such LLMs. For any arbitrary LLM to exhibit ICPL, it needs to have the ability to discern contrast in user profiles. A recent study proposed a measure for degree-of-personalization called EGISES for the first time. EGISES measures a model's responsiveness to user profile differences. However, it cannot test if a model utilizes all three types of cues provided in ICPL prompts: (i) example summaries, (ii) user's reading histories, and (iii) contrast in user profiles. To address this, we propose the iCOPERNICUS framework, a novel In-COntext PERsonalization learNIng sCrUtiny of Summarization capability in LLMs that uses EGISES as a comparative measure. As a case-study, we evaluate 17 state-of-the-art LLMs based on their reported ICL performances and observe that 15 models' ICPL degrades (min: 1.6%; max: 3.6%) when probed with richer prompts, thereby showing lack of true ICPL.
Authors: Qiushuo Hou, Sangwoo Park, Matteo Zecchin, Yunlong Cai, Guanding Yu, Osvaldo Simeone
Abstract: In modern wireless network architectures, such as Open Radio Access Network (O-RAN), the operation of the radio access network (RAN) is managed by applications, or apps for short, deployed at intelligent controllers. These apps are selected from a given catalog based on current contextual information. For instance, a scheduling app may be selected on the basis of current traffic and network conditions. Once an app is chosen and run, it is no longer possible to directly test the performance that would have been obtained with another app. This test, however, would be potentially valuable to monitor and optimize the network operation. With this goal in mind, this paper addresses the "what-if" problem of estimating the values of key performance indicators (KPIs) that would have been obtained if a different app had been implemented by the RAN. To this end, we propose a conformal-prediction-based counterfactual analysis method for wireless systems that provides reliable "error bars" for the estimated KPIs, containing the true KPIs with a user-defined probability, despite the inherent covariate shift between logged and test data. Experimental results for medium access control-layer apps and for physical-layer apps demonstrate the merits of the proposed method.
Authors: Jun Jiang, Raymond Moore, Brenna Novotny, Leo Liu, Zachary Fogarty, Ray Guo, Markovic Svetomir, Chen Wang
Abstract: Histopathological imaging is vital for cancer research and clinical practice, with multiplexed Immunofluorescence (MxIF) and Hematoxylin and Eosin (H&E) providing complementary insights. However, aligning different stains at the cell level remains a challenge due to modality differences. In this paper, we present a novel framework for multimodal image alignment using cell segmentation outcomes. By treating cells as point sets, we apply Coherent Point Drift (CPD) for initial alignment and refine it with Graph Matching (GM). Evaluated on ovarian cancer tissue microarrays (TMAs), our method achieves high alignment accuracy, enabling integration of cell-level features across modalities and generating virtual H&E images from MxIF data for enhanced clinical interpretation.
Authors: Haiyan Zhao, Heng Zhao, Bo Shen, Ali Payani, Fan Yang, Mengnan Du
Abstract: Probing learned concepts in large language models (LLMs) is crucial for understanding how semantic knowledge is encoded internally. Training linear classifiers on probing tasks is a principle approach to denote the vector of a certain concept in the representation space. However, the single vector identified for a concept varies with both data and training, making it less robust and weakening its effectiveness in real-world applications. To address this challenge, we propose an approach to approximate the subspace representing a specific concept. Built on linear probing classifiers, we extend the concept vectors into Gaussian Concept Subspace (GCS). We demonstrate GCS's effectiveness through measuring its faithfulness and plausibility across multiple LLMs with different sizes and architectures. Additionally, we use representation intervention tasks to showcase its efficacy in real-world applications such as emotion steering. Experimental results indicate that GCS concept vectors have the potential to balance steering performance and maintaining the fluency in natural language generation tasks.
Authors: Kush Dubey
Abstract: Few-shot learning benchmarks are critical for evaluating modern NLP techniques. It is possible, however, that benchmarks favor methods which easily make use of unlabeled text, because researchers can use unlabeled text from the test set to pretrain their models. Given the dearth of research on this potential problem, we run experiments to quantify the bias caused by pretraining on unlabeled test set text instead of on unlabeled, independently drawn text. Controlled few-shot and zero-shot experiments on 25 classification tasks and 3 language models -- BERT, GPT-2, and Mistral 7B -- do not find evidence of overoptimism. Furthermore, we demonstrate the importance of repeated subsampling when studying few-shot text classification, and recommend that few-shot learning benchmarks include multiple training folds. Code and data are available at https://github.com/kddubey/pretrain-on-test/.
Authors: Siyeop Yoon, Rui Hu, Yuang Wang, Matthew Tivnan, Young-don Son, Dufan Wu, Xiang Li, Kyungsang Kim, Quanzheng Li
Abstract: PET imaging is a powerful modality offering quantitative assessments of molecular and physiological processes. The necessity for PET denoising arises from the intrinsic high noise levels in PET imaging, which can significantly hinder the accurate interpretation and quantitative analysis of the scans. With advances in deep learning techniques, diffusion model-based PET denoising techniques have shown remarkable performance improvement. However, these models often face limitations when applied to volumetric data. Additionally, many existing diffusion models do not adequately consider the unique characteristics of PET imaging, such as its 3D volumetric nature, leading to the potential loss of anatomic consistency. Our Conditional Score-based Residual Diffusion (CSRD) model addresses these issues by incorporating a refined score function and 3D patch-wise training strategy, optimizing the model for efficient volumetric PET denoising. The CSRD model significantly lowers computational demands and expedites the denoising process. By effectively integrating volumetric data from PET and MRI scans, the CSRD model maintains spatial coherence and anatomical detail. Lastly, we demonstrate that the CSRD model achieves superior denoising performance in both qualitative and quantitative evaluations while maintaining image details and outperforms existing state-of-the-art methods.
Authors: Tim Beyer, Angela Dai
Abstract: The automated creation of accurate musical notation from an expressive human performance is a fundamental task in computational musicology. To this end, we present an end-to-end deep learning approach that constructs detailed musical scores directly from real-world piano performance-MIDI files. We introduce a modern transformer-based architecture with a novel tokenized representation for symbolic music data. Framing the task as sequence-to-sequence translation rather than note-wise classification reduces alignment requirements and annotation costs, while allowing the prediction of more concise and accurate notation. To serialize symbolic music data, we design a custom tokenization stage based on compound tokens that carefully quantizes continuous values. This technique preserves more score information while reducing sequence lengths by $3.5\times$ compared to prior approaches. Using the transformer backbone, our method demonstrates better understanding of note values, rhythmic structure, and details such as staff assignment. When evaluated end-to-end using transcription metrics such as MUSTER, we achieve significant improvements over previous deep learning approaches and complex HMM-based state-of-the-art pipelines. Our method is also the first to directly predict notational details like trill marks or stem direction from performance data. Code and models are available at https://github.com/TimFelixBeyer/MIDI2ScoreTransformer
URLs: https://github.com/TimFelixBeyer/MIDI2ScoreTransformer
Authors: Qin Li, Maria Oprea, Li Wang, Yunan Yang
Abstract: Inverse problems in physical or biological sciences often involve recovering an unknown parameter that is random. The sought-after quantity is a probability distribution of the unknown parameter, that produces data that aligns with measurements. Consequently, these problems are naturally framed as stochastic inverse problems. In this paper, we explore three aspects of this problem: direct inversion, variational formulation with regularization, and optimization via gradient flows, drawing parallels with deterministic inverse problems. A key difference from the deterministic case is the space in which we operate. Here, we work within probability space rather than Euclidean or Sobolev spaces, making tools from measure transport theory necessary for the study. Our findings reveal that the choice of metric -- both in the design of the loss function and in the optimization process -- significantly impacts the stability and properties of the optimizer.
Authors: Qi Wu, Zipeng Fu, Xuxin Cheng, Xiaolong Wang, Chelsea Finn
Abstract: Learning-based methods have achieved strong performance for quadrupedal locomotion. However, several challenges prevent quadrupeds from learning helpful indoor skills that require interaction with environments and humans: lack of end-effectors for manipulation, limited semantic understanding using only simulation data, and low traversability and reachability in indoor environments. We present a system for quadrupedal mobile manipulation in indoor environments. It uses a front-mounted gripper for object manipulation, a low-level controller trained in simulation using egocentric depth for agile skills like climbing and whole-body tilting, and pre-trained vision-language models (VLMs) with a third-person fisheye and an egocentric RGB camera for semantic understanding and command generation. We evaluate our system in two unseen environments without any real-world data collection or training. Our system can zero-shot generalize to these environments and complete tasks, like following user's commands to fetch a randomly placed stuff toy after climbing over a queen-sized bed, with a 60% success rate. Project website: https://helpful-doggybot.github.io/
Authors: Hamid Jafarkhani, Hossein Maleki, Mojtaba Vaezi
Abstract: Next-generation multiple access (NGMA) serves as an umbrella term for transmission schemes distinct from conventional orthogonal methods. A key candidate of NGMA, non-orthogonal multiple access (NOMA), emerges as a solution to enhance connectivity by allowing multiple users to share time, frequency, and space concurrently. However, NOMA faces challenges in implementation, particularly in canceling inter-user interference. In this paper, we discuss the principles behind NOMA and review conventional NOMA methods. Then, to address these challenges, we present asynchronous transmission and interference-aware modulation techniques, enabling decoding without successive interference cancellation. The goal is to design constellations that dynamically adapt to interference, minimizing bit error rates (BERs) and enhancing user throughput in the presence of inter-user, inter-carrier, and inter-cell interference. The traditional link between minimizing BER and increasing spectral efficiency is explored, with deep autoencoders for end-to-end communication emerging as a potential solution to improve BERs. Interference-aware modulation can revolutionize constellation design for non-orthogonal channels. Rate-splitting multiple access (RSMA) is another promising interference management technique in multi-user systems. In addition to addressing challenges in finite-alphabet NOMA, this paper offers new insights and provides an overview of code-domain NOMA, trellis-coded NOMA, and RSMA as key NGMA candidates. We also discuss the evolution of channel coding toward low-latency communication and examine modulation and coding schemes in 5G networks. Finally, we highlight future research directions, emphasizing their importance for realizing NOMA from concept to functional technology.
Authors: Rithvik Prakki
Abstract: Active inference is a mathematical framework for understanding how agents (biological or artificial) interact with their environments, enabling continual adaptation and decision-making. It combines Bayesian inference and free energy minimization to model perception, action, and learning in uncertain and dynamic contexts. Unlike reinforcement learning, active inference integrates exploration and exploitation seamlessly by minimizing expected free energy. In this paper, we present a continual learning framework for agents operating in discrete time environments, using active inference as the foundation. We derive the mathematical formulations of variational and expected free energy and apply them to the design of a self-learning research agent. This agent updates its beliefs and adapts its actions based on new data without manual intervention. Through experiments in changing environments, we demonstrate the agent's ability to relearn and refine its models efficiently, making it suitable for complex domains like finance and healthcare. The paper concludes by discussing how the proposed framework generalizes to other systems, positioning active inference as a flexible approach for adaptive AI.
Authors: Vinayak Arannil, Sourav Sanjukta Bhabesh, Neha Narwal, Sai Nikhil Thirandas, Darren Yow-Bang Wang, Graham Horwood, Alex Anto Chirayath, Gouri Pandeshwar
Abstract: Large Language Models (LLMs) have shown remarkable ability to generalize effectively across numerous industry domains while executing a range of tasks. Many of these competencies are obtained from the data utilized during the pre-training phase of the Language Models (LMs). However, these models exhibit limitations when tasked with performing in specialized or low-resource industry domains. More recent approaches use LLMs for generating domain-specific synthetic data but most often they lack in truthfulness and complexity. Alternatively, in cases where domain data is available like healthcare and finance most of the LMs are proprietary necessitating the need for a scalable method to curate real world industry specific pre-training data. In this work, we propose an automated and scalable framework - DoPAMine:Domain-specific Pre-training Adaptation from seed-guided data Mining, to mine domain specific training data from a large data corpus for domain adaptation of a LM. The framework leverages the parametric knowledge of a LLM to generate diverse and representative seed data tailored to a specific domain which is then used to mine real world data from a large data corpus like Common Crawl. We evaluated our framework's performance in the continual pre-training (CPT) setting by training two domain specific 7B parameter LMs in healthcare and finance with data mined via DoPAMine. Our experiments show that DoPAMine boosts the performance of pre-trained LLMs on average by 4.9% and 5.1% in zero-shot and 5-shot settings respectively on healthcare tasks from MMLU, MedQA, MedMCQA and PubMedQA datasets, and 2.9% and 6.7% for zero-shot and 5-shot settings respectively on finance tasks from FiQA-SA, FPB and Headlines datasets when compared to the baseline.
Authors: Aleyna K\"ut\"uk, Tevfik Metin Sezgin
Abstract: Scene sketch semantic segmentation is a crucial task for various applications including sketch-to-image retrieval and scene understanding. Existing sketch segmentation methods treat sketches as bitmap images, leading to the loss of temporal order among strokes due to the shift from vector to image format. Moreover, these methods struggle to segment objects from categories absent in the training data. In this paper, we propose a Class-Agnostic Visio-Temporal Network (CAVT) for scene sketch semantic segmentation. CAVT employs a class-agnostic object detector to detect individual objects in a scene and groups the strokes of instances through its post-processing module. This is the first approach that performs segmentation at both the instance and stroke levels within scene sketches. Furthermore, there is a lack of free-hand scene sketch datasets with both instance and stroke-level class annotations. To fill this gap, we collected the largest Free-hand Instance- and Stroke-level Scene Sketch Dataset (FrISS) that contains 1K scene sketches and covers 403 object classes with dense annotations. Extensive experiments on FrISS and other datasets demonstrate the superior performance of our method over state-of-the-art scene sketch segmentation models. The code and dataset will be made public after acceptance.
Authors: Yuchen Chu, Zeshi Yang
Abstract: In this work, we present a data-driven framework for generating diverse in-betweening motions for kinematic characters. Our approach injects dynamic conditions and explicit motion controls into the procedure of motion transitions. Notably, this integration enables a finer-grained spatial-temporal control by allowing users to impart additional conditions, such as duration, path, style, etc., into the in-betweening process. We demonstrate that our in-betweening approach can synthesize both locomotion and unstructured motions, enabling rich, versatile, and high-quality animation generation.
Authors: Tuan Do (UCLA), Bernie Boscoe (Southern Oregon University), Evan Jones (UCLA), Yun Qi Li (UCLA, University of Washington), Kevin Alfaro (UCLA)
Abstract: We present a dataset built for machine learning applications consisting of galaxy photometry, images, spectroscopic redshifts, and structural properties. This dataset comprises 286,401 galaxy images and photometry from the Hyper-Suprime-Cam Survey PDR2 in five imaging filters ($g,r,i,z,y$) with spectroscopically confirmed redshifts as ground truth. Such a dataset is important for machine learning applications because it is uniform, consistent, and has minimal outliers but still contains a realistic range of signal-to-noise ratios. We make this dataset public to help spur development of machine learning methods for the next generation of surveys such as Euclid and LSST. The aim of GalaxiesML is to provide a robust dataset that can be used not only for astrophysics but also for machine learning, where image properties cannot be validated by the human eye and are instead governed by physical laws. We describe the challenges associated with putting together a dataset from publicly available archives, including outlier rejection, duplication, establishing ground truths, and sample selection. This is one of the largest public machine learning-ready training sets of its kind with redshifts ranging from 0.01 to 4. The redshift distribution of this sample peaks at redshift of 1.5 and falls off rapidly beyond redshift 2.5. We also include an example application of this dataset for redshift estimation, demonstrating that using images for redshift estimation produces more accurate results compared to using photometry alone. For example, the bias in redshift estimate is a factor of 10 lower when using images between redshift of 0.1 to 1.25 compared to photometry alone. Results from dataset such as this will help inform us on how to best make use of data from the next generation of galaxy surveys.
Authors: Zeda Xu, John Liechty, Sebastian Benthall, Nicholas Skar-Gislinge, Christopher McComb
Abstract: Volatility, which indicates the dispersion of returns, is a crucial measure of risk and is hence used extensively for pricing and discriminating between different financial investments. As a result, accurate volatility prediction receives extensive attention. The Generalized Autoregressive Conditional Heteroscedasticity (GARCH) model and its succeeding variants are well established models for stock volatility forecasting. More recently, deep learning models have gained popularity in volatility prediction as they demonstrated promising accuracy in certain time series prediction tasks. Inspired by Physics-Informed Neural Networks (PINN), we constructed a new, hybrid Deep Learning model that combines the strengths of GARCH with the flexibility of a Long Short-Term Memory (LSTM) Deep Neural Network (DNN), thus capturing and forecasting market volatility more accurately than either class of models are capable of on their own. We refer to this novel model as a GARCH-Informed Neural Network (GINN). When compared to other time series models, GINN showed superior out-of-sample prediction performance in terms of the Coefficient of Determination ($R^2$), Mean Squared Error (MSE), and Mean Absolute Error (MAE).
Authors: Laura Bravo-S\'anchez, Jaewoo Heo, Zhenzhen Weng, Kuan-Chieh Wang, Serena Yeung-Levy
Abstract: Social dynamics in close human interactions pose significant challenges for Human Mesh Estimation (HME), particularly due to the complexity of physical contacts and the scarcity of training data. Addressing these challenges, we introduce a novel data generation method that utilizes Large Vision Language Models (LVLMs) to annotate contact maps which guide test-time optimization to produce paired image and pseudo-ground truth meshes. This methodology not only alleviates the annotation burden but also enables the assembly of a comprehensive dataset specifically tailored for close interactions in HME. Our Ask Pose Unite (APU) dataset, comprising over 6.2k human mesh pairs in contact covering diverse interaction types, is curated from images depicting naturalistic person-to-person scenes. We empirically show that using our dataset to train a diffusion-based contact prior, used as guidance during optimization, improves mesh estimation on unseen interactions. Our work addresses longstanding challenges of data scarcity for close interactions in HME enhancing the field's capabilities of handling complex interaction scenarios.
Authors: Onur Vural, Shah Muhammad Hamdi, Soukaina Filali Boubrahimi
Abstract: Major solar flares are abrupt surges in the Sun's magnetic flux, presenting significant risks to technological infrastructure. In view of this, effectively predicting major flares from solar active region magnetic field data through machine learning methods becomes highly important in space weather research. Magnetic field data can be represented in multivariate time series modality where the data displays an extreme class imbalance due to the rarity of major flare events. In time series classification-based flare prediction, the use of contrastive representation learning methods has been relatively limited. In this paper, we introduce CONTREX, a novel contrastive representation learning approach for multivariate time series data, addressing challenges of temporal dependencies and extreme class imbalance. Our method involves extracting dynamic features from the multivariate time series instances, deriving two extremes from positive and negative class feature vectors that provide maximum separation capability, and training a sequence representation embedding module with the original multivariate time series data guided by our novel contrastive reconstruction loss to generate embeddings aligned with the extreme points. These embeddings capture essential time series characteristics and enhance discriminative power. Our approach shows promising solar flare prediction results on the Space Weather Analytics for Solar Flares (SWAN-SF) multivariate time series benchmark dataset against baseline methods.
Authors: Lilac Atassi
Abstract: Recent music generation methods based on transformers have a context window of up to a minute. The music generated by these methods are largely unstructured beyond the context window. With a longer context window, learning long scale structures from musical data is a prohibitively challenging problem. This paper proposes integrating a text-to-music model with a large language model to generate music with form. We discuss our solutions to the challenges of such integration. The experimental results show that the proposed method can generate 2.5-minute-long music that is highly structured, strongly organized, and cohesive.
Authors: James Bockman, Matthew Howe, Adrian Orenstein, Feras Dayoub
Abstract: Autonomous racing demands safe control of vehicles at their physical limits for extended periods of time, providing insights into advanced vehicle safety systems which increasingly rely on intervention provided by vehicle autonomy. Participation in this field carries with it a high barrier to entry. Physical platforms and their associated sensor suites require large capital outlays before any demonstrable progress can be made. Simulators allow researches to develop soft autonomous systems without purchasing a platform. However, currently available simulators lack visual and dynamic fidelity, can still be expensive to buy, lack customisation, and are difficult to use. AARK provides three packages, ACI, ACDG, and ACMPC. These packages enable research into autonomous control systems in the demanding environment of racing to bring more people into the field and improve reproducibility: ACI provides researchers with a computer vision-friendly interface to Assetto Corsa for convenient comparison and evaluation of autonomous control solutions; ACDG enables generation of depth, normal and semantic segmentation data for training computer vision models to use in perception systems; and ACMPC gives newcomers to the field a modular full-stack autonomous control solution, capable of controlling vehicles to build from. AARK aims to unify and democratise research into a field critical to providing safer roads and trusted autonomous systems.
Authors: Youngjoon Lee, Taehyun Park, Yeongjoon Kang, Jonghoe Kim, Joonhyuk Kang
Abstract: Integrating hyperscale AI into national defense modeling and simulation (M&S) is crucial for enhancing strategic and operational capabilities. We explore how hyperscale AI can revolutionize defense M\&S by providing unprecedented accuracy, speed, and the ability to simulate complex scenarios. Countries such as the United States and China are at the forefront of adopting these technologies and are experiencing varying degrees of success. Maximizing the potential of hyperscale AI necessitates addressing critical challenges, such as closed networks, long-tail data, complex decision-making, and a shortage of experts. Future directions emphasize the adoption of domestic foundation models, the investment in various GPUs / NPUs, the utilization of big tech services, and the use of open source software. These initiatives will enhance national security, maintain competitive advantages, and promote broader technological and economic progress. With this blueprint, the Republic of Korea can strengthen its defense capabilities and stay ahead of the emerging threats of modern warfare.
Authors: Xiao Wang, Fuling Wang, Yuehang Li, Qingchuan Ma, Shiao Wang, Bo Jiang, Chuanfu Li, Jin Tang
Abstract: X-ray image-based medical report generation (MRG) is a pivotal area in artificial intelligence which can significantly reduce diagnostic burdens and patient wait times. Despite significant progress, we believe that the task has reached a bottleneck due to the limited benchmark datasets and the existing large models' insufficient capability enhancements in this specialized domain. Specifically, the recently released CheXpert Plus dataset lacks comparative evaluation algorithms and their results, providing only the dataset itself. This situation makes the training, evaluation, and comparison of subsequent algorithms challenging. Thus, we conduct a comprehensive benchmarking of existing mainstream X-ray report generation models and large language models (LLMs), on the CheXpert Plus dataset. We believe that the proposed benchmark can provide a solid comparative basis for subsequent algorithms and serve as a guide for researchers to quickly grasp the state-of-the-art models in this field. More importantly, we propose a large model for the X-ray image report generation using a multi-stage pre-training strategy, including self-supervised autoregressive generation and Xray-report contrastive learning, and supervised fine-tuning. Extensive experimental results indicate that the autoregressive pre-training based on Mamba effectively encodes X-ray images, and the image-text contrastive pre-training further aligns the feature spaces, achieving better experimental results. Source code can be found on \url{https://github.com/Event-AHU/Medical_Image_Analysis}.
Authors: Hongchao Shu, Mingxu Liu, Lalithkumar Seenivasan, Suxi Gu, Ping-Cheng Ku, Jonathan Knopf, Russell Taylor, Mathias Unberath
Abstract: Arthroscopy is a minimally invasive surgical procedure used to diagnose and treat joint problems. The clinical workflow of arthroscopy typically involves inserting an arthroscope into the joint through a small incision, during which surgeons navigate and operate largely by relying on their visual assessment through the arthroscope. However, the arthroscope's restricted field of view and lack of depth perception pose challenges in navigating complex articular structures and achieving surgical precision during procedures. Aiming at enhancing intraoperative awareness, we present a robust pipeline that incorporates simultaneous localization and mapping, depth estimation, and 3D Gaussian splatting to realistically reconstruct intra-articular structures solely based on monocular arthroscope video. Extending 3D reconstruction to Augmented Reality (AR) applications, our solution offers AR assistance for articular notch measurement and annotation anchoring in a human-in-the-loop manner. Compared to traditional Structure-from-Motion and Neural Radiance Field-based methods, our pipeline achieves dense 3D reconstruction and competitive rendering fidelity with explicit 3D representation in 7 minutes on average. When evaluated on four phantom datasets, our method achieves RMSE = 2.21mm reconstruction error, PSNR = 32.86 and SSIM = 0.89 on average. Because our pipeline enables AR reconstruction and guidance directly from monocular arthroscopy without any additional data and/or hardware, our solution may hold the potential for enhancing intraoperative awareness and facilitating surgical precision in arthroscopy. Our AR measurement tool achieves accuracy within 1.59 +/- 1.81mm and the AR annotation tool achieves a mIoU of 0.721.
Authors: Donghee Lee, Hye-Sung Lee, Jaeok Yi
Abstract: Deep neural network architectures often consist of repetitive structural elements. We introduce a new approach that reveals these patterns and can be broadly applied to the study of deep learning. Similar to how a power strip helps untangle and organize complex cable connections, this approach treats neurons as additional degrees of freedom in interactions, simplifying the structure and enhancing the intuitive understanding of interactions within deep neural networks. Furthermore, it reveals the translational symmetry of deep neural networks, which simplifies the application of the renormalization group transformation - a method that effectively analyzes the scaling behavior of the system. By utilizing translational symmetry and renormalization group transformations, we can analyze critical phenomena. This approach may open new avenues for studying deep neural networks using statistical physics.
Authors: Zhi-Yu Jou, Su-Yun Huang, Hung Hung, Shinto Eguchi
Abstract: Principal component analysis (PCA) is a widely used technique for dimension reduction. As datasets continue to grow in size, distributed-PCA (DPCA) has become an active research area. A key challenge in DPCA lies in efficiently aggregating results across multiple machines or computing nodes due to computational overhead. Fan et al. (2019) introduced a pioneering DPCA method to estimate the leading rank-$r$ eigenspace, aggregating local rank-$r$ projection matrices by averaging. However, their method does not utilize eigenvalue information. In this article, we propose a novel DPCA method that incorporates eigenvalue information to aggregate local results via the matrix $\beta$-mean, which we call $\beta$-DPCA. The matrix $\beta$-mean offers a flexible and robust aggregation method through the adjustable choice of $\beta$ values. Notably, for $\beta=1$, it corresponds to the arithmetic mean; for $\beta=-1$, the harmonic mean; and as $\beta \to 0$, the geometric mean. Moreover, the matrix $\beta$-mean is shown to associate with the matrix $\beta$-divergence, a subclass of the Bregman matrix divergence, to support the robustness of $\beta$-DPCA. We also study the stability of eigenvector ordering under eigenvalue perturbation for $\beta$-DPCA. The performance of our proposal is evaluated through numerical studies.
Authors: Mahamudul Hasan
Abstract: Recommender systems are designed to suggest items based on user preferences, helping users navigate the vast amount of information available on the internet. Given the overwhelming content, outlier detection has emerged as a key research area in recommender systems. It involves identifying unusual or suspicious patterns in user behavior. However, existing studies in this field face several challenges, including the limited universality of algorithms, difficulties in selecting users, and a lack of optimization. In this paper, we propose an approach that addresses these challenges by employing various clustering algorithms. Specifically, we utilize a user-user matrix-based clustering technique to detect outliers. By constructing a user-user matrix, we can identify suspicious users in the system. Both local and global outliers are detected to ensure comprehensive analysis. Our experimental results demonstrate that this approach significantly improves the accuracy of outlier detection in recommender systems.
Authors: Yi Xiong, Hao Wu, Changxu Shao, Ziqing Wang, Rui Zhang, Yuhong Guo, Junping Zhao, Ke Zhang, Zhenxuan Pan
Abstract: The expanding context windows in large language models (LLMs) have greatly enhanced their capabilities in various applications, but they also introduce significant challenges in maintaining low latency, particularly in Time to First Token (TTFT). This paper identifies that the sharp rise in TTFT as context length increases is predominantly driven by queuing delays, which are caused by the growing demands for GPU Key-Value (KV) cache allocation clashing with the limited availability of KV cache blocks. To address this issue, we propose LayerKV, a simple yet effective plug-in method that effectively reduces TTFT without requiring additional hardware or compromising output performance, while seamlessly integrating with existing parallelism strategies and scheduling techniques. Specifically, LayerKV introduces layer-wise KV block allocation, management, and offloading for fine-grained control over system memory, coupled with an SLO-aware scheduler to optimize overall Service Level Objectives (SLOs). Comprehensive evaluations on representative models, ranging from 7B to 70B parameters, across various GPU configurations, demonstrate that LayerKV improves TTFT latency up to 11x and reduces SLO violation rates by 28.7\%, significantly enhancing the user experience
Authors: Hui Ma, Kai Chen
Abstract: Nonlinear data visualization using t-distributed stochastic neighbor embedding (t-SNE) enables the representation of complex single-cell transcriptomic landscapes in two or three dimensions to depict biological populations accurately. However, t-SNE often fails to account for uncertainties in the original dataset, leading to misleading visualizations where cell subsets with noise appear indistinguishable. To address these challenges, we introduce uncertainty-aware t-SNE (Ut-SNE), a noise-defending visualization tool tailored for uncertain single-cell RNA-seq data. By creating a probabilistic representation for each sample, Our Ut-SNE accurately incorporates noise about transcriptomic variability into the visual interpretation of single-cell RNA sequencing data, revealing significant uncertainties in transcriptomic variability. Through various examples, we showcase the practical value of Ut-SNE and underscore the significance of incorporating uncertainty awareness into data visualization practices. This versatile uncertainty-aware visualization tool can be easily adapted to other scientific domains beyond single-cell RNA sequencing, making them valuable resources for high-dimensional data analysis.
Authors: Elise \"Ozalp, Luca Magri
Abstract: Partial differential equations, and their chaotic solutions, are pervasive in the modelling of complex systems in engineering, science, and beyond. Data-driven methods can find solutions to partial differential equations with a divide-and-conquer strategy: The solution is sought in a latent space, on which the temporal dynamics are inferred (``latent-space'' approach). This is achieved by, first, compressing the data with an autoencoder, and, second, inferring the temporal dynamics with recurrent neural networks. The overarching goal of this paper is to show that a latent-space approach can not only infer the solution of a chaotic partial differential equation, but it can also predict the stability properties of the physical system. First, we employ the convolutional autoencoder echo state network (CAE-ESN) on the chaotic Kuramoto-Sivashinsky equation for various chaotic regimes. We show that the CAE-ESN (i) finds a low-dimensional latent-space representation of the observations and (ii) accurately infers the Lyapunov exponents and covariant Lyapunov vectors (CLVs) in this low-dimensional manifold for different attractors. Second, we extend the CAE-ESN to a turbulent flow, comparing the Lyapunov spectrum to estimates obtained from Jacobian-free methods. A latent-space approach based on the CAE-ESN effectively produces a latent space that preserves the key properties of the chaotic system, such as Lyapunov exponents and CLVs, thus retaining the geometric structure of the attractor. The latent-space approach based on the CAE-ESN is a reduced-order model that accurately predicts the dynamics of the chaotic system, or, alternatively, it can be used to infer stability properties of chaotic systems from data.
Authors: Diogo Pernes, Gon\c{c}alo M. Correia, Afonso Mendes
Abstract: Cross-lingual summarization aims to bridge language barriers by summarizing documents in different languages. However, ensuring semantic coherence across languages is an overlooked challenge and can be critical in several contexts. To fill this gap, we introduce multi-target cross-lingual summarization as the task of summarizing a document into multiple target languages while ensuring that the produced summaries are semantically similar. We propose a principled re-ranking approach to this problem and a multi-criteria evaluation protocol to assess semantic coherence across target languages, marking a first step that will hopefully stimulate further research on this problem.
Authors: Krishna Chaitanya, Pablo F. Damasceno, Shreyas Fadnavis, Pooya Mobadersany, Chaitanya Parmar, Emily Scherer, Natalia Zemlianskaia, Lindsey Surace, Louis R. Ghanem, Oana Gabriela Cula, Tommaso Mansi, Kristopher Standish
Abstract: Accurate assessment of disease severity from endoscopy videos in ulcerative colitis (UC) is crucial for evaluating drug efficacy in clinical trials. Severity is often measured by the Mayo Endoscopic Subscore (MES) and Ulcerative Colitis Endoscopic Index of Severity (UCEIS) score. However, expert MES/UCEIS annotation is time-consuming and susceptible to inter-rater variability, factors addressable by automation. Automation attempts with frame-level labels face challenges in fully-supervised solutions due to the prevalence of video-level labels in clinical trials. CNN-based weakly-supervised models (WSL) with end-to-end (e2e) training lack generalization to new disease scores and ignore spatio-temporal information crucial for accurate scoring. To address these limitations, we propose "Arges", a deep learning framework that utilizes a transformer with positional encoding to incorporate spatio-temporal information from frame features to estimate disease severity scores in endoscopy video. Extracted features are derived from a foundation model (ArgesFM), pre-trained on a large diverse dataset from multiple clinical trials (61M frames, 3927 videos). We evaluate four UC disease severity scores, including MES and three UCEIS component scores. Test set evaluation indicates significant improvements, with F1 scores increasing by 4.1% for MES and 18.8%, 6.6%, 3.8% for the three UCEIS component scores compared to state-of-the-art methods. Prospective validation on previously unseen clinical trial data further demonstrates the model's successful generalization.
Authors: Jonathan Ott, Jonas Pirkl, Maximilian Stahlke, Tobias Feigl, Christopher Mutschler
Abstract: Artificial Intelligence (AI)-based radio fingerprinting (FP) outperforms classic localization methods in propagation environments with strong multipath effects. However, the model and data orchestration of FP are time-consuming and costly, as it requires many reference positions and extensive measurement campaigns for each environment. Instead, modern unsupervised and self-supervised learning schemes require less reference data for localization, but either their accuracy is low or they require additional sensor information, rendering them impractical. In this paper we propose a self-supervised learning framework that pre-trains a general transformer (TF) neural network on 5G channel measurements that we collect on-the-fly without expensive equipment. Our novel pretext task randomly masks and drops input information to learn to reconstruct it. So, it implicitly learns the spatiotemporal patterns and information of the propagation environment that enable FP-based localization. Most interestingly, when we optimize this pre-trained model for localization in a given environment, it achieves the accuracy of state-of-the-art methods but requires ten times less reference data and significantly reduces the time from training to operation.
Authors: John-Joseph Brady, Yuhui Luo, Wenwu Wang, V\'ictor Elvira, Yunpeng Li
Abstract: We propose a sequential Monte Carlo algorithm for parameter learning when the studied model exhibits random discontinuous jumps in behaviour. To facilitate the learning of high dimensional parameter sets, such as those associated to neural networks, we adopt the emerging framework of differentiable particle filtering, wherein parameters are trained by gradient descent. We design a new differentiable interacting multiple model particle filter to be capable of learning the individual behavioural regimes and the model which controls the jumping simultaneously. In contrast to previous approaches, our algorithm allows control of the computational effort assigned per regime whilst using the probability of being in a given regime to guide sampling. Furthermore, we develop a new gradient estimator that has a lower variance than established approaches and remains fast to compute, for which we prove consistency. We establish new theoretical results of the presented algorithms and demonstrate superior numerical performance compared to the previous state-of-the-art algorithms.
Authors: Saswati Bhattacharjee, Anirban Sinha, Chinwe Ekenna
Abstract: This paper presents the Language Aided Subset Sampling Based Motion Planner (LASMP), a system that helps mobile robots plan their movements by using natural language instructions. LASMP uses a modified version of the Rapidly Exploring Random Tree (RRT) method, which is guided by user-provided commands processed through a language model (RoBERTa). The system improves efficiency by focusing on specific areas of the robot's workspace based on these instructions, making it faster and less resource-intensive. Compared to traditional RRT methods, LASMP reduces the number of nodes needed by 55% and cuts random sample queries by 80%, while still generating safe, collision-free paths. Tested in both simulated and real-world environments, LASMP has shown better performance in handling complex indoor scenarios. The results highlight the potential of combining language processing with motion planning to make robot navigation more efficient.
Authors: Moein Khajehnejad, Forough Habibollahi, Ahmad Khajehnejad, Brett J. Kagan, Adeel Razi
Abstract: We introduce Temporal Attention-enhanced Variational Graph Recurrent Neural Network (TAVRNN), a novel framework for analyzing the evolving dynamics of neuronal connectivity networks in response to external stimuli and behavioral feedback. TAVRNN captures temporal changes in network structure by modeling sequential snapshots of neuronal activity, enabling the identification of key connectivity patterns. Leveraging temporal attention mechanisms and variational graph techniques, TAVRNN uncovers how connectivity shifts align with behavior over time. We validate TAVRNN on two datasets: in vivo calcium imaging data from freely behaving rats and novel in vitro electrophysiological data from the DishBrain system, where biological neurons control a simulated environment during the game of pong. We show that TAVRNN outperforms previous baseline models in classification, clustering tasks and computational efficiency while accurately linking connectivity changes to performance variations. Crucially, TAVRNN reveals that high game performance in the DishBrain system correlates with the alignment of sensory and motor subregion channels, a relationship not evident in earlier models. This framework represents the first application of dynamic graph representation of electrophysiological (neuronal) data from DishBrain system, providing insights into the reorganization of neuronal networks during learning. TAVRNN's ability to differentiate between neuronal states associated with successful and unsuccessful learning outcomes, offers significant implications for real-time monitoring and manipulation of biological neuronal systems.
Authors: Mazen Balat, Rewaa Awaad, Hend Adel, Ahmed B. Zaky, Salah A. Aly
Abstract: This paper presents an Arabic Alphabet Sign Language recognition approach, using deep learning methods in conjunction with transfer learning and transformer-based models. We study the performance of the different variants on two publicly available datasets, namely ArSL2018 and AASL. This task will make full use of state-of-the-art CNN architectures like ResNet50, MobileNetV2, and EfficientNetB7, and the latest transformer models such as Google ViT and Microsoft Swin Transformer. These pre-trained models have been fine-tuned on the above datasets in an attempt to capture some unique features of Arabic sign language motions. Experimental results present evidence that the suggested methodology can receive a high recognition accuracy, by up to 99.6\% and 99.43\% on ArSL2018 and AASL, respectively. That is far beyond the previously reported state-of-the-art approaches. This performance opens up even more avenues for communication that may be more accessible to Arabic-speaking deaf and hard-of-hearing, and thus encourages an inclusive society.
Authors: Joseph A. P. Quino, Diego A. C. Cardenas, Marcelo A. F. Toledo, Felipe M. Dias, Estela Ribeiro, Jose E. Krieger, Marco A. Gutierrez
Abstract: Accurate sleep stage classification is crucial for diagnosing sleep disorders and evaluating sleep quality. While polysomnography (PSG) remains the gold standard, photoplethysmography (PPG) is more practical due to its affordability and widespread use in wearable devices. However, state-of-the-art sleep staging methods often require prolonged continuous signal acquisition, making them impractical for wearable devices due to high energy consumption. Shorter signal acquisitions are more feasible but less accurate. Our work proposes an adapted sleep staging model based on top-performing state-of-the-art methods and evaluates its performance with different PPG segment sizes. We concatenate 30-second PPG segments over 15-minute intervals to leverage longer segment contexts. This approach achieved an accuracy of 0.75, a Cohen's Kappa of 0.60, an F1-Weighted score of 0.74, and an F1-Macro score of 0.60. Although reducing segment size decreased sensitivity for deep and REM stages, our strategy outperformed single 30-second window methods, particularly for these stages.
Authors: Sparsh Mittal, Yash Chand, Neel Kanth Kundu
Abstract: This paper proposes a hybrid quantum neural network (HQNN) for indoor user localization using received signal strength indicator (RSSI) values. We use publicly available RSSI datasets for indoor localization using WiFi, Bluetooth, and Zigbee to test the performance of the proposed HQNN. We also compare the performance of the HQNN with the recently proposed quantum fingerprinting-based user localization method. Our results show that the proposed HQNN performs better than the quantum fingerprinting algorithm since the HQNN has trainable parameters in the quantum circuits, whereas the quantum fingerprinting algorithm uses a fixed quantum circuit to calculate the similarity between the test data point and the fingerprint dataset. Unlike prior works, we also test the performance of the HQNN and quantum fingerprint algorithm on a real IBM quantum computer using cloud quantum computing services. Therefore, this paper examines the performance of the HQNN on noisy intermediate scale (NISQ) quantum devices using real-world RSSI localization datasets. The novelty of our approach lies in the use of simple feature maps and ansatz with fewer neurons, alongside testing on actual quantum hardware using real-world data, demonstrating practical applicability in real-world scenarios.
Authors: Chi-Sheng Chen
Abstract: NECOMIMI (NEural-COgnitive MultImodal EEG-Informed Image Generation with Diffusion Models) introduces a novel framework for generating images directly from EEG signals using advanced diffusion models. Unlike previous works that focused solely on EEG-image classification through contrastive learning, NECOMIMI extends this task to image generation. The proposed NERV EEG encoder demonstrates state-of-the-art (SoTA) performance across multiple zero-shot classification tasks, including 2-way, 4-way, and 200-way, and achieves top results in our newly proposed Category-based Assessment Table (CAT) Score, which evaluates the quality of EEG-generated images based on semantic concepts. A key discovery of this work is that the model tends to generate abstract or generalized images, such as landscapes, rather than specific objects, highlighting the inherent challenges of translating noisy and low-resolution EEG data into detailed visual outputs. Additionally, we introduce the CAT Score as a new metric tailored for EEG-to-image evaluation and establish a benchmark on the ThingsEEG dataset. This study underscores the potential of EEG-to-image generation while revealing the complexities and challenges that remain in bridging neural activity with visual representation.
Authors: Meiby Ortiz-Bouza, Selin Aviyente
Abstract: Multiplex networks have emerged as a promising approach for modeling complex systems, where each layer represents a different mode of interaction among entities of the same type. A core task in analyzing these networks is to identify the community structure for a better understanding of the overall functioning of the network. While different methods have been proposed to detect the community structure of multiplex networks, the majority deal with extracting the consensus community structure across layers. In this paper, we address the community detection problem across two closely related multiplex networks. For example in neuroimaging studies, it is common to have multiple multiplex brain networks where each layer corresponds to an individual and each group to different experimental conditions. In this setting, one may be interested in both learning the community structure representing each experimental condition and the discriminative community structure between two groups. In this paper, we introduce two discriminative community detection algorithms based on spectral clustering. The first approach aims to identify the discriminative subgraph structure between the groups, while the second one learns the discriminative and the consensus community structures, simultaneously. The proposed approaches are evaluated on both simulated and real world multiplex networks.
Authors: Vihang Patil, Andreas Radler, Daniel Klotz, Sepp Hochreiter
Abstract: Humans excel at abstracting data and constructing \emph{reusable} concepts, a capability lacking in current continual learning systems. The field of object-centric learning addresses this by developing abstract representations, or slots, from data without human supervision. Different methods have been proposed to tackle this task for images, whereas most are overly complex, non-differentiable, or poorly scalable. In this paper, we introduce a conceptually simple, fully-differentiable, non-iterative, and scalable method called SAMP Simplified Slot Attention with Max Pool Priors). It is implementable using only Convolution and MaxPool layers and an Attention layer. Our method encodes the input image with a Convolutional Neural Network and then uses a branch of alternating Convolution and MaxPool layers to create specialized sub-networks and extract primitive slots. These primitive slots are then used as queries for a Simplified Slot Attention over the encoded image. Despite its simplicity, our method is competitive or outperforms previous methods on standard benchmarks.
Authors: Lakshmi Nair
Abstract: Synthetic data generation is an important application of machine learning in the field of medical imaging. While existing approaches have successfully applied fine-tuned diffusion models for synthesizing medical images, we explore potential improvements to this pipeline through feature-aligned diffusion. Our approach aligns intermediate features of the diffusion model to the output features of an expert, and our preliminary findings show an improvement of 9% in generation accuracy and ~0.12 in SSIM diversity. Our approach is also synergistic with existing methods, and easily integrated into diffusion training pipelines for improvements. We make our code available at \url{https://github.com/lnairGT/Feature-Aligned-Diffusion}.
Authors: Paul Weiser, Georg Langs, Stanislav Motyka, Wolfgang Bogner, S\'ebastien Courvoisier, Malte Hoffmann, Antoine Klauser, Ovidiu C. Andronesi
Abstract: Purpose. Proton Magnetic Resonance Spectroscopic Imaging (1H-MRSI) provides non-invasive spectral-spatial mapping of metabolism. However, long-standing problems in whole-brain 1H-MRSI are spectral overlap of metabolite peaks with large lipid signal from scalp, and overwhelming water signal that distorts spectra. Fast and effective methods are needed for high-resolution 1H-MRSI to accurately remove lipid and water signals while preserving the metabolite signal. The potential of supervised neural networks for this task remains unexplored, despite their success for other MRSI processing. Methods. We introduce a deep-learning method based on a modified Y-NET network for water and lipid removal in whole-brain 1H-MRSI. The WALINET (WAter and LIpid neural NETwork) was compared to conventional methods such as the state-of-the-art lipid L2 regularization and Hankel-Lanczos singular value decomposition (HLSVD) water suppression. Methods were evaluated on simulated and in-vivo whole-brain MRSI using NMRSE, SNR, CRLB, and FWHM metrics. Results. WALINET is significantly faster and needs 8s for high-resolution whole-brain MRSI, compared to 42 minutes for conventional HLSVD+L2. Quantitative analysis shows WALINET has better performance than HLSVD+L2: 1) more lipid removal with 41% lower NRMSE, 2) better metabolite signal preservation with 71% lower NRMSE in simulated data, 155% higher SNR and 50% lower CRLB in in-vivo data. Metabolic maps obtained by WALINET in healthy subjects and patients show better gray/white-matter contrast with more visible structural details. Conclusions. WALINET has superior performance for nuisance signal removal and metabolite quantification on whole-brain 1H-MRSI compared to conventional state-of-the-art techniques. This represents a new application of deep-learning for MRSI processing, with potential for automated high-throughput workflow.
Authors: Wenwen Qiang, Zeen Song, Ziyin Gu, Jiangmeng Li, Changwen Zheng, Fuchun Sun, Hui Xiong
Abstract: Self-supervised learning (SSL) methods learn from unlabeled data and achieve high generalization performance on downstream tasks. However, they may also suffer from overfitting to their training data and lose the ability to adapt to new tasks. To investigate this phenomenon, we conduct experiments on various SSL methods and datasets and make two observations: (1) Overfitting occurs abruptly in later layers and epochs, while generalizing features are learned in early layers for all epochs; (2) Coding rate reduction can be used as an indicator to measure the degree of overfitting in SSL models. Based on these observations, we propose Undoing Memorization Mechanism (UMM), a plug-and-play method that mitigates overfitting of the pre-trained feature extractor by aligning the feature distributions of the early and the last layers to maximize the coding rate reduction of the last layer output. The learning process of UMM is a bi-level optimization process. We provide a causal analysis of UMM to explain how UMM can help the pre-trained feature extractor overcome overfitting and recover generalization. We also demonstrate that UMM significantly improves the generalization performance of SSL methods on various downstream tasks.
Authors: Hyogo Hiruma, Hiroshi Ito, Tetusya Ogata
Abstract: Uncertainty of environments has long been a difficult characteristic to handle, when performing real-world robot tasks. This is because the uncertainty produces unexpected observations that cannot be covered by manual scripting. Learning based robot controlling methods are a promising approach for generating flexible motions against unknown situations, but still tend to suffer under uncertainty due to its deterministic nature. In order to adaptively perform the target task under such conditions, the robot control model must be able to accurately understand the possible uncertainty, and to exploratively derive the optimal action that minimizes such uncertainty. This paper extended an existing predictive learning based robot control method, which employ foresight prediction using dynamic internal simulation. The foresight module refines the model's hidden states by sampling multiple possible futures and replace with the one that led to the lower future uncertainty. The adaptiveness of the model was evaluated on a door opening task. The door can be opened either by pushing, pulling, or sliding, but robot cannot visually distinguish which way, and is required to adapt on the fly. The results showed that the proposed model adaptively diverged its motion through interaction with the door, whereas conventional methods failed to stably diverge. The models were analyzed on Lyapunov exponents of RNN hidden states which reflect the possible divergence at each time step during task execution. The result indicated that the foresight module biased the model to consider future consequences, which lead to embedding uncertainties at the policy of the robot controller, rather than the resultant observation. This is beneficial for implementing adaptive behaviors, which indices derivation of diverse motion during exploration.
Authors: Nicolas Christianson, Wenqi Cui, Steven Low, Weiwei Yang, Baosen Zhang
Abstract: Power system operators must ensure that dispatch decisions remain feasible in case of grid outages or contingencies to prevent cascading failures and ensure reliable operation. However, checking the feasibility of all $N - k$ contingencies -- every possible simultaneous failure of $k$ grid components -- is computationally intractable for even small $k$, requiring system operators to resort to heuristic screening methods. Because of the increase in uncertainty and changes in system behaviors, heuristic lists might not include all relevant contingencies, generating false negatives in which unsafe scenarios are misclassified as safe. In this work, we propose to use input-convex neural networks (ICNNs) for contingency screening. We show that ICNN reliability can be determined by solving a convex optimization problem, and by scaling model weights using this problem as a differentiable optimization layer during training, we can learn an ICNN classifier that is both data-driven and has provably guaranteed reliability. Namely, our method can ensure a zero false negative rate. We empirically validate this methodology in a case study on the IEEE 39-bus test network, observing that it yields substantial (10-20x) speedups while having excellent classification accuracy.
Authors: Rinor Cakaj, Jens Mehnert, Bin Yang
Abstract: Convolutional Neural Networks (CNNs) are important for many machine learning tasks. They are built with different types of layers: convolutional layers that detect features, dropout layers that help to avoid over-reliance on any single neuron, and residual layers that allow the reuse of features. However, CNNs lack a dynamic feature retention mechanism similar to the human brain's memory, limiting their ability to use learned information in new contexts. To bridge this gap, we introduce the "Squeeze-and-Remember" (SR) block, a novel architectural unit that gives CNNs dynamic memory-like functionalities. The SR block selectively memorizes important features during training, and then adaptively re-applies these features during inference. This improves the network's ability to make contextually informed predictions. Empirical results on ImageNet and Cityscapes datasets demonstrate the SR block's efficacy: integration into ResNet50 improved top-1 validation accuracy on ImageNet by 0.52% over dropout2d alone, and its application in DeepLab v3 increased mean Intersection over Union in Cityscapes by 0.20%. These improvements are achieved with minimal computational overhead. This show the SR block's potential to enhance the capabilities of CNNs in image processing tasks.
Authors: Gareth Hardwick, Senwei Liang, Haizhao Yang
Abstract: In this paper, we introduce a new finite expression method (FEX) to solve high-dimensional partial integro-differential equations (PIDEs). This approach builds upon the original FEX and its inherent advantages with new advances: 1) A novel method of parameter grouping is proposed to reduce the number of coefficients in high-dimensional function approximation; 2) A Taylor series approximation method is implemented to significantly improve the computational efficiency and accuracy of the evaluation of the integral terms of PIDEs. The new FEX based method, denoted FEX-PG to indicate the addition of the parameter grouping (PG) step to the algorithm, provides both high accuracy and interpretable numerical solutions, with the outcome being an explicit equation that facilitates intuitive understanding of the underlying solution structures. These features are often absent in traditional methods, such as finite element methods (FEM) and finite difference methods, as well as in deep learning-based approaches. To benchmark our method against recent advances, we apply the new FEX-PG to solve benchmark PIDEs in the literature. In high-dimensional settings, FEX-PG exhibits strong and robust performance, achieving relative errors on the order of single precision machine epsilon.
Authors: Katharine M. Clark, Paul D. McNicholas
Abstract: Zhu and Melnykov (2018) develop a model to fit mixture models when the components are derived from the Manly transformation. Their EM algorithm utilizes Nelder-Mead optimization in the M-step to update the skew parameter, $\boldsymbol{\lambda}_g$. An alternative EM gradient algorithm is proposed, using one step of Newton's method, when initial estimates for the model parameters are good.
Authors: Daniel Pfrommer, Swati Padmanabhan, Kwangjun Ahn, Jack Umenberger, Tobia Marcucci, Zakaria Mhammedi, Ali Jadbabaie
Abstract: Recent work in imitation learning has shown that having an expert controller that is both suitably smooth and stable enables stronger guarantees on the performance of the learned controller. However, constructing such smoothed expert controllers for arbitrary systems remains challenging, especially in the presence of input and state constraints. As our primary contribution, we show how such a smoothed expert can be designed for a general class of systems using a log-barrier-based relaxation of a standard Model Predictive Control (MPC) optimization problem. Improving upon our previous work, we show that barrier MPC achieves theoretically optimal error-to-smoothness tradeoff along some direction. At the core of this theoretical guarantee on smoothness is an improved lower bound we prove on the optimality gap of the analytic center associated with a convex Lipschitz function, which we believe could be of independent interest. We validate our theoretical findings via experiments, demonstrating the merits of our smoothing approach over randomized smoothing.
Authors: Megan Wei, Michael Freeman, Chris Donahue, Chen Sun
Abstract: Music foundation models possess impressive music generation capabilities. When people compose music, they may infuse their understanding of music into their work, by using notes and intervals to craft melodies, chords to build progressions, and tempo to create a rhythmic feel. To what extent is this true of music generation models? More specifically, are fundamental Western music theory concepts observable within the "inner workings" of these models? Recent work proposed leveraging latent audio representations from music generation models towards music information retrieval tasks (e.g. genre classification, emotion recognition), which suggests that high-level musical characteristics are encoded within these models. However, probing individual music theory concepts (e.g. tempo, pitch class, chord quality) remains under-explored. Thus, we introduce SynTheory, a synthetic MIDI and audio music theory dataset, consisting of tempos, time signatures, notes, intervals, scales, chords, and chord progressions concepts. We then propose a framework to probe for these music theory concepts in music foundation models (Jukebox and MusicGen) and assess how strongly they encode these concepts within their internal representations. Our findings suggest that music theory concepts are discernible within foundation models and that the degree to which they are detectable varies by model size and layer.
Authors: Kosuke Imai, Kentaro Nakamura
Abstract: In this paper, we demonstrate how to enhance the validity of causal inference with unstructured high-dimensional treatments like texts, by leveraging the power of generative Artificial Intelligence. Specifically, we propose to use a deep generative model such as large language models (LLMs) to efficiently generate treatments and use their internal representation for subsequent causal effect estimation. We show that the knowledge of this true internal representation helps separate the treatment features of interest, such as specific sentiments and certain topics, from other possibly unknown confounding features. Unlike the existing methods, our proposed approach eliminates the need to learn causal representation from the data and hence produces more accurate and efficient estimates. We formally establish the conditions required for the nonparametric identification of the average treatment effect, propose an estimation strategy that avoids the violation of the overlap assumption, and derive the asymptotic properties of the proposed estimator through the application of double machine learning. Finally, using an instrumental variables approach, we extend the proposed methodology to the settings, in which the treatment feature is based on human perception rather than is assumed to be fixed given the treatment object. We conduct simulation studies using the generated text data with an open-source LLM, Llama3, to illustrate the advantages of our estimator over the state-of-the-art causal representation learning algorithms.
Authors: Da-Wei Zhou, Zi-Wen Cai, Han-Jia Ye, Lijun Zhang, De-Chuan Zhan
Abstract: Domain-Incremental Learning (DIL) involves the progressive adaptation of a model to new concepts across different domains. While recent advances in pre-trained models provide a solid foundation for DIL, learning new concepts often results in the catastrophic forgetting of pre-trained knowledge. Specifically, sequential model updates can overwrite both the representation and the classifier with knowledge from the latest domain. Thus, it is crucial to develop a representation and corresponding classifier that accommodate all seen domains throughout the learning process. To this end, we propose DUal ConsolidaTion (Duct) to unify and consolidate historical knowledge at both the representation and classifier levels. By merging the backbone of different stages, we create a representation space suitable for multiple domains incrementally. The merged representation serves as a balanced intermediary that captures task-specific features from all seen domains. Additionally, to address the mismatch between consolidated embeddings and the classifier, we introduce an extra classifier consolidation process. Leveraging class-wise semantic information, we estimate the classifier weights of old domains within the latest embedding space. By merging historical and estimated classifiers, we align them with the consolidated embedding space, facilitating incremental classification. Extensive experimental results on four benchmark datasets demonstrate Duct's state-of-the-art performance.
Authors: Keqin Liu, Tianshuo Zheng, Haoran Chen
Abstract: The multi-armed bandit (MAB) problem is a widely studied model in the field of operations research for sequential decision making and reinforcement learning. This paper mainly considers the classical MAB model with the heavy-tailed reward distributions. We introduce the extended robust UCB policy, which is an extension of the pioneering UCB policies proposed by Bubeck et al. [5] and Lattimore [21]. The previous UCB policies require the knowledge of an upper bound on specific moments of reward distributions or a particular moment to exist, which can be hard to acquire or guarantee in practical scenarios. Our extended robust UCB generalizes Lattimore's seminary work (for moments of orders $p=4$ and $q=2$) to arbitrarily chosen $p$ and $q$ as long as the two moments have a known controlled relationship, while still achieving the optimal regret growth order O(log T), thus providing a broadened application area of the UCB policies for the heavy-tailed reward distributions.
Authors: Wilson E. Marc\'ilio-Jr, Danilo M. Eler, Fernando V. Paulovich, Rafael M. Martins
Abstract: Dimensionality reduction (DR) techniques help analysts to understand patterns in high-dimensional spaces. These techniques, often represented by scatter plots, are employed in diverse science domains and facilitate similarity analysis among clusters and data samples. For datasets containing many granularities or when analysis follows the information visualization mantra, hierarchical DR techniques are the most suitable approach since they present major structures beforehand and details on demand. This work presents HUMAP, a novel hierarchical dimensionality reduction technique designed to be flexible on preserving local and global structures and preserve the mental map throughout hierarchical exploration. We provide empirical evidence of our technique's superiority compared with current hierarchical approaches and show a case study applying HUMAP for dataset labelling.
Authors: Lingzhi Gao, Zhenyuan Zhang, Chao Wu
Abstract: While existing federated learning approaches primarily focus on aggregating local models to construct a global model, in realistic settings, some clients may be reluctant to share their private models due to the inclusion of privacy-sensitive information. Knowledge distillation, which can extract model knowledge without accessing model parameters, is well-suited for this federated scenario. However, most distillation methods in federated learning (federated distillation) require a proxy dataset, which is difficult to obtain in the real world. Therefore, in this paper, we introduce a distributed three-player Generative Adversarial Network (GAN) to implement data-free mutual distillation and propose an effective method called FedDTG. We confirmed that the fake samples generated by GAN can make federated distillation more efficient and robust. Additionally, the distillation process between clients can deliver good individual client performance while simultaneously acquiring global knowledge and protecting data privacy. Our extensive experiments on benchmark vision datasets demonstrate that our method outperforms other federated distillation algorithms in terms of generalization.
Authors: Mohammad Malekzadeh, Deniz Gunduz
Abstract: Privacy-preserving inference in edge computing paradigms encourages the users of machine-learning services to locally run a model on their private input and only share the models outputs for a target task with the server. We study how a vicious server can reconstruct the input data by observing only the models outputs while keeping the target accuracy very close to that of a honest server by jointly training a target model (to run at users' side) and an attack model for data reconstruction (to secretly use at servers' side). We present a new measure to assess the inference-time reconstruction risk. Evaluations on six benchmark datasets show the model's input can be approximately reconstructed from the outputs of a single inference. We propose a primary defense mechanism to distinguish vicious versus honest classifiers at inference time. By studying such a risk associated with emerging ML services our work has implications for enhancing privacy in edge computing. We discuss open challenges and directions for future studies and release our code as a benchmark for the community at https://github.com/mmalekzadeh/vicious-classifiers .
Authors: Tianyi Wang, Rodney Beard, John Hawkins, Rohitash Chandra
Abstract: The gross domestic product (GDP) is the most widely used indicator in macroeconomics and the main tool for measuring a country's economic output. Due to the diversity and complexity of the world economy, a wide range of models have been used, but there are challenges in making decadal GDP forecasts given unexpected changes such as emergence of catastrophic world events including pandemics and wars. Deep learning models are well suited for modelling temporal sequences and time series forecasting. In this paper, we develop a deep learning framework to forecast the GDP growth rate of the world economy over a decade. We use the Penn World Table as the data source featuring 13 countries prior to the COVID-19 pandemic, such as Australia, China, India, and the United States. We present a recursive deep learning framework to predict the GDP growth rate in the next ten years. We test prominent deep learning models and compare their results with traditional econometric models for selected developed and developing countries. Our decadal forecasts reveal that that most of the developed countries would experience economic growth slowdown, stagnation and even recession within five years (2020-2024). Furthermore, our model forecasts show that only China, France, and India would experience stable GDP growth.
Authors: Hao Shu
Abstract: Density-based clustering could be the most popular clustering algorithm since it can identify clusters of arbitrary shape as long as they are separated by low-density regions. However, a high-density region that is not separated by low-density ones might also have different structures belonging to multiple clusters. As far as we know, all previous density-based clustering algorithms fail to detect such structures. In this paper, we provide a novel density-based clustering scheme that can not only detect clusters separated by low-density regions but also detect structures in high-density regions not separated by low-density ones. The algorithm employs secondary directed differential, hierarchy, normalized density, as well as the self-adaption coefficient, and thus is called Structure Detecting Cluster by Hierarchical Secondary Directed Differential with Normalized Density and Self-Adaption, dubbed by SDC-HSDD-NDSA. The algorithm is run on several datasets to verify its effectiveness, robustness, as well as granularity independence, and results demonstrate that it has the ability that previous ones do not have. The Python code is on https://github.com/Hao-B-Shu/SDC-HSDD-NDSA.
Authors: Tongxin Yin, Xuwei Tan, Xueru Zhang, Mohammad Mahdi Khalili, Mingyan Liu
Abstract: Federated learning (FL) is a distributed learning paradigm that allows multiple decentralized clients to collaboratively learn a common model without sharing local data. Although local data is not exposed directly, privacy concerns nonetheless exist as clients' sensitive information can be inferred from intermediate computations. Moreover, such information leakage accumulates substantially over time as the same data is repeatedly used during the iterative learning process. As a result, it can be particularly difficult to balance the privacy-accuracy trade-off when designing privacy-preserving FL algorithms. This paper introduces Upcycled-FL, a simple yet effective strategy that applies first-order approximation at every even round of model update. Under this strategy, half of the FL updates incur no information leakage and require much less computational and transmission costs. We first conduct the theoretical analysis on the convergence (rate) of Upcycled-FL and then apply two perturbation mechanisms to preserve privacy. Extensive experiments on both synthetic and real-world data show that the Upcycled-FL strategy can be adapted to many existing FL frameworks and consistently improve the privacy-accuracy trade-off.
Authors: Naoki Saito, Stefan C. Schonsheck, Eugene Shvarts
Abstract: We propose new scattering networks for signals measured on simplicial complexes, which we call \emph{Multiscale Hodge Scattering Networks} (MHSNs). Our construction is based on multiscale basis dictionaries on simplicial complexes, i.e., the $\kappa$-GHWT and $\kappa$-HGLET, which we recently developed for simplices of dimension $\kappa \in \mathbb{N}$ in a given simplicial complex by generalizing the node-based Generalized Haar-Walsh Transform (GHWT) and Hierarchical Graph Laplacian Eigen Transform (HGLET). The $\kappa$-GHWT and the $\kappa$-HGLET both form redundant sets (i.e., dictionaries) of multiscale basis vectors and the corresponding expansion coefficients of a given signal. Our MHSNs use a layered structure analogous to a convolutional neural network (CNN) to cascade the moments of the modulus of the dictionary coefficients. The resulting features are invariant to reordering of the simplices (i.e., node permutation of the underlying graphs). Importantly, the use of multiscale basis dictionaries in our MHSNs admits a natural pooling operation that is akin to local pooling in CNNs, and which may be performed either locally or per-scale. These pooling operations are harder to define in both traditional scattering networks based on Morlet wavelets, and geometric scattering networks based on Diffusion Wavelets. As a result, we are able to extract a rich set of descriptive yet robust features that can be used along with very simple machine learning methods (i.e., logistic regression or support vector machines) to achieve high-accuracy classification systems with far fewer parameters to train than most modern graph neural networks. Finally, we demonstrate the usefulness of our MHSNs in three distinct types of problems: signal classification, domain (i.e., graph/simplex) classification, and molecular dynamics prediction.
Authors: Luca Scimeca, Alexander Rubinstein, Damien Teney, Seong Joon Oh, Armand Mihai Nicolicioiu, Yoshua Bengio
Abstract: Spurious correlations in the data, where multiple cues are predictive of the target labels, often lead to a phenomenon known as shortcut learning, where a model relies on erroneous, easy-to-learn cues while ignoring reliable ones. In this work, we propose DiffDiv an ensemble diversification framework exploiting Diffusion Probabilistic Models (DPMs) to mitigate this form of bias. We show that at particular training intervals, DPMs can generate images with novel feature combinations, even when trained on samples displaying correlated input features. We leverage this crucial property to generate synthetic counterfactuals to increase model diversity via ensemble disagreement. We show that DPM-guided diversification is sufficient to remove dependence on shortcut cues, without a need for additional supervised signals. We further empirically quantify its efficacy on several diversification objectives, and finally show improved generalization and diversification on par with prior work that relies on auxiliary data collection.
Authors: R\'obert Csord\'as, Piotr Pi\k{e}kos, Kazuki Irie, J\"urgen Schmidhuber
Abstract: Despite many recent works on Mixture of Experts (MoEs) for resource-efficient Transformer language models, existing methods mostly focus on MoEs for feedforward layers. Previous attempts at extending MoE to the self-attention layer fail to match the performance of the parameter-matched baseline. Our novel SwitchHead is an effective MoE method for the attention layer that successfully reduces both the compute and memory requirements, achieving wall-clock speedup, while matching the language modeling performance of the baseline Transformer. Our novel MoE mechanism allows SwitchHead to compute up to 8 times fewer attention matrices than the standard Transformer. SwitchHead can also be combined with MoE feedforward layers, resulting in fully-MoE "SwitchAll" Transformers. For our 262M parameter model trained on C4, SwitchHead matches the perplexity of standard models with only 44% compute and 27% memory usage. Zero-shot experiments on downstream tasks confirm the performance of SwitchHead, e.g., achieving more than 3.5% absolute improvements on BliMP compared to the baseline with an equal compute resource.
Authors: Matteo Ninniri, Marco Podda, Davide Bacciu
Abstract: This work focuses on the task of property targeting: that is, generating molecules conditioned on target chemical properties to expedite candidate screening for novel drug and materials development. DiGress is a recent diffusion model for molecular graphs whose distinctive feature is allowing property targeting through classifier-based (CB) guidance. While CB guidance may work to generate molecular-like graphs, we hint at the fact that its assumptions apply poorly to the chemical domain. Based on this insight we propose a classifier-free DiGress (FreeGress), which works by directly injecting the conditioning information into the training process. CF guidance is convenient given its less stringent assumptions and since it does not require to train an auxiliary property regressor, thus halving the number of trainable parameters in the model. We empirically show that our model yields up to 79% improvement in Mean Absolute Error with respect to DiGress on property targeting tasks on QM9 and ZINC-250k benchmarks. As an additional contribution, we propose a simple yet powerful approach to improve chemical validity of generated samples, based on the observation that certain chemical properties such as molecular weight correlate with the number of atoms in molecules.
Authors: Sebastian Johann Wetzel
Abstract: I introduce a unified framework for finding a closed-form interpretation of any single neuron in an artificial neural network. Using this framework I demonstrate how to interpret neural network classifiers to reveal closed-form expressions of the concepts encoded in their decision boundaries. In contrast to neural network-based regression, for classification, it is in general impossible to express the neural network in the form of a symbolic equation even if the neural network itself bases its classification on a quantity that can be written as a closed-form equation. The interpretation framework is based on embedding trained neural networks into an equivalence class of functions that encode the same concept. I interpret these neural networks by finding an intersection between the equivalence class and human-readable equations defined by a symbolic search space. The approach is not limited to classifiers or full neural networks and can be applied to arbitrary neurons in hidden layers or latent spaces.
Authors: Jonas H\"ubotter, Bhavya Sukhija, Lenart Treven, Yarden As, Andreas Krause
Abstract: We generalize active learning to address real-world settings with concrete prediction targets where sampling is restricted to an accessible region of the domain, while prediction targets may lie outside this region. We analyze a family of decision rules that sample adaptively to minimize uncertainty about prediction targets. We are the first to show, under general regularity assumptions, that such decision rules converge uniformly to the smallest possible uncertainty obtainable from the accessible data. We demonstrate their strong sample efficiency in two key applications: Active few-shot fine-tuning of large neural networks and safe Bayesian optimization, where they improve significantly upon the state-of-the-art.
Authors: Hao Kang, Qingru Zhang, Souvik Kundu, Geonhwa Jeong, Zaoxing Liu, Tushar Krishna, Tuo Zhao
Abstract: Key-value (KV) caching has become the de-facto to accelerate generation speed for large language models (LLMs) inference. However, the growing cache demand with increasing sequence length has transformed LLM inference to be a memory bound problem, significantly constraining the system throughput. Existing methods rely on dropping unimportant tokens or quantizing all entries uniformly. Such methods, however, often incur high approximation errors to represent the compressed matrices. The autoregressive decoding process further compounds the error of each step, resulting in critical deviation in model generation and deterioration of performance. To tackle this challenge, we propose GEAR, an efficient KV cache compression framework that achieves near-lossless high-ratio compression. GEAR first applies quantization to majority of entries of similar magnitudes to ultra-low precision. It then employs a low rank matrix to approximate the quantization error, and a sparse matrix to remedy individual errors from outlier entries. By adeptly integrating three techniques, GEAR is able to fully exploit their synergistic potentials. Our experiments demonstrate that compared to alternatives, GEAR achieves near-lossless 4-bit KV cache compression with up to 2.38x throughput improvement, while reducing peak-memory size up to 2.29x. Our code is publicly available at https://github.com/HaoKang-Timmy/GEAR.
Authors: Yushan Huang, Ranya Aloufi, Xavier Cadet, Yuchen Zhao, Payam Barnaghi, Hamed Haddadi
Abstract: Microcontroller Units (MCUs) are ideal platforms for edge applications due to their low cost and energy consumption, and are widely used in various applications, including personalized machine learning tasks, where customized models can enhance the task adaptation. However, existing approaches for local on-device personalization mostly support simple ML architectures or require complex local pre-training/training, leading to high energy consumption and negating the low-energy advantage of MCUs. In this paper, we introduce $MicroT$, an efficient and low-energy MCU personalization approach. $MicroT$ includes a robust, general, but tiny feature extractor, developed through self-supervised knowledge distillation, which trains a task-specific head to enable independent on-device personalization with minimal energy and computational requirements. MicroT implements an MCU-optimized early-exit inference mechanism called stage-decision to further reduce energy costs. This mechanism allows for user-configurable exit criteria (stage-decision ratio) to adaptively balance energy cost with model performance. We evaluated MicroT using two models, three datasets, and two MCU boards. $MicroT$ outperforms traditional transfer learning (TTL) and two SOTA approaches by 2.12 - 11.60% across two models and three datasets. Targeting widely used energy-aware edge devices, MicroT's on-device training requires no additional complex operations, halving the energy cost compared to SOTA approaches by up to 2.28X while keeping SRAM usage below 1MB. During local inference, MicroT reduces energy cost by 14.17% compared to TTL across two boards and two datasets, highlighting its suitability for long-term use on energy-aware resource-constrained MCUs.
Authors: Joanna Komorniczak, Pawe{\l} Ksieniewicz
Abstract: Practical applications of artificial intelligence increasingly often have to deal with the streaming properties of real data, which, considering the time factor, are subject to phenomena such as periodicity and more or less chaotic degeneration - resulting directly in the concept drifts. The modern concept drift detectors almost always assume immediate access to labels, which due to their cost, limited availability and possible delay has been shown to be unrealistic. This work proposes an unsupervised Parallel Activations Drift Detector, utilizing the outputs of an untrained neural network, presenting its key design elements, intuitions about processing properties, and a pool of computer experiments demonstrating its competitiveness with state-of-the-art methods.
Authors: Oscar Key, So Takao, Daniel Giles, Marc Peter Deisenroth
Abstract: Data assimilation is a core component of numerical weather prediction systems. The large quantity of data processed during assimilation requires the computation to be distributed across increasingly many compute nodes, yet existing approaches suffer from synchronisation overhead in this setting. In this paper, we exploit the formulation of data assimilation as a Bayesian inference problem and apply a message-passing algorithm to solve the spatial inference problem. Since message passing is inherently based on local computations, this approach lends itself to parallel and distributed computation. In combination with a GPU-accelerated implementation, we can scale the algorithm to very large grid sizes while retaining good accuracy and compute and memory requirements.
Authors: Zezheng Song, Jiaxin Yuan, Haizhao Yang
Abstract: The fast simulation of dynamical systems is a key challenge in many scientific and engineering applications, such as weather forecasting, disease control, and drug discovery. With the recent success of deep learning, there is increasing interest in using neural networks to solve differential equations in a data-driven manner. However, existing methods are either limited to specific types of differential equations or require large amounts of data for training. This restricts their practicality in many real-world applications, where data is often scarce or expensive to obtain. To address this, we propose a novel multi-modal foundation model, named \textbf{FMint} (\textbf{F}oundation \textbf{M}odel based on \textbf{In}i\textbf{t}ialization), to bridge the gap between human-designed and data-driven models for the fast simulation of dynamical systems. Built on a decoder-only transformer architecture with in-context learning, FMint utilizes both numerical and textual data to learn a universal error correction scheme for dynamical systems, using prompted sequences of coarse solutions from traditional solvers. The model is pre-trained on a corpus of 40K ODEs, and we perform extensive experiments on challenging ODEs that exhibit chaotic behavior and of high dimensionality. Our results demonstrate the effectiveness of the proposed model in terms of both accuracy and efficiency compared to classical numerical solvers, highlighting FMint's potential as a general-purpose solver for dynamical systems. Our approach achieves an accuracy improvement of 1 to 2 orders of magnitude over state-of-the-art dynamical system simulators, and delivers a 5X speedup compared to traditional numerical algorithms. The code for FMint is available at \url{https://github.com/margotyjx/FMint}.
Authors: Anshuman Chhabra, Bo Li, Jian Chen, Prasant Mohapatra, Hongfu Liu
Abstract: A core data-centric learning challenge is the identification of training samples that are detrimental to model performance. Influence functions serve as a prominent tool for this task and offer a robust framework for assessing training data influence on model predictions. Despite their widespread use, their high computational cost associated with calculating the inverse of the Hessian matrix pose constraints, particularly when analyzing large-sized deep models. In this paper, we establish a bridge between identifying detrimental training samples via influence functions and outlier gradient detection. This transformation not only presents a straightforward and Hessian-free formulation but also provides insights into the role of the gradient in sample impact. Through systematic empirical evaluations, we first validate the hypothesis of our proposed outlier gradient analysis approach on synthetic datasets. We then demonstrate its effectiveness in detecting mislabeled samples in vision models and selecting data samples for improving performance of natural language processing transformer models. We also extend its use to influential sample identification for fine-tuning Large Language Models.
Authors: Ahmed Ali Abbasi, Namrata Vaswani
Abstract: In this work, we develop and analyze a Gradient Descent (GD) based solution, called Alternating GD and Minimization (AltGDmin), for efficiently solving the low rank matrix completion (LRMC) in a federated setting. LRMC involves recovering an $n \times q$ rank-$r$ matrix $\Xstar$ from a subset of its entries when $r \ll \min(n,q)$. Our theoretical guarantees (iteration and sample complexity bounds) imply that AltGDmin is the most communication-efficient solution in a federated setting, is one of the fastest, and has the second best sample complexity among all iterative solutions to LRMC. In addition, we also prove two important corollaries. (a) We provide a guarantee for AltGDmin for solving the noisy LRMC problem. (b) We show how our lemmas can be used to provide an improved sample complexity guarantee for AltMin, which is the fastest centralized solution.
Authors: Jesus Garcia Fernandez, Sander Keemink, Marcel van Gerven
Abstract: Recurrent neural networks (RNNs) hold immense potential for computations due to their Turing completeness and sequential processing capabilities, yet existing methods for their training encounter efficiency challenges. Backpropagation through time (BPTT), the prevailing method, extends the backpropagation (BP) algorithm by unrolling the RNN over time. However, this approach suffers from significant drawbacks, including the need to interleave forward and backward phases and store exact gradient information. Furthermore, BPTT has been shown to struggle to propagate gradient information for long sequences, leading to vanishing gradients. An alternative strategy to using gradient-based methods like BPTT involves stochastically approximating gradients through perturbation-based methods. This learning approach is exceptionally simple, necessitating only forward passes in the network and a global reinforcement signal as feedback. Despite its simplicity, the random nature of its updates typically leads to inefficient optimization, limiting its effectiveness in training neural networks. In this study, we present a new approach to perturbation-based learning in RNNs whose performance is competitive with BPTT, while maintaining the inherent advantages over gradient-based learning. To this end, we extend the recently introduced activity-based node perturbation (ANP) method to operate in the time domain, leading to more efficient learning and generalization. We subsequently conduct a range of experiments to validate our approach. Our results show similar performance, convergence time and scalability compared to BPTT, strongly outperforming standard node and weight perturbation methods. These findings suggest that perturbation-based learning methods offer a versatile alternative to gradient-based methods for training RNNs which can be ideally suited for neuromorphic computing applications
Authors: Jose M. Alvarez, Salvatore Ruggieri
Abstract: Testing for discrimination consists of deriving a profile, known as the comparator, similar to the profile making the discrimination claim, known as the complainant, and comparing the outcomes of these two profiles. An important aspect for establishing discrimination is evidence, often obtained via discrimination testing tools that implement the complainant-comparator pair. In this work, we revisit the role of the comparator in discrimination testing. We argue for the causal modeling nature of deriving the comparator, and introduce a two-kinds classification for the comparator: the ceteris paribus (CP), and mutatis mutandis (MM) comparators. The CP comparator is the standard one among discrimination testing, representing an idealized comparison as it aims for having a complainant-comparator pair that only differs on membership to the protected attribute. As an alternative to it, we define the MM comparator, which requires that the comparator represents what would have been of the complainant without the effects of the protected attribute on the non-protected attributes. The complainant-comparator pair, in that case, may also be dissimilar in terms of all attributes. We illustrate these two comparators and their impact on discrimination testing using a real illustrative example. Importantly, we position generative models and, overall, machine learning methods as useful tools for constructing the MM comparator and, in turn, achieving more complex and realistic comparisons when testing for discrimination.
Authors: Alex Morehead, Nabin Giri, Jian Liu, Jianlin Cheng
Abstract: The effects of ligand binding on protein structures and their in vivo functions carry numerous implications for modern biomedical research and biotechnology development efforts such as drug discovery. Although several deep learning (DL) methods and benchmarks designed for protein-ligand docking have recently been introduced, to date no prior works have systematically studied the behavior of docking methods within the broadly applicable context of (1) using predicted (apo) protein structures for docking (e.g., for applicability to unknown structures); (2) docking multiple ligands concurrently to a given target protein (e.g., for enzyme design); and (3) having no prior knowledge of binding pockets (e.g., for unknown pocket generalization). To enable a deeper understanding of docking methods' real-world utility, we introduce PoseBench, the first comprehensive benchmark for broadly applicable protein-ligand docking. PoseBench enables researchers to rigorously and systematically evaluate DL docking methods for apo-to-holo protein-ligand docking and protein-ligand structure generation using both single and multi-ligand benchmark datasets, the latter of which we introduce for the first time to the DL community. Empirically, using PoseBench, we find that (1) DL methods consistently outperform conventional docking algorithms; (2) most recent DL docking methods fail to generalize to multi-ligand protein targets; and (3) training DL methods with physics-informed loss functions on diverse clusters of protein-ligand complexes is a promising direction for future work. Code, data, tutorials, and benchmark results are available at https://github.com/BioinfoMachineLearning/PoseBench.
Authors: Anna Vettoruzzo, Lorenzo Braccaioli, Joaquin Vanschoren, Marlena Nowaczyk
Abstract: Unsupervised meta-learning aims to learn feature representations from unsupervised datasets that can transfer to downstream tasks with limited labeled data. In this paper, we propose a novel approach to unsupervised meta-learning that leverages the generalization abilities of in-context learning observed in transformer architectures. Our method reframes meta-learning as a sequence modeling problem, enabling the transformer encoder to learn task context from support images and utilize it to predict query images. At the core of our approach lies the creation of diverse tasks generated using a combination of data augmentations and a mixing strategy that challenges the model during training while fostering generalization to unseen tasks at test time. Experimental results on benchmark datasets showcase the superiority of our approach over existing unsupervised meta-learning baselines, establishing it as the new state-of-the-art in the field. Remarkably, our method achieves competitive results with supervised and self-supervised approaches, underscoring the efficacy of the model in leveraging generalization over memorization.
Authors: Minghao Xu, Yunteng Geng, Yihang Zhang, Ling Yang, Jian Tang, Wentao Zhang
Abstract: Glycans are basic biomolecules and perform essential functions within living organisms. The rapid increase of functional glycan data provides a good opportunity for machine learning solutions to glycan understanding. However, there still lacks a standard machine learning benchmark for glycan property and function prediction. In this work, we fill this blank by building a comprehensive benchmark for Glycan Machine Learning (GlycanML). The GlycanML benchmark consists of diverse types of tasks including glycan taxonomy prediction, glycan immunogenicity prediction, glycosylation type prediction, and protein-glycan interaction prediction. Glycans can be represented by both sequences and graphs in GlycanML, which enables us to extensively evaluate sequence-based models and graph neural networks (GNNs) on benchmark tasks. Furthermore, by concurrently performing eight glycan taxonomy prediction tasks, we introduce the GlycanML-MTL testbed for multi-task learning (MTL) algorithms. Also, we evaluate how taxonomy prediction can boost other three function prediction tasks by MTL. Experimental results show the superiority of modeling glycans with multi-relational GNNs, and suitable MTL methods can further boost model performance. We provide all datasets and source codes at https://github.com/GlycanML/GlycanML and maintain a leaderboard at https://GlycanML.github.io/project
URLs: https://github.com/GlycanML/GlycanML, https://GlycanML.github.io/project
Authors: Cory Efird, Alex Murphy, Joel Zylberberg, Alona Fyshe
Abstract: Prior work has offered evidence for functional localization in the brain; different anatomical regions preferentially activate for certain types of visual input. For example, the fusiform face area preferentially activates for visual stimuli that include a face. However, the spectrum of visual semantics is extensive, and only a few semantically-tuned patches of cortex have so far been identified in the human brain. Using a multimodal (natural language and image) neural network architecture (CLIP) we train a highly accurate contrastive model that maps brain responses during naturalistic image viewing to CLIP embeddings. We then use a novel adaptation of the DBSCAN clustering algorithm to cluster the parameters of these participant-specific contrastive models. This reveals what we call Shared Decodable Concepts (SDCs): clusters in CLIP space that are decodable from common sets of voxels across multiple participants. Examining the images most and least associated with each SDC cluster gives us additional insight into the semantic properties of each SDC. We note SDCs for previously reported visual features (e.g. orientation tuning in early visual cortex) as well as visual semantic concepts such as faces, places and bodies. In cases where our method finds multiple clusters for a visuo-semantic concept, the least associated images allow us to dissociate between confounding factors. For example, we discovered two clusters of food images, one driven by color, the other by shape. We also uncover previously unreported areas such as regions of extrastriate body area (EBA) tuned for legs/hands and sensitivity to numerosity in right intraparietal sulcus, and more. Thus, our contrastive-learning methodology better characterizes new and existing visuo-semantic representations in the brain by leveraging multimodal neural network representations and a novel adaptation of clustering algorithms.
Authors: Manh Khoi Duong, Stefan Conrad
Abstract: Motivated by the recital (67) of the current corrigendum of the AI Act in the European Union, we propose and present measures and mitigation strategies for discrimination in tabular datasets. We specifically focus on datasets that contain multiple protected attributes, such as nationality, age, and sex. This makes measuring and mitigating bias more challenging, as many existing methods are designed for a single protected attribute. This paper comes with a twofold contribution: Firstly, new discrimination measures are introduced. These measures are categorized in our framework along with existing ones, guiding researchers and practitioners in choosing the right measure to assess the fairness of the underlying dataset. Secondly, a novel application of an existing bias mitigation method, FairDo, is presented. We show that this strategy can mitigate any type of discrimination, including intersectional discrimination, by transforming the dataset. By conducting experiments on real-world datasets (Adult, Bank, COMPAS), we demonstrate that de-biasing datasets with multiple protected attributes is possible. All transformed datasets show a reduction in discrimination, on average by 28%. Further, these datasets do not compromise any of the tested machine learning models' performances significantly compared to the original datasets. Conclusively, this study demonstrates the effectiveness of the mitigation strategy used and contributes to the ongoing discussion on the implementation of the European Union's AI Act.
Authors: Raja Marjieh, Sreejan Kumar, Declan Campbell, Liyi Zhang, Gianluca Bencomo, Jake Snell, Thomas L. Griffiths
Abstract: Humans rely on strong inductive biases to learn from few examples and abstract useful information from sensory data. Instilling such biases in machine learning models has been shown to improve their performance on various benchmarks including few-shot learning, robustness, and alignment. However, finding effective training procedures to achieve that goal can be challenging as psychologically-rich training data such as human similarity judgments are expensive to scale, and Bayesian models of human inductive biases are often intractable for complex, realistic domains. Here, we address this challenge by introducing a Bayesian notion of generative similarity whereby two datapoints are considered similar if they are likely to have been sampled from the same distribution. This measure can be applied to complex generative processes, including probabilistic programs. We show that generative similarity can be used to define a contrastive learning objective even when its exact form is intractable, enabling learning of spatial embeddings that express specific inductive biases. We demonstrate the utility of our approach by showing that it can be used to capture human inductive biases for geometric shapes, distinguish different abstract drawing styles that are parameterized by probabilistic programs, and capture abstract high-level categories that enable generalization.
Authors: Ahmet Sarigun, Vedran Franke, Bora Uyar, Altuna Akalin
Abstract: Datasets used for molecular docking, such as PDBBind, contain technical variability - they are noisy. Although the origins of the noise have been discussed, a comprehensive analysis of the physical, chemical, and bioactivity characteristics of the datasets is still lacking. To address this gap, we introduce the Comprehensive Accurate Assessment (Compass). Compass integrates two key components: PoseCheck, which examines ligand strain energy, protein-ligand steric clashes, and interactions, and AA-Score, a new empirical scoring function for calculating binding affinity energy. Together, these form a unified workflow that assesses both the physical/chemical properties and bioactivity favorability of ligands and protein-ligand interactions. Our analysis of the PDBBind dataset using Compass reveals substantial noise in the ground truth data. Additionally, we propose CompassDock, which incorporates the Compass module with DiffDock, the state-of-the-art deep learning-based molecular docking method, to enable accurate assessment of docked ligands during inference. Finally, we present a new paradigm for enhancing molecular docking model performance by fine-tuning with Compass Scores, which encompass binding affinity energy, strain energy, and the number of steric clashes identified by Compass. Our results show that, while fine-tuning without Compass improves the percentage of docked poses with RMSD < 2{\AA}, it leads to a decrease in physical/chemical and bioactivity favorability. In contrast, fine-tuning with Compass shows a limited improvement in RMSD < 2{\AA} but enhances the physical/chemical and bioactivity favorability of the ligand conformation. The source code is available publicly at https://github.com/BIMSBbioinfo/CompassDock.
Authors: Grigor Bezirganyan, Sana Sellami, Laure Berti-\'Equille, S\'ebastien Fournier
Abstract: Multimodal Deep Learning enhances decision-making by integrating diverse information sources, such as texts, images, audio, and videos. To develop trustworthy multimodal approaches, it is essential to understand how uncertainty impacts these models. We propose LUMA, a unique benchmark dataset, featuring audio, image, and textual data from 50 classes, for learning from uncertain and multimodal data. It extends the well-known CIFAR 10/100 dataset with audio samples extracted from three audio corpora, and text data generated using the Gemma-7B Large Language Model (LLM). The LUMA dataset enables the controlled injection of varying types and degrees of uncertainty to achieve and tailor specific experiments and benchmarking initiatives. LUMA is also available as a Python package including the functions for generating multiple variants of the dataset with controlling the diversity of the data, the amount of noise for each modality, and adding out-of-distribution samples. A baseline pre-trained model is also provided alongside three uncertainty quantification methods: Monte-Carlo Dropout, Deep Ensemble, and Reliable Conflictive Multi-View Learning. This comprehensive dataset and its benchmarking tools are intended to promote and support the development, evaluation, and benchmarking of trustworthy and robust multimodal deep learning approaches. We anticipate that the LUMA dataset will help the ICLR community to design more trustworthy and robust machine learning approaches for safety critical applications.
Authors: Lin Fan, Yafei Ou, Cenyang Zheng, Pengyu Dai, Tamotsu Kamishima, Masayuki Ikebe, Kenji Suzuki, Xun Gong
Abstract: Multi-modal fusion is crucial in medical data research, enabling a comprehensive understanding of diseases and improving diagnostic performance by combining diverse modalities. However, multi-modal fusion faces challenges, including capturing interactions between modalities, addressing missing modalities, handling erroneous modal information, and ensuring interpretability. Many existing researchers tend to design different solutions for these problems, often overlooking the commonalities among them. This paper proposes a novel multi-modal fusion framework that achieves adaptive adjustment over the weights of each modality by introducing the Modal-Domain Attention (MDA). It aims to facilitate the fusion of multi-modal information while allowing for the inclusion of missing modalities or intrinsic noise, thereby enhancing the representation of multi-modal data. We provide visualizations of accuracy changes and MDA weights by observing the process of modal fusion, offering a comprehensive analysis of its interpretability. Extensive experiments on various gastrointestinal disease benchmarks, the proposed MDA maintains high accuracy even in the presence of missing modalities and intrinsic noise. One thing worth mentioning is that the visualization of MDA is highly consistent with the conclusions of existing clinical studies on the dependence of different diseases on various modalities. Code and dataset will be made available.
Authors: Vahid Jebraeeli, Bo Jiang, Hamid Krim, Derya Cansever
Abstract: Limited data availability in machine learning significantly impacts performance and generalization. Traditional augmentation methods enhance moderately sufficient datasets. GANs struggle with convergence when generating diverse samples. Diffusion models, while effective, have high computational costs. We introduce an Expansive Synthesis model generating large-scale, information-rich datasets from minimal samples. It uses expander graph mappings and feature interpolation to preserve data distribution and feature relationships. The model leverages neural networks' non-linear latent space, captured by a Koopman operator, to create a linear feature space for dataset expansion. An autoencoder with self-attention layers and optimal transport refines distributional consistency. We validate by comparing classifiers trained on generated data to those trained on original datasets. Results show comparable performance, demonstrating the model's potential to augment training data effectively. This work advances data generation, addressing scarcity in machine learning applications.
Authors: Dibyajyoti Chakraborty, Seung Whan Chung, Troy Arcomano, Romit Maulik
Abstract: Forecasting high-dimensional dynamical systems is a fundamental challenge in various fields, such as geosciences and engineering. Neural Ordinary Differential Equations (NODEs), which combine the power of neural networks and numerical solvers, have emerged as a promising algorithm for forecasting complex nonlinear dynamical systems. However, classical techniques used for NODE training are ineffective for learning chaotic dynamical systems. In this work, we propose a novel NODE-training approach that allows for robust learning of chaotic dynamical systems. Our method addresses the challenges of non-convexity and exploding gradients associated with underlying chaotic dynamics. Training data trajectories from such systems are split into multiple, non-overlapping time windows. In addition to the deviation from the training data, the optimization loss term further penalizes the discontinuities of the predicted trajectory between the time windows. The window size is selected based on the fastest Lyapunov time scale of the system. Multi-step penalty(MP) method is first demonstrated on Lorenz equation, to illustrate how it improves the loss landscape and thereby accelerates the optimization convergence. MP method can optimize chaotic systems in a manner similar to least-squares shadowing with significantly lower computational costs. Our proposed algorithm, denoted the Multistep Penalty NODE, is applied to chaotic systems such as the Kuramoto-Sivashinsky equation, the two-dimensional Kolmogorov flow, and ERA5 reanalysis data for the atmosphere. It is observed that MP-NODE provide viable performance for such chaotic systems, not only for short-term trajectory predictions but also for invariant statistics that are hallmarks of the chaotic nature of these dynamics.
Authors: Carlo Orientale Caputo, Matteo Marsili
Abstract: We study how abstract representations emerge in a Deep Belief Network (DBN) trained on benchmark datasets. Our analysis targets the principles of learning in the early stages of information processing, starting from the "primordial soup" of the under-sampling regime. As the data is processed by deeper and deeper layers, features are detected and removed, transferring more and more "context-invariant" information to deeper layers. We show that the representation approaches an universal model -- the Hierarchical Feature Model (HFM) -- determined by the principle of maximal relevance. Relevance quantifies the uncertainty on the model of the data, thus suggesting that "meaning" -- i.e. syntactic information -- is that part of the data which is not yet captured by a model. Our analysis shows that shallow layers are well described by pairwise Ising models, which provide a representation of the data in terms of generic, low order features. We also show that plasticity increases with depth, in a similar way as it does in the brain. These findings suggest that DBNs are capable of extracting a hierarchy of features from the data which is consistent with the principle of maximal relevance.
Authors: Robin C. Geyer, Alessandro Torcinovich, Jo\~ao B. Carvalho, Alexander Meyer, Joachim M. Buhmann
Abstract: In unsupervised representation learning, models aim to distill essential features from high-dimensional data into lower-dimensional learned representations, guided by inductive biases. Understanding the characteristics that make a good representation remains a topic of ongoing research. Disentanglement of independent generative processes has long been credited with producing high-quality representations. However, focusing solely on representations that adhere to the stringent requirements of most disentanglement metrics, may result in overlooking many high-quality representations, well suited for various downstream tasks. These metrics often demand that generative factors be encoded in distinct, single dimensions aligned with the canonical basis of the representation space. Motivated by these observations, we propose two novel metrics: Importance-Weighted Orthogonality (IWO) and Importance-Weighted Rank (IWR). These metrics evaluate the mutual orthogonality and rank of generative factor subspaces. Throughout extensive experiments on common downstream tasks, over several benchmark datasets and models, IWO and IWR consistently show stronger correlations with downstream task performance than traditional disentanglement metrics. Our findings suggest that representation quality is closer related to the orthogonality of independent generative processes rather than their disentanglement, offering a new direction for evaluating and improving unsupervised learning models.
Authors: Hao Feng, Boyuan Zhang, Fanjiang Ye, Min Si, Ching-Hsiang Chu, Jiannan Tian, Chunxing Yin, Summer Deng, Yuchen Hao, Pavan Balaji, Tong Geng, Dingwen Tao
Abstract: DLRM is a state-of-the-art recommendation system model that has gained widespread adoption across various industry applications. The large size of DLRM models, however, necessitates the use of multiple devices/GPUs for efficient training. A significant bottleneck in this process is the time-consuming all-to-all communication required to collect embedding data from all devices. To mitigate this, we introduce a method that employs error-bounded lossy compression to reduce the communication data size and accelerate DLRM training. We develop a novel error-bounded lossy compression algorithm, informed by an in-depth analysis of embedding data features, to achieve high compression ratios. Moreover, we introduce a dual-level adaptive strategy for error-bound adjustment, spanning both table-wise and iteration-wise aspects, to balance the compression benefits with the potential impacts on accuracy. We further optimize our compressor for PyTorch tensors on GPUs, minimizing compression overhead. Evaluation shows that our method achieves a 1.38$\times$ training speedup with a minimal accuracy impact.
Authors: Long Wei, Peiyan Hu, Ruiqi Feng, Haodong Feng, Yixuan Du, Tao Zhang, Rui Wang, Yue Wang, Zhi-Ming Ma, Tailin Wu
Abstract: Controlling the evolution of complex physical systems is a fundamental task across science and engineering. Classical techniques suffer from limited applicability or huge computational costs. On the other hand, recent deep learning and reinforcement learning-based approaches often struggle to optimize long-term control sequences under the constraints of system dynamics. In this work, we introduce Diffusion Physical systems Control (DiffPhyCon), a new class of method to address the physical systems control problem. DiffPhyCon excels by simultaneously minimizing both the learned generative energy function and the predefined control objectives across the entire trajectory and control sequence. Thus, it can explore globally and plan near-optimal control sequences. Moreover, we enhance DiffPhyCon with prior reweighting, enabling the discovery of control sequences that significantly deviate from the training distribution. We test our method on three tasks: 1D Burgers' equation, 2D jellyfish movement control, and 2D high-dimensional smoke control, where our generated jellyfish dataset is released as a benchmark for complex physical system control research. Our method outperforms widely applied classical approaches and state-of-the-art deep learning and reinforcement learning methods. Notably, DiffPhyCon unveils an intriguing fast-close-slow-open pattern observed in the jellyfish, aligning with established findings in the field of fluid dynamics. The project website, jellyfish dataset, and code can be found at https://github.com/AI4Science-WestlakeU/diffphycon.
Authors: Arsenii Mustafin, Aleksei Pakharev, Alex Olshevsky, Ioannis Ch. Paschalidis
Abstract: The Markov Decision Process (MDP) is a widely used mathematical model for sequential decision-making problems. In this paper, we present a new geometric interpretation of MDPs. Based on this interpretation, we show that MDPs can be divided into equivalence classes with indistinguishable key solving algorithms dynamics. This related normalization procedure enables the development of a novel class of MDP-solving algorithms that find optimal policies without computing policy values. The new algorithms we propose for different settings achieve and, in some cases, improve upon state-of-the-art results.
Authors: Matt Clifford, Jonathan Erskine, Alexander Hepburn, Ra\'ul Santos-Rodr\'iguez, Dario Garcia-Garcia
Abstract: Class imbalance poses a significant challenge in classification tasks, where traditional approaches often lead to biased models and unreliable predictions. Undersampling and oversampling techniques have been commonly employed to address this issue, yet they suffer from inherent limitations stemming from their simplistic approach such as loss of information and additional biases respectively. In this paper, we propose a novel framework that leverages learning theory and concentration inequalities to overcome the shortcomings of traditional solutions. We focus on understanding the uncertainty in a class-dependent manner, as captured by confidence bounds that we directly embed into the learning process. By incorporating class-dependent estimates, our method can effectively adapt to the varying degrees of imbalance across different classes, resulting in more robust and reliable classification outcomes. We empirically show how our framework provides a promising direction for handling imbalanced data in classification tasks, offering practitioners a valuable tool for building more accurate and trustworthy models.
Authors: Yuyang Xue, Junyu Yan, Raman Dutt, Fasih Haider, Jingshuai Liu, Steven McDonagh, Sotirios A. Tsaftaris
Abstract: Developing models with robust group fairness properties is paramount, particularly in ethically sensitive domains such as medical diagnosis. Recent approaches to achieving fairness in machine learning require a substantial amount of training data and depend on model retraining, which may not be practical in real-world scenarios. To mitigate these challenges, we propose Bias-based Weight Masking Fine-Tuning (BMFT), a novel post-processing method that enhances the fairness of a trained model in significantly fewer epochs without requiring access to the original training data. BMFT produces a mask over model parameters, which efficiently identifies the weights contributing the most towards biased predictions. Furthermore, we propose a two-step debiasing strategy, wherein the feature extractor undergoes initial fine-tuning on the identified bias-influenced weights, succeeded by a fine-tuning phase on a reinitialised classification layer to uphold discriminative performance. Extensive experiments across four dermatological datasets and two sensitive attributes demonstrate that BMFT outperforms existing state-of-the-art (SOTA) techniques in both diagnostic accuracy and fairness metrics. Our findings underscore the efficacy and robustness of BMFT in advancing fairness across various out-of-distribution (OOD) settings. Our code is available at: https://github.com/vios-s/BMFT
Authors: Giovanni Piunno, Ioannis Stefanou, Cristina Jommi
Abstract: This paper introduces a novel approach that combines Proper Orthogonal Decomposition (POD) with Thermodynamics-based Artificial Neural Networks (TANN) to capture the macroscopic behavior of complex inelastic systems and derive macroelements in geomechanics. The methodology leverages POD to extract macroscopic Internal State Variables from microscopic state information, thereby enriching the macroscopic state description used to train an energy potential network within the TANN framework. The thermodynamic consistency provided by TANN, combined with the hierarchical nature of POD, allows to reproduce complex, non-linear inelastic material behaviors as well as macroscopic geomechanical systems responses. The approach is validated through applications of increasing complexity, demonstrating its capability to reproduce high-fidelity simulation data. The applications proposed include the homogenization of continuous inelastic representative unit cells and the derivation of a macroelement for a geotechnical system involving a monopile in a clay layer subjected to horizontal loading. Eventually, the projection operators directly obtained via POD, are exploit to easily reconstruct the microscopic fields. The results indicate that the POD-TANN approach not only offers accuracy in reproducing the studied constitutive responses, but also reduces computational costs, making it a practical tool for the multiscale modeling of heterogeneous inelastic geomechanical systems.
Authors: Chenqing Hua, Bozitao Zhong, Sitao Luan, Liang Hong, Guy Wolf, Doina Precup, Shuangjia Zheng
Abstract: Enzymes, with their specific catalyzed reactions, are necessary for all aspects of life, enabling diverse biological processes and adaptations. Predicting enzyme functions is essential for understanding biological pathways, guiding drug development, enhancing bioproduct yields, and facilitating evolutionary studies. Addressing the inherent complexities, we introduce a new approach to annotating enzymes based on their catalyzed reactions. This method provides detailed insights into specific reactions and is adaptable to newly discovered reactions, diverging from traditional classifications by protein family or expert-derived reaction classes. We employ machine learning algorithms to analyze enzyme reaction datasets, delivering a much more refined view on the functionality of enzymes. Our evaluation leverages the largest enzyme-reaction dataset to date, derived from the SwissProt and Rhea databases with entries up to January 8, 2024. We frame the enzyme-reaction prediction as a retrieval problem, aiming to rank enzymes by their catalytic ability for specific reactions. With our model, we can recruit proteins for novel reactions and predict reactions in novel proteins, facilitating enzyme discovery and function annotation (https://github.com/WillHua127/ReactZyme).
Authors: Xuan Zhao, Klaus Broelemann, Salvatore Ruggieri, Gjergji Kasneci
Abstract: We introduce an innovative approach to enhancing the empirical risk minimization (ERM) process in model training through a refined reweighting scheme of the training data to enhance fairness. This scheme aims to uphold the sufficiency rule in fairness by ensuring that optimal predictors maintain consistency across diverse sub-groups. We employ a bilevel formulation to address this challenge, wherein we explore sample reweighting strategies. Unlike conventional methods that hinge on model size, our formulation bases generalization complexity on the space of sample weights. We discretize the weights to improve training speed. Empirical validation of our method showcases its effectiveness and robustness, revealing a consistent improvement in the balance between prediction performance and fairness metrics across various experiments.
Authors: Minghai Qin
Abstract: We have observed a distinctive quantization-related behavior in the LLaMA3/3.1-70B models that is absent in both the LLaMA2-70B and LLaMA3/3.1/3.2-1B/3B/8B/405B models. Quantization is a crucial technique for deploying large language models (LLMs) efficiently. The impact of W8A8 post-training quantization on model accuracy, especially on the recently released LLaMA3/3.1 model series, remains contentious. In this paper, we explore three key questions: What makes the LLaMA3-70B model series uniquely vulnerable to quantization? Why is this the case? And how can the issue be addressed? We empirically investigate multiple LLMs featured on an open LLM leaderboard, discovering that the LLaMA3-70B model series have a unique accuracy degradation behavior with W8A8 per-channel post-training quantization. In contrast, other model series such as LLaMA2, LLaMA3/3.1-8B, LLaMA3.2, Qwen, Mixtral, Mistral, Phi-3, and Falcon demonstrate robust performance with W8A8. Contrary to previous assertions attributing degradation to the large dynamic range of activations, our findings indicate that the weight distribution of the LLaMA3-70B is the primary factor behind the vulnerability. By meticulously analyzing the distinct characteristics of weight distributions across Transformer blocks, we propose two solutions that make different tradeoffs in hardware/software overhead. First, we propose a mixed strategy where less than 3\% of the layers employ finer per-group W8A8 quantization granularity. Second, we introduce a bi-smoothing strategy that balances quantization errors between weights and activations while maintaining per-channel quantization throughout. Experimental results demonstrate that both strategies effectively preserve the accuracy of the entire LLaMA3-70B model series under W8A8 quantization, achieving performance on par with their FP16 counterparts.
Authors: Zhichao Wang, Bin Bi, Can Huang, Shiva Kumar Pentyala, Zixu James Zhu, Sitaram Asur, Na Claire Cheng
Abstract: An LLM is pretrained on trillions of tokens, but the pretrained LLM may still generate undesired responses. To solve this problem, alignment techniques such as RLHF, DPO and KTO are proposed. However, these alignment techniques have limitations. For example, RLHF requires training the reward model and policy separately, which is complex, time-consuming, memory intensive and unstable during training processes. DPO proposes a mapping between an optimal policy and a reward, greatly simplifying the training process of RLHF. However, it can not take full advantages of a reward model and it is limited to pairwise preference data. In this paper, we propose \textbf{UN}ified \textbf{A}lignment (UNA) which unifies RLHF/PPO, DPO and KTO. Firstly, we mathematically prove that given the classical RLHF objective, the optimal policy is induced by a generalize implicit reward function. With this novel mapping between a reward model and an optimal policy, UNA can 1. unify RLHF/PPO, DPO and KTO into a supervised learning of minimizing the difference between an implicit reward and an explicit reward; 2. outperform RLHF/PPO while simplify, stabilize, speed up and reduce memory burden of RL fine-tuning process; 3. accommodate different feedback types including pairwise, binary and scalar feedback. Downstream experiments show UNA outperforms DPO, KTO and RLHF.
Authors: Mustafa Co\c{s}kun, Ananth Grama, Mehmet Koyut\"urk
Abstract: Spectral Graph Convolutional Networks (GCNs) have gained popularity in graph machine learning applications due, in part, to their flexibility in specification of network propagation rules. These propagation rules are often constructed as polynomial filters whose coefficients are learned using label information during training. In contrast to learned polynomial filters, explicit filter functions are useful in capturing relationships between network topology and distribution of labels across the network. A number of algorithms incorporating either approach have been proposed; however the relationship between filter functions and polynomial approximations is not fully resolved. This is largely due to the ill-conditioned nature of the linear systems that must be solved to derive polynomial approximations of filter functions. To address this challenge, we propose a novel Arnoldi orthonormalization-based algorithm, along with a unifying approach, called G-Arnoldi-GCN that can efficiently and effectively approximate a given filter function with a polynomial. We evaluate G-Arnoldi-GCN in the context of multi-class node classification across ten datasets with diverse topological characteristics. Our experiments show that G-Arnoldi-GCN consistently outperforms state-of-the-art methods when suitable filter functions are employed. Overall, G-Arnoldi-GCN opens important new directions in graph machine learning by enabling the explicit design and application of diverse filter functions. Code link: https://github.com/mustafaCoskunAgu/GArnoldi-GCN
Authors: Lars B\"ocking, Leopold M\"uller, Niklas K\"uhl
Abstract: The selection of algorithms is a crucial step in designing AI services for real-world time series classification use cases. Traditional methods such as neural architecture search, automated machine learning, combined algorithm selection, and hyperparameter optimizations are effective but require considerable computational resources and necessitate access to all data points to run their optimizations. In this work, we introduce a novel data fingerprint that describes any time series classification dataset in a privacy-preserving manner and provides insight into the algorithm selection problem without requiring training on the (unseen) dataset. By decomposing the multi-target regression problem, only our data fingerprints are used to estimate algorithm performance and uncertainty in a scalable and adaptable manner. Our approach is evaluated on the 112 University of California riverside benchmark datasets, demonstrating its effectiveness in predicting the performance of 35 state-of-the-art algorithms and providing valuable insights for effective algorithm selection in time series classification service systems, improving a naive baseline by 7.32% on average in estimating the mean performance and 15.81% in estimating the uncertainty.
Authors: Mehroush Banday, Sherin Zafar, Parul Agarwal, M Afshar Alam, Abubeker K M
Abstract: Coronary heart disease (CHD) is a severe cardiac disease, and hence, its early diagnosis is essential as it improves treatment results and saves money on medical care. The prevailing development of quantum computing and machine learning (ML) technologies may bring practical improvement to the performance of CHD diagnosis. Quantum machine learning (QML) is receiving tremendous interest in various disciplines due to its higher performance and capabilities. A quantum leap in the healthcare industry will increase processing power and optimise multiple models. Techniques for QML have the potential to forecast cardiac disease and help in early detection. To predict the risk of coronary heart disease, a hybrid approach utilizing an ensemble machine learning model based on QML classifiers is presented in this paper. Our approach, with its unique ability to address multidimensional healthcare data, reassures the method's robustness by fusing quantum and classical ML algorithms in a multi-step inferential framework. The marked rise in heart disease and death rates impacts worldwide human health and the global economy. Reducing cardiac morbidity and mortality requires early detection of heart disease. In this research, a hybrid approach utilizes techniques with quantum computing capabilities to tackle complex problems that are not amenable to conventional machine learning algorithms and to minimize computational expenses. The proposed method has been developed in the Raspberry Pi 5 Graphics Processing Unit (GPU) platform and tested on a broad dataset that integrates clinical and imaging data from patients suffering from CHD and healthy controls. Compared to classical machine learning models, the accuracy, sensitivity, F1 score, and specificity of the proposed hybrid QML model used with CHD are manifold higher.
Authors: Sunny Gupta, Mohit Jindal, Pankhi Kashyap, Pranav Jeevan, Amit Sethi
Abstract: Federated learning faces a critical challenge in balancing communication efficiency with rapid convergence, especially for second-order methods. While Newton-type algorithms achieve linear convergence in communication rounds, transmitting full Hessian matrices is often impractical due to quadratic complexity. We introduce Federated Learning with Enhanced Nesterov-Newton Sketch (FLeNS), a novel method that harnesses both the acceleration capabilities of Nesterov's method and the dimensionality reduction benefits of Hessian sketching. FLeNS approximates the centralized Newton's method without relying on the exact Hessian, significantly reducing communication overhead. By combining Nesterov's acceleration with adaptive Hessian sketching, FLeNS preserves crucial second-order information while preserving the rapid convergence characteristics. Our theoretical analysis, grounded in statistical learning, demonstrates that FLeNS achieves super-linear convergence rates in communication rounds - a notable advancement in federated optimization. We provide rigorous convergence guarantees and characterize tradeoffs between acceleration, sketch size, and convergence speed. Extensive empirical evaluation validates our theoretical findings, showcasing FLeNS's state-of-the-art performance with reduced communication requirements, particularly in privacy-sensitive and edge-computing scenarios. The code is available at https://github.com/sunnyinAI/FLeNS
Authors: Benjamin Feuer, Micah Goldblum, Teresa Datta, Sanjana Nambiar, Raz Besaleli, Samuel Dooley, Max Cembalest, John P. Dickerson
Abstract: The release of ChatGPT in November 2022 sparked an explosion of interest in post-training and an avalanche of new preference optimization (PO) methods. These methods claim superior alignment by virtue of better correspondence with human pairwise preferences, often measured by LLM-judges. In this work, we attempt to answer the following question -- do LLM-judge preferences translate to progress on other, more concrete metrics for alignment, and if not, why not? We define a concrete metric for alignment, and introduce SOS-Bench (Substance Outweighs Style Benchmark), which is to the best of our knowledge the largest standardized, reproducible LLM meta-benchmark to date. We find that (1) LLM-judge preferences do not correlate with concrete measures of safety, world knowledge, and instruction following; (2) LLM-judges have powerful implicit biases, prioritizing style over factuality and safety; and (3) the supervised fine-tuning (SFT) stage of post-training, and not the PO stage, has the greatest impact on alignment, with data scaling and prompt diversity as the driving factors. Our codebase and complete results can be found at https://github.com/penfever/sos-bench.
Authors: East Sun, Yan Wang, Lan Tian
Abstract: We introduce Block-Attention, an attention mechanism designed to address the increased inference latency and cost in Retrieval-Augmented Generation (RAG) scenarios. Traditional approaches often encode the entire context. Instead, Block-Attention divides retrieved documents into discrete blocks, with each block independently calculating key-value (KV) states except for the final block. In RAG scenarios, by defining each passage as a block, Block-Attention enables us to reuse the KV states of passages that have been seen before, thereby significantly reducing the latency and the computation overhead during inference. The implementation of Block-Attention involves block segmentation, position re-encoding, and fine-tuning the LLM to adapt to the Block-Attention mechanism. Experiments on four RAG benchmarks demonstrate that after block fine-tuning, the Block-Attention model achieves performance comparable to self-attention models (68.4\% vs 67.9\% on Llama3) or even superior performance (62.8\% vs 59.6\% on Mistral). Notably, Block-Attention significantly reduces the time to first token (TTFT) and floating point operations (FLOPs) to a very low level. It only takes 45 ms to output the first token for an input sequence with a total length of 32K. Compared to the self-attention models, the time consumption and corresponding FLOPs are reduced by 98.7\% and 99.8\%, respectively.
Authors: Chenlin Wu, Xiaoyu He, Zike Li, Zibin Zheng
Abstract: Federated learning heavily relies on distributed gradient descent techniques. In the situation where gradient information is not available, the gradients need to be estimated from zeroth-order information, which typically involves computing finite-differences along isotropic random directions. This method suffers from high estimation errors, as the geometric features of the objective landscape may be overlooked during the isotropic sampling. In this work, we propose a non-isotropic sampling method to improve the gradient estimation procedure. Gradients in our method are estimated in a subspace spanned by historical trajectories of solutions, aiming to encourage the exploration of promising regions and hence improve the convergence. The proposed method uses a covariance matrix for sampling which is a convex combination of two parts. The first part is a thin projection matrix containing the basis of the subspace which is designed to improve the exploitation ability. The second part is the historical trajectories. We implement this method in zeroth-order federated settings, and show that the convergence rate aligns with existing ones while introducing no significant overheads in communication or local computation. The effectiveness of our proposal is verified on several numerical experiments in comparison to several commonly-used zeroth-order federated optimization algorithms.
Authors: Bo Yue, Jian Li, Guiliang Liu
Abstract: To obtain the optimal constraints in complex environments, Inverse Constrained Reinforcement Learning (ICRL) seeks to recover these constraints from expert demonstrations in a data-driven manner. Existing ICRL algorithms collect training samples from an interactive environment. However, the efficacy and efficiency of these sampling strategies remain unknown. To bridge this gap, we introduce a strategic exploration framework with guaranteed efficiency. Specifically, we define a feasible constraint set for ICRL problems and investigate how expert policy and environmental dynamics influence the optimality of constraints. Motivated by our findings, we propose two exploratory algorithms to achieve efficient constraint inference via 1) dynamically reducing the bounded aggregate error of cost estimation and 2) strategically constraining the exploration policy. Both algorithms are theoretically grounded with tractable sample complexity. We empirically demonstrate the performance of our algorithms under various environments.
Authors: Ziyu Zhao, Tao Shen, Didi Zhu, Zexi Li, Jing Su, Xuwu Wang, Kun Kuang, Fei Wu
Abstract: Low-Rank Adaptation (LoRA) has emerged as a popular technique for fine-tuning large language models (LLMs) to various domains due to its modular design and widespread availability on platforms like Huggingface. This modularity has sparked interest in combining multiple LoRAs to enhance LLM capabilities. However, existing methods for LoRA composition primarily focus on task-specific adaptations that require additional training, and current model merging techniques often fail to fully leverage LoRA's modular nature, leading to parameter interference and performance degradation. In this paper, we investigate the feasibility of disassembling and reassembling multiple LoRAs at a finer granularity, analogous to assembling LEGO blocks. We introduce the concept of Minimal Semantic Units (MSUs), where the parameters corresponding to each rank in LoRA function as independent units. These MSUs demonstrate permutation invariance and concatenation-summation equivalence properties, enabling flexible combinations to create new LoRAs. Building on these insights, we propose the LoRA-LEGO framework. This framework conducts rank-wise parameter clustering by grouping MSUs from different LoRAs into $k$ clusters. The centroid of each cluster serves as a representative MSU, enabling the assembly of a merged LoRA with an adjusted rank of $k$. Additionally, we apply a dual reweighting strategy to optimize the scale of the merged LoRA. Experiments across various benchmarks demonstrate that our method outperforms existing approaches in LoRA merging.
Authors: Swadhin Das, Raksha Sharma
Abstract: Remote sensing images are highly valued for their ability to address complex real-world issues such as risk management, security, and meteorology. However, manually captioning these images is challenging and requires specialized knowledge across various domains. This letter presents an approach for automatically describing (captioning) remote sensing images. We propose a novel encoder-decoder setup that deploys a Text Graph Convolutional Network (TextGCN) and multi-layer LSTMs. The embeddings generated by TextGCN enhance the decoder's understanding by capturing the semantic relationships among words at both the sentence and corpus levels. Furthermore, we advance our approach with a comparison-based beam search method to ensure fairness in the search strategy for generating the final caption. We present an extensive evaluation of our approach against various other state-of-the-art encoder-decoder frameworks. We evaluated our method across three datasets using seven metrics: BLEU-1 to BLEU-4, METEOR, ROUGE-L, and CIDEr. The results demonstrate that our approach significantly outperforms other state-of-the-art encoder-decoder methods.
Authors: Michael S. Yao, Allison Chae, Charles E. Kahn Jr., Walter R. Witschey, James C. Gee, Hersh Sagreiya, Osbert Bastani
Abstract: Diagnostic imaging studies are an increasingly important component of the workup and management of acutely presenting patients. However, ordering appropriate imaging studies according to evidence-based medical guidelines is a challenging task with a high degree of variability between healthcare providers. To address this issue, recent work has investigated if generative AI and large language models can be leveraged to help clinicians order relevant imaging studies for patients. However, it is challenging to ensure that these tools are correctly aligned with medical guidelines, such as the American College of Radiology's Appropriateness Criteria (ACR AC). In this study, we introduce a framework to intelligently leverage language models by recommending imaging studies for patient cases that are aligned with evidence-based guidelines. We make available a novel dataset of patient "one-liner" scenarios to power our experiments, and optimize state-of-the-art language models to achieve an accuracy on par with clinicians in image ordering. Finally, we demonstrate that our language model-based pipeline can be used as intelligent assistants by clinicians to support image ordering workflows and improve the accuracy of imaging study ordering according to the ACR AC. Our work demonstrates and validates a strategy to leverage AI-based software to improve trustworthy clinical decision making in alignment with expert evidence-based guidelines.
Authors: Subash Timilsina, Sagar Shrestha, Xiao Fu
Abstract: A core task in multi-modal learning is to integrate information from multiple feature spaces (e.g., text and audio), offering modality-invariant essential representations of data. Recent research showed that, classical tools such as {\it canonical correlation analysis} (CCA) provably identify the shared components up to minor ambiguities, when samples in each modality are generated from a linear mixture of shared and private components. Such identifiability results were obtained under the condition that the cross-modality samples are aligned/paired according to their shared information. This work takes a step further, investigating shared component identifiability from multi-modal linear mixtures where cross-modality samples are unaligned. A distribution divergence minimization-based loss is proposed, under which a suite of sufficient conditions ensuring identifiability of the shared components are derived. Our conditions are based on cross-modality distribution discrepancy characterization and density-preserving transform removal, which are much milder than existing studies relying on independent component analysis. More relaxed conditions are also provided via adding reasonable structural constraints, motivated by available side information in various applications. The identifiability claims are thoroughly validated using synthetic and real-world data.
Authors: Ethan Blaser, Shangtong Zhang
Abstract: Tabular average reward Temporal Difference (TD) learning is perhaps the simplest and the most fundamental policy evaluation algorithm in average reward reinforcement learning. After at least 25 years since its discovery, we are finally able to provide a long-awaited almost sure convergence analysis. Namely, we are the first to prove that, under very mild conditions, tabular average reward TD converges almost surely to a sample path dependent fixed point. Key to this success is a new general stochastic approximation result concerning nonexpansive mappings with Markovian and additive noise, built on recent advances in stochastic Krasnoselskii-Mann iterations.
Authors: Zezhou Wang, Yaxin Du, Zhuzhong Qian, Siheng Chen
Abstract: Federated Domain-specific Instruction Tuning (FedDIT) utilizes limited cross-client private data alongside server-side public data for instruction augmentation, ultimately enhancing model performance within specific domains. While the factors affecting FedDIT remain unclear and existing instruction augmentation methods mainly focus on the centralized setting without considering the distributed environment. Our experiments reveal that the cross-client domain coverage, rather than data heterogeneity, drives model performance in FedDIT. In response, we propose FedDCA, which optimizes domain coverage through greedy client center selection and retrieval-based augmentation. To alleviate client-side computational burdens, FedDCA$^*$ uses heterogeneous encoders with server-side feature alignment. Extensive experiments across four distinct domains (code, medical, financial, and mathematical) substantiate the effectiveness of both methods. Additionally, we investigate privacy preservation against memory extraction attacks utilizing varying amounts of public data. Results show no significant correlation between the volume of public data and the privacy-preserving capability. However, as the fine-tuning round increases, the risk of privacy leakage reduces or converges.
Authors: Haixiang Wu
Abstract: For multivariate time series (MTS) tasks, previous state space models (SSMs) followed the modeling paradigm of Transformer-based methods. However, none of them explicitly model the complex dependencies of MTS: the Channel Dependency variations with Time (CDT). In view of this, we delve into the derivation of SSM, which involves approximating continuously updated functions by orthogonal function basis. We then develop Poly-Mamba, a novel method for MTS forecasting. Its core concept is to expand the original orthogonal function basis space into a multivariate orthogonal function space containing variable mixing terms, and make a projection on this space so as to explicitly describe the CDT by weighted coefficients. In Poly-Mamba, we propose the Multivariate Orthogonal Polynomial Approximation (MOPA) as a simplified implementation of this concept. For the simple linear relationship between channels, we propose Linear Channel Mixing (LCM) and generate CDT patterns adaptively for different channels through a proposed Order Combining method. Experiments on six real-world datasets demonstrate that Poly-Mamba outperforms the SOTA methods, especially when dealing with datasets having a large number of channels and complex correlations. The codes and log files will be released at: https://github.com/Joeland4/Poly-Mamba.
Authors: Kuba Weimann, Tim O. F. Conrad
Abstract: Recommender systems suffer from the cold-start problem whenever a new user joins the platform or a new item is added to the catalog. To address item cold-start, we propose to replace the embedding layer in sequential recommenders with a dynamic storage that has no learnable weights and can keep an arbitrary number of representations. In this paper, we present FELRec, a large embedding network that refines the existing representations of users and items in a recursive manner, as new information becomes available. In contrast to similar approaches, our model represents new users and items without side information and time-consuming finetuning, instead it runs a single forward pass over a sequence of existing representations. During item cold-start, our method outperforms similar method by 29.50%-47.45%. Further, our proposed model generalizes well to previously unseen datasets in zero-shot settings. The source code is publicly available at https://github.com/kweimann/FELRec .
Authors: Yuanyuan Yang, Claire Birnie, Tariq Alkhalifah
Abstract: Microseismic event detection and location are two primary components in microseismic monitoring, which offers us invaluable insights into the subsurface during reservoir stimulation and evolution. Conventional approaches for event detection and location often suffer from manual intervention and/or heavy computation, while current machine learning-assisted approaches typically address detection and location separately; such limitations hinder the potential for real-time microseismic monitoring. We propose an approach to unify event detection and source location into a single framework by adapting a Convolutional Neural Network backbone and an encoder-decoder Transformer with a set-based Hungarian loss, which is applied directly to recorded waveforms. The proposed network is trained on synthetic data simulating multiple microseismic events corresponding to random source locations in the area of suspected microseismic activities. A synthetic test on a 2D profile of the SEAM Time Lapse model illustrates the capability of the proposed method in detecting the events properly and locating them in the subsurface accurately; while, a field test using the Arkoma Basin data further proves its practicability, efficiency, and its potential in paving the way for real-time monitoring of microseismic events.
Authors: Edmund Lau, Zach Furman, George Wang, Daniel Murfet, Susan Wei
Abstract: The Local Learning Coefficient (LLC) is introduced as a novel complexity measure for deep neural networks (DNNs). Recognizing the limitations of traditional complexity measures, the LLC leverages Singular Learning Theory (SLT), which has long recognized the significance of singularities in the loss landscape geometry. This paper provides an extensive exploration of the LLC's theoretical underpinnings, offering both a clear definition and intuitive insights into its application. Moreover, we propose a new scalable estimator for the LLC, which is then effectively applied across diverse architectures including deep linear networks up to 100M parameters, ResNet image models, and transformer language models. Empirical evidence suggests that the LLC provides valuable insights into how training heuristics might influence the effective complexity of DNNs. Ultimately, the LLC emerges as a crucial tool for reconciling the apparent contradiction between deep learning's complexity and the principle of parsimony.
Authors: Marcus M. Noack, Hengrui Luo, Mark D. Risser
Abstract: The Gaussian process (GP) is a popular statistical technique for stochastic function approximation and uncertainty quantification from data. GPs have been adopted into the realm of machine learning in the last two decades because of their superior prediction abilities, especially in data-sparse scenarios, and their inherent ability to provide robust uncertainty estimates. Even so, their performance highly depends on intricate customizations of the core methodology, which often leads to dissatisfaction among practitioners when standard setups and off-the-shelf software tools are being deployed. Arguably the most important building block of a GP is the kernel function which assumes the role of a covariance operator. Stationary kernels of the Mat\'ern class are used in the vast majority of applied studies; poor prediction performance and unrealistic uncertainty quantification are often the consequences. Non-stationary kernels show improved performance but are rarely used due to their more complicated functional form and the associated effort and expertise needed to define and tune them optimally. In this perspective, we want to help ML practitioners make sense of some of the most common forms of non-stationarity for Gaussian processes. We show a variety of kernels in action using representative datasets, carefully study their properties, and compare their performances. Based on our findings, we propose a new kernel that combines some of the identified advantages of existing kernels.
Authors: Katharine M. Clark, Paul D. McNicholas
Abstract: Matrix-variate distributions are a recent addition to the model-based clustering field, thereby making it possible to analyze data in matrix form with complex structure such as images and time series. Due to its recent appearance, there is limited literature on matrix-variate data, with even less on dealing with outliers in these models. An approach for clustering matrix-variate normal data with outliers is discussed. The approach, which uses the distribution of subset log-likelihoods, extends the OCLUST algorithm to matrix-variate normal data and uses an iterative approach to detect and trim outliers.
Authors: Qingru Zhang, Chandan Singh, Liyuan Liu, Xiaodong Liu, Bin Yu, Jianfeng Gao, Tuo Zhao
Abstract: In human-written articles, we often leverage the subtleties of text style, such as bold and italics, to guide the attention of readers. These textual emphases are vital for the readers to grasp the conveyed information. When interacting with large language models (LLMs), we have a similar need -- steering the model to pay closer attention to user-specified information, e.g., an instruction. Existing methods, however, are constrained to process plain text and do not support such a mechanism. This motivates us to introduce PASTA -- Post-hoc Attention STeering Approach, a method that allows LLMs to read text with user-specified emphasis marks. To this end, PASTA identifies a small subset of attention heads and applies precise attention reweighting on them, directing the model attention to user-specified parts. Like prompting, PASTA is applied at inference time and does not require changing any model parameters. Experiments demonstrate that PASTA can substantially enhance an LLM's ability to follow user instructions or integrate new knowledge from user inputs, leading to a significant performance improvement on a variety of tasks, e.g., an average accuracy improvement of 22% for LLAMA-7B. Our code is publicly available at https://github.com/QingruZhang/PASTA .
Authors: Joseph Paul Cohen, Louis Blankemeier, Akshay Chaudhari
Abstract: Models driven by spurious correlations often yield poor generalization performance. We propose the counterfactual (CF) alignment method to detect and quantify spurious correlations of black box classifiers. Our methodology is based on counterfactual images generated with respect to one classifier being input into other classifiers to see if they also induce changes in the outputs of these classifiers. The relationship between these responses can be quantified and used to identify specific instances where a spurious correlation exists. This is validated by observing intuitive trends in a face-attribute face-attribute and waterbird classifiers, as well as by fabricating spurious correlations and detecting their presence, both visually and quantitatively. Furthermore, utilizing the CF alignment method, we demonstrate that we can evaluate robust optimization methods (GroupDRO, JTT, and FLAC) by detecting a reduction in spurious correlations.
Authors: Yafei Hu, Quanting Xie, Vidhi Jain, Jonathan Francis, Jay Patrikar, Nikhil Keetha, Seungchan Kim, Yaqi Xie, Tianyi Zhang, Hao-Shu Fang, Shibo Zhao, Shayegan Omidshafiei, Dong-Ki Kim, Ali-akbar Agha-mohammadi, Katia Sycara, Matthew Johnson-Roberson, Dhruv Batra, Xiaolong Wang, Sebastian Scherer, Chen Wang, Zsolt Kira, Fei Xia, Yonatan Bisk
Abstract: Building general-purpose robots that operate seamlessly in any environment, with any object, and utilizing various skills to complete diverse tasks has been a long-standing goal in Artificial Intelligence. However, as a community, we have been constraining most robotic systems by designing them for specific tasks, training them on specific datasets, and deploying them within specific environments. These systems require extensively-labeled data and task-specific models. When deployed in real-world scenarios, such systems face several generalization issues and struggle to remain robust to distribution shifts. Motivated by the impressive open-set performance and content generation capabilities of web-scale, large-capacity pre-trained models (i.e., foundation models) in research fields such as Natural Language Processing (NLP) and Computer Vision (CV), we devote this survey to exploring (i) how these existing foundation models from NLP and CV can be applied to the field of general-purpose robotics, and also exploring (ii) what a robotics-specific foundation model would look like. We begin by providing a generalized formulation of how foundation models are used in robotics, and the fundamental barriers to making generalist robots universally applicable. Next, we establish a taxonomy to discuss current work exploring ways to leverage existing foundation models for robotics and develop ones catered to robotics. Finally, we discuss key challenges and promising future directions in using foundation models for enabling general-purpose robotic systems. We encourage readers to view our living GitHub repository 2 of resources, including papers reviewed in this survey, as well as related projects and repositories for developing foundation models for robotics.
Authors: Weilong Chai, DanDan Zheng, Jiajiong Cao, Zhiquan Chen, Changbao Wang, Chenguang Ma
Abstract: Text-to-image diffusion models (SD) exhibit significant advancements while requiring extensive computational resources. Existing acceleration methods usually require extensive training and are not universally applicable. LCM-LoRA, trainable once for diverse models, offers universality but rarely considers ensuring the consistency of generated content before and after acceleration. This paper proposes SpeedUpNet (SUN), an innovative acceleration module, to address the challenges of universality and consistency. Exploiting the role of cross-attention layers in U-Net for SD models, we introduce an adapter specifically designed for these layers, quantifying the offset in image generation caused by negative prompts relative to positive prompts. This learned offset demonstrates stability across a range of models, enhancing SUN's universality. To improve output consistency, we propose a Multi-Step Consistency (MSC) loss, which stabilizes the offset and ensures fidelity in accelerated content. Experiments on SD v1.5 show that SUN leads to an overall speedup of more than 10 times compared to the baseline 25-step DPM-solver++, and offers two extra advantages: (1) training-free integration into various fine-tuned Stable-Diffusion models and (2) state-of-the-art FIDs of the generated data set before and after acceleration guided by random combinations of positive and negative prompts. Code is available: https://williechai.github.io/speedup-plugin-for-stable-diffusions.github.io.
URLs: https://williechai.github.io/speedup-plugin-for-stable-diffusions.github.io.
Authors: Emilio Morales-Juarez, Gibran Fuentes-Pineda
Abstract: Although the capacity of deep generative models for image generation, such as Diffusion Models (DMs) and Generative Adversarial Networks (GANs), has dramatically improved in recent years, much of their success can be attributed to computationally expensive architectures. This has limited their adoption and use to research laboratories and companies with large resources, while significantly raising the carbon footprint for training, fine-tuning, and inference. In this work, we present LadaGAN, an efficient generative adversarial network that is built upon a novel Transformer block named Ladaformer. The main component of this block is a linear additive-attention mechanism that computes a single attention vector per head instead of the quadratic dot-product attention. We employ Ladaformer in both the generator and discriminator, which reduces the computational complexity and overcomes the training instabilities often associated with Transformer GANs. LadaGAN consistently outperforms existing convolutional and Transformer GANs on benchmark datasets at different resolutions while being significantly more efficient. Moreover, LadaGAN shows competitive performance compared to state-of-the-art multi-step generative models (e.g. DMs) using orders of magnitude less computational resources.
Authors: Natasha K. Dudek, Mariam Chakhvadze, Saba Kobakhidze, Omar Kantidze, Yuriy Gankin
Abstract: Machine learning (ML) is set to accelerate innovations in clinical microbiomics, such as in disease diagnostics and prognostics. This will require high-quality, reproducible, interpretable workflows whose predictive capabilities meet or exceed the high thresholds set for clinical tools by regulatory agencies. Here, we capture a snapshot of current practices in the application of supervised ML to microbiomics data, through an in-depth analysis of 100 peer-reviewed journal articles published in 2021-2022. We apply a data-driven approach to steer discussion of the merits of varied approaches to experimental design, including key considerations such as how to mitigate the effects of small dataset size while avoiding data leakage. We further provide guidance on how to avoid common experimental design pitfalls that can hurt model performance, trustworthiness, and reproducibility. Discussion is accompanied by an interactive online tutorial that demonstrates foundational principles of ML experimental design, tailored to the microbiomics community. Formalizing community best practices for supervised ML in microbiomics is an important step towards improving the success and efficiency of clinical research, to the benefit of patients and other stakeholders.
Authors: Novendra Setyawan, Ghufron Wahyu Kurniawan, Chi-Chia Sun, Jun-Wei Hsieh, Jing-Ming Guo, Wen-Kai Kuo
Abstract: Convolutional Neural Networks (CNNs) and Transformers have achieved remarkable success in computer vision tasks. However, their deep architectures often lead to high computational redundancy, making them less suitable for resource-constrained environments, such as edge devices. This paper introduces ParFormer, a novel vision transformer that addresses this challenge by incorporating a Parallel Mixer and a Sparse Channel Attention Patch Embedding (SCAPE). By combining convolutional and attention mechanisms, ParFormer improves feature extraction. This makes spatial feature extraction more efficient and cuts down on unnecessary computation. The SCAPE module further reduces computational redundancy while preserving essential feature information during down-sampling. Experimental results on the ImageNet-1K dataset show that ParFormer-T achieves 78.9\% Top-1 accuracy with a high throughput on a GPU that outperforms other small models with 2.56$\times$ higher throughput than MobileViT-S, 0.24\% faster than FasterNet-T2, and 1.79$\times$ higher than EdgeNeXt-S. For edge device deployment, ParFormer-T excels with a throughput of 278.1 images/sec, which is 1.38 $\times$ higher than EdgeNeXt-S and 2.36$\times$ higher than MobileViT-S, making it highly suitable for real-time applications in resource-constrained settings. The larger variant, ParFormer-L, reaches 83.5\% Top-1 accuracy, offering a balanced trade-off between accuracy and efficiency, surpassing many state-of-the-art models. In COCO object detection, ParFormer-M achieves 40.7 AP for object detection and 37.6 AP for instance segmentation, surpassing models like ResNet-50, PVT-S and PoolFormer-S24 with significantly higher efficiency. These results validate ParFormer as a highly efficient and scalable model for both high-performance and resource-constrained scenarios, making it an ideal solution for edge-based AI applications.
Authors: Bora Yongacoglu, G\"urdal Arslan, Lacra Pavel, Serdar Y\"uksel
Abstract: In multi-agent reinforcement learning (MARL) and game theory, agents repeatedly interact and revise their strategies as new data arrives, producing a sequence of strategy profiles. This paper studies sequences of strategies satisfying a pairwise constraint inspired by policy updating in reinforcement learning, where an agent who is best responding in one period does not switch its strategy in the next period. This constraint merely requires that optimizing agents do not switch strategies, but does not constrain the non-optimizing agents in any way, and thus allows for exploration. Sequences with this property are called satisficing paths, and arise naturally in many MARL algorithms. A fundamental question about strategic dynamics is such: for a given game and initial strategy profile, is it always possible to construct a satisficing path that terminates at an equilibrium? The resolution of this question has implications about the capabilities or limitations of a class of MARL algorithms. We answer this question in the affirmative for normal-form games. Our analysis reveals a counterintuitive insight that reward deteriorating strategic updates are key to driving play to equilibrium along a satisficing path.
Authors: Dieter Coppens, Ben Van Herbruggen, Adnan Shahid, Eli De Poorter
Abstract: Indoor positioning using UWB technology has gained interest due to its centimeter-level accuracy potential. However, multipath effects and non-line-of-sight conditions cause ranging errors between anchors and tags. Existing approaches for mitigating these ranging errors rely on collecting large labeled datasets, making them impractical for real-world deployments. This paper proposes a novel self-supervised deep reinforcement learning approach that does not require labeled ground truth data. A reinforcement learning agent uses the channel impulse response as a state and predicts corrections to minimize the error between corrected and estimated ranges. The agent learns, self-supervised, by iteratively improving corrections that are generated by combining the predictability of trajectories with filtering and smoothening. Experiments on real-world UWB measurements demonstrate comparable performance to state-of-the-art supervised methods, overcoming data dependency and lack of generalizability limitations. This makes self-supervised deep reinforcement learning a promising solution for practical and scalable UWB-ranging error correction.
Authors: Mikhail Galkin, Jincheng Zhou, Bruno Ribeiro, Jian Tang, Zhaocheng Zhu
Abstract: Complex logical query answering (CLQA) in knowledge graphs (KGs) goes beyond simple KG completion and aims at answering compositional queries comprised of multiple projections and logical operations. Existing CLQA methods that learn parameters bound to certain entity or relation vocabularies can only be applied to the graph they are trained on which requires substantial training time before being deployed on a new graph. Here we present UltraQuery, the first foundation model for inductive reasoning that can zero-shot answer logical queries on any KG. The core idea of UltraQuery is to derive both projections and logical operations as vocabulary-independent functions which generalize to new entities and relations in any KG. With the projection operation initialized from a pre-trained inductive KG reasoning model, UltraQuery can solve CLQA on any KG after finetuning on a single dataset. Experimenting on 23 datasets, UltraQuery in the zero-shot inference mode shows competitive or better query answering performance than best available baselines and sets a new state of the art on 15 of them.
Authors: Lakshmi Nair, Evana Gizzi, Jivko Sinapov
Abstract: We advocate for a strong integration of Computational Creativity (CC) with research in large language and vision models (LLVMs) to address a key limitation of these models, i.e., creative problem solving. We present preliminary experiments showing how CC principles can be applied to address this limitation. Our goal is to foster discussions on creative problem solving in LLVMs and CC at prestigious ML venues. Our code is available at: https://github.com/lnairGT/creative-problem-solving-LLMs
URLs: https://github.com/lnairGT/creative-problem-solving-LLMs
Authors: Rudolf Herdt, Louisa Kinzel, Johann Georg Maa{\ss}, Marvin Walther, Henning Fr\"ohlich, Tim Schubert, Peter Maass, Christian Patrick Schaaf
Abstract: Rodents employ a broad spectrum of ultrasonic vocalizations (USVs) for social communication. As these vocalizations offer valuable insights into affective states, social interactions, and developmental stages of animals, various deep learning approaches have aimed to automate both the quantitative (detection) and qualitative (classification) analysis of USVs. Here, we present the first systematic evaluation of different types of neural networks for USV classification. We assessed various feedforward networks, including a custom-built, fully-connected network and convolutional neural network, different residual neural networks (ResNets), an EfficientNet, and a Vision Transformer (ViT). Paired with a refined, entropy-based detection algorithm (achieving recall of 94.9% and precision of 99.3%), the best architecture (achieving 86.79% accuracy) was integrated into a fully automated pipeline capable of analyzing extensive USV datasets with high reliability. Additionally, users can specify an individual minimum accuracy threshold based on their research needs. In this semi-automated setup, the pipeline selectively classifies calls with high pseudo-probability, leaving the rest for manual inspection. Our study focuses exclusively on neonatal USVs. As part of an ongoing phenotyping study, our pipeline has proven to be a valuable tool for identifying key differences in USVs produced by mice with autism-like behaviors.
Authors: Yasi Zhang, Peiyu Yu, Yaxuan Zhu, Yingshan Chang, Feng Gao, Ying Nian Wu, Oscar Leong
Abstract: Generative models based on flow matching have attracted significant attention for their simplicity and superior performance in high-resolution image synthesis. By leveraging the instantaneous change-of-variables formula, one can directly compute image likelihoods from a learned flow, making them enticing candidates as priors for downstream tasks such as inverse problems. In particular, a natural approach would be to incorporate such image probabilities in a maximum-a-posteriori (MAP) estimation problem. A major obstacle, however, lies in the slow computation of the log-likelihood, as it requires backpropagating through an ODE solver, which can be prohibitively slow for high-dimensional problems. In this work, we propose an iterative algorithm to approximate the MAP estimator efficiently to solve a variety of linear inverse problems. Our algorithm is mathematically justified by the observation that the MAP objective can be approximated by a sum of $N$ ``local MAP'' objectives, where $N$ is the number of function evaluations. By leveraging Tweedie's formula, we show that we can perform gradient steps to sequentially optimize these objectives. We validate our approach for various linear inverse problems, such as super-resolution, deblurring, inpainting, and compressed sensing, and demonstrate that we can outperform other methods based on flow matching.
Authors: Youngsuk Park, Kailash Budhathoki, Liangfu Chen, Jonas K\"ubler, Jiaji Huang, Matth\"aus Kleindessner, Jun Huan, Volkan Cevher, Yida Wang, George Karypis
Abstract: Powerful foundation models, including large language models (LLMs), with Transformer architectures have ushered in a new era of Generative AI across various industries. Industry and research community have witnessed a large number of new applications, based on those foundation models. Such applications include question and answer, customer services, image and video generation, and code completions, among others. However, as the number of model parameters reaches to hundreds of billions, their deployment incurs prohibitive inference costs and high latency in real-world scenarios. As a result, the demand for cost-effective and fast inference using AI accelerators is ever more higher. To this end, our tutorial offers a comprehensive discussion on complementary inference optimization techniques using AI accelerators. Beginning with an overview of basic Transformer architectures and deep learning system frameworks, we deep dive into system optimization techniques for fast and memory-efficient attention computations and discuss how they can be implemented efficiently on AI accelerators. Next, we describe architectural elements that are key for fast transformer inference. Finally, we examine various model compression and fast decoding strategies in the same context.
Authors: Jing Xu, Yung-Cheng Hsu, William Biscarri
Abstract: Securities lending is an important part of the financial market structure, where agent lenders help long term institutional investors to lend out their securities to short sellers in exchange for a lending fee. Agent lenders within the market seek to optimize revenue by lending out securities at the highest rate possible. Typically, this rate is set by hard-coded business rules or standard supervised machine learning models. These approaches are often difficult to scale and are not adaptive to changing market conditions. Unlike a traditional stock exchange with a centralized limit order book, the securities lending market is organized similarly to an e-commerce marketplace, where agent lenders and borrowers can transact at any agreed price in a bilateral fashion. This similarity suggests that the use of typical methods for addressing dynamic pricing problems in e-commerce could be effective in the securities lending market. We show that existing contextual bandit frameworks can be successfully utilized in the securities lending market. Using offline evaluation on real historical data, we show that the contextual bandit approach can consistently outperform typical approaches by at least 15% in terms of total revenue generated.
Authors: Khai Le-Duc, Khai-Nguyen Nguyen, Bach Phan Tat, Duy Le, Jerry Ngo, Long Vo-Dang, Anh Totti Nguyen, Truong-Son Hy
Abstract: Transparency in AI decision-making is crucial in healthcare due to the severe consequences of errors, and this is important for building trust among AI and users in sentiment analysis task. Incorporating reasoning capabilities helps Large Language Models (LLMs) understand human emotions within broader contexts, handle nuanced and ambiguous language, and infer underlying sentiments that may not be explicitly stated. In this work, we introduce a new task - Sentiment Reasoning - for both speech and text modalities, along with our proposed multimodal multitask framework and dataset. Our study showed that rationale-augmented training enhances model performance in sentiment classification across both human transcript and ASR settings. Also, we found that the generated rationales typically exhibit different vocabularies compared to human-generated rationales, but maintain similar semantics. All code, data (English-translated and Vietnamese) and models are published online: https://github.com/leduckhai/MultiMed
Authors: Susung Hong
Abstract: Conditional diffusion models have shown remarkable success in visual content generation, producing high-quality samples across various domains, largely due to classifier-free guidance (CFG). Recent attempts to extend guidance to unconditional models have relied on heuristic techniques, resulting in suboptimal generation quality and unintended effects. In this work, we propose Smoothed Energy Guidance (SEG), a novel training- and condition-free approach that leverages the energy-based perspective of the self-attention mechanism to enhance image generation. By defining the energy of self-attention, we introduce a method to reduce the curvature of the energy landscape of attention and use the output as the unconditional prediction. Practically, we control the curvature of the energy landscape by adjusting the Gaussian kernel parameter while keeping the guidance scale parameter fixed. Additionally, we present a query blurring method that is equivalent to blurring the entire attention weights without incurring quadratic complexity in the number of tokens. In our experiments, SEG achieves a Pareto improvement in both quality and the reduction of side effects. The code is available at https://github.com/SusungHong/SEG-SDXL.
Authors: Matan Atad, David Schinz, Hendrik Moeller, Robert Graf, Benedikt Wiestler, Daniel Rueckert, Nassir Navab, Jan S. Kirschke, Matthias Keicher
Abstract: Counterfactual explanations (CEs) aim to enhance the interpretability of machine learning models by illustrating how alterations in input features would affect the resulting predictions. Common CE approaches require an additional model and are typically constrained to binary counterfactuals. In contrast, we propose a novel method that operates directly on the latent space of a generative model, specifically a Diffusion Autoencoder (DAE). This approach offers inherent interpretability by enabling the generation of CEs and the continuous visualization of the model's internal representation across decision boundaries. Our method leverages the DAE's ability to encode images into a semantically rich latent space in an unsupervised manner, eliminating the need for labeled data or separate feature extraction models. We show that these latent representations are helpful for medical condition classification and the ordinal regression of severity pathologies, such as vertebral compression fractures (VCF) and diabetic retinopathy (DR). Beyond binary CEs, our method supports the visualization of ordinal CEs using a linear model, providing deeper insights into the model's decision-making process and enhancing interpretability. Experiments across various medical imaging datasets demonstrate the method's advantages in interpretability and versatility. The linear manifold of the DAE's latent space allows for meaningful interpolation and manipulation, making it a powerful tool for exploring medical image properties. Our code is available at https://doi.org/10.5281/zenodo.13859266.
Authors: Lucas Nedel Kirsten, Zhicheng Fu, Nikhil Ambha Madhusudhana
Abstract: Recent advances in camera design and imaging technology have enabled the capture of high-quality images using smartphones. However, due to the limited dynamic range of digital cameras, the quality of photographs captured in environments with highly imbalanced lighting often results in poor-quality images. To address this issue, most devices capture multi-exposure frames and then use some multi-exposure fusion method to merge those frames into a final fused image. Nevertheless, most traditional and current deep learning approaches are unsuitable for real-time applications on mobile devices due to their heavy computational and memory requirements. We propose a new method for multi-exposure fusion based on an encoder-decoder deep learning architecture with efficient building blocks tailored for mobile devices. This efficient design makes our model capable of processing 4K resolution images in less than 2 seconds on mid-range smartphones. Our method outperforms state-of-the-art techniques regarding full-reference quality measures and computational efficiency (runtime and memory usage), making it ideal for real-time applications on hardware-constrained devices. Our code is available at: https://github.com/LucasKirsten/MobileMEF.
Authors: Thomas Schnake, Farnoush Rezaei Jafari, Jonas Lederer, Ping Xiong, Shinichi Nakajima, Stefan Gugler, Gr\'egoire Montavon, Klaus-Robert M\"uller
Abstract: Explainable Artificial Intelligence (XAI) plays a crucial role in fostering transparency and trust in AI systems, where traditional XAI approaches typically offer one level of abstraction for explanations, often in the form of heatmaps highlighting single or multiple input features. However, we ask whether abstract reasoning or problem-solving strategies of a model may also be relevant, as these align more closely with how humans approach solutions to problems. We propose a framework, called Symbolic XAI, that attributes relevance to symbolic queries expressing logical relationships between input features, thereby capturing the abstract reasoning behind a model's predictions. The methodology is built upon a simple yet general multi-order decomposition of model predictions. This decomposition can be specified using higher-order propagation-based relevance methods, such as GNN-LRP, or perturbation-based explanation methods commonly used in XAI. The effectiveness of our framework is demonstrated in the domains of natural language processing (NLP), vision, and quantum chemistry (QC), where abstract symbolic domain knowledge is abundant and of significant interest to users. The Symbolic XAI framework provides an understanding of the model's decision-making process that is both flexible for customization by the user and human-readable through logical formulas.
Authors: Georgios Pantazopoulos, Malvina Nikandrou, Alessandro Suglia, Oliver Lemon, Arash Eshghi
Abstract: This study explores replacing Transformers in Visual Language Models (VLMs) with Mamba, a recent structured state space model (SSM) that demonstrates promising performance in sequence modeling. We test models up to 3B parameters under controlled conditions, showing that Mamba-based VLMs outperforms Transformers-based VLMs in captioning, question answering, and reading comprehension. However, we find that Transformers achieve greater performance in visual grounding and the performance gap widens with scale. We explore two hypotheses to explain this phenomenon: 1) the effect of task-agnostic visual encoding on the updates of the hidden states, and 2) the difficulty in performing visual grounding from the perspective of in-context multimodal retrieval. Our results indicate that a task-aware encoding yields minimal performance gains on grounding, however, Transformers significantly outperform Mamba at in-context multimodal retrieval. Overall, Mamba shows promising performance on tasks where the correct output relies on a summary of the image but struggles when retrieval of explicit information from the context is required.
Authors: Tianlong Wang, Junzhe Chen, Xueting Han, Jing Bai
Abstract: Post-training, particularly reinforcement learning (RL) using self-play-generated data, has become a new learning paradigm for large language models (LLMs). However, scaling RL to develop a general reasoner remains a research challenge, as existing methods focus on task-specific reasoning without adequately addressing generalization across a broader range of tasks. Moreover, unlike traditional RL with limited action space, LLMs operate in an infinite space, making it crucial to search for valuable and diverse strategies to solve problems effectively. To address this, we propose searching within the action space on high-level abstract plans to enhance model generalization and introduce Critical Plan Step Learning (CPL), comprising: 1) searching on plan, using Monte Carlo Tree Search (MCTS) to explore diverse plan steps in multi-step reasoning tasks, and 2) learning critical plan steps through Step-level Advantage Preference Optimization (Step-APO), which integrates advantage estimates for step preference obtained via MCTS into Direct Preference Optimization (DPO). This combination helps the model effectively learn critical plan steps, enhancing both reasoning capabilities and generalization. Experimental results demonstrate that our method, trained exclusively on GSM8K and MATH, not only significantly improves performance on GSM8K (+10.5%) and MATH (+6.5%), but also enhances out-of-domain reasoning benchmarks, such as HumanEval (+12.2%), GPQA (+8.6%), ARC-C (+4.0%), MMLU-STEM (+2.2%), and BBH (+1.8%).
Authors: Min Lu, Hemant Ishwaran
Abstract: While achieving high prediction accuracy is a fundamental goal in machine learning, an equally important task is finding a small number of features with high explanatory power. One popular selection technique is permutation importance, which assesses a variable's impact by measuring the change in prediction error after permuting the variable. However, this can be problematic due to the need to create artificial data, a problem shared by other methods as well. Another problem is that variable selection methods can be limited by being model-specific. We introduce a new model-independent approach, Variable Priority (VarPro), which works by utilizing rules without the need to generate artificial data or evaluate prediction error. The method is relatively easy to use, requiring only the calculation of sample averages of simple statistics, and can be applied to many data settings, including regression, classification, and survival. We investigate the asymptotic properties of VarPro and show, among other things, that VarPro has a consistent filtering property for noise variables. Empirical studies using synthetic and real-world data show the method achieves a balanced performance and compares favorably to many state-of-the-art procedures currently used for variable selection.
Authors: Neil De La Fuente, Mireia Maj\'o, Irina Luzko, Henry C\'ordova, Gloria Fern\'andez-Esparrach, Jorge Bernal
Abstract: Accurate and robust medical image classification is a challenging task, especially in application domains where available annotated datasets are small and present high imbalance between target classes. Considering that data acquisition is not always feasible, especially for underrepresented classes, our approach introduces a novel synthetic augmentation strategy using class-specific Variational Autoencoders (VAEs) and latent space interpolation to improve discrimination capabilities. By generating realistic, varied synthetic data that fills feature space gaps, we address issues of data scarcity and class imbalance. The method presented in this paper relies on the interpolation of latent representations within each class, thus enriching the training set and improving the model's generalizability and diagnostic accuracy. The proposed strategy was tested in a small dataset of 321 images created to train and validate an automatic method for assessing the quality of cleanliness of esophagogastroduodenoscopy images. By combining real and synthetic data, an increase of over 18\% in the accuracy of the most challenging underrepresented class was observed. The proposed strategy not only benefited the underrepresented class but also led to a general improvement in other metrics, including a 6\% increase in global accuracy and precision.
Authors: Matthew Leigh, Samuel Klein, Fran\c{c}ois Charton, Tobias Golling, Lukas Heinrich, Michael Kagan, In\^es Ochoa, Margarita Osadchy
Abstract: In this work, we significantly enhance masked particle modeling (MPM), a self-supervised learning scheme for constructing highly expressive representations of unordered sets relevant to developing foundation models for high-energy physics. In MPM, a model is trained to recover the missing elements of a set, a learning objective that requires no labels and can be applied directly to experimental data. We achieve significant performance improvements over previous work on MPM by addressing inefficiencies in the implementation and incorporating a more powerful decoder. We compare several pre-training tasks and introduce new reconstruction methods that utilize conditional generative models without data tokenization or discretization. We show that these new methods outperform the tokenized learning objective from the original MPM on a new test bed for foundation models for jets, which includes using a wide variety of downstream tasks relevant to jet physics, such as classification, secondary vertex finding, and track identification.
Authors: Santosh Kumar Radha, Yasamin Nouri Jelyani, Ara Ghukasyan, Oktay Goktas
Abstract: Iterative human engagement is a common and effective means of leveraging the advanced language processing power of large language models (LLMs). Using well-structured prompts in a conversational manner, human users can effectively influence an LLM to develop more thoughtful and accurate responses. Motivated by this insight, we propose the Iteration of Thought (IoT) framework for enhancing LLM responses by generating "thought"-provoking prompts vis a vis an input query and the current iteration of an LLM's response. Unlike static or semi-static approaches, e.g. Chain of Thought (CoT) or Tree of Thoughts (ToT), IoT adapts its reasoning path dynamically, based on evolving context, and without generating alternate explorative thoughts which are ultimately discarded. The three components of the IoT framework are (1) an Inner Dialogue Agent (IDA) responsible for generating instructive, context-specific prompts; (2) an LLM Agent (LLMA) that processes these prompts to refine its responses; and (3) an iterative prompting loop that implements a conversation between the former two components. We introduce two variants of our framework: Autonomous Iteration of Thought (AIoT), where an LLM decides when to stop iterating, and Guided Iteration of Thought (GIoT), which always forces a fixed number iterations. We investigate the performance of IoT across various datasets, spanning complex reasoning tasks from the GPQA dataset, explorative problem-solving in Game of 24, puzzle solving in Mini Crosswords, and multi-hop question answering from the HotpotQA dataset. Our results show that IoT represents a viable paradigm for autonomous response refinement in LLMs, showcasing significant improvements over CoT and thereby enabling more adaptive and efficient reasoning systems that minimize human intervention.
Authors: Xiyana Figuera, Soogeun Park, Hyemin Ahn
Abstract: We propose MR HuBo(Motion Retargeting leveraging a HUman BOdy prior), a cost-effective and convenient method to collect high-quality upper body paired
Authors: Jaehan Kim, Minkyoo Song, Seung Ho Na, Seungwon Shin
Abstract: Parameter-efficient fine-tuning (PEFT) has become a key training strategy for large language models. However, its reliance on fewer trainable parameters poses security risks, such as task-agnostic backdoors. Despite their severe impact on a wide range of tasks, there is no practical defense solution available that effectively counters task-agnostic backdoors within the context of PEFT. In this study, we introduce Obliviate, a PEFT-integrable backdoor defense. We develop two techniques aimed at amplifying benign neurons within PEFT layers and penalizing the influence of trigger tokens. Our evaluations across three major PEFT architectures show that our method can significantly reduce the attack success rate of the state-of-the-art task-agnostic backdoors (83.6%$\downarrow$). Furthermore, our method exhibits robust defense capabilities against both task-specific backdoors and adaptive attacks. Source code will be obtained at https://github.com/obliviateARR/Obliviate.
Authors: Wei Huang, Yinggui Wang, Cen Chen
Abstract: By inducing privacy attacks on NLP models, attackers can obtain sensitive information such as training data and model parameters, etc. Although researchers have studied, in-depth, several kinds of attacks in NLP models, they are non-systematic analyses. It lacks a comprehensive understanding of the impact caused by the attacks. For example, we must consider which scenarios can apply to which attacks, what the common factors are that affect the performance of different attacks, the nature of the relationships between different attacks, and the influence of various datasets and models on the effectiveness of the attacks, etc. Therefore, we need a benchmark to holistically assess the privacy risks faced by NLP models. In this paper, we present a privacy attack and defense evaluation benchmark in the field of NLP, which includes the conventional/small models and large language models (LLMs). This benchmark supports a variety of models, datasets, and protocols, along with standardized modules for comprehensive evaluation of attacks and defense strategies. Based on the above framework, we present a study on the association between auxiliary data from different domains and the strength of privacy attacks. And we provide an improved attack method in this scenario with the help of Knowledge Distillation (KD). Furthermore, we propose a chained framework for privacy attacks. Allowing a practitioner to chain multiple attacks to achieve a higher-level attack objective. Based on this, we provide some defense and enhanced attack strategies. The code for reproducing the results can be found at https://github.com/user2311717757/nlp_doctor.
Authors: Jiaheng Hu, Rose Hendrix, Ali Farhadi, Aniruddha Kembhavi, Roberto Martin-Martin, Peter Stone, Kuo-Hao Zeng, Kiana Ehsani
Abstract: In recent years, the Robotics field has initiated several efforts toward building generalist robot policies through large-scale multi-task Behavior Cloning. However, direct deployments of these policies have led to unsatisfactory performance, where the policy struggles with unseen states and tasks. How can we break through the performance plateau of these models and elevate their capabilities to new heights? In this paper, we propose FLaRe, a large-scale Reinforcement Learning fine-tuning framework that integrates robust pre-trained representations, large-scale training, and gradient stabilization techniques. Our method aligns pre-trained policies towards task completion, achieving state-of-the-art (SoTA) performance both on previously demonstrated and on entirely novel tasks and embodiments. Specifically, on a set of long-horizon mobile manipulation tasks, FLaRe achieves an average success rate of 79.5% in unseen environments, with absolute improvements of +23.6% in simulation and +30.7% on real robots over prior SoTA methods. By utilizing only sparse rewards, our approach can enable generalizing to new capabilities beyond the pretraining data with minimal human effort. Moreover, we demonstrate rapid adaptation to new embodiments and behaviors with less than a day of fine-tuning. Videos can be found on the project website at https://robot-flare.github.io/
Authors: Lucas Robinet, Ahmad Berjaoui, Ziad Kheil, Elizabeth Cohen-Jonathan Moyal
Abstract: Real-life medical data is often multimodal and incomplete, fueling the growing need for advanced deep learning models capable of integrating them efficiently. The use of diverse modalities, including histopathology slides, MRI, and genetic data, offers unprecedented opportunities to improve prognosis prediction and to unveil new treatment pathways. Contrastive learning, widely used for deriving representations from paired data in multimodal tasks, assumes that different views contain the same task-relevant information and leverages only shared information. This assumption becomes restrictive when handling medical data since each modality also harbors specific knowledge relevant to downstream tasks. We introduce DRIM, a new multimodal method for capturing these shared and unique representations, despite data sparsity. More specifically, given a set of modalities, we aim to encode a representation for each one that can be divided into two components: one encapsulating patient-related information common across modalities and the other, encapsulating modality-specific details. This is achieved by increasing the shared information among different patient modalities while minimizing the overlap between shared and unique components within each modality. Our method outperforms state-of-the-art algorithms on glioma patients survival prediction tasks, while being robust to missing modalities. To promote reproducibility, the code is made publicly available at https://github.com/Lucas-rbnt/DRIM
Authors: Ziquan Wei, Tingting Dan, Jiaqi Ding, Guorong Wu
Abstract: Although modern imaging technologies allow us to study connectivity between two distinct brain regions in-vivo, an in-depth understanding of how anatomical structure supports brain function and how spontaneous functional fluctuations emerge remarkable cognition is still elusive. Meanwhile, tremendous efforts have been made in the realm of machine learning to establish the nonlinear mapping between neuroimaging data and phenotypic traits. However, the absence of neuroscience insight in the current approaches poses significant challenges in understanding cognitive behavior from transient neural activities. To address this challenge, we put the spotlight on the coupling mechanism of structural connectivity (SC) and functional connectivity (FC) by formulating such network neuroscience question into an expressive graph representation learning problem for high-order topology. Specifically, we introduce the concept of topological detour to characterize how a ubiquitous instance of FC (direct link) is supported by neural pathways (detour) physically wired by SC, which forms a cyclic loop interacted by brain structure and function. In the clich\'e of machine learning, the multi-hop detour pathway underlying SC-FC coupling allows us to devise a novel multi-head self-attention mechanism within Transformer to capture multi-modal feature representation from paired graphs of SC and FC. Taken together, we propose a biological-inspired deep model, coined as NeuroPath, to find putative connectomic feature representations from the unprecedented amount of neuroimages, which can be plugged into various downstream applications such as task recognition and disease diagnosis. We have evaluated NeuroPath on large-scale public datasets including HCP and UK Biobank under supervised and zero-shot learning, where the state-of-the-art performance by our NeuroPath indicates great potential in network neuroscience.
Authors: Konstantinos Pantazis, Michael Trosset, William N. Frost, Carey E. Priebe, Vince Lyzinski
Abstract: Theoretical and empirical evidence suggests that joint graph embedding algorithms induce correlation across the networks in the embedding space. In the Omnibus joint graph embedding framework, previous results explicitly delineated the dual effects of the algorithm-induced and model-inherent correlations on the correlation across the embedded networks. Accounting for and mitigating the algorithm-induced correlation is key to subsequent inference, as sub-optimal Omnibus matrix constructions have been demonstrated to lead to loss in inference fidelity. This work presents the first efforts to automate the Omnibus construction in order to address two key questions in this joint embedding framework: the correlation-to-OMNI problem and the flat correlation problem. In the flat correlation problem, we seek to understand the minimum algorithm-induced flat correlation (i.e., the same across all graph pairs) produced by a generalized Omnibus embedding. Working in a subspace of the fully general Omnibus matrices, we prove both a lower bound for this flat correlation and that the classical Omnibus construction induces the maximal flat correlation. In the correlation-to-OMNI problem, we present an algorithm -- named corr2Omni -- that, from a given matrix of estimated pairwise graph correlations, estimates the matrix of generalized Omnibus weights that induces optimal correlation in the embedding space. Moreover, in both simulated and real data settings, we demonstrate the increased effectiveness of our corr2Omni algorithm versus the classical Omnibus construction.
Authors: Heegyu Kim, Taeyang Jeon, Seunghwan Choi, Seungtaek Choi, Hyunsouk Cho
Abstract: Text-to-SQL technology has become crucial for translating natural language into SQL queries in various industries, enabling non-technical users to perform complex data operations. The need for accurate evaluation methods has increased as these systems have grown more sophisticated. However, we found that the Execution Accuracy (EX), the most promising evaluation metric, still shows a substantial portion of false positives and negatives compared to human evaluation. Thus, this paper introduces FLEX (False-Less EXecution), a novel approach to evaluating text-to-SQL systems using large language models (LLMs) to emulate human expert-level evaluation of SQL queries. Our method shows significantly higher agreement with human expert judgments, improving Cohen's kappa from 61 to 78.17. Re-evaluating top-performing models on the Spider and BIRD benchmarks using FLEX reveals substantial shifts in performance rankings, with an average performance decrease of 3.15 due to false positive corrections and an increase of 6.07 from addressing false negatives. This work contributes to a more accurate and nuanced evaluation of text-to-SQL systems, potentially reshaping our understanding of state-of-the-art performance in this field.
Authors: Kevin Wang, Junbo Li, Neel P. Bhatt, Yihan Xi, Qiang Liu, Ufuk Topcu, Zhangyang Wang
Abstract: Recent advancements in Large Language Models (LLMs) have showcased their ability to perform complex reasoning tasks, but their effectiveness in planning remains underexplored. In this study, we evaluate the planning capabilities of OpenAI's o1 models across a variety of benchmark tasks, focusing on three key aspects: feasibility, optimality, and generalizability. Through empirical evaluations on constraint-heavy tasks (e.g., $\textit{Barman}$, $\textit{Tyreworld}$) and spatially complex environments (e.g., $\textit{Termes}$, $\textit{Floortile}$), we highlight o1-preview's strengths in self-evaluation and constraint-following, while also identifying bottlenecks in decision-making and memory management, particularly in tasks requiring robust spatial reasoning. Our results reveal that o1-preview outperforms GPT-4 in adhering to task constraints and managing state transitions in structured environments. However, the model often generates suboptimal solutions with redundant actions and struggles to generalize effectively in spatially complex tasks. This pilot study provides foundational insights into the planning limitations of LLMs, offering key directions for future research on improving memory management, decision-making, and generalization in LLM-based planning.
Authors: Osama Mustafa
Abstract: The application of deep learning in cancer research, particularly in early diagnosis, case understanding, and treatment strategy design, emphasizes the need for high-quality data. Generative AI, especially Generative Adversarial Networks (GANs), has emerged as a leading solution to challenges like class imbalance, robust learning, and model training, while addressing issues stemming from patient privacy and the scarcity of real data. Despite their promise, GANs face several challenges, both inherent and specific to histopathology data. Inherent issues include training imbalance, mode collapse, linear learning from insufficient discriminator feedback, and hard boundary convergence due to stringent feedback. Histopathology data presents a unique challenge with its complex representation, high spatial resolution, and multiscale features. To address these challenges, we propose a framework consisting of two components. First, we introduce a contrastive learning-based Multistage Progressive Finetuning Siamese Neural Network (MFT-SNN) for assessing the similarity between histopathology patches. Second, we implement a Reinforcement Learning-based External Optimizer (RL-EO) within the GAN training loop, serving as a reward signal generator. The modified discriminator loss function incorporates a weighted reward, guiding the GAN to maximize this reward while minimizing loss. This approach offers an external optimization guide to the discriminator, preventing generator overfitting and ensuring smooth convergence. Our proposed solution has been benchmarked against state-of-the-art (SOTA) GANs and a Denoising Diffusion Probabilistic model, outperforming previous SOTA across various metrics, including FID score, KID score, Perceptual Path Length, and downstream classification tasks.