Authors: Sylvia Worlali Azumah, Nelly Elsayed, Zag ElSayed, Murat Ozer, Amanda La Guardia
Abstract: Cyberbullying is a significant concern intricately linked to technology that can find resolution through technological means. Despite its prevalence, technology also provides solutions to mitigate cyberbullying. To address growing concerns regarding the adverse impact of cyberbullying on individuals' online experiences, various online platforms and researchers are actively adopting measures to enhance the safety of digital environments. While researchers persist in crafting detection models to counteract or minimize cyberbullying, malicious actors are deploying adversarial techniques to circumvent these detection methods. This paper focuses on detecting cyberbullying in adversarial attack content within social networking site text data, specifically emphasizing hate speech. Utilizing a deep learning-based approach with a correction algorithm, this paper yielded significant results. An LSTM model with a fixed epoch of 100 demonstrated remarkable performance, achieving high accuracy, precision, recall, F1-score, and AUC-ROC scores of 87.57%, 88.73%, 87.57%, 88.15%, and 91% respectively. Additionally, the LSTM model's performance surpassed that of previous studies.
Authors: Jacob O. T{\o}rring, Carl Hvarfner, Luigi Nardi, Magnus Sj\"alander
Abstract: Bayesian optimization is a powerful method for automating tuning of compilers. The complex landscape of autotuning provides a myriad of rarely considered structural challenges for black-box optimizers, and the lack of standardized benchmarks has limited the study of Bayesian optimization within the domain. To address this, we present CATBench, a comprehensive benchmarking suite that captures the complexities of compiler autotuning, ranging from discrete, conditional, and permutation parameter types to known and unknown binary constraints, as well as both multi-fidelity and multi-objective evaluations. The benchmarks in CATBench span a range of machine learning-oriented computations, from tensor algebra to image processing and clustering, and uses state-of-the-art compilers, such as TACO and RISE/ELEVATE. CATBench offers a unified interface for evaluating Bayesian optimization algorithms, promoting reproducibility and innovation through an easy-to-use, fully containerized setup of both surrogate and real-world compiler optimization tasks. We validate CATBench on several state-of-the-art algorithms, revealing their strengths and weaknesses and demonstrating the suite's potential for advancing both Bayesian optimization and compiler autotuning research.
Authors: Wesley Brewer, Aditya Kashi, Sajal Dash, Aristeidis Tsaris, Junqi Yin, Mallikarjun Shankar, Feiyi Wang
Abstract: In a post-ChatGPT world, this paper explores the potential of leveraging scalable artificial intelligence for scientific discovery. We propose that scaling up artificial intelligence on high-performance computing platforms is essential to address such complex problems. This perspective focuses on scientific use cases like cognitive simulations, large language models for scientific inquiry, medical image analysis, and physics-informed approaches. The study outlines the methodologies needed to address such challenges at scale on supercomputers or the cloud and provides exemplars of such approaches applied to solve a variety of scientific problems.
Authors: Salvatore Greco, Bartolomeo Vacchetti, Daniele Apiletti, Tania Cerquitelli
Abstract: Concept Drift is a phenomenon in which the underlying data distribution and statistical properties of a target domain change over time, leading to a degradation of the model's performance. Consequently, models deployed in production require continuous monitoring through drift detection techniques. Most drift detection methods to date are supervised, i.e., based on ground-truth labels. However, true labels are usually not available in many real-world scenarios. Although recent efforts have been made to develop unsupervised methods, they often lack the required accuracy, have a complexity that makes real-time implementation in production environments difficult, or are unable to effectively characterize drift. To address these challenges, we propose DriftLens, an unsupervised real-time concept drift detection framework. It works on unstructured data by exploiting the distribution distances of deep learning representations. DriftLens can also provide drift characterization by analyzing each label separately. A comprehensive experimental evaluation is presented with multiple deep learning classifiers for text, image, and speech. Results show that (i) DriftLens performs better than previous methods in detecting drift in $11/13$ use cases; (ii) it runs at least 5 times faster; (iii) its detected drift value is very coherent with the amount of drift (correlation $\geq 0.85$); (iv) it is robust to parameter changes.
Authors: Feiyang Xu, Shunyu Liu, Yunpeng Qing, Yihe Zhou, Yuwen Wang, Mingli Song
Abstract: Active Voltage Control (AVC) on the Power Distribution Networks (PDNs) aims to stabilize the voltage levels to ensure efficient and reliable operation of power systems. With the increasing integration of distributed energy resources, recent efforts have explored employing multi-agent reinforcement learning (MARL) techniques to realize effective AVC. Existing methods mainly focus on the acquisition of short-term AVC strategies, i.e., only learning AVC within the short-term training trajectories of a singular diurnal cycle. However, due to the dynamic nature of load demands and renewable energy, the operation states of real-world PDNs may exhibit significant distribution shifts across varying timescales (e.g., daily and seasonal changes). This can render those short-term strategies suboptimal or even obsolete when performing continuous AVC over extended periods. In this paper, we propose a novel temporal prototype-aware learning method, abbreviated as TPA, to learn time-adaptive AVC under short-term training trajectories. At the heart of TPA are two complementary components, namely multi-scale dynamic encoder and temporal prototype-aware policy, that can be readily incorporated into various MARL methods. The former component integrates a stacked transformer network to learn underlying temporal dependencies at different timescales of the PDNs, while the latter implements a learnable prototype matching mechanism to construct a dedicated AVC policy that can dynamically adapt to the evolving operation states. Experimental results on the AVC benchmark with different PDN sizes demonstrate that the proposed TPA surpasses the state-of-the-art counterparts not only in terms of control performance but also by offering model transferability. Our code is available at https://github.com/Canyizl/TPA-for-AVC.
Authors: Vincent Blot (LISN, CNRS), Anastasios N Angelopoulos (UC Berkeley), Michael I Jordan (UC Berkeley, Inria), Nicolas J-B Brunel (ENSIIE)
Abstract: Science and technology have a growing need for effective mechanisms that ensure reliable, controlled performance from black-box machine learning algorithms. These performance guarantees should ideally hold conditionally on the input-that is the performance guarantees should hold, at least approximately, no matter what the input. However, beyond stylized discrete groupings such as ethnicity and gender, the right notion of conditioning can be difficult to define. For example, in problems such as image segmentation, we want the uncertainty to reflect the intrinsic difficulty of the test sample, but this may be difficult to capture via a conditioning event. Building on the recent work of Gibbs et al. [2023], we propose a methodology for achieving approximate conditional control of statistical risks-the expected value of loss functions-by adapting to the difficulty of test samples. Our framework goes beyond traditional conditional risk control based on user-provided conditioning events to the algorithmic, data-driven determination of appropriate function classes for conditioning. We apply this framework to various regression and segmentation tasks, enabling finer-grained control over model performance and demonstrating that by continuously monitoring and adjusting these parameters, we can achieve superior precision compared to conventional risk-control methods.
Authors: Thorsten Rudroff, Oona Rainio, Riku Kl\'en
Abstract: Objectives: The objectives of this narrative review are to summarize the current state of AI applications in neuroimaging for early Alzheimer's disease (AD) prediction and to highlight the potential of AI techniques in improving early AD diagnosis, prognosis, and management. Methods: We conducted a narrative review of studies using AI techniques applied to neuroimaging data for early AD prediction. We examined single-modality studies using structural MRI and PET imaging, as well as multi-modality studies integrating multiple neuroimaging techniques and biomarkers. Furthermore, they reviewed longitudinal studies that model AD progression and identify individuals at risk of rapid decline. Results: Single-modality studies using structural MRI and PET imaging have demonstrated high accuracy in classifying AD and predicting progression from mild cognitive impairment (MCI) to AD. Multi-modality studies, integrating multiple neuroimaging techniques and biomarkers, have shown improved performance and robustness compared to single-modality approaches. Longitudinal studies have highlighted the value of AI in modeling AD progression and identifying individuals at risk of rapid decline. However, challenges remain in data standardization, model interpretability, generalizability, clinical integration, and ethical considerations. Conclusion: AI techniques applied to neuroimaging data have the potential to improve early AD diagnosis, prognosis, and management. Addressing challenges related to data standardization, model interpretability, generalizability, clinical integration, and ethical considerations is crucial for realizing the full potential of AI in AD research and clinical practice. Collaborative efforts among researchers, clinicians, and regulatory agencies are needed to develop reliable, robust, and ethical AI tools that can benefit AD patients and society.
Authors: Krzysztof Kotowski, Christoph Haskamp, Jacek Andrzejewski, Bogdan Ruszczak, Jakub Nalepa, Daniel Lakey, Peter Collins, Aybike Kolmas, Mauro Bartesaghi, Jose Martinez-Heras, Gabriele De Canio
Abstract: Machine learning has vast potential to improve anomaly detection in satellite telemetry which is a crucial task for spacecraft operations. This potential is currently hampered by a lack of comprehensible benchmarks for multivariate time series anomaly detection, especially for the challenging case of satellite telemetry. The European Space Agency Benchmark for Anomaly Detection in Satellite Telemetry (ESA-ADB) aims to address this challenge and establish a new standard in the domain. It is a result of close cooperation between spacecraft operations engineers from the European Space Agency (ESA) and machine learning experts. The newly introduced ESA Anomalies Dataset contains annotated real-life telemetry from three different ESA missions, out of which two are included in ESA-ADB. Results of typical anomaly detection algorithms assessed in our novel hierarchical evaluation pipeline show that new approaches are necessary to address operators' needs. All elements of ESA-ADB are publicly available to ensure its full reproducibility.
Authors: Ergun Bi\c{c}ici
Abstract: Extreme Learning Machines (ELM) provide a fast alternative to traditional gradient-based learning in neural networks, offering rapid training and robust generalization capabilities. Its theoretical basis shows its universal approximation capability. We explore the application of ELMs for the task of Click-Through Rate (CTR) prediction, which is largely unexplored by ELMs due to the high dimensionality of the problem. We introduce an ELM-based model enhanced with embedding layers to improve the performance on CTR tasks, which is a novel addition to the field. Experimental results on benchmark datasets, including Avazu and Criteo, demonstrate that our proposed ELM with embeddings achieves competitive F1 results while significantly reducing training time compared to state-of-the-art models such as Masknet. Our findings show that ELMs can be useful for CTR prediction, especially when fast training is needed.
Authors: Vyacheslav Kungurtsev, Apaar Garg, Aarya Khandelwal, Parth Sandeep Ratogi, Bapi Chatterjee, Jakub Marecek
Abstract: In this work, we demonstrate the Empirical Bayes approach to learning a Dynamic Bayesian Network. By starting with several point estimates of structure and weights, we can use a data-driven prior to subsequently obtain a model to quantify uncertainty. This approach uses a recent development of Generalized Variational Inference, and indicates the potential of sampling the uncertainty of a mixture of DAG structures as well as a parameter posterior.
Authors: Giorgio Morales, John W. Sheppard
Abstract: Symbolic regression (SR) methods attempt to learn mathematical expressions that approximate the behavior of an observed system. However, when dealing with multivariate systems, they often fail to identify the functional form that explains the relationship between each variable and the system's response. To begin to address this, we propose an explainable neural SR method that generates univariate symbolic skeletons that aim to explain how each variable influences the system's response. By analyzing multiple sets of data generated artificially, where one input variable varies while others are fixed, relationships are modeled separately for each input variable. The response of such artificial data sets is estimated using a regression neural network (NN). Finally, the multiple sets of input-response pairs are processed by a pre-trained Multi-Set Transformer that solves a problem we termed Multi-Set Skeleton Prediction and outputs a univariate symbolic skeleton. Thus, such skeletons represent explanations of the function approximated by the regression NN. Experimental results demonstrate that this method learns skeleton expressions matching the underlying functions and outperforms two GP-based and two neural SR methods.
Authors: Alexander H. Gower, Konstantin Korovin, Daniel Brunns{\aa}ker, Filip Kronstr\"om, Gabriel K. Reder, Ievgeniia A. Tiukova, Ronald S. Reiserer, John P. Wikswo, Ross D. King
Abstract: The process of developing theories and models and testing them with experiments is fundamental to the scientific method. Automating the entire scientific method then requires not only automation of the induction of theories from data, but also experimentation from design to implementation. This is the idea behind a robot scientist -- a coupled system of AI and laboratory robotics that has agency to test hypotheses with real-world experiments. In this chapter we explore some of the fundamentals of robot scientists in the philosophy of science. We also map the activities of a robot scientist to machine learning paradigms, and argue that the scientific method shares an analogy with active learning. We demonstrate these concepts using examples from previous robot scientists, and also from Genesis: a next generation robot scientist designed for research in systems biology, comprising a micro-fluidic system with 1000 computer-controlled micro-bioreactors and interpretable models based in controlled vocabularies and logic.
Authors: Stephen Menary, Samuel Kaski, Andre Freitas
Abstract: Recent works have shown that transformers can solve contextual reasoning tasks by internally executing computational graphs called circuits. Circuits often use attention to logically match information from subspaces of the representation, e.g. using position-in-sequence to identify the previous token. In this work, we consider a semantic subspace to be any independent subspace of the latent representation that can fully determine an attention distribution. We show that Pre-Norm, the placement of normalisation layer used by state-of-the-art transformers, violates this ability unless the model learns a strict representation structure of orthogonal spheres. This is because it causes linear subspaces to interfere through their common normalisation factor. Theoretically, we analyse circuit stability by modelling this interference as random noise on the $L_2$-norms of the query/key/value vectors, predicting a phenomenon of circuit collapse when sparse-attention shifts to a different token. Empirically, we investigate the sensitivity of real-world models trained for mathematical addition, observing a 1% rate of circuit collapse when the norms are artificially perturbed by $\lesssim$10%. We contrast Pre-Norm with QKV-Norm, which places normalisation after the attention head's linear operators. Theoretically this relaxes the representational constraints. Empirically we observe comparable in-distribution but worse out-of-distribution performance.
Authors: Jinbin Huang, Wenbin He, Liang Gou, Liu Ren, Chris Bryan
Abstract: The emergence of large-scale pre-trained models has heightened their application in various downstream tasks, yet deployment is a challenge in environments with limited computational resources. Knowledge distillation has emerged as a solution in such scenarios, whereby knowledge from large teacher models is transferred into smaller student' models, but this is a non-trivial process that traditionally requires technical expertise in AI/ML. To address these challenges, this paper presents InFiConD, a novel framework that leverages visual concepts to implement the knowledge distillation process and enable subsequent no-code fine-tuning of student models. We develop a novel knowledge distillation pipeline based on extracting text-aligned visual concepts from a concept corpus using multimodal models, and construct highly interpretable linear student models based on visual concepts that mimic a teacher model in a response-based manner. InFiConD's interface allows users to interactively fine-tune the student model by manipulating concept influences directly in the user interface. We validate InFiConD via a robust usage scenario and user study. Our findings indicate that InFiConD's human-in-the-loop and visualization-driven approach enables users to effectively create and analyze student models, understand how knowledge is transferred, and efficiently perform fine-tuning operations. We discuss how this work highlights the potential of interactive and visual methods in making knowledge distillation and subsequent no-code fine-tuning more accessible and adaptable to a wider range of users with domain-specific demands.
Authors: Yu Chen, Tianyu Cui, Alexander Capstick, Nan Fletcher-Loyd, Payam Barnaghi
Abstract: In Explainable AI, rule extraction translates model knowledge into logical rules, such as IF-THEN statements, crucial for understanding patterns learned by black-box models. This could significantly aid in fields like disease diagnosis, disease progression estimation, or drug discovery. However, such application domains often contain imbalanced data, with the class of interest underrepresented. Existing methods inevitably compromise the performance of rules for the minor class to maximise the overall performance. As the first attempt in this field, we propose a model-agnostic approach for extracting rules from specific subgroups of data, featuring automatic rule generation for numerical features. This method enhances the regional explainability of machine learning models and offers wider applicability compared to existing methods. We additionally introduce a new method for selecting features to compose rules, reducing computational costs in high-dimensional spaces. Experiments across various datasets and models demonstrate the effectiveness of our methods.
Authors: Steffen Schotth\"ofer, M. Paul Laiu
Abstract: In this work, we propose a federated dynamical low-rank training (FeDLRT) scheme to reduce client compute and communication costs - two significant performance bottlenecks in horizontal federated learning. Our method builds upon dynamical low-rank splitting schemes for manifold-constrained optimization to create a global low-rank basis of network weights, which enables client training on a small coefficient matrix. A consistent global low-rank basis allows us to incorporate a variance correction scheme and prove global loss descent and convergence to a stationary point. Dynamic augmentation and truncation of the low-rank bases automatically optimizes computing and communication resource utilization. We demonstrate the efficiency of FeDLRT in an array of computer vision benchmarks and show a reduction of client compute and communication costs by up to an order of magnitude with minimal impacts on global accuracy.
Authors: Hugo Inzirillo, Remi Genet
Abstract: We propose a novel approach that enhances multivariate function approximation using learnable path signatures and Kolmogorov-Arnold networks (KANs). We enhance the learning capabilities of these networks by weighting the values obtained by KANs using learnable path signatures, which capture important geometric features of paths. This combination allows for a more comprehensive and flexible representation of sequential and temporal data. We demonstrate through studies that our SigKANs with learnable path signatures perform better than conventional methods across a range of function approximation challenges. By leveraging path signatures in neural networks, this method offers intriguing opportunities to enhance performance in time series analysis and time series forecasting, among other fields.
Authors: Yongjian Zhong, Hieu Vu, Tianbao Yang, Bijaya Adhikari
Abstract: Implicit graph neural networks have gained popularity in recent years as they capture long-range dependencies while improving predictive performance in static graphs. Despite the tussle between performance degradation due to the oversmoothing of learned embeddings and long-range dependency being more pronounced in dynamic graphs, as features are aggregated both across neighborhood and time, no prior work has proposed an implicit graph neural model in a dynamic setting. In this paper, we present Implicit Dynamic Graph Neural Network (IDGNN) a novel implicit neural network for dynamic graphs which is the first of its kind. A key characteristic of IDGNN is that it demonstrably is well-posed, i.e., it is theoretically guaranteed to have a fixed-point representation. We then demonstrate that the standard iterative algorithm often used to train implicit models is computationally expensive in our dynamic setting as it involves computing gradients, which themselves have to be estimated in an iterative manner. To overcome this, we pose an equivalent bilevel optimization problem and propose an efficient single-loop training algorithm that avoids iterative computation by maintaining moving averages of key components of the gradients. We conduct extensive experiments on real-world datasets on both classification and regression tasks to demonstrate the superiority of our approach over the state-of-the-art baselines. We also demonstrate that our bi-level optimization framework maintains the performance of the expensive iterative algorithm while obtaining up to \textbf{1600x} speed-up.
Authors: Avi Amalanshu, Viswesh Nagaswamy, G. V. S. S. Prudhvi, Yash Sirvi, Debashish Chakravarty
Abstract: Vertical Federated Learning (VFL) is a machine learning paradigm for learning from vertically partitioned data (i.e. features for each input are distributed across multiple "guest" clients and an aggregating "host" server owns labels) without communicating raw data. Traditionally, VFL involves an "entity resolution" phase where the host identifies and serializes the unique entities known to all guests. This is followed by private set intersection to find common entities, and an "entity alignment" step to ensure all guests are always processing the same entity's data. However, using only data of entities from the intersection means guests discard potentially useful data. Besides, the effect on privacy is dubious and these operations are computationally expensive. We propose a novel approach that eliminates the need for set intersection and entity alignment in categorical tasks. Our Entity Augmentation technique generates meaningful labels for activations sent to the host, regardless of their originating entity, enabling efficient VFL without explicit entity alignment. With limited overlap between training data, this approach performs substantially better (e.g. with 5% overlap, 48.1% vs 69.48% test accuracy on CIFAR-10). In fact, thanks to the regularizing effect, our model performs marginally better even with 100% overlap.
Authors: Ioannis Tsingalis, Christos Korgialas, Constantine Kotropoulos
Abstract: The identification of device brands and models plays a pivotal role in the realm of multimedia forensic applications. This paper presents a framework capable of identifying devices using audio, visual content, or a fusion of them. The fusion of visual and audio content occurs later by applying two fundamental fusion rules: the product and the sum. The device identification problem is tackled as a classification one by leveraging Convolutional Neural Networks. Experimental evaluation illustrates that the proposed framework exhibits promising classification performance when independently using audio or visual content. Furthermore, although the fusion results don't consistently surpass both individual modalities, they demonstrate promising potential for enhancing classification performance. Future research could refine the fusion process to improve classification performance in both modalities consistently. Finally, a statistical significance test is performed for a more in-depth study of the classification results.
Authors: Dong Liu, Roger Waleffe, Meng Jiang, Shivaram Venkataraman
Abstract: In our recent research, we have developed a framework called GraphSnapShot, which has been proven an useful tool for graph learning acceleration. GraphSnapShot is a framework for fast cache, storage, retrieval and computation for graph learning. It can quickly store and update the local topology of graph structure and allows us to track patterns in the structure of graph networks, just like take snapshots of the graphs. In experiments, GraphSnapShot shows efficiency, it can achieve up to 30% training acceleration and 73% memory reduction for lossless graph ML training compared to current baselines such as dgl.This technique is particular useful for large dynamic graph learning tasks such as social media analysis and recommendation systems to process complex relationships between entities.
Authors: Viet Duong, Qiong Wu, Zhengyi Zhou, Hongjue Zhao, Chenxiang Luo, Eric Zavesky, Huaxiu Yao, Huajie Shao
Abstract: As an emerging interpretable technique, Generalized Additive Models (GAMs) adopt neural networks to individually learn non-linear functions for each feature, which are then combined through a linear model for final predictions. Although GAMs can explain deep neural networks (DNNs) at the feature level, they require large numbers of model parameters and are prone to overfitting, making them hard to train and scale. Additionally, in real-world datasets with many features, the interpretability of feature-based explanations diminishes for humans. To tackle these issues, recent research has shifted towards concept-based interpretable methods. These approaches try to integrate concept learning as an intermediate step before making predictions, explaining the predictions in terms of human-understandable concepts. However, these methods require domain experts to extensively label concepts with relevant names and their ground-truth values. In response, we propose CAT, a novel interpretable Concept-bAsed Taylor additive model to simply this process. CAT does not have to require domain experts to annotate concepts and their ground-truth values. Instead, it only requires users to simply categorize input features into broad groups, which can be easily accomplished through a quick metadata review. Specifically, CAT first embeds each group of input features into one-dimensional high-level concept representation, and then feeds the concept representations into a new white-box Taylor Neural Network (TaylorNet). The TaylorNet aims to learn the non-linear relationship between the inputs and outputs using polynomials. Evaluation results across multiple benchmarks demonstrate that CAT can outperform or compete with the baselines while reducing the need of extensive model parameters. Importantly, it can explain model predictions through high-level concepts that human can understand.
Authors: Constantin Ruhdorfer, Matteo Bortoletto, Anna Penzkofer, Andreas Bulling
Abstract: We introduce the Overcooked Generalisation Challenge (OGC) - the first benchmark to study agents' zero-shot cooperation abilities when faced with novel partners and levels in the Overcooked-AI environment. This perspective starkly contrasts a large body of previous work that has trained and evaluated cooperating agents only on the same level, failing to capture generalisation abilities required for real-world human-AI cooperation. Our challenge interfaces with state-of-the-art dual curriculum design (DCD) methods to generate auto-curricula for training general agents in Overcooked. It is the first cooperative multi-agent environment specially designed for DCD methods and, consequently, the first benchmarked with state-of-the-art methods. It is fully GPU-accelerated, built on the DCD benchmark suite minimax, and freely available under an open-source license: https://git.hcics.simtech.uni-stuttgart.de/public-projects/OGC. We show that current DCD algorithms struggle to produce useful policies in this novel challenge, even if combined with recent network architectures that were designed for scalability and generalisability. The OGC pushes the boundaries of real-world human-AI cooperation by enabling the research community to study the impact of generalisation on cooperating agents.
URLs: https://git.hcics.simtech.uni-stuttgart.de/public-projects/OGC.
Authors: Fan Dong, Henry Leung, Steve Drew
Abstract: Federated learning offers a compelling solution to the challenges of networking and data privacy within aerial and space networks by utilizing vast private edge data and computing capabilities accessible through drones, balloons, and satellites. While current research has focused on optimizing the learning process, computing efficiency, and minimizing communication overhead, the issue of heterogeneity and class imbalance remains a significant barrier to rapid model convergence. In our study, we explore the influence of heterogeneity on class imbalance, which diminishes performance in ASN-based federated learning. We illustrate the correlation between heterogeneity and class imbalance within grouped data and show how constraints such as battery life exacerbate the class imbalance challenge. Our findings indicate that ASN-based FL faces heightened class imbalance issues even with similar levels of heterogeneity compared to other scenarios. Finally, we analyze the impact of varying degrees of heterogeneity on FL training and evaluate the efficacy of current state-of-the-art algorithms under these conditions. Our results reveal that the heterogeneity challenge is more pronounced in ASN-based federated learning and that prevailing algorithms often fail to effectively address high levels of heterogeneity.
Authors: Andrew Dennehy, Xiaoyu Zou, Shabnam J. Semnani, Yuri Fialko, Alexander Cloninger
Abstract: DBSCAN and OPTICS are powerful algorithms for identifying clusters of points in domains where few assumptions can be made about the structure of the data. In this paper, we leverage these strengths and introduce a new algorithm, LINSCAN, designed to seek lineated clusters that are difficult to find and isolate with existing methods. In particular, by embedding points as normal distributions approximating their local neighborhoods and leveraging a distance function derived from the Kullback Leibler Divergence, LINSCAN can detect and distinguish lineated clusters that are spatially close but have orthogonal covariances. We demonstrate how LINSCAN can be applied to seismic data to identify active faults, including intersecting faults, and determine their orientation. Finally, we discuss the properties a generalization of DBSCAN and OPTICS must have in order to retain the stability benefits of these algorithms.
Authors: Betty Shea, Mark Schmidt
Abstract: We introduce the class of SO-friendly neural networks, which include several models used in practice including networks with 2 layers of hidden weights where the number of inputs is larger than the number of outputs. SO-friendly networks have the property that performing a precise line search to set the step size on each iteration has the same asymptotic cost during full-batch training as using a fixed learning. Further, for the same cost a planesearch can be used to set both the learning and momentum rate on each step. Even further, SO-friendly networks also allow us to use subspace optimization to set a learning rate and momentum rate for each layer on each iteration. We explore augmenting gradient descent as well as quasi-Newton methods and Adam with line optimization and subspace optimization, and our experiments indicate that this gives fast and reliable ways to train these networks that are insensitive to hyper-parameters.
Authors: Yiqiao Jin, Andrew Zhao, Yeon-Chang Lee, Meng Ye, Ajay Divakaran, Srijan Kumar
Abstract: We developed DyGETViz, a novel framework for effectively visualizing dynamic graphs (DGs) that are ubiquitous across diverse real-world systems. This framework leverages recent advancements in discrete-time dynamic graph (DTDG) models to adeptly handle the temporal dynamics inherent in dynamic graphs. DyGETViz effectively captures both micro- and macro-level structural shifts within these graphs, offering a robust method for representing complex and massive dynamic graphs. The application of DyGETViz extends to a diverse array of domains, including ethology, epidemiology, finance, genetics, linguistics, communication studies, social studies, and international relations. Through its implementation, DyGETViz has revealed or confirmed various critical insights. These include the diversity of content sharing patterns and the degree of specialization within online communities, the chronological evolution of lexicons across decades, and the distinct trajectories exhibited by aging-related and non-related genes. Importantly, DyGETViz enhances the accessibility of scientific findings to non-domain experts by simplifying the complexities of dynamic graphs. Our framework is released as an open-source Python package for use across diverse disciplines. Our work not only addresses the ongoing challenges in visualizing and analyzing DTDG models but also establishes a foundational framework for future investigations into dynamic graph representation and analysis across various disciplines.
Authors: Tianyu Du, Ayush Kanodia, Herman Brunborg, Keyon Vafa, Susan Athey
Abstract: Many empirical studies of labor market questions rely on estimating relatively simple predictive models using small, carefully constructed longitudinal survey datasets based on hand-engineered features. Large Language Models (LLMs), trained on massive datasets, encode vast quantities of world knowledge and can be used for the next job prediction problem. However, while an off-the-shelf LLM produces plausible career trajectories when prompted, the probability with which an LLM predicts a particular job transition conditional on career history will not, in general, align with the true conditional probability in a given population. Recently, Vafa et al. (2024) introduced a transformer-based "foundation model", CAREER, trained using a large, unrepresentative resume dataset, that predicts transitions between jobs; it further demonstrated how transfer learning techniques can be used to leverage the foundation model to build better predictive models of both transitions and wages that reflect conditional transition probabilities found in nationally representative survey datasets. This paper considers an alternative where the fine-tuning of the CAREER foundation model is replaced by fine-tuning LLMs. For the task of next job prediction, we demonstrate that models trained with our approach outperform several alternatives in terms of predictive performance on the survey data, including traditional econometric models, CAREER, and LLMs with in-context learning, even though the LLM can in principle predict job titles that are not allowed in the survey data. Further, we show that our fine-tuned LLM-based models' predictions are more representative of the career trajectories of various workforce subpopulations than off-the-shelf LLM models and CAREER. We conduct experiments and analyses that highlight the sources of the gains in the performance of our models for representative predictions.
Authors: Pranjal Awasthi, Nishanth Dikkala, Pritish Kamath, Raghu Meka
Abstract: A core component present in many successful neural network architectures, is an MLP block of two fully connected layers with a non-linear activation in between. An intriguing phenomenon observed empirically, including in transformer architectures, is that, after training, the activations in the hidden layer of this MLP block tend to be extremely sparse on any given input. Unlike traditional forms of sparsity, where there are neurons/weights which can be deleted from the network, this form of {\em dynamic} activation sparsity appears to be harder to exploit to get more efficient networks. Motivated by this we initiate a formal study of PAC learnability of MLP layers that exhibit activation sparsity. We present a variety of results showing that such classes of functions do lead to provable computational and statistical advantages over their non-sparse counterparts. Our hope is that a better theoretical understanding of {\em sparsely activated} networks would lead to methods that can exploit activation sparsity in practice.
Authors: Muzhen Cai, Sendong Zhao, Haochun Wang, Yanrui Du, Zewen Qiang, Bing Qin, Ting Liu
Abstract: Artificial Intelligence predicts drug properties by encoding drug molecules, aiding in the rapid screening of candidates. Different molecular representations, such as SMILES and molecule graphs, contain complementary information for molecular encoding. Thus exploiting complementary information from different molecular representations is one of the research priorities in molecular encoding. Most existing methods for combining molecular multi-modalities only use molecular-level information, making it hard to encode intra-molecular alignment information between different modalities. To address this issue, we propose a multi-granularity fusion method that is MolFusion. The proposed MolFusion consists of two key components: (1) MolSim, a molecular-level encoding component that achieves molecular-level alignment between different molecular representations. and (2) AtomAlign, an atomic-level encoding component that achieves atomic-level alignment between different molecular representations. Experimental results show that MolFusion effectively utilizes complementary multimodal information, leading to significant improvements in performance across various classification and regression tasks.
Authors: Nicol\`o Felicioni, Michael Benigni, Maurizio Ferrari Dacrema
Abstract: The Off-Policy Evaluation (OPE) problem consists of evaluating the performance of counterfactual policies with data collected by another one. This problem is of utmost importance for various application domains, e.g., recommendation systems, medical treatments, and many others. To solve the OPE problem, we resort to estimators, which aim to estimate in the most accurate way possible the performance that the counterfactual policies would have had if they were deployed in place of the logging policy. In the literature, several estimators have been developed, all with different characteristics and theoretical guarantees. Therefore, there is no dominant estimator, and each estimator may be the best one for different OPE problems, depending on the characteristics of the dataset at hand. While the selection of the estimator is a crucial choice for an accurate OPE, this problem has been widely overlooked in the literature. We propose an automated data-driven OPE estimator selection method based on machine learning. In particular, the core idea we propose in this paper is to create several synthetic OPE tasks and use a machine learning model trained to predict the best estimator for those synthetic tasks. We empirically show how our method is able to generalize to unseen tasks and make a better estimator selection compared to a baseline method on several real-world datasets, with a computational cost significantly lower than the one of the baseline.
Authors: Jacob Adamczyk, Volodymyr Makarenko, Stas Tiomkin, Rahul V. Kulkarni
Abstract: An agent's ability to leverage past experience is critical for efficiently solving new tasks. Prior work has focused on using value function estimates to obtain zero-shot approximations for solutions to a new task. In soft Q-learning, we show how any value function estimate can also be used to derive double-sided bounds on the optimal value function. The derived bounds lead to new approaches for boosting training performance which we validate experimentally. Notably, we find that the proposed framework suggests an alternative method for updating the Q-function, leading to boosted performance.
Authors: Yaoyu Zhang, Leyang Zhang, Zhongwang Zhang, Zhiwei Bai
Abstract: Determining whether deep neural network (DNN) models can reliably recover target functions at overparameterization is a critical yet complex issue in the theory of deep learning. To advance understanding in this area, we introduce a concept we term "local linear recovery" (LLR), a weaker form of target function recovery that renders the problem more amenable to theoretical analysis. In the sense of LLR, we prove that functions expressible by narrower DNNs are guaranteed to be recoverable from fewer samples than model parameters. Specifically, we establish upper limits on the optimistic sample sizes, defined as the smallest sample size necessary to guarantee LLR, for functions in the space of a given DNN. Furthermore, we prove that these upper bounds are achieved in the case of two-layer tanh neural networks. Our research lays a solid groundwork for future investigations into the recovery capabilities of DNNs in overparameterized scenarios.
Authors: Dong Liu, Meng Jiang
Abstract: The conventional training approaches often face challenges in balancing the breadth of multi-task learning (MTL) with the depth of single-task learning (STL). To address this issue, we introduce the Multi-Task to Single-Task (MT2ST) framework, a groundbreaking approach that can combine the generalizability of MTL with the precision of STL. Our work include two strategies: 'Diminish' and 'Switch'. 'Diminish' Strategy will gradually reduce the influence of auxiliary tasks, while the 'Switch' strategy involves a shift from multi-tasking to single-tasking at a specific timepoint at the training process. In this paper, we propose the Multi-Task to Single-Task (MT2ST) framework, a novel approach that significantly enhances the efficiency and accuracy of word embedding training while concurrently addressing prevalent issues such as overfitting. Our empirical studies demonstrate that MT2ST can reduce training time by 67\% when contrasted with single-task learning approaches, and by 13\% compared to traditional multi-task learning methods. These findings underscore MT2ST's potential to be a powerful tools for word embedding training acceleration.
Authors: Yu Luo, Fuchun Sun, Tianying Ji, Xianyuan Zhan
Abstract: Hierarchical reinforcement learning (HRL) addresses complex long-horizon tasks by skillfully decomposing them into subgoals. Therefore, the effectiveness of HRL is greatly influenced by subgoal reachability. Typical HRL methods only consider subgoal reachability from the unilateral level, where a dominant level enforces compliance to the subordinate level. However, we observe that when the dominant level becomes trapped in local exploration or generates unattainable subgoals, the subordinate level is negatively affected and cannot follow the dominant level's actions. This can potentially make both levels stuck in local optima, ultimately hindering subsequent subgoal reachability. Allowing real-time bilateral information sharing and error correction would be a natural cure for this issue, which motivates us to propose a mutual response mechanism. Based on this, we propose the Bidirectional-reachable Hierarchical Policy Optimization (BrHPO)--a simple yet effective algorithm that also enjoys computation efficiency. Experiment results on a variety of long-horizon tasks showcase that BrHPO outperforms other state-of-the-art HRL baselines, coupled with a significantly higher exploration efficiency and robustness.
Authors: Chung-En Sun, Sicun Gao, Tsui-Wei Weng
Abstract: Robustness remains a paramount concern in deep reinforcement learning (DRL), with randomized smoothing emerging as a key technique for enhancing this attribute. However, a notable gap exists in the performance of current smoothed DRL agents, often characterized by significantly low clean rewards and weak robustness. In response to this challenge, our study introduces innovative algorithms aimed at training effective smoothed robust DRL agents. We propose S-DQN and S-PPO, novel approaches that demonstrate remarkable improvements in clean rewards, empirical robustness, and robustness guarantee across standard RL benchmarks. Notably, our S-DQN and S-PPO agents not only significantly outperform existing smoothed agents by an average factor of $2.16\times$ under the strongest attack, but also surpass previous robustly-trained agents by an average factor of $2.13\times$. This represents a significant leap forward in the field. Furthermore, we introduce Smoothed Attack, which is $1.89\times$ more effective in decreasing the rewards of smoothed agents than existing adversarial attacks.
Authors: Enoch Luk, Eviatar Bach, Ricardo Baptista, Andrew Stuart
Abstract: Filtering-the task of estimating the conditional distribution of states of a dynamical system given partial, noisy, observations-is important in many areas of science and engineering, including weather and climate prediction. However, the filtering distribution is generally intractable to obtain for high-dimensional, nonlinear systems. Filters used in practice, such as the ensemble Kalman filter (EnKF), are biased for nonlinear systems and have numerous tuning parameters. Here, we present a framework for learning a parameterized analysis map-the map that takes a forecast distribution and observations to the filtering distribution-using variational inference. We show that this methodology can be used to learn gain matrices for filtering linear and nonlinear dynamical systems, as well as inflation and localization parameters for an EnKF. Future work will apply this framework to learn new filtering algorithms.
Authors: Martina Doneda, Pieter Smet, Giuliana Carello, Ettore Lanzarone, Greet Vanden Berghe
Abstract: Disruptions to personnel rosters caused by absenteeism often necessitate last-minute adjustments to the employees' working hours. A common strategy to mitigate the impact of such changes is to assign employees to reserve shifts: special on-call duties during which an employee can be called in to cover for an absent employee. To maximize roster robustness, we assume a predict-then-optimize approach that uses absence predictions from a machine learning model to schedule an adequate number of reserve shifts. In this paper we propose a methodology to evaluate the robustness of rosters generated by the predict-then-optimize approach, assuming the machine learning model will make predictions at a predetermined prediction performance level. Instead of training and testing machine learning models, our methodology simulates the predictions based on a characterization of model performance. We show how this methodology can be applied to identify the minimum performance level needed for the model to outperform simple non-data-driven robust rostering policies. In a computational study on a nurse rostering problem, we demonstrate how the predict-then-optimize approach outperforms non-data-driven policies under reasonable performance requirements, particularly when employees possess interchangeable skills.
Authors: Nimrod Berman, Ilan Naiman, Idan Arbiv, Gal Fadlon, Omri Azencot
Abstract: One of the fundamental representation learning tasks is unsupervised sequential disentanglement, where latent codes of inputs are decomposed to a single static factor and a sequence of dynamic factors. To extract this latent information, existing methods condition the static and dynamic codes on the entire input sequence. Unfortunately, these models often suffer from information leakage, i.e., the dynamic vectors encode both static and dynamic information, or vice versa, leading to a non-disentangled representation. Attempts to alleviate this problem via reducing the dynamic dimension and auxiliary loss terms gain only partial success. Instead, we propose a novel and simple architecture that mitigates information leakage by offering a simple and effective subtraction inductive bias while conditioning on a single sample. Remarkably, the resulting variational framework is simpler in terms of required loss terms, hyperparameters, and data augmentation. We evaluate our method on multiple data-modality benchmarks including general time series, video, and audio, and we show beyond state-of-the-art results on generation and prediction tasks in comparison to several strong baselines.
Authors: Linping Qu, Shenghui Song, Chi-Ying Tsui
Abstract: Federated learning (FL) is a powerful machine learning paradigm which leverages the data as well as the computational resources of clients, while protecting clients' data privacy. However, the substantial model size and frequent aggregation between the server and clients result in significant communication overhead, making it challenging to deploy FL in resource-limited wireless networks. In this work, we aim to mitigate the communication overhead by using quantization. Previous research on quantization has primarily focused on the uplink communication, employing either fixed-bit quantization or adaptive quantization methods. In this work, we introduce a holistic approach by joint uplink and downlink adaptive quantization to reduce the communication overhead. In particular, we optimize the learning convergence by determining the optimal uplink and downlink quantization bit-length, with a communication energy constraint. Theoretical analysis shows that the optimal quantization levels depend on the range of model gradients or weights. Based on this insight, we propose a decreasing-trend quantization for the uplink and an increasing-trend quantization for the downlink, which aligns with the change of the model parameters during the training process. Experimental results show that, the proposed joint uplink and downlink adaptive quantization strategy can save up to 66.7% energy compared with the existing schemes.
Authors: Chaonan Ji, Tonio Fincke, Vitus Benson, Gustau Camps-Valls, Miguel-Angel Fernandez-Torres, Fabian Gans, Guido Kraemer, Francesco Martinuzzi, David Montero, Karin Mora, Oscar J. Pellicer-Valero, Claire Robin, Maximilian Soechting, Melanie Weynants, Miguel D. Mahecha
Abstract: With climate extremes' rising frequency and intensity, robust analytical tools are crucial to predict their impacts on terrestrial ecosystems. Machine learning techniques show promise but require well-structured, high-quality, and curated analysis-ready datasets. Earth observation datasets comprehensively monitor ecosystem dynamics and responses to climatic extremes, yet the data complexity can challenge the effectiveness of machine learning models. Despite recent progress in deep learning to ecosystem monitoring, there is a need for datasets specifically designed to analyse compound heatwave and drought extreme impact. Here, we introduce the DeepExtremeCubes database, tailored to map around these extremes, focusing on persistent natural vegetation. It comprises over 40,000 spatially sampled small data cubes (i.e. minicubes) globally, with a spatial coverage of 2.5 by 2.5 km. Each minicube includes (i) Sentinel-2 L2A images, (ii) ERA5-Land variables and generated extreme event cube covering 2016 to 2022, and (iii) ancillary land cover and topography maps. The paper aims to (1) streamline data accessibility, structuring, pre-processing, and enhance scientific reproducibility, and (2) facilitate biosphere dynamics forecasting in response to compound extremes.
Authors: Hamideh Kerdegari, Kyle Higgins, Dennis Veselkov, Ivan Laponogov, Inese Polaka, Miguel Coimbra, Junior Andrea Pescino, Marcis Leja, Mario Dinis-Ribeiro, Tania Fleitas Kanonnikoff, Kirill Veselkov
Abstract: The integration of artificial intelligence (AI) in medical diagnostics represents a significant advancement in managing upper gastrointestinal (GI) cancer, a major cause of global cancer mortality. Specifically for gastric cancer (GC), chronic inflammation causes changes in the mucosa such as atrophy, intestinal metaplasia (IM), dysplasia and ultimately cancer. Early detection through endoscopic regular surveillance is essential for better outcomes. Foundation models (FM), which are machine or deep learning models trained on diverse data and applicable to broad use cases, offer a promising solution to enhance the accuracy of endoscopy and its subsequent pathology image analysis. This review explores the recent advancements, applications, and challenges associated with FM in endoscopy and pathology imaging. We started by elucidating the core principles and architectures underlying these models, including their training methodologies and the pivotal role of large-scale data in developing their predictive capabilities. Moreover, this work discusses emerging trends and future research directions, emphasizing the integration of multimodal data, the development of more robust and equitable models, and the potential for real-time diagnostic support. This review aims to provide a roadmap for researchers and practitioners in navigating the complexities of incorporating FM into clinical practice for prevention/management of GC cases, thereby improving patient outcomes.
Authors: Julian Dierkes, Emma Cramer, Holger H. Hoos, Sebastian Trimpe
Abstract: There has been significant progress in deep reinforcement learning (RL) in recent years. Nevertheless, finding suitable hyperparameter configurations and reward functions remains challenging even for experts, and performance heavily relies on these design choices. Also, most RL research is conducted on known benchmarks where knowledge about these choices already exists. However, novel practical applications often pose complex tasks for which no prior knowledge about good hyperparameters and reward functions is available, thus necessitating their derivation from scratch. Prior work has examined automatically tuning either hyperparameters or reward functions individually. We demonstrate empirically that an RL algorithm's hyperparameter configurations and reward function are often mutually dependent, meaning neither can be fully optimised without appropriate values for the other. We then propose a methodology for the combined optimisation of hyperparameters and the reward function. Furthermore, we include a variance penalty as an optimisation objective to improve the stability of learned policies. We conducted extensive experiments using Proximal Policy Optimisation and Soft Actor-Critic on four environments. Our results show that combined optimisation significantly improves over baseline performance in half of the environments and achieves competitive performance in the others, with only a minor increase in computational costs. This suggests that combined optimisation should be best practice.
Authors: Elpiniki Maria Lygizou, Michael Reiter, Margarita Maurer-Granofszky, Michael Dworzak, Radu Grosu
Abstract: Acute Leukemia is the most common hematologic malignancy in children and adolescents. A key methodology in the diagnostic evaluation of this malignancy is immunophenotyping based on Multiparameter Flow Cytometry (FCM). However, this approach is manual, and thus time-consuming and subjective. To alleviate this situation, we propose in this paper the FCM-Former, a machine learning, self-attention based FCM-diagnostic tool, automating the immunophenotyping assessment in Childhood Acute Leukemia. The FCM-Former is trained in a supervised manner, by directly using flow cytometric data. Our FCM-Former achieves an accuracy of 96.5% assigning lineage to each sample among 960 cases of either acute B-cell, T-cell lymphoblastic, and acute myeloid leukemia (B-ALL, T-ALL, AML). To the best of our knowledge, the FCM-Former is the first work that automates the immunophenotyping assessment with FCM data in diagnosing pediatric Acute Leukemia.
Authors: Yixin Jin, Wenjing Zhou, Meiqi Wang, Meng Li, Xintao Li, Tianyu Hu, Xingyuan Bu
Abstract: This paper examines an online multi-task learning (OMTL) method, which processes data sequentially to predict labels across related tasks. The framework learns task weights and their relatedness concurrently. Unlike previous models that assumed static task relatedness, our approach treats tasks as initially independent, updating their relatedness iteratively using newly calculated weight vectors. We introduced three rules to update the task relatedness matrix: OMTLCOV, OMTLLOG, and OMTLVON, and compared them against a conventional method (CMTL) that uses a fixed relatedness value. Performance evaluations on three datasets a spam dataset and two EEG datasets from construction workers under varying conditions demonstrated that our OMTL methods outperform CMTL, improving accuracy by 1\% to 3\% on EEG data, and maintaining low error rates around 12\% on the spam dataset.
Authors: Matan Halfon, Tomer Cohen, Raanan Fattal, Dina Schneidman-Duhovny
Abstract: Deep learning approaches achieved significant progress in predicting protein structures. These methods are often applied to protein-protein interactions (PPIs) yet require Multiple Sequence Alignment (MSA) which is unavailable for various interactions, such as antibody-antigen. Computational docking methods are capable of sampling accurate complex models, but also produce thousands of invalid configurations. The design of scoring functions for identifying accurate models is a long-standing challenge. We develop a novel attention-based Graph Neural Network (GNN), ContactNet, for classifying PPI models obtained from docking algorithms into accurate and incorrect ones. When trained on docked antigen and modeled antibody structures, ContactNet doubles the accuracy of current state-of-the-art scoring functions, achieving accurate models among its Top-10 at 43% of the test cases. When applied to unbound antibodies, its Top-10 accuracy increases to 65%. This performance is achieved without MSA and the approach is applicable to other types of interactions, such as host-pathogens or general PPIs.
Authors: Matan Halfon, Eyal Rozenberg, Ehud Rivlin, Daniel Freedman
Abstract: Machine learning approaches to Structure-Based Drug Design (SBDD) have proven quite fertile over the last few years. In particular, diffusion-based approaches to SBDD have shown great promise. We present a technique which expands on this diffusion approach in two crucial ways. First, we address the size disparity between the drug molecule and the target/receptor, which makes learning more challenging and inference slower. We do so through the notion of a Virtual Receptor, which is a compressed version of the receptor; it is learned so as to preserve key aspects of the structural information of the original receptor, while respecting the relevant group equivariance. Second, we incorporate a protein language embedding used originally in the context of protein folding. We experimentally demonstrate the contributions of both the virtual receptors and the protein embeddings: in practice, they lead to both better performance, as well as significantly faster computations.
Authors: Aur\'elien Renault, Alexis Bondu, Antoine Cornu\'ejols, Vincent Lemaire
Abstract: In many situations, the measurements of a studied phenomenon are provided sequentially, and the prediction of its class needs to be made as early as possible so as not to incur too high a time penalty, but not too early and risk paying the cost of misclassification. This problem has been particularly studied in the case of time series, and is known as Early Classification of Time Series (ECTS). Although it has been the subject of a growing body of literature, there is still a lack of a systematic, shared evaluation protocol to compare the relative merits of the various existing methods. This document begins by situating these methods within a principle-based taxonomy. It defines dimensions for organizing their evaluation, and then reports the results of a very extensive set of experiments along these dimensions involving nine state-of-the art ECTS algorithms. In addition, these and other experiments can be carried out using an open-source library in which most of the existing ECTS algorithms have been implemented (see \url{https://github.com/ML-EDM/ml_edm}).
Authors: Hubert Baniecki, Giuseppe Casalicchio, Bernd Bischl, Przemyslaw Biecek
Abstract: Exact computation of various machine learning explanations requires numerous model evaluations and in extreme cases becomes impractical. The computational cost of approximation increases with an ever-increasing size of data and model parameters. Many heuristics have been proposed to approximate post-hoc explanations efficiently. This paper shows that the standard i.i.d. sampling used in a broad spectrum of algorithms for explanation estimation leads to an approximation error worthy of improvement. To this end, we introduce Compress Then Explain (CTE), a new paradigm for more efficient and accurate explanation estimation. CTE uses distribution compression through kernel thinning to obtain a data sample that best approximates the marginal distribution. We show that CTE improves the estimation of removal-based local and global explanations with negligible computational overhead. It often achieves an on-par explanation approximation error using 2-3x less samples, i.e. requiring 2-3x less model evaluations. CTE is a simple, yet powerful, plug-in for any explanation method that now relies on i.i.d. sampling.
Authors: Yi Ding, Chengxuan Tong, Shuailei Zhang, Muyun Jiang, Yong Li, Kevin Lim Jun Liang, Cuntai Guan
Abstract: Integrating prior knowledge of neurophysiology into neural network architecture enhances the performance of emotion decoding. While numerous techniques emphasize learning spatial and short-term temporal patterns, there has been limited emphasis on capturing the vital long-term contextual information associated with emotional cognitive processes. In order to address this discrepancy, we introduce a novel transformer model called emotion transformer (EmT). EmT is designed to excel in both generalized cross-subject EEG emotion classification and regression tasks. In EmT, EEG signals are transformed into a temporal graph format, creating a sequence of EEG feature graphs using a temporal graph construction module (TGC). A novel residual multi-view pyramid GCN module (RMPG) is then proposed to learn dynamic graph representations for each EEG feature graph within the series, and the learned representations of each graph are fused into one token. Furthermore, we design a temporal contextual transformer module (TCT) with two types of token mixers to learn the temporal contextual information. Finally, the task-specific output module (TSO) generates the desired outputs. Experiments on four publicly available datasets show that EmT achieves higher results than the baseline methods for both EEG emotion classification and regression tasks. The code is available at https://github.com/yi-ding-cs/EmT.
Authors: Zifan Liu, Xinran Li, Shibo Chen, Gen Li, Jiashuo Jiang, Jun Zhang
Abstract: Reinforcement learning (RL) has proven to be well-performed and general-purpose in the inventory control (IC). However, further improvement of RL algorithms in the IC domain is impeded due to two limitations of online experience. First, online experience is expensive to acquire in real-world applications. With the low sample efficiency nature of RL algorithms, it would take extensive time to train the RL policy to convergence. Second, online experience may not reflect the true demand due to the lost sales phenomenon typical in IC, which makes the learning process more challenging. To address the above challenges, we propose a decision framework that combines reinforcement learning with feedback graph (RLFG) and intrinsically motivated exploration (IME) to boost sample efficiency. In particular, we first take advantage of the inherent properties of lost-sales IC problems and design the feedback graph (FG) specially for lost-sales IC problems to generate abundant side experiences aid RL updates. Then we conduct a rigorous theoretical analysis of how the designed FG reduces the sample complexity of RL methods. Based on the theoretical insights, we design an intrinsic reward to direct the RL agent to explore to the state-action space with more side experiences, further exploiting FG's power. Experimental results demonstrate that our method greatly improves the sample efficiency of applying RL in IC. Our code is available at https://anonymous.4open.science/r/RLIMFG4IC-811D/
Authors: Gianluca De Carlo, Andrea Mastropietro, Aris Anagnostopoulos
Abstract: Graph neural networks (GNNs) excel in learning from network-like data but often lack interpretability, making their application challenging in domains requiring transparent decision-making. We propose the Graph Kolmogorov-Arnold Network (GKAN), a novel GNN model leveraging spline-based activation functions on edges to enhance both accuracy and interpretability. Our experiments on five benchmark datasets demonstrate that GKAN outperforms state-of-the-art GNN models in node classification, link prediction, and graph classification tasks. In addition to the improved accuracy, GKAN's design inherently provides clear insights into the model's decision-making process, eliminating the need for post-hoc explainability techniques. This paper discusses the methodology, performance, and interpretability of GKAN, highlighting its potential for applications in domains where interpretability is crucial.
Authors: Roman Bresson, Giannis Nikolentzos, George Panagopoulos, Michail Chatzianastasis, Jun Pang, Michalis Vazirgiannis
Abstract: In recent years, Graph Neural Networks (GNNs) have become the de facto tool for learning node and graph representations. Most GNNs typically consist of a sequence of neighborhood aggregation (a.k.a., message passing) layers. Within each of these layers, the representation of each node is updated from an aggregation and transformation of its neighbours representations at the previous layer. The upper bound for the expressive power of message passing GNNs was reached through the use of MLPs as a transformation, due to their universal approximation capabilities. However, MLPs suffer from well-known limitations, which recently motivated the introduction of Kolmogorov-Arnold Networks (KANs). KANs rely on the Kolmogorov-Arnold representation theorem, rendering them a promising alternative to MLPs. In this work, we compare the performance of KANs against that of MLPs in graph learning tasks. We perform extensive experiments on node classification, graph classification and graph regression datasets. Our preliminary results indicate that while KANs are on-par with MLPs in classification tasks, they seem to have a clear advantage in the graph regression tasks.
Authors: Tobias Sebastian Finn, Charlotte Durand, Alban Farchi, Marc Bocquet, Julien Brajard
Abstract: We make the first steps towards diffusion models for unconditional generation of multivariate and Arctic-wide sea-ice states. While targeting to reduce the computational costs by diffusion in latent space, latent diffusion models also offer the possibility to integrate physical knowledge into the generation process. We tailor latent diffusion models to sea-ice physics with a censored Gaussian distribution in data space to generate data that follows the physical bounds of the modelled variables. Our latent diffusion models reach similar scores as the diffusion model trained in data space, but they smooth the generated fields as caused by the latent mapping. While enforcing physical bounds cannot reduce the smoothing, it improves the representation of the marginal ice zone. Therefore, for large-scale Earth system modelling, latent diffusion models can have many advantages compared to diffusion in data space if the significant barrier of smoothing can be resolved.
Authors: Timon Willi, Johan Obando-Ceron, Jakob Foerster, Karolina Dziugaite, Pablo Samuel Castro
Abstract: Mixtures of Experts (MoEs) have gained prominence in (self-)supervised learning due to their enhanced inference efficiency, adaptability to distributed training, and modularity. Previous research has illustrated that MoEs can significantly boost Deep Reinforcement Learning (DRL) performance by expanding the network's parameter count while reducing dormant neurons, thereby enhancing the model's learning capacity and ability to deal with non-stationarity. In this work, we shed more light on MoEs' ability to deal with non-stationarity and investigate MoEs in DRL settings with "amplified" non-stationarity via multi-task training, providing further evidence that MoEs improve learning capacity. In contrast to previous work, our multi-task results allow us to better understand the underlying causes for the beneficial effect of MoE in DRL training, the impact of the various MoE components, and insights into how best to incorporate them in actor-critic-based DRL networks. Finally, we also confirm results from previous work.
Authors: Younghyun Koo, Maryam Rahnemoonfar
Abstract: Although numerical models provide accurate solutions for ice sheet dynamics based on physics laws, they accompany intensified computational demands to solve partial differential equations. In recent years, convolutional neural networks (CNNs) have been widely used as statistical emulators for those numerical models. However, since CNNs operate on regular grids, they cannot represent the refined meshes and computational efficiency of finite-element numerical models. Therefore, instead of CNNs, this study adopts an equivariant graph convolutional network (EGCN) as an emulator for the ice sheet dynamics modeling. EGCN reproduces ice thickness and velocity changes in the Helheim Glacier, Greenland, and Pine Island Glacier, Antarctica, with 260 times and 44 times faster computation time, respectively. Compared to the traditional CNN and graph convolutional network, EGCN shows outstanding accuracy in thickness prediction near fast ice streams by preserving the equivariance to the translation and rotation of graphs.
Authors: Xingfu Wu, Tupendra Oli, ustin H. Qian, Valerie Taylor, Mark C. Hersam, Vinod K. Sangwan
Abstract: Support Vector Machine (SVM) is a state-of-the-art classification method widely used in science and engineering due to its high accuracy, its ability to deal with high dimensional data, and its flexibility in modeling diverse sources of data. In this paper, we propose an autotuning-based optimization framework to quantify the ranges of hyperparameters in SVMs to identify their optimal choices, and apply the framework to two SVMs with the mixed-kernel between Sigmoid and Gaussian kernels for smart pixel datasets in high energy physics (HEP) and mixed-kernel heterojunction transistors (MKH). Our experimental results show that the optimal selection of hyperparameters in the SVMs and the kernels greatly varies for different applications and datasets, and choosing their optimal choices is critical for a high classification accuracy of the mixed kernel SVMs. Uninformed choices of hyperparameters C and coef0 in the mixed-kernel SVMs result in severely low accuracy, and the proposed framework effectively quantifies the proper ranges for the hyperparameters in the SVMs to identify their optimal choices to achieve the highest accuracy 94.6\% for the HEP application and the highest average accuracy 97.2\% with far less tuning time for the MKH application.
Authors: Aliz\'ee Pace, Bernhard Sch\"olkopf, Gunnar R\"atsch, Giorgia Ramponi
Abstract: Applying reinforcement learning (RL) to real-world problems is often made challenging by the inability to interact with the environment and the difficulty of designing reward functions. Offline RL addresses the first challenge by considering access to an offline dataset of environment interactions labeled by the reward function. In contrast, Preference-based RL does not assume access to the reward function and learns it from preferences, but typically requires an online interaction with the environment. We bridge the gap between these frameworks by exploring efficient methods for acquiring preference feedback in a fully offline setup. We propose Sim-OPRL, an offline preference-based reinforcement learning algorithm, which leverages a learned environment model to elicit preference feedback on simulated rollouts. Drawing on insights from both the offline RL and the preference-based RL literature, our algorithm employs a pessimistic approach for out-of-distribution data, and an optimistic approach for acquiring informative preferences about the optimal policy. We provide theoretical guarantees regarding the sample complexity of our approach, dependent on how well the offline data covers the optimal policy. Finally, we demonstrate the empirical performance of Sim-OPRL in different environments.
Authors: Jonas Ngnaw\'e, Sabyasachi Sahoo, Yann Pequignot, Fr\'ed\'eric Precioso, Christian Gagn\'e
Abstract: Despite extensive research on adversarial training strategies to improve robustness, the decisions of even the most robust deep learning models can still be quite sensitive to imperceptible perturbations, creating serious risks when deploying them for high-stakes real-world applications. While detecting such cases may be critical, evaluating a model's vulnerability at a per-instance level using adversarial attacks is computationally too intensive and unsuitable for real-time deployment scenarios. The input space margin is the exact score to detect non-robust samples and is intractable for deep neural networks. This paper introduces the concept of margin consistency -- a property that links the input space margins and the logit margins in robust models -- for efficient detection of vulnerable samples. First, we establish that margin consistency is a necessary and sufficient condition to use a model's logit margin as a score for identifying non-robust samples. Next, through comprehensive empirical analysis of various robustly trained models on CIFAR10 and CIFAR100 datasets, we show that they indicate strong margin consistency with a strong correlation between their input space margins and the logit margins. Then, we show that we can effectively use the logit margin to confidently detect brittle decisions with such models and accurately estimate robust accuracy on an arbitrarily large test set by estimating the input margins only on a small subset. Finally, we address cases where the model is not sufficiently margin-consistent by learning a pseudo-margin from the feature representation. Our findings highlight the potential of leveraging deep representations to efficiently assess adversarial vulnerability in deployment scenarios.
Authors: Mahtab Talaei, Iman Izadi
Abstract: Federated learning (FL), a novel branch of distributed machine learning (ML), develops global models through a private procedure without direct access to local datasets. However, it is still possible to access the model updates (gradient updates of deep neural networks) transferred between clients and servers, potentially revealing sensitive local information to adversaries using model inversion attacks. Differential privacy (DP) offers a promising approach to addressing this issue by adding noise to the parameters. On the other hand, heterogeneities in data structure, storage, communication, and computational capabilities of devices can cause convergence problems and delays in developing the global model. A personalized weighted averaging of local parameters based on the resources of each device can yield a better aggregated model in each round. In this paper, to efficiently preserve privacy, we propose a personalized DP framework that injects noise based on clients' relative impact factors and aggregates parameters while considering heterogeneities and adjusting properties. To fulfill the DP requirements, we first analyze the convergence boundary of the FL algorithm when impact factors are personalized and fixed throughout the learning process. We then further study the convergence property considering time-varying (adaptive) impact factors.
Authors: Wenhao Lu, Xufeng Zhao, Josua Spisak, Jae Hee Lee, Stefan Wermter
Abstract: Can emergent language models faithfully model the intelligence of decision-making agents? Though modern language models exhibit already some reasoning ability, and theoretically can potentially express any probable distribution over tokens, it remains underexplored how the world knowledge these pretrained models have memorized can be utilized to comprehend an agent's behaviour in the physical world. This study empirically examines, for the first time, how well large language models (LLMs) can build a mental model of agents, termed agent mental modelling, by reasoning about an agent's behaviour and its effect on states from agent interaction history. This research may unveil the potential of leveraging LLMs for elucidating RL agent behaviour, addressing a key challenge in eXplainable reinforcement learning (XRL). To this end, we propose specific evaluation metrics and test them on selected RL task datasets of varying complexity, reporting findings on agent mental model establishment. Our results disclose that LLMs are not yet capable of fully mental modelling agents through inference alone without further innovations. This work thus provides new insights into the capabilities and limitations of modern LLMs.
Authors: Tian Tian, Lin F. Yang, Csaba Szepesv\'ari
Abstract: The constrained Markov decision process (CMDP) framework emerges as an important reinforcement learning approach for imposing safety or other critical objectives while maximizing cumulative reward. However, the current understanding of how to learn efficiently in a CMDP environment with a potentially infinite number of states remains under investigation, particularly when function approximation is applied to the value functions. In this paper, we address the learning problem given linear function approximation with $q_{\pi}$-realizability, where the value functions of all policies are linearly representable with a known feature map, a setting known to be more general and challenging than other linear settings. Utilizing a local-access model, we propose a novel primal-dual algorithm that, after $\tilde{O}(\text{poly}(d) \epsilon^{-3})$ queries, outputs with high probability a policy that strictly satisfies the constraints while nearly optimizing the value with respect to a reward function. Here, $d$ is the feature dimension and $\epsilon > 0$ is a given error. The algorithm relies on a carefully crafted off-policy evaluation procedure to evaluate the policy using historical data, which informs policy updates through policy gradients and conserves samples. To our knowledge, this is the first result achieving polynomial sample complexity for CMDP in the $q_{\pi}$-realizable setting.
Authors: Justin Reverdi (IRIT, IMT), Sixin Zhang (IRIT), Sa\"id Aoues (IMT), Fabrice Gamboa (IMT), Serge Gratton (IRIT), Thomas Pellegrini (IRIT)
Abstract: In Vapor Cycle Systems, the mass flow sensor playsa key role for different monitoring and control purposes. However,physical sensors can be inaccurate, heavy, cumbersome, expensive orhighly sensitive to vibrations, which is especially problematic whenembedded into an aircraft. The conception of a virtual sensor, basedon other standard sensors, is a good alternative. This paper has twomain objectives. Firstly, a data-driven model using a ConvolutionalNeural Network is proposed to estimate the mass flow of thecompressor. We show that it significantly outperforms the standardPolynomial Regression model (thermodynamic maps), in terms of thestandard MSE metric and Engineer Performance metrics. Secondly,a semi-automatic segmentation method is proposed to compute theEngineer Performance metrics for real datasets, as the standard MSEmetric may pose risks in analyzing the dynamic behavior of VaporCycle Systems.
Authors: Shikun Feng, Jiaxin Zheng, Yinjun Jia, Yanwen Huang, Fengfeng Zhou, Wei-Ying Ma, Yanyan Lan
Abstract: Molecular representation learning is pivotal for various molecular property prediction tasks related to drug discovery. Robust and accurate benchmarks are essential for refining and validating current methods. Existing molecular property benchmarks derived from wet experiments, however, face limitations such as data volume constraints, unbalanced label distribution, and noisy labels. To address these issues, we construct a large-scale and precise molecular representation dataset of approximately 140,000 small molecules, meticulously designed to capture an extensive array of chemical, physical, and biological properties, derived through a robust computational ligand-target binding analysis pipeline. We conduct extensive experiments on various deep learning models, demonstrating that our dataset offers significant physicochemical interpretability to guide model development and design. Notably, the dataset's properties are linked to binding affinity metrics, providing additional insights into model performance in drug-target interaction tasks. We believe this dataset will serve as a more accurate and reliable benchmark for molecular representation learning, thereby expediting progress in the field of artificial intelligence-driven drug discovery.
Authors: Xirui Li, Hengguang Zhou, Ruochen Wang, Tianyi Zhou, Minhao Cheng, Cho-Jui Hsieh
Abstract: Humans are prone to cognitive distortions -- biased thinking patterns that lead to exaggerated responses to specific stimuli, albeit in very different contexts. This paper demonstrates that advanced Multimodal Large Language Models (MLLMs) exhibit similar tendencies. While these models are designed to respond queries under safety mechanism, they sometimes reject harmless queries in the presence of certain visual stimuli, disregarding the benign nature of their contexts. As the initial step in investigating this behavior, we identify three types of stimuli that trigger the oversensitivity of existing MLLMs: Exaggerated Risk, Negated Harm, and Counterintuitive Interpretation. To systematically evaluate MLLMs' oversensitivity to these stimuli, we propose the Multimodal OverSenSitivity Benchmark (MOSSBench). This toolkit consists of 300 manually collected benign multimodal queries, cross-verified by third-party reviewers (AMT). Empirical studies using MOSSBench on 20 MLLMs reveal several insights: (1). Oversensitivity is prevalent among SOTA MLLMs, with refusal rates reaching up to 76% for harmless queries. (2). Safer models are more oversensitive: increasing safety may inadvertently raise caution and conservatism in the model's responses. (3). Different types of stimuli tend to cause errors at specific stages -- perception, intent reasoning, and safety judgement -- in the response process of MLLMs. These findings highlight the need for refined safety mechanisms that balance caution with contextually appropriate responses, improving the reliability of MLLMs in real-world applications. We make our project available at https://turningpoint-ai.github.io/MOSSBench/.
Authors: Jeffrey Willette, Heejun Lee, Youngwan Lee, Myeongjae Jeon, Sung Ju Hwang
Abstract: The context window within a transformer provides a form of active memory for the current task, which can be useful for few-shot learning and conditional generation, both which depend heavily on previous context tokens. However, as the context length grows, the computational cost increases quadratically. Recent works have shown that saving a few initial tokens along with a fixed-sized sliding window leads to stable streaming generation with linear complexity in transformer-based Large Language Models (LLMs). However, they make suboptimal use of the fixed window by naively evicting all tokens unconditionally from the key-value (KV) cache once they reach the end of the window, resulting in tokens being forgotten and no longer able to affect subsequent predictions. To overcome this limitation, we propose a novel mechanism for storing longer sliding window contexts with the same total cache size by keeping separate cascading sub-cache buffers whereby each subsequent buffer conditionally accepts a fraction of the relatively more important tokens evicted from the previous buffer. Our method results in a dynamic KV cache that can store tokens from the more distant past than a fixed, static sliding window approach. Our experiments show improvements of 5.6% on long context generation (LongBench), 1.2% in streaming perplexity (PG19), and 0.6% in language understanding (MMLU STEM) using LLMs given the same fixed cache size. Additionally, we provide an efficient implementation that improves the KV cache latency from 1.33ms per caching operation to 0.54ms, a 59% speedup over previous work.
Authors: Shai Ben-David, Alex Bie, Gautam Kamath, Tosca Lechner
Abstract: We examine the relationship between learnability and robust (or agnostic) learnability for the problem of distribution learning. We show that, contrary to other learning settings (e.g., PAC learning of function classes), realizable learnability of a class of probability distributions does not imply its agnostic learnability. We go on to examine what type of data corruption can disrupt the learnability of a distribution class and what is such learnability robust against. We show that realizable learnability of a class of distributions implies its robust learnability with respect to only additive corruption, but not against subtractive corruption. We also explore related implications in the context of compression schemes and differentially private learnability.
Authors: Vaclav Voracek
Abstract: Randomized smoothing is a popular certified defense against adversarial attacks. In its essence, we need to solve a problem of statistical estimation which is usually very time-consuming since we need to perform numerous (usually $10^5$) forward passes of the classifier for every point to be certified. In this paper, we review the statistical estimation problems for randomized smoothing to find out if the computational burden is necessary. In particular, we consider the (standard) task of adversarial robustness where we need to decide if a point is robust at a certain radius or not using as few samples as possible while maintaining statistical guarantees. We present estimation procedures employing confidence sequences enjoying the same statistical guarantees as the standard methods, with the optimal sample complexities for the estimation task and empirically demonstrate their good performance. Additionally, we provide a randomized version of Clopper-Pearson confidence intervals resulting in strictly stronger certificates.
Authors: Ye Won Byun, Cathy Jiao, Shahriar Noroozizadeh, Jimin Sun, Rosa Vitiello
Abstract: We introduce a simple method that employs pre-trained CLIP encoders to enhance model generalization in the ALFRED task. In contrast to previous literature where CLIP replaces the visual encoder, we suggest using CLIP as an additional module through an auxiliary object detection objective. We validate our method on the recently proposed Episodic Transformer architecture and demonstrate that incorporating CLIP improves task performance on the unseen validation set. Additionally, our analysis results support that CLIP especially helps with leveraging object descriptions, detecting small objects, and interpreting rare words.
Authors: Nafis Neehal, Bowen Wang, Shayom Debopadhaya, Soham Dan, Keerthiram Murugesan, Vibha Anand, Kristin P. Bennett
Abstract: CTBench is introduced as a benchmark to assess language models (LMs) in aiding clinical study design. Given study-specific metadata, CTBench evaluates AI models' ability to determine the baseline features of a clinical trial (CT), which include demographic and relevant features collected at the trial's start from all participants. These baseline features, typically presented in CT publications (often as Table 1), are crucial for characterizing study cohorts and validating results. Baseline features, including confounders and covariates, are also necessary for accurate treatment effect estimation in studies involving observational data. CTBench consists of two datasets: "CT-Repo," containing baseline features from 1,690 clinical trials sourced from clinicaltrials.gov, and "CT-Pub," a subset of 100 trials with more comprehensive baseline features gathered from relevant publications. Two LM-based evaluation methods are developed to compare the actual baseline feature lists against LM-generated responses. "ListMatch-LM" and "ListMatch-BERT" use GPT-4o and BERT scores (at various thresholds), respectively, for evaluation. To establish baseline results, advanced prompt engineering techniques using LLaMa3-70B-Instruct and GPT-4o in zero-shot and three-shot learning settings are applied to generate potential baseline features. The performance of GPT-4o as an evaluator is validated through human-in-the-loop evaluations on the CT-Pub dataset, where clinical experts confirm matches between actual and LM-generated features. The results highlight a promising direction with significant potential for improvement, positioning CTBench as a useful tool for advancing research on AI in CT design and potentially enhancing the efficacy and robustness of CTs.
Authors: Arnaud Judge, Thierry Judge, Nicolas Duchateau, Roman A. Sandler, Joseph Z. Sokol, Olivier Bernard, Pierre-Marc Jodoin
Abstract: Performance of deep learning segmentation models is significantly challenged in its transferability across different medical imaging domains, particularly when aiming to adapt these models to a target domain with insufficient annotated data for effective fine-tuning. While existing domain adaptation (DA) methods propose strategies to alleviate this problem, these methods do not explicitly incorporate human-verified segmentation priors, compromising the potential of a model to produce anatomically plausible segmentations. We introduce RL4Seg, an innovative reinforcement learning framework that reduces the need to otherwise incorporate large expertly annotated datasets in the target domain, and eliminates the need for lengthy manual human review. Using a target dataset of 10,000 unannotated 2D echocardiographic images, RL4Seg not only outperforms existing state-of-the-art DA methods in accuracy but also achieves 99% anatomical validity on a subset of 220 expert-validated subjects from the target domain. Furthermore, our framework's reward network offers uncertainty estimates comparable with dedicated state-of-the-art uncertainty methods, demonstrating the utility and effectiveness of RL4Seg in overcoming domain adaptation challenges in medical image segmentation.
Authors: Marwan Zouinkhi, Jeff L. Rhoades, Aubrey V. Weigel
Abstract: Machine learning models are only as good as the data to which they are fit. As such, it is always preferable to use as much data as possible in training models. What data can be used for fitting a model depends a lot on the formulation of the task. We introduce Hot-Distance, a novel segmentation target that incorporates the strength of signed boundary distance prediction with the flexibility of one-hot encoding, to increase the amount of usable training data for segmentation of subcellular structures in focused ion beam scanning electron microscopy (FIB-SEM).
Authors: Ziwei Ji, Himanshu Jain, Andreas Veit, Sashank J. Reddi, Sadeep Jayasumana, Ankit Singh Rawat, Aditya Krishna Menon, Felix Yu, Sanjiv Kumar
Abstract: Cross-Encoder (CE) and Dual-Encoder (DE) models are two fundamental approaches for query-document relevance in information retrieval. To predict relevance, CE models use joint query-document embeddings, while DE models maintain factorized query and document embeddings; usually, the former has higher quality while the latter benefits from lower latency. Recently, late-interaction models have been proposed to realize more favorable latency-quality tradeoffs, by using a DE structure followed by a lightweight scorer based on query and document token embeddings. However, these lightweight scorers are often hand-crafted, and there is no understanding of their approximation power; further, such scorers require access to individual document token embeddings, which imposes an increased latency and storage burden. In this paper, we propose novel learnable late-interaction models (LITE) that resolve these issues. Theoretically, we prove that LITE is a universal approximator of continuous scoring functions, even for relatively small embedding dimension. Empirically, LITE outperforms previous late-interaction models such as ColBERT on both in-domain and zero-shot re-ranking tasks. For instance, experiments on MS MARCO passage re-ranking show that LITE not only yields a model with better generalization, but also lowers latency and requires 0.25x storage compared to ColBERT.
Authors: Matthieu Meeus, Shubham Jain, Marek Rei, Yves-Alexandre de Montjoye
Abstract: Large Language Models (LLMs) are often trained on vast amounts of undisclosed data, motivating the development of post-hoc Membership Inference Attacks (MIAs) to gain insight into their training data composition. However, in this paper, we identify inherent challenges in post-hoc MIA evaluation due to potential distribution shifts between collected member and non-member datasets. Using a simple bag-of-words classifier, we demonstrate that datasets used in recent post-hoc MIAs suffer from significant distribution shifts, in some cases achieving near-perfect distinction between members and non-members. This implies that previously reported high MIA performance may be largely attributable to these shifts rather than model memorization. We confirm that randomized, controlled setups eliminate such shifts and thus enable the development and fair evaluation of new MIAs. However, we note that such randomized setups are rarely available for the latest LLMs, making post-hoc data collection still required to infer membership for real-world LLMs. As a potential solution, we propose a Regression Discontinuity Design (RDD) approach for post-hoc data collection, which substantially mitigates distribution shifts. Evaluating various MIA methods on this RDD setup yields performance barely above random guessing, in stark contrast to previously reported results. Overall, our findings highlight the challenges in accurately measuring LLM memorization and the need for careful experimental design in (post-hoc) membership inference tasks.
Authors: Vikas Yadav, Hyuk Joon Kwon, Vijay Srinivasan, Hongxia Jin
Abstract: Question Answer Generation (QAG) is an effective data augmentation technique to improve the accuracy of question answering systems, especially in low-resource domains. While recent pretrained and large language model-based QAG methods have made substantial progress, they face the critical issue of redundant QA pair generation, affecting downstream QA systems. Implicit diversity techniques such as sampling and diverse beam search are proven effective solutions but often yield smaller diversity. We present explicit diversity conditions for QAG, focusing on spatial aspects, question types, and entities, substantially increasing diversity in QA generation. Our work emphasizes the need of explicit diversity conditions for generating diverse question-answer synthetic data by showing significant improvements in downstream QA task over existing widely adopted implicit diversity techniques. In particular, generated QA pairs from explicit diversity conditions when used to train the downstream QA model results in an average 4.1% exact match and 4.5% F1 improvement over QAG from implicit sampling techniques on SQuADDU. Our work emphasizes the need for explicit diversity conditions even more in low-resource datasets (SubjQA), where average downstream QA performance improvements are around 12% EM.
Authors: Shuaishuai Ye, Shunfei Chen, Xinhui Hu, Xinkang Xu
Abstract: In this work, we propose a Switch-Conformer-based MoE system named SC-MoE for unified streaming and non-streaming code-switching (CS) automatic speech recognition (ASR), where we design a streaming MoE layer consisting of three language experts, which correspond to Mandarin, English, and blank, respectively, and equipped with a language identification (LID) network with a Connectionist Temporal Classification (CTC) loss as a router in the encoder of SC-MoE to achieve a real-time streaming CS ASR system. To further utilize the language information embedded in text, we also incorporate MoE layers into the decoder of SC-MoE. In addition, we introduce routers into every MoE layer of the encoder and the decoder and achieve better recognition performance. Experimental results show that the SC-MoE significantly improves CS ASR performances over baseline with comparable computational efficiency.
Authors: Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt, Aaron Courville, Sai Rajeswar
Abstract: Learning generalist embodied agents, able to solve multitudes of tasks in different domains is a long-standing problem. Reinforcement learning (RL) is hard to scale up as it requires a complex reward design for each task. In contrast, language can specify tasks in a more natural way. Current foundation vision-language models (VLMs) generally require fine-tuning or other adaptations to be functional, due to the significant domain gap. However, the lack of multimodal data in such domains represents an obstacle toward developing foundation models for embodied applications. In this work, we overcome these problems by presenting multimodal foundation world models, able to connect and align the representation of foundation VLMs with the latent space of generative world models for RL, without any language annotations. The resulting agent learning framework, GenRL, allows one to specify tasks through vision and/or language prompts, ground them in the embodied domain's dynamics, and learns the corresponding behaviors in imagination. As assessed through large-scale multi-task benchmarking, GenRL exhibits strong multi-task generalization performance in several locomotion and manipulation domains. Furthermore, by introducing a data-free RL strategy, it lays the groundwork for foundation model-based RL for generalist embodied agents.
Authors: Yifan Yang, Kai Zhen, Ershad Banijamal, Athanasios Mouchtaris, Zheng Zhang
Abstract: Fine-tuning large language models (LLMs) has achieved remarkable performance across various natural language processing tasks, yet it demands more and more memory as model sizes keep growing. To address this issue, the recently proposed Memory-efficient Zeroth-order (MeZO) methods attempt to fine-tune LLMs using only forward passes, thereby avoiding the need for a backpropagation graph. However, significant performance drops and a high risk of divergence have limited their widespread adoption. In this paper, we propose the Adaptive Zeroth-order Tensor-Train Adaption (AdaZeta) framework, specifically designed to improve the performance and convergence of the ZO methods. To enhance dimension-dependent ZO estimation accuracy, we introduce a fast-forward, low-parameter tensorized adapter. To tackle the frequently observed divergence issue in large-scale ZO fine-tuning tasks, we propose an adaptive query number schedule that guarantees convergence. Detailed theoretical analysis and extensive experimental results on Roberta-Large and Llama-2-7B models substantiate the efficacy of our AdaZeta framework in terms of accuracy, memory efficiency, and convergence speed.
Authors: Osama Hanna, Merve Karakas, Lin F. Yang, Christina Fragouli
Abstract: We consider a novel multi-arm bandit (MAB) setup, where a learner needs to communicate the actions to distributed agents over erasure channels, while the rewards for the actions are directly available to the learner through external sensors. In our model, while the distributed agents know if an action is erased, the central learner does not (there is no feedback), and thus does not know whether the observed reward resulted from the desired action or not. We propose a scheme that can work on top of any (existing or future) MAB algorithm and make it robust to action erasures. Our scheme results in a worst-case regret over action-erasure channels that is at most a factor of $O(1/\sqrt{1-\epsilon})$ away from the no-erasure worst-case regret of the underlying MAB algorithm, where $\epsilon$ is the erasure probability. We also propose a modification of the successive arm elimination algorithm and prove that its worst-case regret is $\Tilde{O}(\sqrt{KT}+K/(1-\epsilon))$, which we prove is optimal by providing a matching lower bound.
Authors: Gil Keren, Wei Zhou, Ozlem Kalinli
Abstract: ASR models are commonly trained with the cross-entropy criterion to increase the probability of a target token sequence. While optimizing the probability of all tokens in the target sequence is sensible, one may want to de-emphasize tokens that reflect transcription errors. In this work, we propose a novel token-weighted RNN-T criterion that augments the RNN-T objective with token-specific weights. The new objective is used for mitigating accuracy loss from transcriptions errors in the training data, which naturally appear in two settings: pseudo-labeling and human annotation errors. Experiments results show that using our method for semi-supervised learning with pseudo-labels leads to a consistent accuracy improvement, up to 38% relative. We also analyze the accuracy degradation resulting from different levels of WER in the reference transcription, and show that token-weighted RNN-T is suitable for overcoming this degradation, recovering 64%-99% of the accuracy loss.
Authors: Ahmed Heakl, Youssef Zaghloul, Mennatullah Ali, Rania Hossam, Walid Gomaa
Abstract: Motivated by the widespread increase in the phenomenon of code-switching between Egyptian Arabic and English in recent times, this paper explores the intricacies of machine translation (MT) and automatic speech recognition (ASR) systems, focusing on translating code-switched Egyptian Arabic-English to either English or Egyptian Arabic. Our goal is to present the methodologies employed in developing these systems, utilizing large language models such as LLama and Gemma. In the field of ASR, we explore the utilization of the Whisper model for code-switched Egyptian Arabic recognition, detailing our experimental procedures including data preprocessing and training techniques. Through the implementation of a consecutive speech-to-text translation system that integrates ASR with MT, we aim to overcome challenges posed by limited resources and the unique characteristics of the Egyptian Arabic dialect. Evaluation against established metrics showcases promising results, with our methodologies yielding a significant improvement of $56\%$ in English translation over the state-of-the-art and $9.3\%$ in Arabic translation. Since code-switching is deeply inherent in spoken languages, it is crucial that ASR systems can effectively handle this phenomenon. This capability is crucial for enabling seamless interaction in various domains, including business negotiations, cultural exchanges, and academic discourse. Our models and code are available as open-source resources. Code: \url{http://github.com/ahmedheakl/arazn-llm}}, Models: \url{http://huggingface.co/collections/ahmedheakl/arazn-llm-662ceaf12777656607b9524e}.
URLs: http://github.com/ahmedheakl/arazn-llm, http://huggingface.co/collections/ahmedheakl/arazn-llm-662ceaf12777656607b9524e
Authors: Ahmed Heakl, Youssef Mohamed, Noran Mohamed, Ali Sharkaway, Ahmed Zaky
Abstract: The increasing reliance on online recruitment platforms coupled with the adoption of AI technologies has highlighted the critical need for efficient resume classification methods. However, challenges such as small datasets, lack of standardized resume templates, and privacy concerns hinder the accuracy and effectiveness of existing classification models. In this work, we address these challenges by presenting a comprehensive approach to resume classification. We curated a large-scale dataset of 13,389 resumes from diverse sources and employed Large Language Models (LLMs) such as BERT and Gemma1.1 2B for classification. Our results demonstrate significant improvements over traditional machine learning approaches, with our best model achieving a top-1 accuracy of 92\% and a top-5 accuracy of 97.5\%. These findings underscore the importance of dataset quality and advanced model architectures in enhancing the accuracy and robustness of resume classification systems, thus advancing the field of online recruitment practices.
Authors: Meiying Zhang, Weiyuan Peng, Guangyao Ding, Chenyang Lei, Chunlin Ji, Qi Hao
Abstract: Simulation data can be accurately labeled and have been expected to improve the performance of data-driven algorithms, including object detection. However, due to the various domain inconsistencies from simulation to reality (sim-to-real), cross-domain object detection algorithms usually suffer from dramatic performance drops. While numerous unsupervised domain adaptation (UDA) methods have been developed to address cross-domain tasks between real-world datasets, progress in sim-to-real remains limited. This paper presents a novel Complex-to-Simple (CTS) framework to transfer models from labeled simulation (source) to unlabeled reality (target) domains. Based on a two-stage detector, the novelty of this work is threefold: 1) developing fixed-size anchor heads and RoI augmentation to address size bias and feature diversity between two domains, thereby improving the quality of pseudo-label; 2) developing a novel corner-format representation of aleatoric uncertainty (AU) for the bounding box, to uniformly quantify pseudo-label quality; 3) developing a noise-aware mean teacher domain adaptation method based on AU, as well as object-level and frame-level sampling strategies, to migrate the impact of noisy labels. Experimental results demonstrate that our proposed approach significantly enhances the sim-to-real domain adaptation capability of 3D object detection models, outperforming state-of-the-art cross-domain algorithms, which are usually developed for real-to-real UDA tasks.
Authors: Dongya Wu, Xin Li
Abstract: Generalization theory has been established for sparse deep neural networks under high-dimensional regime. Beyond generalization, parameter estimation is also important since it is crucial for variable selection and interpretability of deep neural networks. Current theoretical studies concerning parameter estimation mainly focus on two-layer neural networks, which is due to the fact that the convergence of parameter estimation heavily relies on the regularity of the Hessian matrix, while the Hessian matrix of deep neural networks is highly singular. To avoid the unidentifiability of deep neural networks in parameter estimation, we propose to conduct nonparametric estimation of partial derivatives with respect to inputs. We first show that model convergence of sparse deep neural networks is guaranteed in that the sample complexity only grows with the logarithm of the number of parameters or the input dimension when the $\ell_{1}$-norm of parameters is well constrained. Then by bounding the norm and the divergence of partial derivatives, we establish that the convergence rate of nonparametric estimation of partial derivatives scales as $\mathcal{O}(n^{-1/4})$, a rate which is slower than the model convergence rate $\mathcal{O}(n^{-1/2})$. To the best of our knowledge, this study combines nonparametric estimation and parametric sparse deep neural networks for the first time. As nonparametric estimation of partial derivatives is of great significance for nonlinear variable selection, the current results show the promising future for the interpretability of deep neural networks.
Authors: Shaowei Wang, Changyu Dong, Di Wang, Xiangfu Song
Abstract: The shuffle model of differential privacy (DP) has recently emerged as a powerful one for decentralized computation without fully trustable parties. Since it anonymizes and permutes messages from clients through a shuffler, the privacy can be amplified and utility can be improved. However, the shuffling procedure in turn restricts its applications only to statistical tasks that are permutation-invariant. This work explores the feasibility of shuffle privacy amplification for prevalent non-statistical computations: spatial crowdsourcing, combinatorial optimization, location-based social systems, and federated learning with incentives, which suffer either computationally intractability or intolerable utility loss in existing approaches (e.g., secure MPC and local DP). We proposes a new paradigm of shuffle model that can provide critical security functionalities like message authorization and result access control, meanwhile maintaining the most of privacy amplification effects. It incurs almost the same computation/communication costs as the non-private setting, and permits the server to run arbitrary algorithms on (noisy) client information in plaintext. Our novel technique is introducing statistically random identity into DP and force identical random distribution on all clients, so as to support secure functionalities even after message shuffling and to maintain privacy amplification simultaneously. Given that existing DP randomizers fails in the new shuffle model, we also propose a new mechanism and prove its optimality therein. Experimental results on spatial crowdsourcing, location-based social system, and federated learning with incentives, show that our paradigm and mechanism is fast as non-private settings, while reducing up to 90% error and increasing utility performance indicates by 100%-300% relatively, and can be practical under reasonable privacy budget.
Authors: Akshay Chaturvedi, Kate Thompson, Nicholas Asher
Abstract: When engaging in collaborative tasks, humans efficiently exploit the semantic structure of a conversation to optimize verbal and nonverbal interactions. But in recent "language to code" or "language to action" models, this information is lacking. We show how incorporating the prior discourse and nonlinguistic context of a conversation situated in a nonlinguistic environment can improve the "language to action" component of such interactions. We fine tune an LLM to predict actions based on prior context; our model, NeBuLa, doubles the net-action F1 score over the baseline on this task of Jayannavar et al.(2020). We also investigate our model's ability to construct shapes and understand location descriptions using a synthetic dataset.
Authors: Qiushi Huang, Xubo Liu, Tom Ko, Bo Wu, Wenwu Wang, Yu Zhang, Lilian Tang
Abstract: In conversational AI, personalizing dialogues with persona profiles and contextual understanding is essential. Despite large language models' (LLMs) improved response coherence, effective persona integration remains a challenge. In this work, we first study two common approaches for personalizing LLMs: textual prompting and direct fine-tuning. We observed that textual prompting often struggles to yield responses that are similar to the ground truths in datasets, while direct fine-tuning tends to produce repetitive or overly generic replies. To alleviate those issues, we propose \textbf{S}elective \textbf{P}rompt \textbf{T}uning (SPT), which softly prompts LLMs for personalized conversations in a selective way. Concretely, SPT initializes a set of soft prompts and uses a trainable dense retriever to adaptively select suitable soft prompts for LLMs according to different input contexts, where the prompt retriever is dynamically updated through feedback from the LLMs. Additionally, we propose context-prompt contrastive learning and prompt fusion learning to encourage the SPT to enhance the diversity of personalized conversations. Experiments on the CONVAI2 dataset demonstrate that SPT significantly enhances response diversity by up to 90\%, along with improvements in other critical performance indicators. Those results highlight the efficacy of SPT in fostering engaging and personalized dialogue generation. The SPT model code (https://github.com/hqsiswiliam/SPT) is publicly available for further exploration.
Authors: Ka Man Lo, Zeyu Huang, Zihan Qiu, Zili Wang, Jie Fu
Abstract: Mixture-of-experts (MoE) is gaining increasing attention due to its unique properties and remarkable performance, especially for language tasks. By sparsely activating a subset of parameters for each token, MoE architecture could increase the model size without sacrificing computational efficiency, achieving a better trade-off between performance and training costs. However, the underlying mechanism of MoE still lacks further exploration, and its modularization degree remains questionable. In this paper, we make an initial attempt to understand the inner workings of MoE-based large language models. Concretely, we comprehensively study the parametric and behavioral features of three recent MoE-based models and reveal some intriguing observations, including (1) Neurons act like fine-grained experts. (2) The router of MoE usually selects experts with larger output norms. (3) The expert diversity increases as the layer increases, while the last layer is an outlier. Based on the observations, we also provide suggestions for a broad spectrum of MoE practitioners, such as router design and expert allocation. We hope this work could shed light on future research on the MoE framework and other modular architectures. Code is available at https://github.com/kamanphoebe/Look-into-MoEs.
Authors: Patrick Takenaka, Johannes Maucher, Marco F. Huber
Abstract: We propose a general way to integrate procedural knowledge of a domain into deep learning models. We apply it to the case of video prediction, building on top of object-centric deep models and show that this leads to a better performance than using data-driven models alone. We develop an architecture that facilitates latent space disentanglement in order to use the integrated procedural knowledge, and establish a setup that allows the model to learn the procedural interface in the latent space using the downstream task of video prediction. We contrast the performance to a state-of-the-art data-driven approach and show that problems where purely data-driven approaches struggle can be handled by using knowledge about the domain, providing an alternative to simply collecting more data.
Authors: I. R. Slootweg, M. Thach, K. R. Curro-Tafili, F. D. Verbraak, F. H. Bouwman, Y. A. L. Pijnenburg, J. F. Boer, J. H. P. de Kwisthout, L. Bagheriye, P. J. Gonz\'alez
Abstract: Background/Aim. This study aims to predict Amyloid Positron Emission Tomography (AmyloidPET) status with multimodal retinal imaging and convolutional neural networks (CNNs) and to improve the performance through pretraining with synthetic data. Methods. Fundus autofluorescence, optical coherence tomography (OCT), and OCT angiography images from 328 eyes of 59 AmyloidPET positive subjects and 108 AmyloidPET negative subjects were used for classification. Denoising Diffusion Probabilistic Models (DDPMs) were trained to generate synthetic images and unimodal CNNs were pretrained on synthetic data and finetuned on real data or trained solely on real data. Multimodal classifiers were developed to combine predictions of the four unimodal CNNs with patient metadata. Class activation maps of the unimodal classifiers provided insight into the network's attention to inputs. Results. DDPMs generated diverse, realistic images without memorization. Pretraining unimodal CNNs with synthetic data improved AUPR at most from 0.350 to 0.579. Integration of metadata in multimodal CNNs improved AUPR from 0.486 to 0.634, which was the best overall best classifier. Class activation maps highlighted relevant retinal regions which correlated with AD. Conclusion. Our method for generating and leveraging synthetic data has the potential to improve AmyloidPET prediction from multimodal retinal imaging. A DDPM can generate realistic and unique multimodal synthetic retinal images. Our best performing unimodal and multimodal classifiers were not pretrained on synthetic data, however pretraining with synthetic data slightly improved classification performance for two out of the four modalities.
Authors: Nikolaos Dionelis, Nicolas Longepe
Abstract: Confidence assessments of semantic segmentation algorithms in remote sensing are important. It is a desirable property of models to a priori know if they produce an incorrect output. Evaluations of the confidence assigned to the estimates of models for the task of classification in Earth Observation (EO) are crucial as they can be used to achieve improved semantic segmentation performance and prevent high error rates during inference and deployment. The model we develop, the Confidence Assessments of classification algorithms for Semantic segmentation (CAS) model, performs confidence evaluations at both the segment and pixel levels, and outputs both labels and confidence. The outcome of this work has important applications. The main application is the evaluation of EO Foundation Models on semantic segmentation downstream tasks, in particular land cover classification using satellite Copernicus Sentinel-2 data. The evaluation shows that the proposed model is effective and outperforms other alternative baseline models.
Authors: Nikolaos Dionelis, Casper Fibaek, Luke Camilleri, Andreas Luyts, Jente Bosmans, Bertrand Le Saux
Abstract: When we are primarily interested in solving several problems jointly with a given prescribed high performance accuracy for each target application, then Foundation Models should for most cases be used rather than problem-specific models. We focus on the specific Computer Vision application of Foundation Models for Earth Observation (EO) and geospatial AI. These models can solve important problems we are tackling, including for example land cover classification, crop type mapping, flood segmentation, building density estimation, and road regression segmentation. In this paper, we show that for a limited number of labelled data, Foundation Models achieve improved performance compared to problem-specific models. In this work, we also present our proposed evaluation benchmark for Foundation Models for EO. Benchmarking the generalization performance of Foundation Models is important as it has become difficult to standardize a fair comparison across the many different models that have been proposed recently. We present the results using our evaluation benchmark for EO Foundation Models and show that Foundation Models are label efficient in the downstream tasks and help us solve problems we are tackling in EO and remote sensing.
Authors: Wenting Chen, Jie Liu, Tommy W. S. Chow, Yixuan Yuan
Abstract: Pathology image are essential for accurately interpreting lesion cells in cytopathology screening, but acquiring high-resolution digital slides requires specialized equipment and long scanning times. Though super-resolution (SR) techniques can alleviate this problem, existing deep learning models recover pathology image in a black-box manner, which can lead to untruthful biological details and misdiagnosis. Additionally, current methods allocate the same computational resources to recover each pixel of pathology image, leading to the sub-optimal recovery issue due to the large variation of pathology image. In this paper, we propose the first hierarchical reinforcement learning framework named Spatial-Temporal hierARchical Reinforcement Learning (STAR-RL), mainly for addressing the aforementioned issues in pathology image super-resolution problem. We reformulate the SR problem as a Markov decision process of interpretable operations and adopt the hierarchical recovery mechanism in patch level, to avoid sub-optimal recovery. Specifically, the higher-level spatial manager is proposed to pick out the most corrupted patch for the lower-level patch worker. Moreover, the higher-level temporal manager is advanced to evaluate the selected patch and determine whether the optimization should be stopped earlier, thereby avoiding the over-processed problem. Under the guidance of spatial-temporal managers, the lower-level patch worker processes the selected patch with pixel-wise interpretable actions at each time step. Experimental results on medical images degraded by different kernels show the effectiveness of STAR-RL. Furthermore, STAR-RL validates the promotion in tumor diagnosis with a large margin and shows generalizability under various degradations. The source code is available at https://github.com/CUHK-AIM-Group/STAR-RL.
Authors: Koki Chinzei, Shinichiro Yamano, Quoc Hoan Tran, Yasuhiro Endo, Hirotaka Oshima
Abstract: Quantum neural networks (QNNs) require an efficient training algorithm to achieve practical quantum advantages. A promising approach is the use of gradient-based optimization algorithms, where gradients are estimated through quantum measurements. However, it is generally difficult to efficiently measure gradients in QNNs because the quantum state collapses upon measurement. In this work, we prove a general trade-off between gradient measurement efficiency and expressivity in a wide class of deep QNNs, elucidating the theoretical limits and possibilities of efficient gradient estimation. This trade-off implies that a more expressive QNN requires a higher measurement cost in gradient estimation, whereas we can increase gradient measurement efficiency by reducing the QNN expressivity to suit a given task. We further propose a general QNN ansatz called the stabilizer-logical product ansatz (SLPA), which can reach the upper limit of the trade-off inequality by leveraging the symmetric structure of the quantum circuit. In learning an unknown symmetric function, the SLPA drastically reduces the quantum resources required for training while maintaining accuracy and trainability compared to a well-designed symmetric circuit based on the parameter-shift method. Our results not only reveal a theoretical understanding of efficient training in QNNs but also provide a standard and broadly applicable efficient QNN design.
Authors: Yuxuan Qi, Li Lin, Jiajun Wang, Jingya Zhang, Bin Zhang
Abstract: Accurate segmentation of tumors in PET/CT images is important in computer-aided diagnosis and treatment of cancer. The key issue of such a segmentation problem lies in the effective integration of complementary information from PET and CT images. However, the quality of PET and CT images varies widely in clinical settings, which leads to uncertainty in the modality information extracted by networks. To take the uncertainty into account in multi-modal information fusion, this paper proposes a novel Multi-modal Evidential Fusion Network (MEFN) comprising a Cross-Modal Feature Learning (CFL) module and a Multi-modal Trusted Fusion (MTF) module. The CFL module reduces the domain gap upon modality conversion and highlights common tumor features, thereby alleviating the needs of the segmentation module to handle modality specificity. The MTF module utilizes mutual attention mechanisms and an uncertainty calibrator to fuse modality features based on modality uncertainty and then fuse the segmentation results under the guidance of Dempster-Shafer Theory. Besides, a new uncertainty perceptual loss is introduced to force the model focusing on uncertain features and hence improve its ability to extract trusted modality information. Extensive comparative experiments are conducted on two publicly available PET/CT datasets to evaluate the performance of our proposed method whose results demonstrate that our MEFN significantly outperforms state-of-the-art methods with improvements of 2.15% and 3.23% in DSC scores on the AutoPET dataset and the Hecktor dataset, respectively. More importantly, our model can provide radiologists with credible uncertainty of the segmentation results for their decision in accepting or rejecting the automatic segmentation results, which is particularly important for clinical applications. Our code will be available at https://github.com/QPaws/MEFN.
Authors: Robert Baumgartner, Sicco Verwer
Abstract: Probabilistic deterministic finite automata (PDFA) are discrete event systems modeling conditional probabilities over languages: Given an already seen sequence of tokens they return the probability of tokens of interest to appear next. These types of models have gained interest in the domain of explainable machine learning, where they are used as surrogate models for neural networks trained as language models. In this work we present an algorithm to distill PDFA from neural networks. Our algorithm is a derivative of the L# algorithm and capable of learning PDFA from a new type of query, in which the algorithm infers conditional probabilities from the probability of the queried string to occur. We show its effectiveness on a recent public dataset by distilling PDFA from a set of trained neural networks.
Authors: Josep Lumbreras, Mikhail Terekhov, Marco Tomamichel
Abstract: We initiate the study of quantum state tomography with minimal regret. A learner has sequential oracle access to an unknown pure quantum state, and in each round selects a pure probe state. Regret is incurred if the unknown state is measured orthogonal to this probe, and the learner's goal is to minimise the expected cumulative regret over $T$ rounds. The challenge is to find a balance between the most informative measurements and measurements incurring minimal regret. We show that the cumulative regret scales as $\Theta(\operatorname{polylog} T)$ using a new tomography algorithm based on a median of means least squares estimator. This algorithm employs measurements biased towards the unknown state and produces online estimates that are optimal (up to logarithmic terms) in the number of observed samples.
Authors: Fredrik Nestaas, Edoardo Debenedetti, Florian Tram\`er
Abstract: Large Language Models (LLMs) are increasingly used in applications where the model selects from competing third-party content, such as in LLM-powered search engines or chatbot plugins. In this paper, we introduce Preference Manipulation Attacks, a new class of attacks that manipulate an LLM's selections to favor the attacker. We demonstrate that carefully crafted website content or plugin documentations can trick an LLM to promote the attacker products and discredit competitors, thereby increasing user traffic and monetization. We show this leads to a prisoner's dilemma, where all parties are incentivized to launch attacks, but the collective effect degrades the LLM's outputs for everyone. We demonstrate our attacks on production LLM search engines (Bing and Perplexity) and plugin APIs (for GPT-4 and Claude). As LLMs are increasingly used to rank third-party content, we expect Preference Manipulation Attacks to emerge as a significant threat.
Authors: Mohamed Sayed, Filippo Aleotti, Jamie Watson, Zawar Qureshi, Guillermo Garcia-Hernando, Gabriel Brostow, Sara Vicente, Michael Firman
Abstract: Estimating depth from a sequence of posed RGB images is a fundamental computer vision task, with applications in augmented reality, path planning etc. Prior work typically makes use of previous frames in a multi view stereo framework, relying on matching textures in a local neighborhood. In contrast, our model leverages historical predictions by giving the latest 3D geometry data as an extra input to our network. This self-generated geometric hint can encode information from areas of the scene not covered by the keyframes and it is more regularized when compared to individual predicted depth maps for previous frames. We introduce a Hint MLP which combines cost volume features with a hint of the prior geometry, rendered as a depth map from the current camera location, together with a measure of the confidence in the prior geometry. We demonstrate that our method, which can run at interactive speeds, achieves state-of-the-art estimates of depth and 3D scene reconstruction in both offline and incremental evaluation scenarios.
Authors: Aza\"is Jean-Marc, Dalmao Federico, De Castro Yohann
Abstract: In this article, we introduce the novel concept of the second maximum of a Gaussian random field on a Riemannian submanifold. This second maximum serves as a powerful tool for characterizing the distribution of the maximum. By utilizing an ad-hoc Kac Rice formula, we derive the explicit form of the maximum's distribution, conditioned on the second maximum and some regressed component of the Riemannian Hessian. This approach results in an exact test, based on the evaluation of spacing between these maxima, which we refer to as the spacing test. We investigate the applicability of this test in detecting sparse alternatives within Gaussian symmetric tensors, continuous sparse deconvolution, and two-layered neural networks with smooth rectifiers. Our theoretical results are supported by numerical experiments, which illustrate the calibration and power of the proposed tests. More generally, this test can be applied to any Gaussian random field on a Riemannian manifold, and we provide a general framework for the application of the spacing test in continuous sparse kernel regression. Furthermore, when the variance-covariance function of the Gaussian random field is known up to a scaling factor, we derive an exact Studentized version of our test, coined the $t$-spacing test. This test is perfectly calibrated under the null hypothesis and has high power for detecting sparse alternatives.
Authors: Yibo Jiang, Goutham Rajendran, Pradeep Ravikumar, Bryon Aragam
Abstract: Large Language Models (LLMs) have the capacity to store and recall facts. Through experimentation with open-source models, we observe that this ability to retrieve facts can be easily manipulated by changing contexts, even without altering their factual meanings. These findings highlight that LLMs might behave like an associative memory model where certain tokens in the contexts serve as clues to retrieving facts. We mathematically explore this property by studying how transformers, the building blocks of LLMs, can complete such memory tasks. We study a simple latent concept association problem with a one-layer transformer and we show theoretically and empirically that the transformer gathers information using self-attention and uses the value matrix for associative memory.
Authors: Roula Nassif, Stefan Vlaski, Marco Carpentiero, Vincenzo Matta, Ali H. Sayed
Abstract: Communication-constrained algorithms for decentralized learning and optimization rely on local updates coupled with the exchange of compressed signals. In this context, differential quantization is an effective technique to mitigate the negative impact of compression by leveraging correlations between successive iterates. In addition, the use of error feedback, which consists of incorporating the compression error into subsequent steps, is a powerful mechanism to compensate for the bias caused by the compression. Under error feedback, performance guarantees in the literature have so far focused on algorithms employing a fusion center or a special class of contractive compressors that cannot be implemented with a finite number of bits. In this work, we propose a new decentralized communication-efficient learning approach that blends differential quantization with error feedback. The approach is specifically tailored for decentralized learning problems where agents have individual risk functions to minimize subject to subspace constraints that require the minimizers across the network to lie in low-dimensional subspaces. This constrained formulation includes consensus or single-task optimization as special cases, and allows for more general task relatedness models such as multitask smoothness and coupled optimization. We show that, under some general conditions on the compression noise, and for sufficiently small step-sizes $\mu$, the resulting communication-efficient strategy is stable both in terms of mean-square error and average bit rate: by reducing $\mu$, it is possible to keep the estimation errors small (on the order of $\mu$) without increasing indefinitely the bit rate as $\mu\rightarrow 0$. The results establish that, in the small step-size regime and with a finite number of bits, it is possible to attain the performance achievable in the absence of compression.
Authors: Alexandros Kontogiannis, Scott V. Elgersma, Andrew J. Sederman, Matthew P. Juniper
Abstract: We formulate and solve a Bayesian inverse Navier-Stokes (N-S) problem that assimilates velocimetry data in order to jointly reconstruct a 3D flow field and learn the unknown N-S parameters, including the boundary position. By hardwiring a generalised N-S problem, and regularising its unknown parameters using Gaussian prior distributions, we learn the most likely parameters in a collapsed search space. The most likely flow field reconstruction is then the N-S solution that corresponds to the learned parameters. We develop the method in the variational setting and use a stabilised Nitsche weak form of the N-S problem that permits the control of all N-S parameters. To regularise the inferred the geometry, we use a viscous signed distance field (vSDF) as an auxiliary variable, which is given as the solution of a viscous Eikonal boundary value problem. We devise an algorithm that solves this inverse problem, and numerically implement it using an adjoint-consistent stabilised cut-cell finite element method. We then use this method to reconstruct magnetic resonance velocimetry (flow-MRI) data of a 3D steady laminar flow through a physical model of an aortic arch for two different Reynolds numbers and signal-to-noise ratio (SNR) levels (low/high). We find that the method can accurately i) reconstruct the low SNR data by filtering out the noise/artefacts and recovering flow features that are obscured by noise, and ii) reproduce the high SNR data without overfitting. Although the framework that we develop applies to 3D steady laminar flows in complex geometries, it readily extends to time-dependent laminar and Reynolds-averaged turbulent flows, as well as non-Newtonian (e.g. viscoelastic) fluids.
Authors: Yang Liu, Yitong Wang, Chenyue Feng
Abstract: Representation learning in sequential recommendation is critical for accurately modeling user interaction patterns and improving recommendation precision. However, existing approaches predominantly emphasize item-to-item transitions, often neglecting the time intervals between interactions, which are closely related to behavior pattern changes. Additionally, broader interaction attributes, such as item frequency, are frequently overlooked. We found that both sequences with more uniform time intervals and items with higher frequency yield better prediction performance. Conversely, non-uniform sequences exacerbate user interest drift and less-frequent items are difficult to model due to sparse sampling, presenting unique challenges inadequately addressed by current methods. In this paper, we propose UniRec, a novel bidirectional enhancement sequential recommendation method. UniRec leverages sequence uniformity and item frequency to enhance performance, particularly improving the representation of non-uniform sequences and less-frequent items. These two branches mutually reinforce each other, driving comprehensive performance optimization in complex sequential recommendation scenarios. Additionally, we present a multidimensional time module to further enhance adaptability. To the best of our knowledge, UniRec is the first method to utilize the characteristics of uniformity and frequency for feature augmentation. Comparing with eleven advanced models across four datasets, we demonstrate that UniRec outperforms SOTA models significantly. The code is available at https://github.com/Linxi000/UniRec.
Authors: Zuxin Liu, Thai Hoang, Jianguo Zhang, Ming Zhu, Tian Lan, Shirley Kokane, Juntao Tan, Weiran Yao, Zhiwei Liu, Yihao Feng, Rithesh Murthy, Liangwei Yang, Silvio Savarese, Juan Carlos Niebles, Huan Wang, Shelby Heinecke, Caiming Xiong
Abstract: The advancement of function-calling agent models requires diverse, reliable, and high-quality datasets. This paper presents APIGen, an automated data generation pipeline designed to synthesize verifiable high-quality datasets for function-calling applications. We leverage APIGen and collect 3,673 executable APIs across 21 different categories to generate diverse function-calling datasets in a scalable and structured manner. Each data in our dataset is verified through three hierarchical stages: format checking, actual function executions, and semantic verification, ensuring its reliability and correctness. We demonstrate that models trained with our curated datasets, even with only 7B parameters, can achieve state-of-the-art performance on the Berkeley Function-Calling Benchmark, outperforming multiple GPT-4 models. Moreover, our 1B model achieves exceptional performance, surpassing GPT-3.5-Turbo and Claude-3 Haiku. We release a dataset containing 60,000 high-quality entries, aiming to advance the field of function-calling agent domains. The dataset is available on Huggingface: https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k and the project homepage: https://apigen-pipeline.github.io/
URLs: https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k, https://apigen-pipeline.github.io/
Authors: Wangchunshu Zhou, Yixin Ou, Shengwei Ding, Long Li, Jialong Wu, Tiannan Wang, Jiamin Chen, Shuai Wang, Xiaohua Xu, Ningyu Zhang, Huajun Chen, Yuchen Eleanor Jiang
Abstract: The AI community has been exploring a pathway to artificial general intelligence (AGI) by developing "language agents", which are complex large language models (LLMs) pipelines involving both prompting techniques and tool usage methods. While language agents have demonstrated impressive capabilities for many real-world tasks, a fundamental limitation of current language agents research is that they are model-centric, or engineering-centric. That's to say, the progress on prompts, tools, and pipelines of language agents requires substantial manual engineering efforts from human experts rather than automatically learning from data. We believe the transition from model-centric, or engineering-centric, to data-centric, i.e., the ability of language agents to autonomously learn and evolve in environments, is the key for them to possibly achieve AGI. In this work, we introduce agent symbolic learning, a systematic framework that enables language agents to optimize themselves on their own in a data-centric way using symbolic optimizers. Specifically, we consider agents as symbolic networks where learnable weights are defined by prompts, tools, and the way they are stacked together. Agent symbolic learning is designed to optimize the symbolic network within language agents by mimicking two fundamental algorithms in connectionist learning: back-propagation and gradient descent. Instead of dealing with numeric weights, agent symbolic learning works with natural language simulacrums of weights, loss, and gradients. We conduct proof-of-concept experiments on both standard benchmarks and complex real-world tasks and show that agent symbolic learning enables language agents to update themselves after being created and deployed in the wild, resulting in "self-evolving agents".
Authors: Adam Stein, Aaditya Naik, Yinjun Wu, Mayur Naik, Eric Wong
Abstract: Concept-based interpretability methods offer a lens into the internals of foundation models by decomposing their embeddings into high-level concepts. These concept representations are most useful when they are compositional, meaning that the individual concepts compose to explain the full sample. We show that existing unsupervised concept extraction methods find concepts which are not compositional. To automatically discover compositional concept representations, we identify two salient properties of such representations, and propose Compositional Concept Extraction (CCE) for finding concepts which obey these properties. We evaluate CCE on five different datasets over image and text data. Our evaluation shows that CCE finds more compositional concept representations than baselines and yields better accuracy on four downstream classification tasks. Code and data are available at https://github.com/adaminsky/compositional_concepts .
Authors: Shachi Deshpande, Charles Marx, Volodymyr Kuleshov
Abstract: Accurate uncertainty estimates are important in sequential model-based decision-making tasks such as Bayesian optimization. However, these estimates can be imperfect if the data violates assumptions made by the model (e.g., Gaussianity). This paper studies which uncertainties are needed in model-based decision-making and in Bayesian optimization, and argues that uncertainties can benefit from calibration -- i.e., an 80% predictive interval should contain the true outcome 80% of the time. Maintaining calibration, however, can be challenging when the data is non-stationary and depends on our actions. We propose using simple algorithms based on online learning to provably maintain calibration on non-i.i.d. data, and we show how to integrate these algorithms in Bayesian optimization with minimal overhead. Empirically, we find that calibrated Bayesian optimization converges to better optima in fewer steps, and we demonstrate improved performance on standard benchmark functions and hyperparameter optimization tasks.
Authors: Jingwei Guo, Kaizhu Huang, Rui Zhang, Xinping Yi
Abstract: While Graph Neural Networks (GNNs) have achieved enormous success in multiple graph analytical tasks, modern variants mostly rely on the strong inductive bias of homophily. However, real-world networks typically exhibit both homophilic and heterophilic linking patterns, wherein adjacent nodes may share dissimilar attributes and distinct labels. Therefore, GNNs smoothing node proximity holistically may aggregate both task-relevant and irrelevant (even harmful) information, limiting their ability to generalize to heterophilic graphs and potentially causing non-robustness. In this work, we propose a novel Edge Splitting GNN (ES-GNN) framework to adaptively distinguish between graph edges either relevant or irrelevant to learning tasks. This essentially transfers the original graph into two subgraphs with the same node set but complementary edge sets dynamically. Given that, information propagation separately on these subgraphs and edge splitting are alternatively conducted, thus disentangling the task-relevant and irrelevant features. Theoretically, we show that our ES-GNN can be regarded as a solution to a disentangled graph denoising problem, which further illustrates our motivations and interprets the improved generalization beyond homophily. Extensive experiments over 11 benchmark and 1 synthetic datasets not only demonstrate the effective performance of ES-GNN but also highlight its robustness to adversarial graphs and mitigation of the over-smoothing problem.
Authors: Fan-Ming Luo, Xingchen Cao, Rong-Jun Qin, Yang Yu
Abstract: Recovering reward function from expert demonstrations is a fundamental problem in reinforcement learning. The recovered reward function captures the motivation of the expert. Agents can imitate experts by following these reward functions in their environment, which is known as apprentice learning. However, the agents may face environments different from the demonstrations, and therefore, desire transferable reward functions. Classical reward learning methods such as inverse reinforcement learning (IRL) or, equivalently, adversarial imitation learning (AIL), recover reward functions coupled with training dynamics, which are hard to be transferable. Previous dynamics-agnostic reward learning methods rely on assumptions such as that the reward function has to be state-only, restricting their applicability. In this work, we present a dynamics-agnostic discriminator-ensemble reward learning method (DARL) within the AIL framework, capable of learning both state-action and state-only reward functions. DARL achieves this by decoupling the reward function from training dynamics, employing a dynamics-agnostic discriminator on a latent space derived from the original state-action space. This latent space is optimized to minimize information on the dynamics. We moreover discover the policy-dependency issue of the AIL framework that reduces the transferability. DARL represents the reward function as an ensemble of discriminators during training to eliminate policy dependencies. Empirical studies on MuJoCo tasks with changed dynamics show that DARL better recovers the reward function and results in better imitation performance in transferred environments, handling both state-only and state-action reward scenarios.
Authors: Kenneth Li, Aspen K. Hopkins, David Bau, Fernanda Vi\'egas, Hanspeter Pfister, Martin Wattenberg
Abstract: Language models show a surprising range of capabilities, but the source of their apparent competence is unclear. Do these networks just memorize a collection of surface statistics, or do they rely on internal representations of the process that generates the sequences they see? We investigate this question by applying a variant of the GPT model to the task of predicting legal moves in a simple board game, Othello. Although the network has no a priori knowledge of the game or its rules, we uncover evidence of an emergent nonlinear internal representation of the board state. Interventional experiments indicate this representation can be used to control the output of the network and create "latent saliency maps" that can help explain predictions in human terms.
Authors: Xiulin Wang, Jing Liu, Fengyu Cong
Abstract: Tensor decomposition is a fundamental technique widely applied in signal processing, machine learning, and various other fields. However, traditional tensor decomposition methods encounter limitations when jointly analyzing multi-block tensors, as they often struggle to effectively explore shared information among tensors. In this study, we first introduce a novel coupled nonnegative CANDECOMP/PARAFAC decomposition algorithm optimized by the alternating proximal gradient method (CoNCPD-APG). This algorithm is specially designed to address the challenges of jointly decomposing different tensors that are partially or fully linked, while simultaneously extracting common components, individual components and, core tensors. Recognizing the computational challenges inherent in optimizing nonnegative constraints over high-dimensional tensor data, we further propose the lraCoNCPD-APG algorithm. By integrating low-rank approximation with the proposed CoNCPD-APG method, the proposed algorithm can significantly decrease the computational burden without compromising decomposition quality, particularly for multi-block large-scale tensors. Simulation experiments conducted on synthetic data, real-world face image data, and two kinds of electroencephalography (EEG) data demonstrate the practicality and superiority of the proposed algorithms for coupled nonnegative tensor decomposition problems. Our results underscore the efficacy of our methods in uncovering meaningful patterns and structures from complex multi-block tensor data, thereby offering valuable insights for future applications.
Authors: Philipp Becker, Sebastian Mossburger, Fabian Otto, Gerhard Neumann
Abstract: Learning self-supervised representations using reconstruction or contrastive losses improves performance and sample complexity of image-based and multimodal reinforcement learning (RL). Here, different self-supervised loss functions have distinct advantages and limitations depending on the information density of the underlying sensor modality. Reconstruction provides strong learning signals but is susceptible to distractions and spurious information. While contrastive approaches can ignore those, they may fail to capture all relevant details and can lead to representation collapse. For multimodal RL, this suggests that different modalities should be treated differently based on the amount of distractions in the signal. We propose Contrastive Reconstructive Aggregated representation Learning (CoRAL), a unified framework enabling us to choose the most appropriate self-supervised loss for each sensor modality and allowing the representation to better focus on relevant aspects. We evaluate CoRAL's benefits on a wide range of tasks with images containing distractions or occlusions, a new locomotion suite, and a challenging manipulation suite with visually realistic distractions. Our results show that learning a multimodal representation by combining contrastive and reconstruction-based losses can significantly improve performance and solve tasks that are out of reach for more naive representation learning approaches and other recent baselines.
Authors: Ryota Kawasumi, Tsuyoshi Yoneda
Abstract: In this paper, we clarify the crucial difference between a deep neural network and the Fourier series. For the multiple Fourier series of periodization of some radial functions on $\mathbb{R}^d$, Kuratsubo (2010) investigated the behavior of the spherical partial sum and discovered the third phenomenon other than the well-known Gibbs-Wilbraham and Pinsky phenomena. In particular, the third one exhibits prevention of pointwise convergence. In contrast to it, we give a specific deep neural network and prove pointwise convergence.
Authors: Suzanna Parkinson, Greg Ongie, Rebecca Willett
Abstract: Neural networks often operate in the overparameterized regime, in which there are far more parameters than training samples, allowing the training data to be fit perfectly. That is, training the network effectively learns an interpolating function, and properties of the interpolant affect predictions the network will make on new samples. This manuscript explores how properties of such functions learned by neural networks of depth greater than two layers. Our framework considers a family of networks of varying depths that all have the same capacity but different representation costs. The representation cost of a function induced by a neural network architecture is the minimum sum of squared weights needed for the network to represent the function; it reflects the function space bias associated with the architecture. Our results show that adding additional linear layers to the input side of a shallow ReLU network yields a representation cost favoring functions with low mixed variation - that is, it has limited variation in directions orthogonal to a low-dimensional subspace and can be well approximated by a single- or multi-index model. Such functions may be represented by the composition of a function with low two-layer representation cost and a low-rank linear operator. Our experiments confirm this behavior in standard network training regimes. They additionally show that linear layers can improve generalization and the learned network is well-aligned with the true latent low-dimensional linear subspace when data is generated using a multi-index model.
Authors: Hanna Mazzawi, Xavi Gonzalvo, Michael Wunder, Sammy Jerome, Benoit Dherin
Abstract: In recent years, deep learning has made remarkable progress in a wide range of domains, with a particularly notable impact on natural language processing tasks. One of the challenges associated with training deep neural networks in the context of LLMs is the need for large amounts of computational resources and time. To mitigate this, network growing algorithms offer potential cost savings, but their underlying mechanisms are poorly understood. We present two notable contributions in this paper. First, we present Deep Fusion, an efficient approach to network training that leverages pre-trained initializations of smaller networks. Second, we propose a theoretical framework using backward error analysis to illustrate the dynamics of mid-training network growth. Our experiments show how Deep Fusion is a practical and effective approach that not only accelerates the training process but also reduces computational requirements, maintaining or surpassing traditional training methods' performance in various NLP tasks and T5 model sizes. Finally, we validate our theoretical framework, which guides the optimal use of Deep Fusion, showing that with carefully optimized training dynamics, it significantly reduces both training time and resource consumption.
Authors: Lingda Li, Thomas Flynn, Adolfy Hoisie
Abstract: Performance modeling is an essential tool in many areas, including performance characterization/optimization, design space exploration, and resource allocation problems, to name a few. However, existing performance modeling approaches have limitations, such as high computational cost for discrete-event simulators, narrow flexibility of hardware emulators, or restricted accuracy/generality of analytical/data-driven models. To address these limitations, this paper proposes PerfVec, a novel deep learning-based performance modeling framework that learns high-dimensional and independent/orthogonal program and microarchitecture representations. Once learned, a program representation can be used to predict its performance on any microarchitecture, and likewise, a microarchitecture representation can be applied in the performance prediction of any program. Additionally, PerfVec yields a foundation model that captures the performance essence of instructions, which can be directly used by developers in numerous performance modeling related tasks without incurring its training cost. The evaluation demonstrates that PerfVec is more general and efficient than previous approaches.
Authors: Juncai He, Xinliang Liu, Jinchao Xu
Abstract: In this work, we propose a concise neural operator architecture for operator learning. Drawing an analogy with a conventional fully connected neural network, we define the neural operator as follows: the output of the $i$-th neuron in a nonlinear operator layer is defined by $O_i(u) = \sigma\left( \sum_j W_{ij} u + B_{ij}\right)$. Here, $ W_{ij}$ denotes the bounded linear operator connecting $j$-th input neuron to $i$-th output neuron, and the bias $ B_{ij}$ takes the form of a function rather than a scalar. Given its new universal approximation property, the efficient parameterization of the bounded linear operators between two neurons (Banach spaces) plays a critical role. As a result, we introduce MgNO, utilizing multigrid structures to parameterize these linear operators between neurons. This approach offers both mathematical rigor and practical expressivity. Additionally, MgNO obviates the need for conventional lifting and projecting operators typically required in previous neural operators. Moreover, it seamlessly accommodates diverse boundary conditions. Our empirical observations reveal that MgNO exhibits superior ease of training compared to other CNN-based models, while also displaying a reduced susceptibility to overfitting when contrasted with spectral-type neural operators. We demonstrate the efficiency and accuracy of our method with consistently state-of-the-art performance on different types of partial differential equations (PDEs).
Authors: Alberto Altozano, Maria Eleonora Minissi, Mariano Alca\~niz, Javier Mar\'in-Morales
Abstract: Autism Spectrum Disorder (ASD) is characterized by challenges in social communication and restricted patterns, with motor abnormalities gaining traction for early detection. However, kinematic analysis in ASD is limited, often lacking robust validation and relying on hand-crafted features for single tasks, leading to inconsistencies across studies. End-to-end models have emerged as promising methods to overcome the need for feature engineering. Our aim is to propose a newly adapted 3DCNN ResNet from and compare it to widely used hand-crafted features for motor ASD assessment. Specifically, we developed a virtual reality environment with multiple motor tasks and trained models using both approaches. We prioritized a reliable validation framework with repeated cross-validation. Results show the proposed model achieves a maximum accuracy of 85$\pm$3%, outperforming state-of-the-art end-to-end models with short 1-to-3 minute samples. Our comparative analysis with hand-crafted features shows feature-engineered models outperformed our end-to-end model in certain tasks. However, our end-to-end model achieved a higher mean AUC of 0.80$\pm$0.03. Additionally, statistical differences were found in model variance, with our end-to-end model providing more consistent results with less variability across all VR tasks, demonstrating domain generalization and reliability. These findings show that end-to-end models enable less variable and context-independent ASD classification without requiring domain knowledge or task specificity. However, they also recognize the effectiveness of hand-crafted features in specific task scenarios.
Authors: Jan Mielniczuk, Adam Wawrze\'nczyk
Abstract: In the paper we argue that performance of the classifiers based on Empirical Risk Minimization (ERM) for positive unlabeled data, which are designed for case-control sampling scheme may significantly deteriorate when applied to a single-sample scenario. We reveal why their behavior depends, in all but very specific cases, on the scenario. Also, we introduce a single-sample case analogue of the popular non-negative risk classifier designed for case-control data and compare its performance with the original proposal. We show that the significant differences occur between them, especiall when half or more positive of observations are labeled. The opposite case when ERM minimizer designed for the case-control case is applied for single-sample data is also considered and similar conclusions are drawn. Taking into account difference of scenarios requires a sole, but crucial, change in the definition of the Empirical Risk.
Authors: Lirui Zhao, Yuxin Zhang, Fei Chao, Rongrong Ji
Abstract: The poor cross-architecture generalization of dataset distillation greatly weakens its practical significance. This paper attempts to mitigate this issue through an empirical study, which suggests that the synthetic datasets undergo an inductive bias towards the distillation model. Therefore, the evaluation model is strictly confined to having similar architectures of the distillation model. We propose a novel method of EvaLuation with distillation Feature (ELF), which utilizes features from intermediate layers of the distillation model for the cross-architecture evaluation. In this manner, the evaluation model learns from bias-free knowledge therefore its architecture becomes unfettered while retaining performance. By performing extensive experiments, we successfully prove that ELF can well enhance the cross-architecture generalization of current DD methods. Code of this project is at \url{https://github.com/Lirui-Zhao/ELF}.
Authors: Chanon Puttanawarut, Panu Looareesuwan, Romen Samuel Wabina, Prut Saowaprut
Abstract: Survival analysis is a widely known method for predicting the likelihood of an event over time. The challenge of dealing with censored samples still remains. Traditional methods, such as the Cox Proportional Hazards (CPH) model, hinge on the limitations due to the strong assumptions of proportional hazards and the predetermined relationships between covariates. The rise of models based on deep neural networks (DNNs) has demonstrated enhanced effectiveness in survival analysis. This research introduces the Implicit Continuous-Time Survival Function (ICTSurF), built on a continuous-time survival model, and constructs survival distribution through implicit representation. As a result, our method is capable of accepting inputs in continuous-time space and producing survival probabilities in continuous-time space, independent of neural network architecture. Comparative assessments with existing methods underscore the high competitiveness of our proposed approach. Our implementation of ICTSurF is available at https://github.com/44REAM/ICTSurF.
Authors: Kichang Lee, Songkuk Kim, JeongGil Ko
Abstract: Federated learning is inherently hampered by data heterogeneity: non-i.i.d. training data over local clients. We propose a novel model training approach for federated learning, FLex&Chill, which exploits the Logit Chilling method. Through extensive evaluations, we demonstrate that, in the presence of non-i.i.d. data characteristics inherent in federated learning systems, this approach can expedite model convergence and improve inference accuracy. Quantitatively, from our experiments, we observe up to 6X improvement in the global federated learning model convergence time, and up to 3.37% improvement in inference accuracy.
Authors: Yin Li, Yu Xiong, Wenxin Fan, Kai Wang, Qingqing Yu, Liping Si, Patrick van der Smagt, Jun Tang, Nutan Chen
Abstract: Objective: Subcutaneous Immunotherapy (SCIT) is the long-lasting causal treatment of allergic rhinitis (AR). How to enhance the adherence of patients to maximize the benefit of allergen immunotherapy (AIT) plays a crucial role in the management of AIT. This study aims to leverage novel machine learning models to precisely predict the risk of non-adherence of AR patients and related local symptom scores in three years SCIT. Methods: The research develops and analyzes two models, sequential latent-variable model (SLVM) of Sequential Latent Actor-Critic (SLAC) and Long Short-Term Memory (LSTM) evaluating them based on scoring and adherence prediction capabilities. Results: Excluding the biased samples at the first time step, the predictive adherence accuracy of the SLAC models is from 60\% to 72\%, and for LSTM models, it is 66\% to 84\%, varying according to the time steps. The range of Root Mean Square Error (RMSE) for SLAC models is between 0.93 and 2.22, while for LSTM models it is between 1.09 and 1.77. Notably, these RMSEs are significantly lower than the random prediction error of 4.55. Conclusion: We creatively apply sequential models in the long-term management of SCIT with promising accuracy in the prediction of SCIT nonadherence in AR patients. While LSTM outperforms SLAC in adherence prediction, SLAC excels in score prediction for patients undergoing SCIT for AR. The state-action-based SLAC adds flexibility, presenting a novel and effective approach for managing long-term AIT.
Authors: Adane Nega Tarekegn, Mohib Ullah, Faouzi Alaya Cheikh
Abstract: Multi-label learning is a rapidly growing research area that aims to predict multiple labels from a single input data point. In the era of big data, tasks involving multi-label classification (MLC) or ranking present significant and intricate challenges, capturing considerable attention in diverse domains. Inherent difficulties in MLC include dealing with high-dimensional data, addressing label correlations, and handling partial labels, for which conventional methods prove ineffective. Recent years have witnessed a notable increase in adopting deep learning (DL) techniques to address these challenges more effectively in MLC. Notably, there is a burgeoning effort to harness the robust learning capabilities of DL for improved modelling of label dependencies and other challenges in MLC. However, it is noteworthy that comprehensive studies specifically dedicated to DL for multi-label learning are limited. Thus, this survey aims to thoroughly review recent progress in DL for multi-label learning, along with a summary of open research problems in MLC. The review consolidates existing research efforts in DL for MLC,including deep neural networks, transformers, autoencoders, and convolutional and recurrent architectures. Finally, the study presents a comparative analysis of the existing methods to provide insightful observations and stimulate future research directions in this domain.
Authors: Carl Hvarfner, Erik Orm Hellsten, Luigi Nardi
Abstract: High-dimensional problems have long been considered the Achilles' heel of Bayesian optimization algorithms. Spurred by the curse of dimensionality, a large collection of algorithms aim to make it more performant in this setting, commonly by imposing various simplifying assumptions on the objective. In this paper, we identify the degeneracies that make vanilla Bayesian optimization poorly suited to high-dimensional tasks, and further show how existing algorithms address these degeneracies through the lens of lowering the model complexity. Moreover, we propose an enhancement to the prior assumptions that are typical to vanilla Bayesian optimization algorithms, which reduces the complexity to manageable levels without imposing structural restrictions on the objective. Our modification - a simple scaling of the Gaussian process lengthscale prior with the dimensionality - reveals that standard Bayesian optimization works drastically better than previously thought in high dimensions, clearly outperforming existing state-of-the-art algorithms on multiple commonly considered real-world high-dimensional tasks.
Authors: Snir Hordan, Tal Amir, Nadav Dym
Abstract: The $k$-Weisfeiler-Leman ($k$-WL) graph isomorphism test hierarchy is a common method for assessing the expressive power of graph neural networks (GNNs). Recently, GNNs whose expressive power is equivalent to the $2$-WL test were proven to be universal on weighted graphs which encode $3\mathrm{D}$ point cloud data, yet this result is limited to invariant continuous functions on point clouds. In this paper, we extend this result in three ways: Firstly, we show that PPGN can simulate $2$-WL uniformly on all point clouds with low complexity. Secondly, we show that $2$-WL tests can be extended to point clouds which include both positions and velocities, a scenario often encountered in applications. Finally, we provide a general framework for proving equivariant universality and leverage it to prove that a simple modification of this invariant PPGN architecture can be used to obtain a universal equivariant architecture that can approximate all continuous equivariant functions uniformly. Building on our results, we develop our WeLNet architecture, which sets new state-of-the-art results on the N-Body dynamics task and the GEOM-QM9 molecular conformation generation task.
Authors: Oubo Ma, Yuwen Pu, Linkang Du, Yang Dai, Ruo Wang, Xiaolei Liu, Yingcai Wu, Shouling Ji
Abstract: Recent advancements in multi-agent reinforcement learning (MARL) have opened up vast application prospects, such as swarm control of drones, collaborative manipulation by robotic arms, and multi-target encirclement. However, potential security threats during the MARL deployment need more attention and thorough investigation. Recent research reveals that attackers can rapidly exploit the victim's vulnerabilities, generating adversarial policies that result in the failure of specific tasks. For instance, reducing the winning rate of a superhuman-level Go AI to around 20%. Existing studies predominantly focus on two-player competitive environments, assuming attackers possess complete global state observation. In this study, we unveil, for the first time, the capability of attackers to generate adversarial policies even when restricted to partial observations of the victims in multi-agent competitive environments. Specifically, we propose a novel black-box attack (SUB-PLAY) that incorporates the concept of constructing multiple subgames to mitigate the impact of partial observability and suggests sharing transitions among subpolicies to improve attackers' exploitative ability. Extensive evaluations demonstrate the effectiveness of SUB-PLAY under three typical partial observability limitations. Visualization results indicate that adversarial policies induce significantly different activations of the victims' policy networks. Furthermore, we evaluate three potential defenses aimed at exploring ways to mitigate security threats posed by adversarial policies, providing constructive recommendations for deploying MARL in competitive environments.
Authors: Andrea Bonfanti, Giuseppe Bruno, Cristina Cipriani
Abstract: The Neural Tangent Kernel (NTK) viewpoint is widely employed to analyze the training dynamics of overparameterized Physics-Informed Neural Networks (PINNs). However, unlike the case of linear Partial Differential Equations (PDEs), we show how the NTK perspective falls short in the nonlinear scenario. Specifically, we establish that the NTK yields a random matrix at initialization that is not constant during training, contrary to conventional belief. Another significant difference from the linear regime is that, even in the idealistic infinite-width limit, the Hessian does not vanish and hence it cannot be disregarded during training. This motivates the adoption of second-order optimization methods. We explore the convergence guarantees of such methods in both linear and nonlinear cases, addressing challenges such as spectral bias and slow convergence. Every theoretical result is supported by numerical examples with both linear and nonlinear PDEs, and we highlight the benefits of second-order methods in benchmark test cases.
Authors: Tara Akhound-Sadegh, Jarrid Rector-Brooks, Avishek Joey Bose, Sarthak Mittal, Pablo Lemos, Cheng-Hao Liu, Marcin Sendera, Siamak Ravanbakhsh, Gauthier Gidel, Yoshua Bengio, Nikolay Malkin, Alexander Tong
Abstract: Efficiently generating statistically independent samples from an unnormalized probability distribution, such as equilibrium samples of many-body systems, is a foundational problem in science. In this paper, we propose Iterated Denoising Energy Matching (iDEM), an iterative algorithm that uses a novel stochastic score matching objective leveraging solely the energy function and its gradient -- and no data samples -- to train a diffusion-based sampler. Specifically, iDEM alternates between (I) sampling regions of high model density from a diffusion-based sampler and (II) using these samples in our stochastic matching objective to further improve the sampler. iDEM is scalable to high dimensions as the inner matching objective, is simulation-free, and requires no MCMC samples. Moreover, by leveraging the fast mode mixing behavior of diffusion, iDEM smooths out the energy landscape enabling efficient exploration and learning of an amortized sampler. We evaluate iDEM on a suite of tasks ranging from standard synthetic energy functions to invariant $n$-body particle systems. We show that the proposed approach achieves state-of-the-art performance on all metrics and trains $2-5\times$ faster, which allows it to be the first method to train using energy on the challenging $55$-particle Lennard-Jones system.
Authors: Zhen-Yu Zhang, Siwei Han, Huaxiu Yao, Gang Niu, Masashi Sugiyama
Abstract: To improve the ability of the large language model (LLMs) to tackle complex reasoning problems, chain-of-thoughts (CoT) methods were proposed to guide LLMs to reason step-by-step, enabling problem solving from simple to complex. State-of-the-art methods for generating such a chain involve interactive collaboration, where the learner generates candidate intermediate thoughts, evaluated by the LLM, guiding the generation of subsequent thoughts. However, a widespread yet understudied problem is that the evaluation from the LLM is typically noisy and unreliable, potentially misleading the generation process in selecting promising intermediate thoughts. In this paper, motivated by Vapnik's principle, we use pairwise-comparison evaluation instead of point-wise scoring to search for promising intermediate thoughts with the noisy feedback from the LLM. In each round, we randomly pair intermediate thoughts and directly prompt the LLM to select the more promising one from each pair, allowing us to identify the most promising thoughts through an iterative process. To further alleviate the noise in the comparison, we incorporate techniques from ensemble learning and dueling bandits, proposing two variants of the algorithm. Experiments on three real-world tasks demonstrate the effectiveness of our proposed algorithm and verify the rationale of the pairwise comparison mechanism.
Authors: Johan Obando-Ceron, Ghada Sokar, Timon Willi, Clare Lyle, Jesse Farebrother, Jakob Foerster, Gintare Karolina Dziugaite, Doina Precup, Pablo Samuel Castro
Abstract: The recent rapid progress in (self) supervised learning models is in large part predicted by empirical scaling laws: a model's performance scales proportionally to its size. Analogous scaling laws remain elusive for reinforcement learning domains, however, where increasing the parameter count of a model often hurts its final performance. In this paper, we demonstrate that incorporating Mixture-of-Expert (MoE) modules, and in particular Soft MoEs (Puigcerver et al., 2023), into value-based networks results in more parameter-scalable models, evidenced by substantial performance increases across a variety of training regimes and model sizes. This work thus provides strong empirical evidence towards developing scaling laws for reinforcement learning.
Authors: Nathan Stromberg, Rohan Ayyagari, Monica Welfert, Sanmi Koyejo, Richard Nock, Lalitha Sankar
Abstract: Existing methods for last layer retraining that aim to optimize worst-group accuracy (WGA) rely heavily on well-annotated groups in the training data. We show, both in theory and practice, that annotation-based data augmentations using either downsampling or upweighting for WGA are susceptible to domain annotation noise, and in high-noise regimes approach the WGA of a model trained with vanilla empirical risk minimization. We introduce Regularized Annotation of Domains (RAD) in order to train robust last layer classifiers without the need for explicit domain annotations. Our results show that RAD is competitive with other recently proposed domain annotation-free techniques. Most importantly, RAD outperforms state-of-the-art annotation-reliant methods even with only 5% noise in the training data for several publicly available datasets.
Authors: Theresa Stadler, Bogdan Kulynych, Michael C. Gastpar, Nicolas Papernot, Carmela Troncoso
Abstract: The promise of least-privilege learning -- to find feature representations that are useful for a learning task but prevent inference of any sensitive information unrelated to this task -- is highly appealing. However, so far this concept has only been stated informally. It thus remains an open question whether and how we can achieve this goal. In this work, we provide the first formalisation of the least-privilege principle for machine learning and characterise its feasibility. We prove that there is a fundamental trade-off between a representation's utility for a given task and its leakage beyond the intended task: it is not possible to learn representations that have high utility for the intended task but, at the same time prevent inference of any attribute other than the task label itself. This trade-off holds under realistic assumptions on the data distribution and regardless of the technique used to learn the feature mappings that produce these representations. We empirically validate this result for a wide range of learning techniques, model architectures, and datasets.
Authors: Aritra Mitra
Abstract: We study the finite-time convergence of TD learning with linear function approximation under Markovian sampling. Existing proofs for this setting either assume a projection step in the algorithm to simplify the analysis, or require a fairly intricate argument to ensure stability of the iterates. We ask: \textit{Is it possible to retain the simplicity of a projection-based analysis without actually performing a projection step in the algorithm?} Our main contribution is to show this is possible via a novel two-step argument. In the first step, we use induction to prove that under a standard choice of a constant step-size $\alpha$, the iterates generated by TD learning remain uniformly bounded in expectation. In the second step, we establish a recursion that mimics the steady-state dynamics of TD learning up to a bounded perturbation on the order of $O(\alpha^2)$ that captures the effect of Markovian sampling. Combining these pieces leads to an overall approach that considerably simplifies existing proofs. We conjecture that our inductive proof technique will find applications in the analyses of more complex stochastic approximation algorithms, and conclude by providing some examples of such applications.
Authors: Xiangxin Zhou, Liang Wang, Yichi Zhou
Abstract: Considering generating samples with high rewards, we focus on optimizing deep neural networks parameterized stochastic differential equations (SDEs), the advanced generative models with high expressiveness, with policy gradient, the leading algorithm in reinforcement learning. Nevertheless, when applying policy gradients to SDEs, since the policy gradient is estimated on a finite set of trajectories, it can be ill-defined, and the policy behavior in data-scarce regions may be uncontrolled. This challenge compromises the stability of policy gradients and negatively impacts sample complexity. To address these issues, we propose constraining the SDE to be consistent with its associated perturbation process. Since the perturbation process covers the entire space and is easy to sample, we can mitigate the aforementioned problems. Our framework offers a general approach allowing for a versatile selection of policy gradient methods to effectively and efficiently train SDEs. We evaluate our algorithm on the task of structure-based drug design and optimize the binding affinity of generated ligand molecules. Our method achieves the best Vina score -9.07 on the CrossDocked2020 dataset.
Authors: Armin Karamzade, Kyungmin Kim, Montek Kalsi, Roy Fox
Abstract: In standard reinforcement learning settings, agents typically assume immediate feedback about the effects of their actions after taking them. However, in practice, this assumption may not hold true due to physical constraints and can significantly impact the performance of learning algorithms. In this paper, we address observation delays in partially observable environments. We propose leveraging world models, which have shown success in integrating past observations and learning dynamics, to handle observation delays. By reducing delayed POMDPs to delayed MDPs with world models, our methods can effectively handle partial observability, where existing approaches achieve sub-optimal performance or degrade quickly as observability decreases. Experiments suggest that one of our methods can outperform a naive model-based approach by up to 250%. Moreover, we evaluate our methods on visual delayed environments, for the first time showcasing delay-aware reinforcement learning continuous control with visual observations.
Authors: Lucas Lingle
Abstract: Large artificial neural networks have become a mainstay of language, vision, and audio processing and synthesis, yet their initializations and learning rates are often set in an unsophisticated fashion, due to the high cost of hyperparameter sweeps at scale. The $\mu$-Parameterization ($\mu$P) offers a potential solution to this challenge, yielding scaling rules for model initialization and learning rates while reportedly enabling zero-shot hyperparameter transfer from small to large models. Despite its evident promise, the $\mu$P method is not yet widely adopted, perhaps due to higher implementation complexity, many variations, or complex theoretical background. This work investigates $\mu$P empirically, focusing on the ubiquitous transformer architecture, and aims to answer a simple question: does $\mu$-Transfer yield optimal learning rates in practice? Studying models of up to 10B parameters and training budgets of up to 190B tokens, we find $\mu$-Transfer works as intended for the majority of important cases, yet also identify a few cases where it may not.
Authors: Haifeng Qian, Sujan Kumar Gonugondla, Sungsoo Ha, Mingyue Shang, Sanjay Krishna Gouda, Ramesh Nallapati, Sudipta Sengupta, Xiaofei Ma, Anoop Deoras
Abstract: Speculative decoding has emerged as a powerful method to improve latency and throughput in hosting large language models. However, most existing implementations focus on generating a single sequence. Real-world generative AI applications often require multiple responses and how to perform speculative decoding in a batched setting while preserving its latency benefits poses non-trivial challenges. This paper describes a system of batched speculative decoding that sets a new state of the art in multi-sequence generation latency and that demonstrates superior GPU utilization as well as quality of generations within a time budget. For example, for a 7.8B-size model on a single A100 GPU and with a batch size of 8, each sequence is generated at an average speed of 5.8ms per token, the overall throughput being 1.1K tokens per second. These results represent state-of-the-art latency and a 2.15X speed-up over optimized regular decoding. Within a time budget that regular decoding does not finish, our system is able to generate sequences with HumanEval Pass@First of 43% and Pass@All of 61%, far exceeding what's feasible with single-sequence speculative decoding. Our peak GPU utilization during decoding reaches as high as 15.8%, more than 3X the highest of that of regular decoding and around 10X of single-sequence speculative decoding.
Authors: Alvaro H. C. Correia, Fabio Valerio Massoli, Christos Louizos, Arash Behboodi
Abstract: Conformal Prediction (CP) is a distribution-free uncertainty estimation framework that constructs prediction sets guaranteed to contain the true answer with a user-specified probability. Intuitively, the size of the prediction set encodes a general notion of uncertainty, with larger sets associated with higher degrees of uncertainty. In this work, we leverage information theory to connect conformal prediction to other notions of uncertainty. More precisely, we prove three different ways to upper bound the intrinsic uncertainty, as described by the conditional entropy of the target variable given the inputs, by combining CP with information theoretical inequalities. Moreover, we demonstrate two direct and useful applications of such connection between conformal prediction and information theory: (i) more principled and effective conformal training objectives that generalize previous approaches and enable end-to-end training of machine learning models from scratch, and (ii) a natural mechanism to incorporate side information into conformal prediction. We empirically validate both applications in centralized and federated learning settings, showing our theoretical results translate to lower inefficiency (average prediction set size) for popular CP methods.
Authors: Yilun Liu, Ruihong Qiu, Zi Huang
Abstract: Large-scale graphs are valuable for graph representation learning, yet the abundant data in these graphs hinders the efficiency of the training process. Graph condensation (GC) alleviates this issue by compressing the large graph into a significantly smaller one that still supports effective model training. Although recent research has introduced various approaches to improve the effectiveness of the condensed graph, comprehensive and practical evaluations across different GC methods are neglected. This paper proposes the first large-scale graph condensation benchmark, GCondenser, to holistically evaluate and compare mainstream GC methods. GCondenser includes a standardised GC paradigm, consisting of condensation, validation, and evaluation procedures, as well as enabling extensions to new GC methods and datasets. With GCondenser, a comprehensive performance study is conducted, presenting the effectiveness of existing methods. GCondenser is open-sourced and available at https://github.com/superallen13/GCondenser.
Authors: Leif Bergerhoff
Abstract: We propose an efficient offline pointing calibration method for operational antenna systems which does not require any downtime. Our approach minimizes the calibration effort and exploits technical signal information which is typically used for monitoring and control purposes in ground station operations. Using a standard antenna interface and data from an operational satellite contact, we come up with a robust strategy for training data set generation. On top of this, we learn the parameters of a suitable coordinate transform by means of linear regression. In our experiments, we show the usefulness of the method in a real-world setup.
Authors: Jikun Kang, Xin Zhe Li, Xi Chen, Amirreza Kazemi, Qianyi Sun, Boxing Chen, Dong Li, Xu He, Quan He, Feng Wen, Jianye Hao, Jun Yao
Abstract: Although Large Language Models (LLMs) achieve remarkable performance across various tasks, they often struggle with complex reasoning tasks, such as answering mathematical questions. Recent efforts to address this issue have primarily focused on leveraging mathematical datasets through supervised fine-tuning or self-improvement techniques. However, these methods often depend on high-quality datasets that are difficult to prepare, or they require substantial computational resources for fine-tuning. Inspired by findings that LLMs know how to produce the right answer but struggle to select the correct reasoning path, we propose a purely inference-based searching method -- MindStar (M*). This method formulates reasoning tasks as searching problems and proposes two search ideas to identify the optimal reasoning paths. We evaluate the M* framework on both the GSM8K and MATH datasets, comparing its performance with existing open and closed-source LLMs. Our results demonstrate that M* significantly enhances the reasoning abilities of open-source models, such as Llama-2-13B and Mistral-7B, and achieves comparable performance to GPT-3.5 and Grok-1, but with substantially reduced model size and computational costs.
Authors: Alireza Olama, Andreas Lundell, Jan Kronqvist, Elham Ahmadi, Eduardo Camponogara
Abstract: This paper introduces the Bi-linear consensus Alternating Direction Method of Multipliers (Bi-cADMM), aimed at solving large-scale regularized Sparse Machine Learning (SML) problems defined over a network of computational nodes. Mathematically, these are stated as minimization problems with convex local loss functions over a global decision vector, subject to an explicit $\ell_0$ norm constraint to enforce the desired sparsity. The considered SML problem generalizes different sparse regression and classification models, such as sparse linear and logistic regression, sparse softmax regression, and sparse support vector machines. Bi-cADMM leverages a bi-linear consensus reformulation of the original non-convex SML problem and a hierarchical decomposition strategy that divides the problem into smaller sub-problems amenable to parallel computing. In Bi-cADMM, this decomposition strategy is based on a two-phase approach. Initially, it performs a sample decomposition of the data and distributes local datasets across computational nodes. Subsequently, a delayed feature decomposition of the data is conducted on Graphics Processing Units (GPUs) available to each node. This methodology allows Bi-cADMM to undertake computationally intensive data-centric computations on GPUs, while CPUs handle more cost-effective computations. The proposed algorithm is implemented within an open-source Python package called Parallel Sparse Fitting Toolbox (PsFiT), which is publicly available. Finally, computational experiments demonstrate the efficiency and scalability of our algorithm through numerical benchmarks across various SML problems featuring distributed datasets.
Authors: Vincenzo Buono, Peyman Sheikholharam Mashhadi, Mahmoud Rahat, Prayag Tiwari, Stefan Byttner
Abstract: Although input-gradients techniques have evolved to mitigate and tackle the challenges associated with gradients, modern gradient-weighted CAM approaches still rely on vanilla gradients, which are inherently susceptible to the saturation phenomena. Despite recent enhancements have incorporated counterfactual gradient strategies as a mitigating measure, these local explanation techniques still exhibit a lack of sensitivity to their baseline parameter. Our work proposes a gradient-weighted CAM augmentation that tackles both the saturation and sensitivity problem by reshaping the gradient computation, incorporating two well-established and provably approaches: Expected Gradients and kernel smoothing. By revisiting the original formulation as the smoothed expectation of the perturbed integrated gradients, one can concurrently construct more faithful, localized and robust explanations which minimize infidelity. Through fine modulation of the perturbation distribution it is possible to regulate the complexity characteristic of the explanation, selectively discriminating stable features. Our technique, Expected Grad-CAM, differently from recent works, exclusively optimizes the gradient computation, purposefully designed as an enhanced substitute of the foundational Grad-CAM algorithm and any method built therefrom. Quantitative and qualitative evaluations have been conducted to assess the effectiveness of our method.
Authors: Jeongyeol Kwon, Shie Mannor, Constantine Caramanis, Yonathan Efroni
Abstract: In many real-world decision problems there is partially observed, hidden or latent information that remains fixed throughout an interaction. Such decision problems can be modeled as Latent Markov Decision Processes (LMDPs), where a latent variable is selected at the beginning of an interaction and is not disclosed to the agent. In the last decade, there has been significant progress in solving LMDPs under different structural assumptions. However, for general LMDPs, there is no known learning algorithm that provably matches the existing lower bound (Kwon et al., 2021). We introduce the first sample-efficient algorithm for LMDPs without any additional structural assumptions. Our result builds off a new perspective on the role of off-policy evaluation guarantees and coverage coefficients in LMDPs, a perspective, that has been overlooked in the context of exploration in partially observed environments. Specifically, we establish a novel off-policy evaluation lemma and introduce a new coverage coefficient for LMDPs. Then, we show how these can be used to derive near-optimal guarantees of an optimistic exploration algorithm. These results, we believe, can be valuable for a wide range of interactive learning problems beyond LMDPs, and especially, for partially observed environments.
Authors: Nicolo Colombo
Abstract: Conformal Prediction (CP) algorithms estimate the uncertainty of a prediction model by calibrating its outputs on labeled data. The same calibration scheme usually applies to any model and data without modifications. The obtained prediction intervals are valid by construction but could be inefficient, i.e. unnecessarily big, if the prediction errors are not uniformly distributed over the input space. We present a general scheme to localize the intervals by training the calibration process. The standard prediction error is replaced by an optimized distance metric that depends explicitly on the object attributes. Learning the optimal metric is equivalent to training a Normalizing Flow that acts on the joint distribution of the errors and the inputs. Unlike the Error Reweighting CP algorithm of Papadopoulos et al. (2008), the framework allows estimating the gap between nominal and empirical conditional validity. The approach is compatible with existing locally-adaptive CP strategies based on re-weighting the calibration samples and applies to any point-prediction model without retraining.
Authors: Jingwu Tang, Gokul Swamy, Fei Fang, Zhiwei Steven Wu
Abstract: We study a multi-agent imitation learning (MAIL) problem where we take the perspective of a learner attempting to coordinate a group of agents based on demonstrations of an expert doing so. Most prior work in MAIL essentially reduces the problem to matching the behavior of the expert within the support of the demonstrations. While doing so is sufficient to drive the value gap between the learner and the expert to zero under the assumption that agents are non-strategic, it does not guarantee robustness to deviations by strategic agents. Intuitively, this is because strategic deviations can depend on a counterfactual quantity: the coordinator's recommendations outside of the state distribution their recommendations induce. In response, we initiate the study of an alternative objective for MAIL in Markov Games we term the regret gap that explicitly accounts for potential deviations by agents in the group. We first perform an in-depth exploration of the relationship between the value and regret gaps. First, we show that while the value gap can be efficiently minimized via a direct extension of single-agent IL algorithms, even value equivalence can lead to an arbitrarily large regret gap. This implies that achieving regret equivalence is harder than achieving value equivalence in MAIL. We then provide a pair of efficient reductions to no-regret online convex optimization that are capable of minimizing the regret gap (a) under a coverage assumption on the expert (MALICE) or (b) with access to a queryable expert (BLADES).
Authors: Binchuan Qi, Li Li, Wei Gong
Abstract: There remain numerous unanswered research questions on deep learning (DL) within the classical learning theory framework. These include the remarkable generalization capabilities of overparametrized neural networks (NNs), the efficient optimization performance despite non-convexity of objectives, the mechanism of flat minima for generalization, and the exceptional performance of deep architectures in solving physical problems. This paper introduces General Distribution Learning (GD Learning), a novel theoretical learning framework designed to address a comprehensive range of machine learning and statistical tasks, including classification, regression and parameter estimation. Departing from traditional statistical machine learning, GD Learning focuses on the true underlying distribution. In GD Learning, learning error, corresponding to the expected error in classical statistical learning framework, is divided into fitting errors due to models and algorithms, as well as sampling errors introduced by limited sampling data. The framework significantly incorporates prior knowledge, especially in scenarios characterized by data scarcity, thereby enhancing performance. Within the GD Learning framework, we demonstrate that the global optimal solutions in non-convex optimization can be approached by minimizing the gradient norm and the non-uniformity of the eigenvalues of the model's Jacobian matrix. This insight leads to the development of the gradient structure control algorithm. GD Learning also offers fresh insights into the questions on deep learning, including overparameterization and non-convex optimization, bias-variance trade-off, and the mechanism of flat minima.
Authors: Jonathan Booher, Khashayar Rohanimanesh, Junhong Xu, Vladislav Isenbaev, Ashwin Balakrishna, Ishan Gupta, Wei Liu, Aleksandr Petiushko
Abstract: Modern approaches to autonomous driving rely heavily on learned components trained with large amounts of human driving data via imitation learning. However, these methods require large amounts of expensive data collection and even then face challenges with safely handling long-tail scenarios and compounding errors over time. At the same time, pure Reinforcement Learning (RL) methods can fail to learn performant policies in sparse, constrained, and challenging-to-define reward settings like driving. Both of these challenges make deploying purely cloned policies in safety critical applications like autonomous vehicles challenging. In this paper we propose Combining IMitation and Reinforcement Learning (CIMRL) approach - a framework that enables training driving policies in simulation through leveraging imitative motion priors and safety constraints. CIMRL does not require extensive reward specification and improves on the closed loop behavior of pure cloning methods. By combining RL and imitation, we demonstrate that our method achieves state-of-the-art results in closed loop simulation driving benchmarks.
Authors: Pratik Gajane
Abstract: We introduce the problem of regret minimization in adversarial multi-dueling bandits. While adversarial preferences have been studied in dueling bandits, they have not been explored in multi-dueling bandits. In this setting, the learner is required to select $m \geq 2$ arms at each round and observes as feedback the identity of the most preferred arm which is based on an arbitrary preference matrix chosen obliviously. We introduce a novel algorithm, MiDEX (Multi Dueling EXP3), to learn from such preference feedback that is assumed to be generated from a pairwise-subset choice model. We prove that the expected cumulative $T$-round regret of MiDEX compared to a Borda-winner from a set of $K$ arms is upper bounded by $O((K \log K)^{1/3} T^{2/3})$. Moreover, we prove a lower bound of $\Omega(K^{1/3} T^{2/3})$ for the expected regret in this setting which demonstrates that our proposed algorithm is near-optimal.
Authors: Jinuk Kim, Marwa El Halabi, Mingi Ji, Hyun Oh Song
Abstract: Recent works show that reducing the number of layers in a convolutional neural network can enhance efficiency while maintaining the performance of the network. Existing depth compression methods remove redundant non-linear activation functions and merge the consecutive convolution layers into a single layer. However, these methods suffer from a critical drawback; the kernel size of the merged layers becomes larger, significantly undermining the latency reduction gained from reducing the depth of the network. We show that this problem can be addressed by jointly pruning convolution layers and activation functions. To this end, we propose LayerMerge, a novel depth compression method that selects which activation layers and convolution layers to remove, to achieve a desired inference speed-up while minimizing performance loss. Since the corresponding selection problem involves an exponential search space, we formulate a novel surrogate optimization problem and efficiently solve it via dynamic programming. Empirical results demonstrate that our method consistently outperforms existing depth compression and layer pruning methods on various network architectures, both on image classification and generation tasks. We release the code at https://github.com/snu-mllab/LayerMerge.
Authors: Shayne Longpre, Stella Biderman, Alon Albalak, Hailey Schoelkopf, Daniel McDuff, Sayash Kapoor, Kevin Klyman, Kyle Lo, Gabriel Ilharco, Nay San, Maribeth Rauh, Aviya Skowron, Bertie Vidgen, Laura Weidinger, Arvind Narayanan, Victor Sanh, David Adelani, Percy Liang, Rishi Bommasani, Peter Henderson, Sasha Luccioni, Yacine Jernite, Luca Soldaini
Abstract: Foundation model development attracts a rapidly expanding body of contributors, scientists, and applications. To help shape responsible development practices, we introduce the Foundation Model Development Cheatsheet: a growing collection of 250+ tools and resources spanning text, vision, and speech modalities. We draw on a large body of prior work to survey resources (e.g. software, documentation, frameworks, guides, and practical tools) that support informed data selection, processing, and understanding, precise and limitation-aware artifact documentation, efficient model training, advance awareness of the environmental impact from training, careful model evaluation of capabilities, risks, and claims, as well as responsible model release, licensing and deployment practices. We hope this curated collection of resources helps guide more responsible development. The process of curating this list, enabled us to review the AI development ecosystem, revealing what tools are critically missing, misused, or over-used in existing practices. We find that (i) tools for data sourcing, model evaluation, and monitoring are critically under-serving ethical and real-world needs, (ii) evaluations for model safety, capabilities, and environmental impact all lack reproducibility and transparency, (iii) text and particularly English-centric analyses continue to dominate over multilingual and multi-modal analyses, and (iv) evaluation of systems, rather than just models, is needed so that capabilities and impact are assessed in context.
Authors: Yushun Zhang, Congliang Chen, Ziniu Li, Tian Ding, Chenwei Wu, Yinyu Ye, Zhi-Quan Luo, Ruoyu Sun
Abstract: We propose Adam-mini, an optimizer that achieves on-par or better performance than AdamW with 45% to 50% less memory footprint. Adam-mini reduces memory by cutting down the learning rate resources in Adam (i.e., $1/\sqrt{v}$). We find that $\geq$ 90% of these learning rates in $v$ could be harmlessly removed if we (1) carefully partition the parameters into blocks following our proposed principle on Hessian structure; (2) assign a single but good learning rate to each parameter block. We further find that, for each of these parameter blocks, there exists a single high-quality learning rate that can outperform Adam, provided that sufficient resources are available to search it out. We then provide one cost-effective way to find good learning rates and propose Adam-mini. Empirically, we verify that Adam-mini performs on par or better than AdamW on various language models sized from 125M to 7B for pre-training, supervised fine-tuning, and RLHF. The reduced memory footprint of Adam-mini also alleviates communication overheads among GPUs and CPUs, thereby increasing throughput. For instance, Adam-mini achieves 49.6% higher throughput than AdamW when pre-training Llama2-7B on $2\times$ A800-80GB GPUs, which saves 33% wall-clock time for pre-training.
Authors: Kai Shao, Rui Wang, Yixue Hao, Long Hu, Min Chen, Hans Arno Jacobsen
Abstract: Depression recognition based on physiological signals such as functional near-infrared spectroscopy (fNIRS) and electroencephalogram (EEG) has made considerable progress. However, most existing studies ignore the complementarity and semantic consistency of multimodal physiological signals under the same stimulation task in complex spatio-temporal patterns. In this paper, we introduce a multimodal physiological signals representation learning framework using Siamese architecture via multiscale contrasting for depression recognition (MRLMC). First, fNIRS and EEG are transformed into different but correlated data based on a time-domain data augmentation strategy. Then, we design a spatio-temporal contrasting module to learn the representation of fNIRS and EEG through weight-sharing multiscale spatio-temporal convolution. Furthermore, to enhance the learning of semantic representation associated with stimulation tasks, a semantic consistency contrast module is proposed, aiming to maximize the semantic similarity of fNIRS and EEG. Extensive experiments on publicly available and self-collected multimodal physiological signals datasets indicate that MRLMC outperforms the state-of-the-art models. Moreover, our proposed framework is capable of transferring to multimodal time series downstream tasks.
Authors: Pranav Ajit Nair, Arun Sai Suggala
Abstract: Large language models (LLMs) have recently demonstrated remarkable performance across diverse language tasks. But their deployment is often constrained by their substantial computational and storage requirements. Quantization has emerged as a key technique for addressing this challenge, enabling the compression of large models with minimal impact on performance. The recent GPTQ algorithm, a post-training quantization (PTQ) method, has proven highly effective for compressing LLMs, sparking a wave of research that leverages GPTQ as a core component. Recognizing the pivotal role of GPTQ in the PTQ landscape, we introduce CDQuant, a simple and scalable alternative to GPTQ with improved performance. CDQuant uses coordinate descent to minimize the layer-wise reconstruction loss to achieve high-quality quantized weights. Our algorithm is easy to implement and scales efficiently to models with hundreds of billions of parameters. Through extensive evaluation on the PaLM2 model family, we demonstrate that CDQuant consistently outperforms GPTQ across diverse model sizes and quantization levels. In particular, for INT2 quantization of PaLM2-Otter, CDQuant achieves a 10% reduction in perplexity compared to GPTQ.
Authors: Yong-Yeon Jo, Young Sang Choi, Jong-Hwan Jang, Joon-Myoung Kwon
Abstract: The electrocardiogram (ECG) records electrical signals in a non-invasive way to observe the condition of the heart, typically looking at the heart from 12 different directions. Several types of the cardiac disease are diagnosed by using 12-lead ECGs Recently, various wearable devices have enabled immediate access to the ECG without the use of wieldy equipment. However, they only provide ECGs with a couple of leads. This results in an inaccurate diagnosis of cardiac disease due to lacking of required leads. We propose a deep generative model for ECG synthesis from two asynchronous leads to ten leads. It first represents a heart condition referring to two leads, and then generates ten leads based on the represented heart condition. Both the rhythm and amplitude of leads generated resemble those of the original ones, while the technique removes noise and the baseline wander appearing in the original leads. As a data augmentation method, our model improves the classification performance of models compared with models using ECGs with only one or two leads.
Authors: Yuka Hashimoto, Masahiro Ikeda, Hachem Kadri
Abstract: Supervised learning in reproducing kernel Hilbert space (RKHS) and vector-valued RKHS (vvRKHS) has been investigated for more than 30 years. In this paper, we provide a new twist to this rich literature by generalizing supervised learning in RKHS and vvRKHS to reproducing kernel Hilbert $C^*$-module (RKHM), and show how to construct effective positive-definite kernels by considering the perspective of $C^*$-algebra. Unlike the cases of RKHS and vvRKHS, we can use $C^*$-algebras to enlarge representation spaces. This enables us to construct RKHMs whose representation power goes beyond RKHSs, vvRKHSs, and existing methods such as convolutional neural networks. Our framework is suitable, for example, for effectively analyzing image data by allowing the interaction of Fourier components.
Authors: Xiaohong Chen, Zhengling Qi, Runzhe Wan
Abstract: Batch reinforcement learning (RL) aims at leveraging pre-collected data to find an optimal policy that maximizes the expected total rewards in a dynamic environment. The existing methods require absolutely continuous assumption (e.g., there do not exist non-overlapping regions) on the distribution induced by target policies with respect to the data distribution over either the state or action or both. We propose a new batch RL algorithm that allows for singularity for both state and action spaces (e.g., existence of non-overlapping regions between offline data distribution and the distribution induced by the target policies) in the setting of an infinite-horizon Markov decision process with continuous states and actions. We call our algorithm STEEL: SingulariTy-awarE rEinforcement Learning. Our algorithm is motivated by a new error analysis on off-policy evaluation, where we use maximum mean discrepancy, together with distributionally robust optimization, to characterize the error of off-policy evaluation caused by the possible singularity and to enable model extrapolation. By leveraging the idea of pessimism and under some technical conditions, we derive a first finite-sample regret guarantee for our proposed algorithm under singularity. Compared with existing algorithms,by requiring only minimal data-coverage assumption, STEEL improves the applicability and robustness of batch RL. In addition, a two-step adaptive STEEL, which is nearly tuning-free, is proposed. Extensive simulation studies and one (semi)-real experiment on personalized pricing demonstrate the superior performance of our methods in dealing with possible singularity in batch RL.
Authors: \'Alvaro Torras-Casas, Eduardo Paluzo-Hidalgo, Rocio Gonzalez-Diaz
Abstract: Data quality is crucial for the successful training, generalization and performance of artificial intelligence models. We propose to measure data quality for supervised learning using topological data analysis techniques. Specifically, we provide a novel topological invariant based on persistence matchings induced by inclusions and using $0$-dimensional persistent homology. We show that such an invariant is stable. We provide an algorithm and relate it to images, kernels, and cokernels of the induced morphisms. Also, we show that the invariant allows us to understand whether the subset "represents well" the clusters from the larger dataset or not, and we also use it to estimate bounds for the Hausdorff distance between the subset and the complete dataset. This approach enables us to explain why the chosen dataset will lead to poor performance.
Authors: Mike Laszkiewicz, Jonas Ricker, Johannes Lederer, Asja Fischer
Abstract: Recent breakthroughs in generative modeling have sparked interest in practical single-model attribution. Such methods predict whether a sample was generated by a specific generator or not, for instance, to prove intellectual property theft. However, previous works are either limited to the closed-world setting or require undesirable changes to the generative model. We address these shortcomings by, first, viewing single-model attribution through the lens of anomaly detection. Arising from this change of perspective, we propose FLIPAD, a new approach for single-model attribution in the open-world setting based on final-layer inversion and anomaly detection. We show that the utilized final-layer inversion can be reduced to a convex lasso optimization problem, making our approach theoretically sound and computationally efficient. The theoretical findings are accompanied by an experimental study demonstrating the effectiveness of our approach and its flexibility to various domains.
Authors: Emiland Garrabe, Hozefa Jesawada, Carmen Del Vecchio, Giovanni Russo
Abstract: This paper is concerned with a finite-horizon inverse control problem, which has the goal of reconstructing, from observations, the possibly non-convex and non-stationary cost driving the actions of an agent. In this context, we present a result enabling cost reconstruction by solving an optimization problem that is convex even when the agent cost is not and when the underlying dynamics is nonlinear, non-stationary and stochastic. To obtain this result, we also study a finite-horizon forward control problem that has randomized policies as decision variables. We turn our findings into algorithmic procedures and show the effectiveness of our approach via in-silico and hardware validations. All experiments confirm the effectiveness of our approach.
Authors: Pangpang Liu, Zhuoran Yang, Zhaoran Wang, Will Wei Sun
Abstract: Personalized pricing, which involves tailoring prices based on individual characteristics, is commonly used by firms to implement a consumer-specific pricing policy. In this process, buyers can also strategically manipulate their feature data to obtain a lower price, incurring certain manipulation costs. Such strategic behavior can hinder firms from maximizing their profits. In this paper, we study the contextual dynamic pricing problem with strategic buyers. The seller does not observe the buyer's true feature, but a manipulated feature according to buyers' strategic behavior. In addition, the seller does not observe the buyers' valuation of the product, but only a binary response indicating whether a sale happens or not. Recognizing these challenges, we propose a strategic dynamic pricing policy that incorporates the buyers' strategic behavior into the online learning to maximize the seller's cumulative revenue. We first prove that existing non-strategic pricing policies that neglect the buyers' strategic behavior result in a linear $\Omega(T)$ regret with $T$ the total time horizon, indicating that these policies are not better than a random pricing policy. We then establish that our proposed policy achieves a sublinear regret upper bound of $O(\sqrt{T})$. Importantly, our policy is not a mere amalgamation of existing dynamic pricing policies and strategic behavior handling algorithms. Our policy can also accommodate the scenario when the marginal cost of manipulation is unknown in advance. To account for it, we simultaneously estimate the valuation parameter and the cost parameter in the online pricing policy, which is shown to also achieve an $O(\sqrt{T})$ regret bound. Extensive experiments support our theoretical developments and demonstrate the superior performance of our policy compared to other pricing policies that are unaware of the strategic behaviors.
Authors: Neophytos Charalambides, Mert Pilanci, Alfred Hero
Abstract: We generalize the leverage score sampling sketch for $\ell_2$-subspace embeddings, to accommodate sampling subsets of the transformed data, so that the sketching approach is appropriate for distributed settings. This is then used to derive an approximate coded computing approach for first-order methods; known as gradient coding, to accelerate linear regression in the presence of failures in distributed computational networks, \textit{i.e.} stragglers. We replicate the data across the distributed network, to attain the approximation guarantees through the induced sampling distribution. The significance and main contribution of this work, is that it unifies randomized numerical linear algebra with approximate coded computing, while attaining an induced $\ell_2$-subspace embedding through uniform sampling. The transition to uniform sampling is done without applying a random projection, as in the case of the subsampled randomized Hadamard transform. Furthermore, by incorporating this technique to coded computing, our scheme is an iterative sketching approach to approximately solving linear regression. We also propose weighting when sketching takes place through sampling with replacement, for further compression.
Authors: Xiaofei Wang, Manthan Thakker, Zhuo Chen, Naoyuki Kanda, Sefik Emre Eskimez, Sanyuan Chen, Min Tang, Shujie Liu, Jinyu Li, Takuya Yoshioka
Abstract: Recent advancements in generative speech models based on audio-text prompts have enabled remarkable innovations like high-quality zero-shot text-to-speech. However, existing models still face limitations in handling diverse audio-text speech generation tasks involving transforming input speech and processing audio captured in adverse acoustic conditions. This paper introduces SpeechX, a versatile speech generation model capable of zero-shot TTS and various speech transformation tasks, dealing with both clean and noisy signals. SpeechX combines neural codec language modeling with multi-task learning using task-dependent prompting, enabling unified and extensible modeling and providing a consistent way for leveraging textual input in speech enhancement and transformation tasks. Experimental results show SpeechX's efficacy in various tasks, including zero-shot TTS, noise suppression, target speaker extraction, speech removal, and speech editing with or without background noise, achieving comparable or superior performance to specialized models across tasks. See https://aka.ms/speechx for demo samples.
URLs: https://aka.ms/speechx
Authors: The CMS ECAL Collaboration
Abstract: The CMS detector is a general-purpose apparatus that detects high-energy collisions produced at the LHC. Online Data Quality Monitoring of the CMS electromagnetic calorimeter is a vital operational tool that allows detector experts to quickly identify, localize, and diagnose a broad range of detector issues that could affect the quality of physics data. A real-time autoencoder-based anomaly detection system using semi-supervised machine learning is presented enabling the detection of anomalies in the CMS electromagnetic calorimeter data. A novel method is introduced which maximizes the anomaly detection performance by exploiting the time-dependent evolution of anomalies as well as spatial variations in the detector response. The autoencoder-based system is able to efficiently detect anomalies, while maintaining a very low false discovery rate. The performance of the system is validated with anomalies found in 2018 and 2022 LHC collision data. Additionally, the first results from deploying the autoencoder-based system in the CMS online Data Quality Monitoring workflow during the beginning of Run 3 of the LHC are presented, showing its ability to detect issues missed by the existing system.
Authors: Md Rakibul Hasan, Md Zakir Hossain, Shreya Ghosh, Aneesh Krishna, Tom Gedeon
Abstract: Empathy indicates an individual's ability to understand others. Over the past few years, empathy has drawn attention from various disciplines, including but not limited to Affective Computing, Cognitive Science and Psychology. Detecting empathy has potential applications in society, healthcare and education. Despite being a broad and overlapping topic, the avenue of empathy detection leveraging Machine Learning remains underexplored from a systematic literature review perspective. We collected 828 papers from 10 well-known databases, systematically screened them and analysed the final 61 papers. Our analyses reveal several prominent task formulations $-$ including empathy on localised utterances or overall expressions, unidirectional or parallel empathy, and emotional contagion $-$ in monadic, dyadic and group interactions. Empathy detection methods are summarised based on four input modalities $-$ text, audiovisual, audio and physiological signals $-$ thereby presenting modality-specific network architecture design protocols. We discuss challenges, research gaps and potential applications in the Affective Computing-based empathy domain, which can facilitate new avenues of exploration. We further enlist the public availability of datasets and codes. We believe that our work is a stepping stone to developing a robust empathy detection system that can be deployed in practice to enhance the overall well-being of human life.
Authors: Trevor Ablett, Oliver Limoyo, Adam Sigal, Affan Jilani, Jonathan Kelly, Kaleem Siddiqi, Francois Hogan, Gregory Dudek
Abstract: Contact-rich tasks continue to present a variety of challenges for robotic manipulation. In this work, we leverage a multimodal visuotactile sensor within the framework of imitation learning (IL) to perform contact rich tasks that involve relative motion (slipping/sliding) between the end-effector and object. We introduce two algorithmic contributions, tactile force matching and learned mode switching, as complimentary methods for improving IL. Tactile force matching enhances kinesthetic teaching by reading approximate forces during the demonstration and generating an adapted robot trajectory that recreates the recorded forces. Learned mode switching uses IL to couple visual and tactile sensor modes with the learned motion policy, simplifying the transition from reaching to contacting. We perform robotic manipulation experiments on four door opening tasks with a variety of observation and method configurations to study the utility of our proposed improvements and multimodal visuotactile sensing. Our results show that the inclusion of force matching raises average policy success rates by 62.5%, visuotactile mode switching by 30.3%, and visuotactile data as a policy input by 42.5%, emphasizing the value of see-through tactile sensing for IL, both for data collection to allow force matching, and for policy execution to allow accurate task feedback.
Authors: Jinbin Huang, Wenbin He, Liang Gou, Liu Ren, Chris Bryan
Abstract: Deep learning models are widely used in critical applications, highlighting the need for pre-deployment model understanding and improvement. Visual concept-based methods, while increasingly used for this purpose, face challenges: (1) most concepts lack interpretability, (2) existing methods require model knowledge, often unavailable at run time. Additionally, (3) there lacks a no-code method for post-understanding model improvement. Addressing these, we present InterVLS. The system facilitates model understanding by discovering text-aligned concepts, measuring their influence with model-agnostic linear surrogates. Employing visual analytics, InterVLS offers concept-based explanations and performance insights. It enables users to adjust concept influences to update a model, facilitating no-code model improvement. We evaluate InterVLS in a user study, illustrating its functionality with two scenarios. Results indicates that InterVLS is effective to help users identify influential concepts to a model, gain insights and adjust concept influence to improve the model. We conclude with a discussion based on our study results.
Authors: Manuel Brack, Felix Friedrich, Katharina Kornmeier, Linoy Tsaban, Patrick Schramowski, Kristian Kersting, Apolin\'ario Passos
Abstract: Text-to-image diffusion models have recently received increasing interest for their astonishing ability to produce high-fidelity images from solely text inputs. Subsequent research efforts aim to exploit and apply their capabilities to real image editing. However, existing image-to-image methods are often inefficient, imprecise, and of limited versatility. They either require time-consuming finetuning, deviate unnecessarily strongly from the input image, and/or lack support for multiple, simultaneous edits. To address these issues, we introduce LEDITS++, an efficient yet versatile and precise textual image manipulation technique. LEDITS++'s novel inversion approach requires no tuning nor optimization and produces high-fidelity results with a few diffusion steps. Second, our methodology supports multiple simultaneous edits and is architecture-agnostic. Third, we use a novel implicit masking technique that limits changes to relevant image regions. We propose the novel TEdBench++ benchmark as part of our exhaustive evaluation. Our results demonstrate the capabilities of LEDITS++ and its improvements over previous methods.
Authors: Wasu Top Piriyakulkij, Volodymyr Kuleshov, Kevin Ellis
Abstract: Actively inferring user preferences, for example by asking good questions, is important for any human-facing decision-making system. Active inference allows such systems to adapt and personalize themselves to nuanced individual preferences. To enable this ability for instruction-tuned large language models (LLMs), one may prompt them to ask users questions to infer their preferences, transforming the language models into more robust, interactive systems. However, out of the box, these models are not efficient at extracting preferences: the questions they generate are not informative, requiring a high number of user interactions and impeding the usability of the downstream system. In this work, we introduce an inference-time algorithm that helps LLMs quickly infer preferences by using more informative questions. Our algorithm uses a probabilistic model whose conditional distributions are defined by prompting an LLM, and returns questions that optimize expected entropy and expected model change. Results in a simplified interactive web shopping setting with real product items show that an LLM equipped with our entropy reduction algorithm outperforms baselines with the same underlying LLM on task performance while using fewer user interactions.
Authors: Ayush Jain, Pushkal Katara, Nikolaos Gkanatsios, Adam W. Harley, Gabriel Sarch, Kriti Aggarwal, Vishrav Chaudhary, Katerina Fragkiadaki
Abstract: State-of-the-art models on contemporary 3D segmentation benchmarks like ScanNet consume and label dataset-provided 3D point clouds, obtained through post processing of sensed multiview RGB-D images. They are typically trained in-domain, forego large-scale 2D pre-training and outperform alternatives that featurize the posed RGB-D multiview images instead. The gap in performance between methods that consume posed images versus post-processed 3D point clouds has fueled the belief that 2D and 3D perception require distinct model architectures. In this paper, we challenge this view and propose ODIN (Omni-Dimensional INstance segmentation), a model that can segment and label both 2D RGB images and 3D point clouds, using a transformer architecture that alternates between 2D within-view and 3D cross-view information fusion. Our model differentiates 2D and 3D feature operations through the positional encodings of the tokens involved, which capture pixel coordinates for 2D patch tokens and 3D coordinates for 3D feature tokens. ODIN achieves state-of-the-art performance on ScanNet200, Matterport3D and AI2THOR 3D instance segmentation benchmarks, and competitive performance on ScanNet, S3DIS and COCO. It outperforms all previous works by a wide margin when the sensed 3D point cloud is used in place of the point cloud sampled from 3D mesh. When used as the 3D perception engine in an instructable embodied agent architecture, it sets a new state-of-the-art on the TEACh action-from-dialogue benchmark. Our code and checkpoints can be found at the project website (https://odin-seg.github.io).
Authors: Constantin Gahr, Ionut-Gabriel Farcas, Frank Jenko
Abstract: This paper focuses on the construction of non-intrusive Scientific Machine Learning (SciML) Reduced-Order Models (ROMs) for plasma turbulence simulations. In particular, we propose using Operator Inference (OpInf) to build low-cost physics-based ROMs from data for such simulations. As a representative example, we focus on the Hasegawa-Wakatani (HW) equations used for modeling two-dimensional electrostatic drift-wave turbulence. For a comprehensive perspective of the potential of OpInf to construct accurate ROMs, we consider three setups for the HW equations by varying a key model parameter, namely the adiabaticity coefficient. These setups lead to the formation of complex and nonlinear dynamics, which makes the construction of accurate ROMs of any kind challenging. We generate the training datasets by performing direct numerical simulations of the HW equations and recording the computed state data and outputs the over a time horizon of 100 time units in the turbulent phase. We then use these datasets to construct OpInf ROMs for predictions over 400 additional time units. Our results show that the OpInf ROMs capture the important features of the turbulent dynamics and generalize beyond the training time horizon while reducing the computational effort of the high-fidelity simulation by up to five orders of magnitude. In the broader context of fusion research, this shows that non-intrusive SciML ROMs have the potential to drastically accelerate numerical studies, which can ultimately enable tasks such as the design of optimized fusion devices.
Authors: Han-Xiao Tao, Jiaqi Hu, Re-Bing Wu
Abstract: Quantum machine learning (QML) based on Noisy Intermediate-Scale Quantum (NISQ) devices hinges on the optimal utilization of limited quantum resources. While gate-based QML models are user-friendly for software engineers, their expressivity is restricted by the permissible circuit depth within a finite coherence time. In contrast, pulse-based models enable the construction of "infinitely" deep quantum neural networks within the same time, which may unleash greater expressive power for complex learning tasks. In this paper, this potential is investigated from the perspective of quantum control theory. We first indicate that the nonlinearity of pulse-based models comes from the encoding process that can be viewed as the continuous limit of data-reuploading in gate-based models. Subsequently, we prove that the pulse-based model can approximate arbitrary nonlinear functions when the underlying physical system is ensemble controllable. Under this condition, numerical simulations demonstrate the enhanced expressivity by either increasing the pulse length or the number of qubits. As anticipated, we show through numerical examples that the pulse-based model can unleash more expressive power compared to the gate-based model. These findings lay a theoretical foundation for understanding and designing expressive QML models using NISQ devices.
Authors: Yu-Neng Chuang, Guanchu Wang, Chia-Yuan Chang, Ruixiang Tang, Shaochen Zhong, Fan Yang, Mengnan Du, Xuanting Cai, Xia Hu
Abstract: Large Language Models (LLMs) have become proficient in addressing complex tasks by leveraging their extensive internal knowledge and reasoning capabilities. However, the black-box nature of these models complicates the task of explaining their decision-making processes. While recent advancements demonstrate the potential of leveraging LLMs to self-explain their predictions through natural language (NL) explanations, their explanations may not accurately reflect the LLMs' decision-making process due to a lack of fidelity optimization on the derived explanations. Measuring the fidelity of NL explanations is a challenging issue, as it is difficult to manipulate the input context to mask the semantics of these explanations. To this end, we introduce FaithLM to explain the decision of LLMs with NL explanations. Specifically, FaithLM designs a method for evaluating the fidelity of NL explanations by incorporating the contrary explanations to the query process. Moreover, FaithLM conducts an iterative process to improve the fidelity of derived explanations. Experiment results on three datasets from multiple domains demonstrate that FaithLM can significantly improve the fidelity of derived explanations, which also provides a better alignment with the ground-truth explanations.
Authors: Dongyang Liu, Renrui Zhang, Longtian Qiu, Siyuan Huang, Weifeng Lin, Shitian Zhao, Shijie Geng, Ziyi Lin, Peng Jin, Kaipeng Zhang, Wenqi Shao, Chao Xu, Conghui He, Junjun He, Hao Shao, Pan Lu, Hongsheng Li, Yu Qiao, Peng Gao
Abstract: We propose SPHINX-X, an extensive Multimodality Large Language Model (MLLM) series developed upon SPHINX. To improve the architecture and training efficiency, we modify the SPHINX framework by removing redundant visual encoders, bypassing fully-padded sub-images with skip tokens, and simplifying multi-stage training into a one-stage all-in-one paradigm. To fully unleash the potential of MLLMs, we assemble a comprehensive multi-domain and multimodal dataset covering publicly available resources in language, vision, and vision-language tasks. We further enrich this collection with our curated OCR intensive and Set-of-Mark datasets, extending the diversity and generality. By training over different base LLMs including TinyLlama1.1B, InternLM2-7B, LLaMA2-13B, and Mixtral8x7B, we obtain a spectrum of MLLMs that vary in parameter size and multilingual capabilities. Comprehensive benchmarking reveals a strong correlation between the multi-modal performance with the data and parameter scales. Code and models are released at https://github.com/Alpha-VLLM/LLaMA2-Accessory
Authors: Xiangru Tang, Howard Dai, Elizabeth Knight, Fang Wu, Yunyang Li, Tianxiao Li, Mark Gerstein
Abstract: Artificial intelligence (AI)-driven methods can vastly improve the historically costly drug design process, with various generative models already in widespread use. Generative models for de novo drug design, in particular, focus on the creation of novel biological compounds entirely from scratch, representing a promising future direction. Rapid development in the field, combined with the inherent complexity of the drug design process, creates a difficult landscape for new researchers to enter. In this survey, we organize de novo drug design into two overarching themes: small molecule and protein generation. Within each theme, we identify a variety of subtasks and applications, highlighting important datasets, benchmarks, and model architectures and comparing the performance of top models. We take a broad approach to AI-driven drug design, allowing for both micro-level comparisons of various methods within each subtask and macro-level observations across different fields. We discuss parallel challenges and approaches between the two applications and highlight future directions for AI-driven de novo drug design as a whole. An organized repository of all covered sources is available at https://github.com/gersteinlab/GenAI4Drug.
Authors: Alessandro Licciardi (Politecnico di Torino, Istituto Nazionale di Fisica Nucleare Sezione di Torino), Davide Carbone (Politecnico di Torino, Istituto Nazionale di Fisica Nucleare Sezione di Torino)
Abstract: Marine mammal communication is a complex field, hindered by the diversity of vocalizations and environmental factors. The Watkins Marine Mammal Sound Database (WMMD) constitutes a comprehensive labeled dataset employed in machine learning applications. Nevertheless, the methodologies for data preparation, preprocessing, and classification documented in the literature exhibit considerable variability and are typically not applied to the dataset in its entirety. This study initially undertakes a concise review of the state-of-the-art benchmarks pertaining to the dataset, with a particular focus on clarifying data preparation and preprocessing techniques. Subsequently, we explore the utilization of the Wavelet Scattering Transform (WST) and Mel spectrogram as preprocessing mechanisms for feature extraction. In this paper, we introduce \textbf{WhaleNet} (Wavelet Highly Adaptive Learning Ensemble Network), a sophisticated deep ensemble architecture for the classification of marine mammal vocalizations, leveraging both WST and Mel spectrogram for enhanced feature discrimination. By integrating the insights derived from WST and Mel representations, we achieved an improvement in classification accuracy by $8-10\%$ over existing architectures, corresponding to a classification accuracy of $97.61\%$.
Authors: David Heurtel-Depeiges, Charles C. Margossian, Ruben Ohana, Bruno R\'egaldo-Saint Blancard
Abstract: In recent years, denoising problems have become intertwined with the development of deep generative models. In particular, diffusion models are trained like denoisers, and the distribution they model coincide with denoising priors in the Bayesian picture. However, denoising through diffusion-based posterior sampling requires the noise level and covariance to be known, preventing blind denoising. We overcome this limitation by introducing Gibbs Diffusion (GDiff), a general methodology addressing posterior sampling of both the signal and the noise parameters. Assuming arbitrary parametric Gaussian noise, we develop a Gibbs algorithm that alternates sampling steps from a conditional diffusion model trained to map the signal prior to the family of noise distributions, and a Monte Carlo sampler to infer the noise parameters. Our theoretical analysis highlights potential pitfalls, guides diagnostic usage, and quantifies errors in the Gibbs stationary distribution caused by the diffusion model. We showcase our method for 1) blind denoising of natural images involving colored noises with unknown amplitude and spectral index, and 2) a cosmology problem, namely the analysis of cosmic microwave background data, where Bayesian inference of "noise" parameters means constraining models of the evolution of the Universe.
Authors: Xiangxin Zhou, Dongyu Xue, Ruizhe Chen, Zaixiang Zheng, Liang Wang, Quanquan Gu
Abstract: Antibody design, a crucial task with significant implications across various disciplines such as therapeutics and biology, presents considerable challenges due to its intricate nature. In this paper, we tackle antigen-specific antibody sequence-structure co-design as an optimization problem towards specific preferences, considering both rationality and functionality. Leveraging a pre-trained conditional diffusion model that jointly models sequences and structures of antibodies with equivariant neural networks, we propose direct energy-based preference optimization to guide the generation of antibodies with both rational structures and considerable binding affinities to given antigens. Our method involves fine-tuning the pre-trained diffusion model using a residue-level decomposed energy preference. Additionally, we employ gradient surgery to address conflicts between various types of energy, such as attraction and repulsion. Experiments on RAbD benchmark show that our approach effectively optimizes the energy of generated antibodies and achieves state-of-the-art performance in designing high-quality antibodies with low total energy and high binding affinity simultaneously, demonstrating the superiority of our approach.
Authors: Thanh Tam Nguyen, Thanh Trung Huynh, Zhao Ren, Thanh Toan Nguyen, Phi Le Nguyen, Hongzhi Yin, Quoc Viet Hung Nguyen
Abstract: As the adoption of explainable AI (XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving model explanations. This article presents the first thorough survey about privacy attacks on model explanations and their countermeasures. Our contribution to this field comprises a thorough analysis of research papers with a connected taxonomy that facilitates the categorisation of privacy attacks and countermeasures based on the targeted explanations. This work also includes an initial investigation into the causes of privacy leaks. Finally, we discuss unresolved issues and prospective research directions uncovered in our analysis. This survey aims to be a valuable resource for the research community and offers clear insights for those new to this domain. To support ongoing research, we have established an online resource repository, which will be continuously updated with new and relevant findings. Interested readers are encouraged to access our repository at https://github.com/tamlhp/awesome-privex.
Authors: Aparajithan Venkateswaran, Anirudh Sankar, Arun G. Chandrasekhar, Tyler H. McCormick
Abstract: Many statistical analyses, in both observational data and randomized control trials, ask: how does the outcome of interest vary with combinations of observable covariates? How do various drug combinations affect health outcomes, or how does technology adoption depend on incentives and demographics? Our goal is to partition this factorial space into "pools" of covariate combinations where the outcome differs across the pools (but not within a pool). Existing approaches (i) search for a single "optimal" partition under assumptions about the association between covariates or (ii) sample from the entire set of possible partitions. Both these approaches ignore the reality that, especially with correlation structure in covariates, many ways to partition the covariate space may be statistically indistinguishable, despite very different implications for policy or science. We develop an alternative perspective, called Rashomon Partition Sets (RPSs). Each item in the RPS partitions the space of covariates using a tree-like geometry. RPSs incorporate all partitions that have posterior values near the maximum a posteriori partition, even if they offer substantively different explanations, and do so using a prior that makes no assumptions about associations between covariates. This prior is the $\ell_0$ prior, which we show is minimax optimal. Given the RPS we calculate the posterior of any measurable function of the feature effects vector on outcomes, conditional on being in the RPS. We also characterize approximation error relative to the entire posterior and provide bounds on the size of the RPS. Simulations demonstrate this framework allows for robust conclusions relative to conventional regularization techniques. We apply our method to three empirical settings: price effects on charitable giving, chromosomal structure (telomere length), and the introduction of microfinance.
Authors: Jonas Niederle, Simon Koop, Marc Pag\`es-Gallego, Vlado Menkovski
Abstract: Nanopore sequencing offers the ability for real-time analysis of long DNA sequences at a low cost, enabling new applications such as early detection of cancer. Due to the complex nature of nanopore measurements and the high cost of obtaining ground truth datasets, there is a need for nanopore simulators. Existing simulators rely on handcrafted rules and parameters and do not learn an internal representation that would allow for analysing underlying biological factors of interest. Instead, we propose VADA, a purely data-driven method for simulating nanopores based on an autoregressive latent variable model. We embed subsequences of DNA and introduce a conditional prior to address the challenge of a collapsing conditioning. We introduce an auxiliary regressor on the latent variable to encourage our model to learn an informative latent representation. We empirically demonstrate that our model achieves competitive simulation performance on experimental nanopore data. Moreover, we show we have learned an informative latent representation that is predictive of the DNA labels. We hypothesize that other biological factors of interest, beyond the DNA labels, can potentially be extracted from such a learned latent representation.
Authors: Andrew Zammit-Mangion, Matthew Sainsbury-Dale, Rapha\"el Huser
Abstract: Simulation-based methods for statistical inference have evolved dramatically over the past 50 years, keeping pace with technological advancements. The field is undergoing a new revolution as it embraces the representational capacity of neural networks, optimisation libraries and graphics processing units for learning complex mappings between data and inferential targets. The resulting tools are amortised, in the sense that they allow rapid inference through fast feedforward operations. In this article we review recent progress in the context of point estimation, approximate Bayesian inference, summary-statistic construction, and likelihood approximation. We also cover software, and include a simple illustration to showcase the wide array of tools available for amortised inference and the benefits they offer over Markov chain Monte Carlo methods. The article concludes with an overview of relevant topics and an outlook on future research directions.
Authors: Fanghui Liu, Leello Dadi, Volkan Cevher
Abstract: Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks as the curse of dimensionality (CoD) cannot be evaded when trying to approximate even a single ReLU neuron (Bach, 2017). In this paper, we study a suitable function space for over-parameterized two-layer neural networks with bounded norms (e.g., the path norm, the Barron norm) in the perspective of sample complexity and generalization properties. First, we show that the path norm (as well as the Barron norm) is able to obtain width-independence sample complexity bounds, which allows for uniform convergence guarantees. Based on this result, we derive the improved result of metric entropy for $\epsilon$-covering up to $O(\epsilon^{-\frac{2d}{d+2}})$ ($d$ is the input dimension and the depending constant is at most linear order of $d$) via the convex hull technique, which demonstrates the separation with kernel methods with $\Omega(\epsilon^{-d})$ to learn the target function in a Barron space. Second, this metric entropy result allows for building a sharper generalization bound under a general moment hypothesis setting, achieving the rate at $O(n^{-\frac{d+2}{2d+2}})$. Our analysis is novel in that it offers a sharper and refined estimation for metric entropy with a linear dimension dependence and unbounded sampling in the estimation of the sample error and the output error.
Authors: Alexander Atanasov, Jacob A. Zavatone-Veth, Cengiz Pehlevan
Abstract: This paper presents a succinct derivation of the training and generalization performance of a variety of high-dimensional ridge regression models using the basic tools of random matrix theory and free probability. We provide an introduction and review of recent results on these topics, aimed at readers with backgrounds in physics and deep learning. Analytic formulas for the training and generalization errors are obtained in a few lines of algebra directly from the properties of the $S$-transform of free probability. This allows for a straightforward identification of the sources of power-law scaling in model performance. We compute the generalization error of a broad class of random feature models. We find that in all models, the $S$-transform corresponds to the train-test generalization gap, and yields an analogue of the generalized-cross-validation estimator. Using these techniques, we derive fine-grained bias-variance decompositions for a very general class of random feature models with structured covariates. These novel results allow us to discover a scaling regime for random feature models where the variance due to the features limits performance in the overparameterized setting. We also demonstrate how anisotropic weight structure in random feature models can limit performance and lead to nontrivial exponents for finite-width corrections in the overparameterized setting. Our results extend and provide a unifying perspective on earlier models of neural scaling laws.
Authors: Heng Jin, Chaoyu Zhang, Shanghao Shi, Wenjing Lou, Y. Thomas Hou
Abstract: Large language models (LLMs) have attracted significant attention in recent years. Due to their "Large" nature, training LLMs from scratch consumes immense computational resources. Since several major players in the artificial intelligence (AI) field have open-sourced their original LLMs, an increasing number of individual researchers and smaller companies are able to build derivative LLMs based on these open-sourced models at much lower costs. However, this practice opens up possibilities for unauthorized use or reproduction that may not comply with licensing agreements, and fine-tuning can change the model's behavior, thus complicating the determination of model ownership. Current intellectual property (IP) protection schemes for LLMs are either designed for white-box settings or require additional modifications to the original model, which restricts their use in real-world settings. In this paper, we propose ProFLingo, a black-box fingerprinting-based IP protection scheme for LLMs. ProFLingo generates queries that elicit specific responses from an original model, thereby establishing unique fingerprints. Our scheme assesses the effectiveness of these queries on a suspect model to determine whether it has been derived from the original model. ProFLingo offers a non-invasive approach, which neither requires knowledge of the suspect model nor modifications to the base model or its training process. To the best of our knowledge, our method represents the first black-box fingerprinting technique for IP protection for LLMs. Our source code and generated queries are available at: https://github.com/hengvt/ProFLingo.
Authors: Yuyang Zhang, Shahriar Talebi, Na Li
Abstract: In this paper, we focus on learning a linear time-invariant (LTI) model with low-dimensional latent variables but high-dimensional observations. We provide an algorithm that recovers the high-dimensional features, i.e. column space of the observer, embeds the data into low dimensions and learns the low-dimensional model parameters. Our algorithm enjoys a sample complexity guarantee of order $\tilde{\mathcal{O}}(n/\epsilon^2)$, where $n$ is the observation dimension. We further establish a fundamental lower bound indicating this complexity bound is optimal up to logarithmic factors and dimension-independent constants. We show that this inevitable linear factor of $n$ is due to the learning error of the observer's column space in the presence of high-dimensional noises. Extending our results, we consider a meta-learning problem inspired by various real-world applications, where the observer column space can be collectively learned from datasets of multiple LTI systems. An end-to-end algorithm is then proposed, facilitating learning LTI systems from a meta-dataset which breaks the sample complexity lower bound in certain scenarios.
Authors: Changshuai Wei, Benjamin Zelditch, Joyce Chen, Andre Assuncao Silva T Ribeiro, Jingyi Kenneth Tay, Borja Ocejo Elizondo, Keerthi Selvaraj, Aman Gupta, Licurgo Benemann De Almeida
Abstract: Computational marketing has become increasingly important in today's digital world, facing challenges such as massive heterogeneous data, multi-channel customer journeys, and limited marketing budgets. In this paper, we propose a general framework for marketing AI systems, the Neural Optimization with Adaptive Heuristics (NOAH) framework. NOAH is the first general framework for marketing optimization that considers both to-business (2B) and to-consumer (2C) products, as well as both owned and paid channels. We describe key modules of the NOAH framework, including prediction, optimization, and adaptive heuristics, providing examples for bidding and content optimization. We then detail the successful application of NOAH to LinkedIn's email marketing system, showcasing significant wins over the legacy ranking system. Additionally, we share details and insights that are broadly useful, particularly on: (i) addressing delayed feedback with lifetime value, (ii) performing large-scale linear programming with randomization, (iii) improving retrieval with audience expansion, (iv) reducing signal dilution in targeting tests, and (v) handling zero-inflated heavy-tail metrics in statistical testing.
Authors: Rudolf Herdt, Peter Maass
Abstract: We investigate how generated structures of GANs correlate with their activations in hidden layers, with the purpose of better understanding the inner workings of those models and being able to paint structures with unconditionally trained GANs. This gives us more control over the generated images, allowing to generate them from a semantic segmentation map while not requiring such a segmentation in the training data. To this end we introduce the concept of tileable features, allowing us to identify activations that work well for painting.
Authors: Fan Wang, Chuan Lin, Yang Cao, Yu Kang
Abstract: In-context learning (ICL) empowers generative models to address new tasks effectively and efficiently on the fly, without relying on any artificially crafted optimization techniques. In this paper, we study extending ICL to address a broader range of tasks with an extended learning horizon and higher improvement potential, namely General-Purpose In-Context Learning (GPICL). To this end, we introduce two lightweight benchmarks specifically crafted to train and evaluate GPICL functionalities. Each benchmark encompasses a vast number of tasks characterized by significant task variance, facilitating meta-training that minimizes inductive bias. These tasks are also crafted to promote long-horizon in-context learning through continuous generation and interaction. These characteristics necessitate the models to leverage contexts and history interactions to enhance their capabilities, across domains such as language modeling, decision-making, and world modeling. Our experiments on the baseline models demonstrate that meta-training with minimal inductive bias and ICL from the ground up is feasible across all the domains we've discussed. Additionally, our findings indicate that the scale of parameters alone may not be crucial for ICL or GPICL, suggesting alternative approaches such as increasing the scale of contexts and memory states.
Authors: Yunze Man, Liang-Yan Gui, Yu-Xiong Wang
Abstract: Being able to carry out complicated vision language reasoning tasks in 3D space represents a significant milestone in developing household robots and human-centered embodied AI. In this work, we demonstrate that a critical and distinct challenge in 3D vision language reasoning is situational awareness, which incorporates two key components: (1) The autonomous agent grounds its self-location based on a language prompt. (2) The agent answers open-ended questions from the perspective of its calculated position. To address this challenge, we introduce SIG3D, an end-to-end Situation-Grounded model for 3D vision language reasoning. We tokenize the 3D scene into sparse voxel representation and propose a language-grounded situation estimator, followed by a situated question answering module. Experiments on the SQA3D and ScanQA datasets show that SIG3D outperforms state-of-the-art models in situation estimation and question answering by a large margin (e.g., an enhancement of over 30% on situation estimation accuracy). Subsequent analysis corroborates our architectural design choices, explores the distinct functions of visual and textual tokens, and highlights the importance of situational awareness in the domain of 3D question answering.
Authors: Adane Nega Tarekegn
Abstract: The news landscape is continuously evolving, with an ever-increasing volume of information from around the world. Automated event detection within this vast data repository is essential for monitoring, identifying, and categorizing significant news occurrences across diverse platforms. This paper presents an event detection framework that leverages Large Language Models (LLMs) combined with clustering analysis to detect news events from the Global Database of Events, Language, and Tone (GDELT). The framework enhances event clustering through both pre-event detection tasks (keyword extraction and text embedding) and post-event detection tasks (event summarization and topic labeling). We also evaluate the impact of various textual embeddings on the quality of clustering outcomes, ensuring robust news categorization. Additionally, we introduce a novel Cluster Stability Assessment Index (CSAI) to assess the validity and robustness of clustering results. CSAI utilizes latent feature vectors to provide a new way of measuring clustering quality. Our experiments indicate that combining LLM embeddings with clustering algorithms yields the best results, demonstrating greater robustness in terms of CSAI scores. Moreover, post-event detection tasks generate meaningful insights, facilitating effective interpretation of event clustering results. Overall, our experimental results indicate that the proposed framework offers valuable insights and could enhance the accuracy and depth of news reporting.
Authors: Sophia Hager, Kathleen Hablutzel, Katherine M. Kinnaird
Abstract: Despite the innovations in deep learning and generative AI, creating long term structure as well as the layers of repeated structure common in musical works remains an open challenge in music generation. We propose an attention layer that uses a novel approach applying user-supplied self-similarity matrices to previous time steps, and demonstrate it in our Similarity Incentivized Neural Generator (SING) system, a deep learning autonomous music generation system with two layers. The first is a vanilla Long Short Term Memory layer, and the second is the proposed attention layer. During generation, this attention mechanism imposes a suggested structure from a template piece on the generated music. We train SING on the MAESTRO dataset using a novel variable batching method, and compare its performance to the same model without the attention mechanism. The addition of our proposed attention mechanism significantly improves the network's ability to replicate specific structures, and it performs better on an unseen test set than a model without the attention mechanism.
Authors: Hao Wang, Ye Wang, Xiangyu Yang
Abstract: This paper considers the problem of minimizing the sum of a smooth function and the Schatten-$p$ norm of the matrix. Our contribution involves proposing accelerated iteratively reweighted nuclear norm methods designed for solving the nonconvex low-rank minimization problem. Two major novelties characterize our approach. Firstly, the proposed method possesses a rank identification property, enabling the provable identification of the "correct" rank of the stationary point within a finite number of iterations. Secondly, we introduce an adaptive updating strategy for smoothing parameters. This strategy automatically fixes parameters associated with zero singular values as constants upon detecting the "correct" rank while quickly driving the rest of the parameters to zero. This adaptive behavior transforms the algorithm into one that effectively solves smooth problems after a few iterations, setting our work apart from existing iteratively reweighted methods for low-rank optimization. We prove the global convergence of the proposed algorithm, guaranteeing that every limit point of the iterates is a critical point. Furthermore, a local convergence rate analysis is provided under the Kurdyka-{\L}ojasiewicz property. We conduct numerical experiments using both synthetic and real data to showcase our algorithm's efficiency and superiority over existing methods.
Authors: Alex Lence, Ahmad Fall, Federica Granese, Blaise Hanczar, Joe-Elie Salem, Jean-Daniel Zucker, Edi Prifti
Abstract: In this work, we address the challenge of reconstructing the complete 12-lead ECG signal from incomplete parts of it. We focus on two main scenarii: (i) reconstructing missing signal segments within an ECG lead and (ii) recovering missing leads from a single-lead. We propose a model with a U-Net architecture trained on a novel objective function to address the reconstruction problem. This function incorporates both spatial and temporal aspects of the ECG by combining the distance in amplitude between the reconstructed and real signals with the signal trend. Through comprehensive assessments using both a real-life dataset and a publicly accessible one, we demonstrate that the proposed approach consistently outperforms state-of-the-art methods based on generative adversarial networks and a CopyPaste strategy. Our proposed model demonstrates superior performance in standard distortion metrics and preserves critical ECG characteristics, particularly the P, Q, R, S, and T wave coordinates. Two emerging clinical applications emphasize the relevance of our work. The first is the increasing need to digitize paper-stored ECGs for utilization in AI-based applications (automatic annotation and risk-quantification), often limited to digital ECG complete 10s recordings. The second is the widespread use of wearable devices that record ECGs but typically capture only a small subset of the 12 standard leads. In both cases, a non-negligible amount of information is lost or not recorded, which our approach aims to recover to overcome these limitations.
Authors: Platon Lukyanenko, Joshua Mayourian, Mingxuan Liu, John K. Triedman, Sunil J. Ghelani, William G. La Cava
Abstract: Several recent high-impact studies leverage large hospital-owned electrocardiographic (ECG) databases to model and predict patient mortality. MIMIC-IV, released September 2023, is the first comparable public dataset and includes 800,000 ECGs from a U.S. hospital system. Previously, the largest public ECG dataset was Code-15, containing 345,000 ECGs collected during routine care in Brazil. These datasets now provide an excellent resource for a broader audience to explore ECG survival modeling. Here, we benchmark survival model performance on Code-15 and MIMIC-IV with two neural network architectures, compare four deep survival modeling approaches to Cox regressions trained on classifier outputs, and evaluate performance at one to ten years. Our results yield AUROC and concordance scores comparable to past work (circa 0.8) and reasonable AUPRC scores (MIMIC-IV: 0.4-0.5, Code-15: 0.05-0.13) considering the fraction of ECG samples linked to a mortality (MIMIC-IV: 27\%, Code-15: 4\%). When evaluating models on the opposite dataset, AUROC and concordance values drop by 0.1-0.15, which may be due to cohort differences. All code and results are made public.
Authors: Razvan-Gabriel Dumitru, Vikas Yadav, Rishabh Maheshwary, Paul-Ioan Clotan, Sathwik Tejaswi Madhusudhan, Mihai Surdeanu
Abstract: We present a simple variable quantization approach that quantizes different layers of a large language model (LLM) at different bit levels. Specifically, we quantize the most important layers to higher bit precision and less important layers to lower bits to achieve floating point quantization levels. We propose two effective strategies to measure the importance of layers within LLMs: the first measures the importance of a layer based on how different its output embeddings are from the input embeddings (the higher the better); the second estimates the importance of a layer using the number of layer weights that are much larger than average (the smaller the better). We show that quantizing different layers at varying bits according to our importance scores results in minimal performance drop with a far more compressed model size. Finally, we present several practical key takeaways from our variable layer-wise quantization experiments: (a) LLM performance under variable quantization remains close to the original model until 25-50% of layers are moved in lower quantization using our proposed ordering but only until 5-10% if moved using no specific ordering; (b) Quantizing LLMs to lower bits performs substantially better than pruning unless extreme quantization (2-bit) is used; and (c) Layer-wise quantization to lower bits works better in the case of larger LLMs with more layers compared to smaller LLMs with fewer layers. The code used to run the experiments is available at: https://github.com/RazvanDu/LayerwiseQuant.
Authors: Francesco Di Salvo, Sebastian Doerrich, Christian Ledig
Abstract: The integration of neural-network-based systems into clinical practice is limited by challenges related to domain generalization and robustness. The computer vision community established benchmarks such as ImageNet-C as a fundamental prerequisite to measure progress towards those challenges. Similar datasets are largely absent in the medical imaging community which lacks a comprehensive benchmark that spans across imaging modalities and applications. To address this gap, we create and open-source MedMNIST-C, a benchmark dataset based on the MedMNIST+ collection covering 12 datasets and 9 imaging modalities. We simulate task and modality-specific image corruptions of varying severity to comprehensively evaluate the robustness of established algorithms against real-world artifacts and distribution shifts. We further provide quantitative evidence that our simple-to-use artificial corruptions allow for highly performant, lightweight data augmentation to enhance model robustness. Unlike traditional, generic augmentation strategies, our approach leverages domain knowledge, exhibiting significantly higher robustness when compared to widely adopted methods. By introducing MedMNIST-C and open-sourcing the corresponding library allowing for targeted data augmentations, we contribute to the development of increasingly robust methods tailored to the challenges of medical imaging. The code is available at https://github.com/francescodisalvo05/medmnistc-api}{github.com/francescodisalvo05/medmnistc-api .
Authors: Sedigheh Eslami, Gerard de Melo
Abstract: Contrastive Language--Image Pre-training (CLIP) has manifested remarkable improvements in zero-shot classification and cross-modal vision-language tasks. Yet, from a geometrical point of view, the CLIP embedding space has been found to have a pronounced modality gap. This gap renders the embedding space overly sparse and disconnected, with different modalities being densely distributed in distinct subregions of the hypersphere. In this work, we aim at answering two main questions: 1. Does sharing the parameter space between the multi-modal encoders reduce the modality gap? 2. Can the gap be mitigated by pushing apart the uni-modal embeddings via intra-modality separation? We design AlignCLIP, in order to answer these questions and show that answers to both questions are positive. Through extensive experiments, we show that AlignCLIP achieves noticeable enhancements in the cross-modal alignment of the embeddings, and thereby, reduces the modality gap, while maintaining the performance across several downstream evaluations, such as zero-shot image classification, zero-shot multi-modal retrieval and zero-shot semantic text similarity.