Authors: Bishal Thapaliya, Esra Akbas, Ram Sapkota, Bhaskar Ray, Vince Calhoun, Jingyu Liu
Abstract: Resting-state functional magnetic resonance imaging (rs-fMRI) offers valuable insights into the human brain's functional organization and is a powerful tool for investigating the relationship between brain function and cognitive processes, as it allows for the functional organization of the brain to be captured without relying on a specific task or stimuli. In this study, we introduce a novel attention mechanism for graphs with subnetworks, named Self-Clustering Graph Transformer (SCGT), designed to handle the issue of uniform node updates in graph transformers. By using static functional connectivity (FC) correlation features as input to the transformer model, SCGT effectively captures the sub-network structure of the brain by performing cluster-specific updates to the nodes, unlike uniform node updates in vanilla graph transformers, further allowing us to learn and interpret the subclusters. We validate our approach on the Adolescent Brain Cognitive Development (ABCD) dataset, comprising 7,957 participants, for the prediction of total cognitive score and gender classification. Our results demonstrate that SCGT outperforms the vanilla graph transformer method and other recent models, offering a promising tool for modeling brain functional connectivity and interpreting the underlying subnetwork structures.
Authors: Yicheng Leng, Syed Muhammad Anwar, Islem Rekik, Sen He, Eung-Joo Lee
Abstract: Functional Magnetic Resonance Imaging (fMRI) provides useful insights into the brain function both during task or rest. Representing fMRI data using correlation matrices is found to be a reliable method of analyzing the inherent connectivity of the brain in the resting and active states. Graph Neural Networks (GNNs) have been widely used for brain network analysis due to their inherent explainability capability. In this work, we introduce a novel framework using contrastive self-supervised learning graph transformers, incorporating a brain network transformer encoder with random graph alterations. The proposed network leverages both contrastive learning and graph alterations to effectively train the graph transformer for autism detection. Our approach, tested on Autism Brain Imaging Data Exchange (ABIDE) data, demonstrates superior autism detection, achieving an AUROC of 82.6 and an accuracy of 74%, surpassing current state-of-the-art methods.
Authors: Anindita Chattopadhyay, Siddharth Bisariya, Vijay Kumar Sutrakar
Abstract: In the evolving landscape of integrated circuit design, detecting Hardware Trojans (HTs) within a multi entity based design cycle presents significant challenges. This research proposes an innovative machine learning-based methodology for identifying malicious logic gates in gate-level netlists. By focusing on path retrace algorithms. The methodology is validated across three distinct cases, each employing different machine learning models to classify HTs. Case I utilizes a decision tree algorithm for node-to-node comparisons, significantly improving detection accuracy through the integration of Principal Component Analysis (PCA). Case II introduces a graph-to-graph classification using a Graph Neural Network (GNN) model, enabling the differentiation between normal and Trojan-infected circuit designs. Case III applies GNN-based node classification to identify individual compromised nodes and its location. Additionally, nearest neighbor (NN) method has been combined with GNN graph-to-graph in Case II and GNN node-to-node in Case III. Despite the potential of GNN model graph-to-graph classification, NN approach demonstrated superior performance, with the first nearest neighbor (1st NN) achieving 73.2% accuracy and the second nearest neighbor (2nd NN) method reaching 97.7%. In comparison, the GNN model achieved an accuracy of 62.8%. Similarly, GNN model node-to-node classification, NN approach demonstrated superior performance, with the 1st NN achieving 93% accuracy and the 2nd NN method reaching 97.7%. In comparison, the GNN model achieved an accuracy of 79.8%. However, higher and higher NN will lead to large code coverage for the identification of HTs.
Authors: Tasnim Ahmed, Salimur Choudhury
Abstract: Artificial Intelligence-Generated Content, a subset of Generative Artificial Intelligence, holds significant potential for advancing the e-health sector by generating diverse forms of data. In this paper, we propose an end-to-end class-conditioned framework that addresses the challenge of data scarcity in health applications by generating synthetic medical images and text data, evaluating on practical applications such as retinopathy detection, skin infections and mental health assessments. Our framework integrates Diffusion and Large Language Models (LLMs) to generate data that closely match real-world patterns, which is essential for improving downstream task performance and model robustness in e-health applications. Experimental results demonstrate that the synthetic images produced by the proposed diffusion model outperform traditional GAN architectures. Similarly, in the text modality, data generated by uncensored LLM achieves significantly better alignment with real-world data than censored models in replicating the authentic tone.
Authors: Junlan Chen, Pei Liu, Zihao Zhang, Hongyi Zhao, Yufei Ji, Ziyuan Pu
Abstract: Trajectory prediction methods have been widely applied in autonomous driving technologies. Although the overall performance accuracy of trajectory prediction is relatively high, the lack of trajectory data in critical scenarios in the training data leads to the long-tail phenomenon. Normally, the trajectories of the tail data are more critical and more difficult to predict and may include rare scenarios such as crashes. To solve this problem, we extracted the trajectory data from real-world crash scenarios, which contain more long-tail data. Meanwhile, based on the trajectory data in this scenario, we integrated graph-based risk information and diffusion with transformer and proposed the Risk-Informed Diffusion Transformer (RI-DiT) trajectory prediction method. Extensive experiments were conducted on trajectory data in the real-world crash scenario, and the results show that the algorithm we proposed has good performance. When predicting the data of the tail 10\% (Top 10\%), the minADE and minFDE indicators are 0.016/2.667 m. At the same time, we showed the trajectory conditions of different long-tail distributions. The distribution of trajectory data is closer to the tail, the less smooth the trajectory is. Through the trajectory data in real-world crash scenarios, Our work expands the methods to overcome the long-tail challenges in trajectory prediction. Our method, RI-DiT, integrates inverse time to collision (ITTC) and the feature of traffic flow, which can predict long-tail trajectories more accurately and improve the safety of autonomous driving systems.
Authors: Wensheng Gan, Zhenyao Ning, Zhenlian Qi, Philip S. Yu
Abstract: As the era of big data arrives, traditional artificial intelligence algorithms have difficulty processing the demands of massive and diverse data. Mixture of experts (MoE) has shown excellent performance and broad application prospects. This paper provides an in-depth review and analysis of the latest progress in this field from multiple perspectives, including the basic principles, algorithmic models, key technical challenges, and application practices of MoE. First, we introduce the basic concept of MoE and its core idea and elaborate on its advantages over traditional single models. Then, we discuss the basic architecture of MoE and its main components, including the gating network, expert networks, and learning algorithms. Next, we review the applications of MoE in addressing key technical issues in big data. For each challenge, we provide specific MoE solutions and their innovations. Furthermore, we summarize the typical use cases of MoE in various application domains. This fully demonstrates the powerful capability of MoE in big data processing. We also analyze the advantages of MoE in big data environments. Finally, we explore the future development trends of MoE. We believe that MoE will become an important paradigm of artificial intelligence in the era of big data. In summary, this paper systematically elaborates on the principles, techniques, and applications of MoE in big data processing, providing theoretical and practical references to further promote the application of MoE in real scenarios.
Authors: Zakaria El Mrabet, Daisy Flora Selvaraj, Prakash Ranganathan
Abstract: Synchrophasor technology or phasor measurement units (PMUs) are known to detect multiple type of oscillations or faults better than Supervisory Control and Data Acquisition (SCADA) systems, but the volume of Bigdata (e.g., 30-120 samples per second on a single PMU) generated by these sensors at the aggregator level (e.g., several PMUs) requires special handling. Conventional machine learning or data mining methods are not suitable to handle such larger streaming realtime data. This is primarily due to latencies associated with cloud environments (e.g., at an aggregator or PDC level), and thus necessitates the need for local computing to move the data on the edge (or locally at the PMU level) for processing. This requires faster real-time streaming algorithms to be processed at the local level (e.g., typically by a Field Programmable Gate Array (FPGA) based controllers). This paper proposes a transfer learning-based hoeffding tree with ADWIN (THAT) method to detect anomalous synchrophasor signatures. The proposed algorithm is trained and tested with the OzaBag method. The preliminary results with transfer learning indicate that a computational time saving of 0.7ms is achieved with THAT algorithm (0.34ms) over Ozabag (1.04ms), while the accuracy of both methods in detecting fault events remains at 94% for four signatures.
Authors: Tian Xie, Pavan Rauch, Xueru Zhang
Abstract: When machine learning (ML) algorithms are used to automate human-related decisions, human agents may gain knowledge of the decision policy and behave strategically to obtain desirable outcomes. Strategic Classification (SC) has been proposed to address the interplay between agents and decision-makers. Prior work on SC has relied on assumptions that agents are perfectly or approximately rational, responding to decision policies by maximizing their utilities. Verifying these assumptions is challenging due to the difficulty of collecting real-world agent responses. Meanwhile, the growing adoption of large language models (LLMs) makes it increasingly likely that human agents in SC settings will seek advice from these tools. We propose using strategic advice generated by LLMs to simulate human agent responses in SC. Specifically, we examine five critical SC scenarios -- hiring, loan applications, school admissions, personal income, and public assistance programs -- and simulate how human agents with diverse profiles seek advice from LLMs. We then compare the resulting agent responses with the best responses generated by existing theoretical models. Our findings reveal that: (i) LLMs and theoretical models generally lead to agent score or qualification changes in the same direction across most settings, with both achieving similar levels of fairness; (ii) state-of-the-art commercial LLMs (e.g., GPT-3.5, GPT-4) consistently provide helpful suggestions, though these suggestions typically do not result in maximal score or qualification improvements; and (iii) LLMs tend to produce more diverse agent responses, often favoring more balanced effort allocation strategies. These results suggest that theoretical models align with LLMs to some extent and that leveraging LLMs to simulate more realistic agent responses offers a promising approach to designing trustworthy ML systems.
Authors: Alicia Vidler, Toby Walsh
Abstract: Large Language Models (LLMs) are increasingly being used to simulate human-like decision making in agent-based financial market models (ABMs). As models become more powerful and accessible, researchers can now incorporate individual LLM decisions into ABM environments. However, integration may introduce inherent biases that need careful evaluation. In this paper we test three state-of-the-art GPT models for bias using two model sampling approaches: one-shot and few-shot API queries. We observe significant variations in distributions of outputs between specific models, and model sub versions, with GPT-4o-Mini-2024-07-18 showing notably better performance (32-43% yes responses) compared to GPT-4-0125-preview's extreme bias (98-99% yes responses). We show that sampling methods and model sub-versions significantly impact results: repeated independent API calls produce different distributions compared to batch sampling within a single call. While no current GPT model can simultaneously achieve a uniform distribution and Markovian properties in one-shot testing, few-shot sampling can approach uniform distributions under certain conditions. We explore the Temperature parameter, providing a definition and comparative results. We further compare our results to true random binary series and test specifically for the common human bias of Negative Recency - finding LLMs have a mixed ability to 'beat' humans in this one regard. These findings emphasise the critical importance of careful LLM integration into ABMs for financial markets and more broadly.
Authors: Vincenzo Dentamaro, Paolo Giglio, Donato Impedovo, Giuseppe Pirlo
Abstract: The widespread use of artificial intelligence deep neural networks in fields such as medicine and engineering necessitates understanding their decision-making processes. Current explainability methods often produce inconsistent results and struggle to highlight essential signals influencing model inferences. This paper introduces the Evolutionary Independent Deterministic Explanation (EVIDENCE) theory, a novel approach offering a deterministic, model-independent method for extracting significant signals from black-box models. EVIDENCE theory, grounded in robust mathematical formalization, is validated through empirical tests on diverse datasets, including COVID-19 audio diagnostics, Parkinson's disease voice recordings, and the George Tzanetakis music classification dataset (GTZAN). Practical applications of EVIDENCE include improving diagnostic accuracy in healthcare and enhancing audio signal analysis. For instance, in the COVID-19 use case, EVIDENCE-filtered spectrograms fed into a frozen Residual Network with 50 layers improved precision by 32% for positive cases and increased the area under the curve (AUC) by 16% compared to baseline models. For Parkinson's disease classification, EVIDENCE achieved near-perfect precision and sensitivity, with a macro average F1-Score of 0.997. In the GTZAN, EVIDENCE maintained a high AUC of 0.996, demonstrating its efficacy in filtering relevant features for accurate genre classification. EVIDENCE outperformed other Explainable Artificial Intelligence (XAI) methods such as LIME, SHAP, and GradCAM in almost all metrics. These findings indicate that EVIDENCE not only improves classification accuracy but also provides a transparent and reproducible explanation mechanism, crucial for advancing the trustworthiness and applicability of AI systems in real-world settings.
Authors: Anyang Peng, Xinzijian Liu, Ming-Yu Guo, Linfeng Zhang, Han Wang
Abstract: Inspired by the success of Large Language Models (LLMs), the development of Large Atom Models (LAMs) has gained significant momentum in scientific computation. Since 2022, the Deep Potential team has been actively pretraining LAMs and launched the OpenLAM Initiative to develop an open-source foundation model spanning the periodic table. A core objective is establishing comprehensive benchmarks for reliable LAM evaluation, addressing limitations in existing datasets. As a first step, the LAM Crystal Philately competition has collected over 19.8 million valid structures, including 1 million on the OpenLAM convex hull, driving advancements in generative modeling and materials science applications.
Authors: Duy Hoang, Huy Ngo, Khoi Pham, Tri Nguyen, Gia Bao, Huy Phan
Abstract: Contrastive learning has become pivotal in unsupervised representation learning, with frameworks like Momentum Contrast (MoCo) effectively utilizing large negative sample sets to extract discriminative features. However, traditional approaches often overlook the full potential of key embeddings and are susceptible to performance degradation from noisy negative samples in the memory bank. This study addresses these challenges by proposing an enhanced contrastive learning framework that incorporates two key innovations. First, we introduce a dual-view loss function, which ensures balanced optimization of both query and key embeddings, improving representation quality. Second, we develop a selective negative sampling strategy that emphasizes the most challenging negatives based on cosine similarity, mitigating the impact of noise and enhancing feature discrimination. Extensive experiments demonstrate that our framework achieves superior performance on downstream tasks, delivering robust and well-structured representations. These results highlight the potential of optimized contrastive mechanisms to advance unsupervised learning and extend its applicability across domains such as computer vision and natural language processing
Authors: Haoran Song, Jiarui Feng, Guangfu Li, Michael Province, Philip Payne, Yixin Chen, Fuhai Li
Abstract: In real-world scientific discovery, human beings always make use of the accumulated prior knowledge with imagination pick select one or a few most promising hypotheses from large and noisy data analysis results. In this study, we introduce a new type of graph structure, the text-numeric graph (TNG), which is defined as graph entities and associations have both text-attributed information and numeric information. The TNG is an ideal data structure model for novel scientific discovery via graph reasoning because it integrates human-understandable textual annotations or prior knowledge, with numeric values that represent the observed or activation levels of graph entities or associations in different samples. Together both the textual information and numeric values determine the importance of graph entities and associations in graph reasoning for novel scientific knowledge discovery. We further propose integrating large language models (LLMs) and graph neural networks (GNNs) to analyze the TNGs for graph understanding and reasoning. To demonstrate the utility, we generated the text-omic(numeric) signaling graphs (TOSG), as one type of TNGs, in which all graphs have the same entities, associations and annotations, but have sample-specific entity numeric (omic) values using single cell RNAseq (scRNAseq) datasets of different diseases. We proposed joint LLM-GNN models for key entity mining and signaling pathway mining on the TOSGs. The evaluation results showed the LLM-GNN and TNGs models significantly improve classification accuracy and network inference. In conclusion, the TNGs and joint LLM-GNN models are important approaches for scientific discovery.
Authors: Haoyun Xing, Kaiyan Jin, Guice Yao, Jin Zhao, Dichu Xu, Dongsheng Wen
Abstract: A novel Trunk-Branch (TB)-net physics-informed neural network (PINN) architecture is developed, which is a PINN-based method incorporating trunk and branch nets to capture both global and local features. The aim is to solve four main classes of problems: forward flow problem, forward heat transfer problem, inverse heat transfer problem, and transfer learning problem within the porous medium, which are notoriously complex that could not be handled by origin PINN. In the proposed TB-net PINN architecture, a Fully-connected Neural Network (FNN) is used as the trunk net, followed by separated FNNs as the branch nets with respect to outputs, and automatic differentiation is performed for partial derivatives of outputs with respect to inputs by considering various physical loss. The effectiveness and flexibility of the novel TB-net PINN architecture is demonstrated through a collection of forward problems, and transfer learning validates the feasibility of resource reuse. Combining with the superiority over traditional numerical methods in solving inverse problems, the proposed TB-net PINN shows its great potential for practical engineering applications.
Authors: Yongzheng Xie, Hongyu Zhang, Muhammad Ali Babar
Abstract: Multivariate time series anomaly detection is essential for failure management in web application operations, as it directly influences the effectiveness and timeliness of implementing remedial or preventive measures. This task is often framed as a semi-supervised learning problem, where only normal data are available for model training, primarily due to the labor-intensive nature of data labeling and the scarcity of anomalous data. Existing semi-supervised methods often detect anomalies by capturing intra-variate temporal dependencies and/or inter-variate relationships to learn normal patterns, flagging timestamps that deviate from these patterns as anomalies. However, these approaches often fail to capture salient intra-variate temporal and inter-variate dependencies in time series due to their focus on excessively fine granularity, leading to suboptimal performance. In this study, we introduce MtsCID, a novel semi-supervised multivariate time series anomaly detection method. MtsCID employs a dual network architecture: one network operates on the attention maps of multi-scale intra-variate patches for coarse-grained temporal dependency learning, while the other works on variates to capture coarse-grained inter-variate relationships through convolution and interaction with sinusoidal prototypes. This design enhances the ability to capture the patterns from both intra-variate temporal dependencies and inter-variate relationships, resulting in improved performance. Extensive experiments across seven widely used datasets demonstrate that MtsCID achieves performance comparable or superior to state-of-the-art benchmark methods.
Authors: Lo Pang-Yun Ting, Zhen Tan, Hong-Pei Chen, Cheng-Te Li, Po-Lin Chen, Kun-Ta Chuang, Huan Liu
Abstract: Early detection of patient deterioration is essential for timely treatment, with vital signs like heart rates being key health indicators. Existing methods tend to solely analyze vital sign waveforms, ignoring transition relationships of waveforms within each vital sign and the correlation strengths among various vital signs. Such studies often overlook nuanced illness deterioration, which is the early sign of worsening health but is difficult to detect. In this paper, we introduce CAND, a novel method that organizes the transition relationships and the correlations within and among vital signs as domain-specific and cross-domain knowledge. CAND jointly models these knowledge in a unified representation space, considerably enhancing the early detection of nuanced illness deterioration. In addition, CAND integrates a Bayesian inference method that utilizes augmented knowledge from domain-specific and cross-domain knowledge to address the ambiguities in correlation strengths. With this architecture, the correlation strengths can be effectively inferred to guide joint modeling and enhance representations of vital signs. This allows a more holistic and accurate interpretation of patient health. Our experiments on a real-world ICU dataset demonstrate that CAND significantly outperforms existing methods in both effectiveness and earliness in detecting nuanced illness deterioration. Moreover, we conduct a case study for the interpretable detection process to showcase the practicality of CAND.
Authors: Ozan Baris, Yizhuo Chen, Gaofeng Dong, Liying Han, Tomoyoshi Kimura, Pengrui Quan, Ruijie Wang, Tianchen Wang, Tarek Abdelzaher, Mario Berg\'es, Paul Pu Liang, Mani Srivastava
Abstract: Methods from machine learning (ML) have transformed the implementation of Perception-Cognition-Communication-Action loops in Cyber-Physical Systems (CPS) and the Internet of Things (IoT), replacing mechanistic and basic statistical models with those derived from data. However, the first generation of ML approaches, which depend on supervised learning with annotated data to create task-specific models, faces significant limitations in scaling to the diverse sensor modalities, deployment configurations, application tasks, and operating dynamics characterizing real-world CPS-IoT systems. The success of task-agnostic foundation models (FMs), including multimodal large language models (LLMs), in addressing similar challenges across natural language, computer vision, and human speech has generated considerable enthusiasm for and exploration of FMs and LLMs as flexible building blocks in CPS-IoT analytics pipelines, promising to reduce the need for costly task-specific engineering. Nonetheless, a significant gap persists between the current capabilities of FMs and LLMs in the CPS-IoT domain and the requirements they must meet to be viable for CPS-IoT applications. In this paper, we analyze and characterize this gap through a thorough examination of the state of the art and our research, which extends beyond it in various dimensions. Based on the results of our analysis and research, we identify essential desiderata that CPS-IoT domain-specific FMs and LLMs must satisfy to bridge this gap. We also propose actions by CPS-IoT researchers to collaborate in developing key community resources necessary for establishing FMs and LLMs as foundational tools for the next generation of CPS-IoT systems.
Authors: Ahmed Alagha, Hadi Otrok, Shakti Singh, Rabeb Mizouni, Jamal Bentahar
Abstract: Deep Reinforcement Learning (DRL) has emerged as a powerful paradigm for solving complex problems. However, its full potential remains inaccessible to a broader audience due to its complexity, which requires expertise in training and designing DRL solutions, high computational capabilities, and sometimes access to pre-trained models. This necessitates the need for hassle-free services that increase the availability of DRL solutions to a variety of users. To enhance the accessibility to DRL services, this paper proposes a novel blockchain-based crowdsourced DRL as a Service (DRLaaS) framework. The framework provides DRL-related services to users, covering two types of tasks: DRL training and model sharing. Through crowdsourcing, users could benefit from the expertise and computational capabilities of workers to train DRL solutions. Model sharing could help users gain access to pre-trained models, shared by workers in return for incentives, which can help train new DRL solutions using methods in knowledge transfer. The DRLaaS framework is built on top of a Consortium Blockchain to enable traceable and autonomous execution. Smart Contracts are designed to manage worker and model allocation, which are stored using the InterPlanetary File System (IPFS) to ensure tamper-proof data distribution. The framework is tested on several DRL applications, proving its efficacy.
Authors: Mahdi Movahedian Moghaddam, Kourosh Parand, Saeed Reza Kheradpisheh
Abstract: In this paper, we present the Residual Integral Solver Network (RISN), a novel neural network architecture designed to solve a wide range of integral and integro-differential equations, including one-dimensional, multi-dimensional, ordinary and partial integro-differential, systems, and fractional types. RISN integrates residual connections with high-accurate numerical methods such as Gaussian quadrature and fractional derivative operational matrices, enabling it to achieve higher accuracy and stability than traditional Physics-Informed Neural Networks (PINN). The residual connections help mitigate vanishing gradient issues, allowing RISN to handle deeper networks and more complex kernels, particularly in multi-dimensional problems. Through extensive experiments, we demonstrate that RISN consistently outperforms PINN, achieving significantly lower Mean Absolute Errors (MAE) across various types of equations. The results highlight RISN's robustness and efficiency in solving challenging integral and integro-differential problems, making it a valuable tool for real-world applications where traditional methods often struggle.
Authors: Elham Kiyani, Khemraj Shukla, Jorge F. Urb\'an, J\'er\^ome Darbon, George Em Karniadakis
Abstract: Physics-Informed Neural Networks (PINNs) have revolutionized the computation of PDE solutions by integrating partial differential equations (PDEs) into the neural network's training process as soft constraints, becoming an important component of the scientific machine learning (SciML) ecosystem. In its current implementation, PINNs are mainly optimized using first-order methods like Adam, as well as quasi-Newton methods such as BFGS and its low-memory variant, L-BFGS. However, these optimizers often struggle with highly non-linear and non-convex loss landscapes, leading to challenges such as slow convergence, local minima entrapment, and (non)degenerate saddle points. In this study, we investigate the performance of Self-Scaled Broyden (SSBroyden) methods and other advanced quasi-Newton schemes, including BFGS and L-BFGS with different line search strategies approaches. These methods dynamically rescale updates based on historical gradient information, thus enhancing training efficiency and accuracy. We systematically compare these optimizers on key challenging linear, stiff, multi-scale and non-linear PDEs benchmarks, including the Burgers, Allen-Cahn, Kuramoto-Sivashinsky, and Ginzburg-Landau equations, and extend our study to Physics-Informed Kolmogorov-Arnold Networks (PIKANs) representation. Our findings provide insights into the effectiveness of second-order optimization strategies in improving the convergence and accurate generalization of PINNs for complex PDEs by orders of magnitude compared to the state-of-the-art.
Authors: J. Pablo Mu\~noz, Jinjie Yuan, Nilesh Jain
Abstract: The rapid expansion of Large Language Models (LLMs) has posed significant challenges regarding the computational resources required for fine-tuning and deployment. Recent advancements in low-rank adapters have demonstrated their efficacy in parameter-efficient fine-tuning (PEFT) of these models. This retrospective paper comprehensively discusses innovative approaches that synergize low-rank representations with Neural Architecture Search (NAS) techniques, particularly weight-sharing super-networks. Robust solutions for compressing and fine-tuning large pre-trained models are developed by integrating these methodologies. Our analysis highlights the potential of these combined strategies to democratize the use of LLMs, making them more accessible for deployment in resource-constrained environments. The resulting models exhibit reduced memory footprints and faster inference times, paving the way for more practical and scalable applications of LLMs. Models and code are available at https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning.
URLs: https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning.
Authors: Chuang Zhao, Hui Tang, Jiheng Zhang, Xiaomeng Li
Abstract: Accurate healthcare prediction is essential for improving patient outcomes. Existing work primarily leverages advanced frameworks like attention or graph networks to capture the intricate collaborative (CO) signals in electronic health records. However, prediction for rare diseases remains challenging due to limited co-occurrence and inadequately tailored approaches. To address this issue, this paper proposes UDC, a novel method that unveils discrete clues to bridge consistent textual knowledge and CO signals within a unified semantic space, thereby enriching the representation semantics of rare diseases. Specifically, we focus on addressing two key sub-problems: (1) acquiring distinguishable discrete encodings for precise disease representation and (2) achieving semantic alignment between textual knowledge and the CO signals at the code level. For the first sub-problem, we refine the standard vector quantized process to include condition awareness. Additionally, we develop an advanced contrastive approach in the decoding stage, leveraging synthetic and mixed-domain targets as hard negatives to enrich the perceptibility of the reconstructed representation for downstream tasks. For the second sub-problem, we introduce a novel codebook update strategy using co-teacher distillation. This approach facilitates bidirectional supervision between textual knowledge and CO signals, thereby aligning semantically equivalent information in a shared discrete latent space. Extensive experiments on three datasets demonstrate our superiority.
Authors: Ruidi Chang, Chunyuan Deng, Hanjie Chen
Abstract: Superposition refers to encoding representations of multiple features within a single neuron, which is common in transformers. This property allows neurons to combine and represent multiple features, enabling the model to capture intricate information and handle complex tasks. Despite promising performance, the model's interpretability has been diminished. This paper presents a novel approach to enhance transformer interpretability by regularizing feature superposition. We introduce SAFR, which simply applies regularizations to the loss function to promote monosemantic representations for important tokens while encouraging polysemanticity for correlated token pairs, where important tokens and correlated token pairs are identified via VMASK and attention weights. With a transformer model on two classification tasks, SAFR improves interpretability without compromising prediction performance. Given an input to the model, SAFR provides an explanation by visualizing the neuron allocation and interaction within the MLP layers.
Authors: Taiga Ikeda, Daisuke Miyashita, Jun Deguchi
Abstract: Large-scale approximate nearest neighbor search (ANN) has been gaining attention along with the latest machine learning researches employing ANNs. If the data is too large to fit in memory, it is necessary to search for the most similar vectors to a given query vector from the data stored in storage devices, not from that in memory. The storage device such as NAND flash memory has larger capacity than the memory device such as DRAM, but they also have larger latency to read data. Therefore, ANN methods for storage require completely different approaches from conventional in-memory ANN methods. Since the approximation that the time required for search is determined only by the amount of data fetched from storage holds under reasonable assumptions, our goal is to minimize it while maximizing recall. For partitioning-based ANNs, vectors are partitioned into clusters in the index building phase. In the search phase, some of the clusters are chosen, the vectors in the chosen clusters are fetched from storage, and the nearest vector is retrieved from the fetched vectors. Thus, the key point is to accurately select the clusters containing the ground truth nearest neighbor vectors. We accomplish this by proposing a method to predict the correct clusters by means of a neural network that is gradually refined by alternating supervised learning and duplicated cluster assignment. Compared to state-of-the-art SPANN and an exhaustive method using k-means clustering and linear search, the proposed method achieves 90% recall on SIFT1M with 80% and 58% less data fetched from storage, respectively.
Authors: Yuhan Kang, Zhongdi Luo, Mei Wen, Yang Shi, Jun He, Jianchao Yang, Zeyu Xue, Jing Feng, Xinwang Liu
Abstract: Large Language Models (LLMs) have achieved remarkable success across numerous domains. However, the high time complexity of existing pruning and quantization methods significantly hinders their effective deployment on resource-constrained consumer or edge devices. In this study, we propose a novel Hessian-free Weight Pruning-Quantization (HWPQ) method. HWPQ eliminates the need for computationally intensive Hessian matrix calculations by introducing a contribution-based weight metric, which evaluates the importance of weights without relying on second-order derivatives. Additionally, we employ the Exponentially Weighted Moving Average (EWMA) technique to bypass weight sorting, enabling the selection of weights that contribute most to LLM accuracy and further reducing time complexity. Our approach is extended to support 2:4 structured sparsity pruning, facilitating efficient execution on modern hardware accelerators. Experimental results demonstrate that HWPQ significantly enhances the compression performance of LLaMA2. Compared to state-of-the-art quantization and pruning frameworks, HWPQ achieves average speedups of 5.97x (up to 20.75x) in quantization time and 12.29x (up to 56.02x) in pruning time, while largely preserving model accuracy. Furthermore, we observe a 1.50x inference speedup compared to the baseline.
Authors: Vijay Babu Pamshetti, Wei Zhang, King Jet Tseng, Bor Kiat Ng, Qingyu Yan
Abstract: Battery health estimation is fundamental to ensure battery safety and reduce cost. However, achieving accurate estimation has been challenging due to the batteries' complex nonlinear aging patterns and capacity regeneration phenomena. In this paper, we propose OSL, an optimal signal decomposition-based multi-stage machine learning for battery health estimation. OSL treats battery signals optimally. It uses optimized variational mode decomposition to extract decomposed signals capturing different frequency bands of the original battery signals. It also incorporates a multi-stage learning process to analyze both spatial and temporal battery features effectively. An experimental study is conducted with a public battery aging dataset. OSL demonstrates exceptional performance with a mean error of just 0.26%. It significantly outperforms comparison algorithms, both those without and those with suboptimal signal decomposition and analysis. OSL considers practical battery challenges and can be integrated into real-world battery management systems, offering a good impact on battery monitoring and optimization.
Authors: Qing Li, Jiahui Geng, Zongxiong Chen, Kun Song, Lei Ma, Fakhri Karray
Abstract: Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs). Our investigation reveals that the integration of images significantly shifts the model's internal activations during the forward pass, diverging from those triggered by textual input. Moreover, the safety alignments of LLMs embedded within VLMs are not sufficiently robust to handle the activations discrepancies, making the models vulnerable to even the simplest jailbreaking attacks. To address this issue, we propose an \textbf{internal activation revision} approach that efficiently revises activations during generation, steering the model toward safer outputs. Our framework incorporates revisions at both the layer and head levels, offering control over the model's generation at varying levels of granularity. In addition, we explore three strategies for constructing positive and negative samples and two approaches for extracting revision vectors, resulting in different variants of our method. Comprehensive experiments demonstrate that the internal activation revision method significantly improves the safety of widely used VLMs, reducing attack success rates by an average of 48.94\%, 34.34\%, 43.92\%, and 52.98\% on SafeBench, Safe-Unsafe, Unsafe, and MM-SafetyBench, respectively, while minimally impacting model helpfulness.
Authors: Jiarui Song, Yunheng Shen, Chengbin Hou, Pengyu Wang, Jinbao Wang, Ke Tang, Hairong Lv
Abstract: Personalized Federated Learning (PFL) aims to address the statistical heterogeneity of data across clients by learning the personalized model for each client. Among various PFL approaches, the personalized aggregation-based approach conducts parameter aggregation in the server-side aggregation phase to generate personalized models, and focuses on learning appropriate collaborative relationships among clients for aggregation. However, the collaborative relationships vary in different scenarios and even at different stages of the FL process. To this end, we propose Personalized Federated Learning with Attentive Graph HyperNetworks (FedAGHN), which employs Attentive Graph HyperNetworks (AGHNs) to dynamically capture fine-grained collaborative relationships and generate client-specific personalized initial models. Specifically, AGHNs empower graphs to explicitly model the client-specific collaborative relationships, construct collaboration graphs, and introduce tunable attentive mechanism to derive the collaboration weights, so that the personalized initial models can be obtained by aggregating parameters over the collaboration graphs. Extensive experiments can demonstrate the superiority of FedAGHN. Moreover, a series of visualizations are presented to explore the effectiveness of collaboration graphs learned by FedAGHN.
Authors: Zhiwei Chen, Hao Tang
Abstract: Quantum computing is a transformative technology with wide-ranging applications, and efficient quantum circuit generation is crucial for unlocking its full potential. Current diffusion model approaches based on U-Net architectures, while promising, encounter challenges related to computational efficiency and modeling global context. To address these issues, we propose UDiT,a novel U-Net-style Diffusion Transformer architecture, which combines U-Net's strengths in multi-scale feature extraction with the Transformer's ability to model global context. We demonstrate the framework's effectiveness on two tasks: entanglement generation and unitary compilation, where UDiTQC consistently outperforms existing methods. Additionally, our framework supports tasks such as masking and editing circuits to meet specific physical property requirements. This dual advancement, improving quantum circuit synthesis and refining generative model architectures, marks a significant milestone in the convergence of quantum computing and machine learning research.
Authors: Pauline Rothmann-Brumm, Steven L. Brunton, Isabel Scherl
Abstract: Hydrodynamic pattern formation phenomena in printing and coating processes are still not fully understood. However, fundamental understanding is essential to achieve high-quality printed products and to tune printed patterns according to the needs of a specific application like printed electronics, graphical printing, or biomedical printing. The aim of the paper is to develop an automated pattern classification algorithm based on methods from supervised machine learning and reduced-order modeling. We use the HYPA-p dataset, a large image dataset of gravure-printed images, which shows various types of hydrodynamic pattern formation phenomena. It enables the correlation of printing process parameters and resulting printed patterns for the first time. 26880 images of the HYPA-p dataset have been labeled by a human observer as dot patterns, mixed patterns, or finger patterns; 864000 images (97%) are unlabeled. A singular value decomposition (SVD) is used to find the modes of the labeled images and to reduce the dimensionality of the full dataset by truncation and projection. Selected machine learning classification techniques are trained on the reduced-order data. We investigate the effect of several factors, including classifier choice, whether or not fast Fourier transform (FFT) is used to preprocess the labeled images, data balancing, and data normalization. The best performing model is a k-nearest neighbor (kNN) classifier trained on unbalanced, FFT-transformed data with a test error of 3%, which outperforms a human observer by 7%. Data balancing slightly increases the test error of the kNN-model to 5%, but also increases the recall of the mixed class from 90% to 94%. Finally, we demonstrate how the trained models can be used to predict the pattern class of unlabeled images and how the predictions can be correlated to the printing process parameters, in the form of regime maps.
Authors: Zunhai Su, Zhe Chen, Wang Shen, Hanyu Wei, Linge Li, Huangqi Yu, Kehong Yuan
Abstract: Key-Value (KV) cache facilitates efficient large language models (LLMs) inference by avoiding recomputation of past KVs. As the batch size and context length increase, the oversized KV caches become a significant memory bottleneck, highlighting the need for efficient compression. Existing KV quantization rely on fine-grained quantization or the retention of a significant portion of high bit-widths caches, both of which compromise compression ratio and often fail to maintain robustness at extremely low average bit-widths. In this work, we explore the potential of rotation technique for 2-bit KV quantization and propose RotateKV, which achieves accurate and robust performance through the following innovations: (i) Outlier-Aware Rotation, which utilizes channel-reordering to adapt the rotations to varying channel-wise outlier distributions without sacrificing the computational efficiency of the fast Walsh-Hadamard transform (FWHT); (ii) Pre-RoPE Grouped-Head Rotation, which mitigates the impact of rotary position embedding (RoPE) on proposed outlier-aware rotation and further smooths outliers across heads; (iii) Attention-Sink-Aware Quantization, which leverages the massive activations to precisely identify and protect attention sinks. RotateKV achieves less than 0.3 perplexity (PPL) degradation with 2-bit quantization on WikiText-2 using LLaMA-2-13B, maintains strong CoT reasoning and long-context capabilities, with less than 1.7\% degradation on GSM8K, outperforming existing methods even at lower average bit-widths. RotateKV also showcases a 3.97x reduction in peak memory usage, supports 5.75x larger batch sizes, and achieves a 2.32x speedup in decoding stage.
Authors: Yijiang Liu, Hengyu Fang, Liulu He, Rongyu Zhang, Yichuan Bai, Yuan Du, Li Du
Abstract: Deploying Large Language Models (LLMs) on edge devices is increasingly important, as it eliminates reliance on network connections, reduces expensive API calls, and enhances user privacy. However, on-device deployment is challenging due to the limited computational resources of edge devices. In particular, the key bottleneck stems from memory bandwidth constraints related to weight loading. Weight-only quantization effectively reduces memory access, yet often induces significant accuracy degradation. Recent efforts to incorporate sub-branches have shown promise for mitigating quantization errors, but these methods either lack robust optimization strategies or rely on suboptimal objectives. To address these gaps, we propose FeedBack Quantization (FBQuant), a novel approach inspired by negative feedback mechanisms in automatic control. FBQuant inherently ensures that the reconstructed weights remain bounded by the quantization process, thereby reducing the risk of overfitting. To further offset the additional latency introduced by sub-branches, we develop an efficient CUDA kernel that decreases 60\% of extra inference time. Comprehensive experiments demonstrate the efficiency and effectiveness of FBQuant across various LLMs. Notably, for 3-bit Llama2-7B, FBQuant improves zero-shot accuracy by 1.2\%.
Authors: Jingying Ma, Jinwei Wang, Lanlan Lu, Yexiang Sun, Mengling Feng, Peng Shen, Zhiqin Jiang, Shenda Hong, Luxia Zhang
Abstract: Background: Chronic kidney disease (CKD), a progressive disease with high morbidity and mortality, has become a significant global public health problem. At present, most of the models used for predicting the progression of CKD are static models. We aim to develop a dynamic kidney failure prediction model based on deep learning (KFDeep) for CKD patients, utilizing all available data on common clinical indicators from real-world Electronic Health Records (EHRs) to provide real-time predictions. Findings: A retrospective cohort of 4,587 patients from EHRs of Yinzhou, China, is used as the development dataset (2,752 patients for training, 917 patients for validation) and internal validation dataset (917 patients), while a prospective cohort of 934 patients from the Peking University First Hospital CKD cohort (PKUFH cohort) is used as the external validation dataset. The AUROC of the KFDeep model reaches 0.946 (95\% CI: 0.922-0.970) on the internal validation dataset and 0.805 (95\% CI: 0.763-0.847) on the external validation dataset, both surpassing existing models. The KFDeep model demonstrates stable performance in simulated dynamic scenarios, with the AUROC progressively increasing over time. Both the calibration curve and decision curve analyses confirm that the model is unbiased and safe for practical use, while the SHAP analysis and hidden layer clustering results align with established medical knowledge. Interpretation: The KFDeep model built from real-world EHRs enhances the prediction accuracy of kidney failure without increasing clinical examination costs and can be easily integrated into existing hospital systems, providing physicians with a continuously updated decision-support tool due to its dynamic design.
Authors: Xiaoqing Lian, Jie Zhu, Tianxu Lv, Shiyun Nie, Hang Fan, Guosheng Wu, Yunjun Ge, Lihua Li, Xiangxiang Zeng, Xiang Pan
Abstract: Significant differences in protein structures hinder the generalization of existing drug-target interaction (DTI) models, which often rely heavily on pre-learned binding principles or detailed annotations. In contrast, BioBridge designs an Inductive-Associative pipeline inspired by the workflow of scientists who base their accumulated expertise on drawing insights into novel drug-target pairs from weakly related references. BioBridge predicts novel drug-target interactions using limited sequence data, incorporating multi-level encoders with adversarial training to accumulate transferable binding principles. On these principles basis, BioBridge employs a dynamic prototype meta-learning framework to associate insights from weakly related annotations, enabling robust predictions for previously unseen drug-target pairs. Extensive experiments demonstrate that BioBridge surpasses existing models, especially for unseen proteins. Notably, when only homologous protein binding data is available, BioBridge proves effective for virtual screening of the epidermal growth factor receptor and adenosine receptor, underscoring its potential in drug discovery.
Authors: Tianzi Zhao, Xinran Liu, Zhaoxin Zhang, Dong Zhao, Ning Li, Zhichao Zhang, Xinye Wang
Abstract: Fine-grained IP geolocation plays a critical role in applications such as location-based services and cybersecurity. Most existing fine-grained IP geolocation methods are regression-based; however, due to noise in the input data, these methods typically encounter kilometer-level prediction errors and provide incorrect region information for users. To address this issue, this paper proposes a novel hierarchical multi-label classification framework for IP region prediction, named HMCGeo. This framework treats IP geolocation as a hierarchical multi-label classification problem and employs residual connection-based feature extraction and attention prediction units to predict the target host region across multiple geographical granularities. Furthermore, we introduce probabilistic classification loss during training, combining it with hierarchical cross-entropy loss to form a composite loss function. This approach optimizes predictions by utilizing hierarchical constraints between regions at different granularities. IP region prediction experiments on the New York, Los Angeles, and Shanghai datasets demonstrate that HMCGeo achieves superior performance across all geographical granularities, significantly outperforming existing IP geolocation methods.
Authors: Lili Zhang, Quanyan Zhu, Herman Ray, Ying Xie
Abstract: Network threat detection has been challenging due to the complexities of attack activities and the limitation of historical threat data to learn from. To help enhance the existing practices of using analytics, machine learning, and artificial intelligence methods to detect the network threats, we propose an integrated modelling framework, where Knowledge Graph is used to analyze the users' activity patterns, Imbalanced Learning techniques are used to prune and weigh Knowledge Graph, and LLM is used to retrieve and interpret the users' activities from Knowledge Graph. The proposed framework is applied to Agile Threat Detection through Online Sequential Learning. The preliminary results show the improved threat capture rate by 3%-4% and the increased interpretabilities of risk predictions based on the users' activities.
Authors: Lumen AI, Tengzhou No. 1 Middle School, Shihao Ji, Zihui Song, Fucheng Zhong, Jisen Jia, Zhaobo Wu, Zheyi Cao, Xu Tianhao
Abstract: Addressing the resource waste caused by fixed computation paradigms in deep learning models under dynamic scenarios, this paper proposes a Transformer$^{-1}$ architecture based on the principle of deep adaptivity. This architecture achieves dynamic matching between input features and computational resources by establishing a joint optimization model for complexity and computation. Our core contributions include: (1) designing a two-layer control mechanism, composed of a complexity predictor and a reinforcement learning policy network, enabling end-to-end optimization of computation paths; (2) deriving a lower bound theory for dynamic computation, proving the system's theoretical reach to optimal efficiency; and (3) proposing a layer folding technique and a CUDA Graph pre-compilation scheme, overcoming the engineering bottlenecks of dynamic architectures. In the ImageNet-1K benchmark test, our method reduces FLOPs by 42.7\% and peak memory usage by 34.1\% compared to the standard Transformer, while maintaining comparable accuracy ($\pm$0.3\%). Furthermore, we conducted practical deployment on the Jetson AGX Xavier platform, verifying the effectiveness and practical value of this method in resource-constrained environments. To further validate the generality of the method, we also conducted experiments on several natural language processing tasks and achieved significant improvements in resource efficiency.
Authors: Mayukh Deb, Mainak Deb, N. Apurva Ratan Murty
Abstract: Neurons in the brain are organized such that nearby cells tend to share similar functions. AI models lack this organization, and past efforts to introduce topography have often led to trade-offs between topography and task performance. In this work, we present TopoLoss, a new loss function that promotes spatially organized topographic representations in AI models without significantly sacrificing task performance. TopoLoss is highly adaptable and can be seamlessly integrated into the training of leading model architectures. We validate our method on both vision (ResNet-18, ResNet-50, ViT) and language models (GPT-Neo-125M, NanoGPT), collectively TopoNets. TopoNets are the highest-performing supervised topographic models to date, exhibiting brain-like properties such as localized feature processing, lower dimensionality, and increased efficiency. TopoNets also predict responses in the brain and replicate the key topographic signatures observed in the brain's visual and language cortices. Together, this work establishes a robust and generalizable framework for integrating topography into leading model architectures, advancing the development of high-performing models that more closely emulate the computational strategies of the human brain.
Authors: Jiaru Zhang, Zesong Wang, Hao Wang, Tao Song, Huai-an Su, Rui Chen, Yang Hua, Xiangwei Zhou, Ruhui Ma, Miao Pan, Haibing Guan
Abstract: Battery-powered mobile devices (e.g., smartphones, AR/VR glasses, and various IoT devices) are increasingly being used for AI training due to their growing computational power and easy access to valuable, diverse, and real-time data. On-device training is highly energy-intensive, making accurate energy consumption estimation crucial for effective job scheduling and sustainable AI. However, the heterogeneity of devices and the complexity of models challenge the accuracy and generalizability of existing estimation methods. This paper proposes THOR, a generic approach for energy consumption estimation in deep neural network (DNN) training. First, we examine the layer-wise energy additivity property of DNNs and strategically partition the entire model into layers for fine-grained energy consumption profiling. Then, we fit Gaussian Process (GP) models to learn from layer-wise energy consumption measurements and estimate a DNN's overall energy consumption based on its layer-wise energy additivity property. We conduct extensive experiments with various types of models across different real-world platforms. The results demonstrate that THOR has effectively reduced the Mean Absolute Percentage Error (MAPE) by up to 30%. Moreover, THOR is applied in guiding energy-aware pruning, successfully reducing energy consumption by 50%, thereby further demonstrating its generality and potential.
Authors: Xuqiang Shao, Yuqi Zhang, Di Zhang, Tianxiang Gao, Xinyuan Liu, Zhiran Gan, Fanshun Meng, Hao Li, Weijie Yang
Abstract: This paper addresses the challenges of creating efficient and high-quality datasets for machine learning potential functions. We present a novel approach, termed DV-LAE (Difference Vectors based on Local Atomic Environments), which utilizes the properties of atomic local environments and employs histogram statistics to generate difference vectors. This technique facilitates dataset screening and optimization, effectively minimizing redundancy while maintaining data diversity. We have validated the optimized datasets in high-temperature and high-pressure hydrogen systems as well as the {\alpha}-Fe/H binary system, demonstrating a significant reduction in computational resource usage without compromising prediction accuracy. Additionally, our method has revealed new structures that emerge during simulations but were underrepresented in the initial training datasets. The redundancy in the datasets and the distribution of these new structures can be visually analyzed through the visualization of difference vectors. This approach enhances our understanding of the characteristics of these newly formed structures and their impact on physical processes.
Authors: Kara Liu, Russ Altman, Vasilis Syrgkanis
Abstract: Clinical decisions to treat and diagnose patients are affected by implicit biases formed by racism, ableism, sexism, and other stereotypes. These biases reflect broader systemic discrimination in healthcare and risk marginalizing already disadvantaged groups. Existing methods for measuring implicit biases require controlled randomized testing and only capture individual attitudes rather than outcomes. However, the "big-data" revolution has led to the availability of large observational medical datasets, like EHRs and biobanks, that provide the opportunity to investigate discrepancies in patient health outcomes. In this work, we propose a causal inference approach to detect the effect of clinician implicit biases on patient outcomes in large-scale medical data. Specifically, our method uses proximal mediation to disentangle pathway-specific effects of a patient's sociodemographic attribute on a clinician's diagnosis decision. We test our method on real-world data from the UK Biobank. Our work can serve as a tool that initiates conversation and brings awareness to unequal health outcomes caused by implicit biases.
Authors: Zehao Xiao, Shilin Yan, Jack Hong, Jiayin Cai, Xiaolong Jiang, Yao Hu, Jiayi Shen, Qi Wang, Cees G. M. Snoek
Abstract: Test-time prompt tuning enhances zero-shot generalization of vision-language models but tends to ignore the relatedness among test samples during inference. Online test-time prompt tuning provides a simple way to leverage the information in previous test samples, albeit with the risk of prompt collapse due to error accumulation. To enhance test-time prompt tuning, we propose DynaPrompt, short for dynamic test-time prompt tuning, exploiting relevant data distribution information while reducing error accumulation. Built on an online prompt buffer, DynaPrompt adaptively selects and optimizes the relevant prompts for each test sample during tuning. Specifically, we introduce a dynamic prompt selection strategy based on two metrics: prediction entropy and probability difference. For unseen test data information, we develop dynamic prompt appending, which allows the buffer to append new prompts and delete the inactive ones. By doing so, the prompts are optimized to exploit beneficial information on specific test data, while alleviating error accumulation. Experiments on fourteen datasets demonstrate the effectiveness of dynamic test-time prompt tuning.
Authors: Weipu Zhang, Adam Jelley, Trevor McInroe, Amos Storkey
Abstract: Deep reinforcement learning has achieved remarkable success in learning control policies from pixels across a wide range of tasks, yet its application remains hindered by low sample efficiency, requiring significantly more environment interactions than humans to reach comparable performance. Model-based reinforcement learning (MBRL) offers a solution by leveraging learnt world models to generate simulated experience, thereby improving sample efficiency. However, in visually complex environments, small or dynamic elements can be critical for decision-making. Yet, traditional MBRL methods in pixel-based environments typically rely on auto-encoding with an $L_2$ loss, which is dominated by large areas and often fails to capture decision-relevant details. To address these limitations, we propose an object-centric MBRL pipeline, which integrates recent advances in computer vision to allow agents to focus on key decision-related elements. Our approach consists of four main steps: (1) annotating key objects related to rewards and goals with segmentation masks, (2) extracting object features using a pre-trained, frozen foundation vision model, (3) incorporating these object features with the raw observations to predict environmental dynamics, and (4) training the policy using imagined trajectories generated by this object-centric world model. Building on the efficient MBRL algorithm STORM, we call this pipeline OC-STORM. We demonstrate OC-STORM's practical value in overcoming the limitations of conventional MBRL approaches on both Atari games and the visually complex game Hollow Knight.
Authors: Faizan Manzoor, Vanshaj Khattar, Akila Herath, Clifton Black, Matthew C Nielsen, Junho Hong, Chen-Ching Liu, Ming Jin
Abstract: The occurrences of cyber attacks on the power grids have been increasing every year, with novel attack techniques emerging every year. In this paper, we address the critical challenge of detecting novel/zero-day attacks in digital substations that employ the IEC-61850 communication protocol. While many heuristic and machine learning (ML)-based methods have been proposed for attack detection in IEC-61850 digital substations, generalization to novel or zero-day attacks remains challenging. We propose an approach that leverages the in-context learning (ICL) capability of the transformer architecture, the fundamental building block of large language models. The ICL approach enables the model to detect zero-day attacks and learn from a few examples of that attack without explicit retraining. Our experiments on the IEC-61850 dataset demonstrate that the proposed method achieves more than $85\%$ detection accuracy on zero-day attacks while the existing state-of-the-art baselines fail. This work paves the way for building more secure and resilient digital substations of the future.
Authors: Claas Beger, Saikat Dutta
Abstract: Large Language Models (LLMs) have shown impressive performance across a wide array of tasks involving both structured and unstructured textual data. Recent results on various benchmarks for code generation, repair, or completion suggest that certain models have programming abilities comparable to or even surpass humans. In this work, we demonstrate that high performance on such benchmarks does not correlate to humans' innate ability to understand structural control flow in code. To this end, we extract solutions from the HumanEval benchmark, which the relevant models perform strongly on, and trace their execution path using function calls sampled from the respective test set. Using this dataset, we investigate the ability of seven state-of-the-art LLMs to match the execution trace and find that, despite their ability to generate semantically identical code, they possess limited ability to trace execution paths, especially for longer traces and specific control structures. We find that even the top-performing model, Gemini, can fully and correctly generate only 47% of HumanEval task traces. Additionally, we introduce a subset for three key structures not contained in HumanEval: Recursion, Parallel Processing, and Object-Oriented Programming, including concepts like Inheritance and Polymorphism. Besides OOP, we show that none of the investigated models achieve an accuracy over 5% on the relevant traces. Aggregating these specialized parts with HumanEval tasks, we present Benchmark CoCoNUT: Code Control Flow for Navigation Understanding and Testing, which measures a model's ability to trace execution of code upon relevant calls, including advanced structural components. We conclude that current LLMs need significant improvement to enhance code reasoning abilities. We hope our dataset helps researchers bridge this gap.
Authors: Simon Dahan, Gabriel B\'en\'edict, Logan Z. J. Williams, Yourong Guo, Daniel Rueckert, Robert Leech, Emma C. Robinson
Abstract: Current AI frameworks for brain decoding and encoding, typically train and test models within the same datasets. This limits their utility for brain computer interfaces (BCI) or neurofeedback, for which it would be useful to pool experiences across individuals to better simulate stimuli not sampled during training. A key obstacle to model generalisation is the degree of variability of inter-subject cortical organisation, which makes it difficult to align or compare cortical signals across participants. In this paper we address this through the use of surface vision transformers, which build a generalisable model of cortical functional dynamics, through encoding the topography of cortical networks and their interactions as a moving image across a surface. This is then combined with tri-modal self-supervised contrastive (CLIP) alignment of audio, video, and fMRI modalities to enable the retrieval of visual and auditory stimuli from patterns of cortical activity (and vice-versa). We validate our approach on 7T task-fMRI data from 174 healthy participants engaged in the movie-watching experiment from the Human Connectome Project (HCP). Results show that it is possible to detect which movie clips an individual is watching purely from their brain activity, even for individuals and movies not seen during training. Further analysis of attention maps reveals that our model captures individual patterns of brain activity that reflect semantic and visual systems. This opens the door to future personalised simulations of brain function. Code & pre-trained models will be made available at https://github.com/metrics-lab/sim, processed data for training will be available upon request at https://gin.g-node.org/Sdahan30/sim.
URLs: https://github.com/metrics-lab/sim,, https://gin.g-node.org/Sdahan30/sim.
Authors: Robert O'Shea, Bipin Rajendran
Abstract: State-of-the-art methods for backpropagation-free learning employ local error feedback to direct iterative optimisation via gradient descent. In this study, we examine the more restrictive setting where retrograde communication from neuronal outputs is unavailable for pre-synaptic weight optimisation. To address this challenge, we propose Forward Projection (FP). This novel randomised closed-form training method requires only a single forward pass over the entire dataset for model fitting, without retrograde communication. Target values for pre-activation membrane potentials are generated layer-wise via nonlinear projections of pre-synaptic inputs and the labels. Local loss functions are optimised over pre-synaptic inputs using closed-form regression, without feedback from neuronal outputs or downstream layers. Interpretability is a key advantage of FP training; membrane potentials of hidden neurons in FP-trained networks encode information which is interpretable layer-wise as label predictions. We demonstrate the effectiveness of FP across four biomedical datasets. In few-shot learning tasks, FP yielded more generalisable models than those optimised via backpropagation. In large-sample tasks, FP-based models achieve generalisation comparable to gradient descent-based local learning methods while requiring only a single forward propagation step, achieving significant speed up for training. Interpretation functions defined on local neuronal activity in FP-based models successfully identified clinically salient features for diagnosis in two biomedical datasets. Forward Projection is a computationally efficient machine learning approach that yields interpretable neural network models without retrograde communication of neuronal activity during training.
Authors: Lee Sharkey, Bilal Chughtai, Joshua Batson, Jack Lindsey, Jeff Wu, Lucius Bushnaq, Nicholas Goldowsky-Dill, Stefan Heimersheim, Alejandro Ortega, Joseph Bloom, Stella Biderman, Adria Garriga-Alonso, Arthur Conmy, Neel Nanda, Jessica Rumbelow, Martin Wattenberg, Nandi Schoots, Joseph Miller, Eric J. Michaud, Stephen Casper, Max Tegmark, William Saunders, David Bau, Eric Todd, Atticus Geiger, Mor Geva, Jesse Hoogland, Daniel Murfet, Tom McGrath
Abstract: Mechanistic interpretability aims to understand the computational mechanisms underlying neural networks' capabilities in order to accomplish concrete scientific and engineering goals. Progress in this field thus promises to provide greater assurance over AI system behavior and shed light on exciting scientific questions about the nature of intelligence. Despite recent progress toward these goals, there are many open problems in the field that require solutions before many scientific and practical benefits can be realized: Our methods require both conceptual and practical improvements to reveal deeper insights; we must figure out how best to apply our methods in pursuit of specific goals; and the field must grapple with socio-technical challenges that influence and are influenced by our work. This forward-facing review discusses the current frontier of mechanistic interpretability and the open problems that the field may benefit from prioritizing.
Authors: Ryo Hase, Md Rafi Ur Rashid, Ashley Lewis, Jing Liu, Toshiaki Koike-Akino, Kieran Parsons, Ye Wang
Abstract: Improving the safety and reliability of large language models (LLMs) is a crucial aspect of realizing trustworthy AI systems. Although alignment methods aim to suppress harmful content generation, LLMs are often still vulnerable to jailbreaking attacks that employ adversarial inputs that subvert alignment and induce harmful outputs. We propose the Randomized Embedding Smoothing and Token Aggregation (RESTA) defense, which adds random noise to the embedding vectors and performs aggregation during the generation of each output token, with the aim of better preserving semantic information. Our experiments demonstrate that our approach achieves superior robustness versus utility tradeoffs compared to the baseline defenses.
Authors: J. M. Diederik Kruijssen (Allora Foundation), Renata Valieva (Allora Foundation), Steven N. Longmore (Allora Foundation, Liverpool John Moores University)
Abstract: Decentralized learning networks aim to synthesize a single network inference from a set of raw inferences provided by multiple participants. To determine the combined inference, these networks must adopt a mapping from historical participant performance to weights, and to appropriately incentivize contributions they must adopt a mapping from performance to fair rewards. Despite the increased prevalence of decentralized learning networks, there exists no systematic study that performs a calibration of the associated free parameters. Here we present an optimization framework for key parameters governing decentralized online learning in supervised regression and classification problems. These parameters include the slope of the mapping between historical performance and participant weight, the timeframe for performance evaluation, and the slope of the mapping between performance and rewards. These parameters are optimized using a suite of numerical experiments that mimic the design of the Allora Network, but have been extended to handle classification tasks in addition to regression tasks. This setup enables a comparative analysis of parameter tuning and network performance optimization (loss minimization) across both problem types. We demonstrate how the optimal performance-weight mapping, performance timeframe, and performance-reward mapping vary with network composition and problem type. Our findings provide valuable insights for the optimization of decentralized learning protocols, and we discuss how these results can be generalized to optimize any inference synthesis-based, decentralized AI network.
Authors: Abhishek Dalvi, Neil Ashtekar, Vasant Honavar
Abstract: We consider the problem of estimating causal effects from observational data in the presence of network confounding. In this context, an individual's treatment assignment and outcomes may be affected by their neighbors within the network. We propose a novel matching technique which leverages hyperdimensional computing to model network information and improve predictive performance. We present results of extensive experiments which show that the proposed method outperforms or is competitive with the state-of-the-art methods for causal effect estimation from network data, including advanced computationally demanding deep learning methods. Further, our technique benefits from simplicity and speed, with roughly an order of magnitude lower runtime compared to state-of-the-art methods, while offering similar causal effect estimation error rates.
Authors: Girnar Goyal, Philipp Holl, Sweta Agrawal, Nils Thuerey
Abstract: Solving inverse problems in physics is central to understanding complex systems and advancing technologies in various fields. Iterative optimization algorithms, commonly used to solve these problems, often encounter local minima, chaos, or regions with zero gradients. This is due to their overreliance on local information and highly chaotic inverse loss landscapes governed by underlying partial differential equations (PDEs). In this work, we show that deep neural networks successfully replicate such complex loss landscapes through spatio-temporal trajectory inputs. They also offer the potential to control the underlying complexity of these chaotic loss landscapes during training through various regularization methods. We show that optimizing on network-smoothened loss landscapes leads to improved convergence in predicting optimum inverse parameters over conventional momentum-based optimizers such as BFGS on multiple challenging problems.
Authors: Muhammad Bilal Shahid, Cody Fleming
Abstract: Deep learning models are often trained to approximate dynamical systems that can be modeled using differential equations. These models are optimized to predict one step ahead and produce calibrated predictions if the predictive model can quantify uncertainty, such as deep ensembles. At inference time, multi-step predictions are generated via autoregression, which needs a sound uncertainty propagation method (e.g., Trajectory Sampling) to produce calibrated multi-step predictions. This paper introduces an approach named HopCast that uses the Modern Hopfield Network (MHN) to learn the residuals of a deterministic model that approximates the dynamical system. The MHN predicts the density of residuals based on a context vector at any timestep during autoregression. This approach produces calibrated multi-step predictions without uncertainty propagation and turns a deterministic model into a calibrated probabilistic model. This work is also the first to benchmark existing uncertainty propagation methods based on calibration errors with deep ensembles for multi-step predictions.
Authors: Enrico M. Zucchelli, Di Wu, Julia Briden, Christian Hofmann, Victor Rodriguez-Fernandez, Richard Linares
Abstract: Large language models (LLMs), or foundation models (FMs), are pretrained transformers that coherently complete sentences auto-regressively. In this paper, we show that LLMs can control simplified space systems after some additional training, called fine-tuning. We look at relatively small language models, ranging between 7 and 13 billion parameters. We focus on four problems: a three-dimensional spring toy problem, low-thrust orbit transfer, low-thrust cislunar control, and powered descent guidance. The fine-tuned LLMs are capable of controlling systems by generating sufficiently accurate outputs that are multi-dimensional vectors with up to 10 significant digits. We show that for several problems the amount of data required to perform fine-tuning is smaller than what is generally required of traditional deep neural networks (DNNs), and that fine-tuned LLMs are good at generalizing outside of the training dataset. Further, the same LLM can be fine-tuned with data from different problems, with only minor performance degradation with respect to LLMs trained for a single application. This work is intended as a first step towards the development of a general space systems controller.
Authors: Hongjin Song, Qianrun Chen, Tianqi Jiang, Yongfeng Li, Xusheng Li, Wenjun Xi, Songtao Huang
Abstract: Accurately predicting the wind power output of a wind farm across various time scales utilizing Wind Power Forecasting (WPF) is a critical issue in wind power trading and utilization. The WPF problem remains unresolved due to numerous influencing variables, such as wind speed, temperature, latitude, and longitude. Furthermore, achieving high prediction accuracy is crucial for maintaining electric grid stability and ensuring supply security. In this paper, we model all wind turbines within a wind farm as graph nodes in a graph built by their geographical locations. Accordingly, we propose an ensemble model based on graph neural networks and reinforcement learning (EMGRL) for WPF. Our approach includes: (1) applying graph neural networks to capture the time-series data from neighboring wind farms relevant to the target wind farm; (2) establishing a general state embedding that integrates the target wind farm's data with the historical performance of base models on the target wind farm; (3) ensembling and leveraging the advantages of all base models through an actor-critic reinforcement learning framework for WPF.
Authors: Jungwoo Cho, Seongjin Choi
Abstract: Integrating Urban Air Mobility (UAM) into airspace managed by Air Traffic Control (ATC) poses significant challenges, particularly in congested terminal environments. This study proposes a framework to assess the feasibility of UAM route integration using probabilistic aircraft trajectory prediction. By leveraging conditional Normalizing Flows, the framework predicts short-term trajectory distributions of conventional aircraft, enabling UAM vehicles to dynamically adjust speeds and maintain safe separations. The methodology was applied to airspace over Seoul metropolitan area, encompassing interactions between UAM and conventional traffic at multiple altitudes and lanes. The results reveal that different physical locations of lanes and routes experience varying interaction patterns and encounter dynamics. For instance, Lane 1 at lower altitudes (1,500 ft and 2,000 ft) exhibited minimal interactions with conventional aircraft, resulting in the largest separations and the most stable delay proportions. In contrast, Lane 4 near the airport experienced more frequent and complex interactions due to its proximity to departing traffic. The limited trajectory data for departing aircraft in this region occasionally led to tighter separations and increased operational challenges. This study underscores the potential of predictive modeling in facilitating UAM integration while highlighting critical trade-offs between safety and efficiency. The findings contribute to refining airspace management strategies and offer insights for scaling UAM operations in complex urban environments.
Authors: Julian Bedei, Lucas Koch, Kevin Badalian, Alexander Winkler, Patrick Schaber, Jakob Andert
Abstract: This work introduces a toolchain for applying Reinforcement Learning (RL), specifically the Deep Deterministic Policy Gradient (DDPG) algorithm, in safety-critical real-world environments. As an exemplary application, transient load control is demonstrated on a single-cylinder internal combustion engine testbench in Homogeneous Charge Compression Ignition (HCCI) mode, that offers high thermal efficiency and low emissions. However, HCCI poses challenges for traditional control methods due to its nonlinear, autoregressive, and stochastic nature. RL provides a viable solution, however, safety concerns, such as excessive pressure rise rates, must be addressed when applying to HCCI. A single unsuitable control input can severely damage the engine or cause misfiring and shut down. Additionally, operating limits are not known a priori and must be determined experimentally. To mitigate these risks, real-time safety monitoring based on the k-nearest neighbor algorithm is implemented, enabling safe interaction with the testbench. The feasibility of this approach is demonstrated as the RL agent learns a control policy through interaction with the testbench. A root mean square error of 0.1374 bar is achieved for the indicated mean effective pressure, comparable to neural network-based controllers from the literature. The toolchain's flexibility is further demonstrated by adapting the agent's policy to increase ethanol energy shares, promoting renewable fuel use while maintaining safety. This RL approach addresses the longstanding challenge of applying RL to safety-critical real-world environments. The developed toolchain, with its adaptability and safety mechanisms, paves the way for future applicability of RL in engine testbenches and other safety-critical settings.
Authors: Zitong Li, Qingqing Ye, Haibo Hu
Abstract: Machine unlearning is an emerging field that selectively removes specific data samples from a trained model. This capability is crucial for addressing privacy concerns, complying with data protection regulations, and correcting errors or biases introduced by certain data. Unlike traditional machine learning, where models are typically static once trained, machine unlearning facilitates dynamic updates that enable the model to ``forget'' information without requiring complete retraining from scratch. There are various machine unlearning methods, some of which are more time-efficient when data removal requests are fewer. To decrease the execution time of such machine unlearning methods, we aim to reduce the size of data removal requests based on the fundamental assumption that the removal of certain data would not result in a distinguishable retrained model. We first propose the concept of unnecessary unlearning, which indicates that the model would not alter noticeably after removing some data points. Subsequently, we review existing solutions that can be used to solve our problem. We highlight their limitations in adaptability to different unlearning scenarios and their reliance on manually selected parameters. We consequently put forward FUNU, a method to identify data points that lead to unnecessary unlearning. FUNU circumvents the limitations of existing solutions. The idea is to discover data points within the removal requests that have similar neighbors in the remaining dataset. We utilize a reference model to set parameters for finding neighbors, inspired from the area of model memorization. We provide a theoretical analysis of the privacy guarantee offered by FUNU and conduct extensive experiments to validate its efficacy.
Authors: Gon\c{c}alo Paulo, Nora Belrose
Abstract: Sparse autoencoders (SAEs) are a useful tool for uncovering human-interpretable features in the activations of large language models (LLMs). While some expect SAEs to find the true underlying features used by a model, our research shows that SAEs trained on the same model and data, differing only in the random seed used to initialize their weights, identify different sets of features. For example, in an SAE with 131K latents trained on a feedforward network in Llama 3 8B, only 30% of the features were shared across different seeds. We observed this phenomenon across multiple layers of three different LLMs, two datasets, and several SAE architectures. While ReLU SAEs trained with the L1 sparsity loss showed greater stability across seeds, SAEs using the state-of-the-art TopK activation function were more seed-dependent, even when controlling for the level of sparsity. Our results suggest that the set of features uncovered by an SAE should be viewed as a pragmatically useful decomposition of activation space, rather than an exhaustive and universal list of features "truly used" by the model.
Authors: Lumen AI, Tengzhou No. 1 Middle School, Shihao Ji, Zihui Song, Fucheng Zhong, Jisen Jia, Zhaobo Wu, Zheyi Cao, Xu Tianhao
Abstract: This paper proposes an innovative Multi-Modal Transformer framework (MMF-Trans) designed to significantly improve the prediction accuracy of the Chinese stock market by integrating multi-source heterogeneous information including macroeconomy, micro-market, financial text, and event knowledge. The framework consists of four core modules: (1) A four-channel parallel encoder that processes technical indicators, financial text, macro data, and event knowledge graph respectively for independent feature extraction of multi-modal data; (2) A dynamic gated cross-modal fusion mechanism that adaptively learns the importance of different modalities through differentiable weight allocation for effective information integration; (3) A time-aligned mixed-frequency processing layer that uses an innovative position encoding method to effectively fuse data of different time frequencies and solves the time alignment problem of heterogeneous data; (4) A graph attention-based event impact quantification module that captures the dynamic impact of events on the market through event knowledge graph and quantifies the event impact coefficient. We introduce a hybrid-frequency Transformer and Event2Vec algorithm to effectively fuse data of different frequencies and quantify the event impact. Experimental results show that in the prediction task of CSI 300 constituent stocks, the root mean square error (RMSE) of the MMF-Trans framework is reduced by 23.7% compared to the baseline model, the event response prediction accuracy is improved by 41.2%, and the Sharpe ratio is improved by 32.6%.
Authors: Ashim Dahal, Prabin Bajgai, Nick Rahimi
Abstract: Any exploit taking advantage of zero-day is called a zero-day attack. Previous research and social media trends show a massive demand for research in zero-day attack detection. This paper analyzes Machine Learning (ML) and Deep Learning (DL) based approaches to create Intrusion Detection Systems (IDS) and scrutinizing them using Explainable AI (XAI) by training an explainer based on randomly sampled data from the testing set. The focus is on using the KDD99 dataset, which has the most research done among all the datasets for detecting zero-day attacks. The paper aims to synthesize the dataset to have fewer classes for multi-class classification, test ML and DL approaches on pattern recognition, establish the robustness and dependability of the model, and establish the interpretability and scalability of the model. We evaluated the performance of four multilayer perceptron (MLP) trained on the KDD99 dataset, including baseline ML models, weighted ML models, truncated ML models, and weighted truncated ML models. Our results demonstrate that the truncated ML model achieves the highest accuracy (99.62%), precision, and recall, while weighted truncated ML model shows lower accuracy (97.26%) but better class representation (less bias) among all the classes with improved unweighted recall score. We also used Shapely Additive exPlanations (SHAP) to train explainer for our truncated models to check for feature importance among the two weighted and unweighted models.
Authors: Jiawei Xue, Ruichen Tan, Jianzhu Ma, Satish V. Ukkusuri
Abstract: Data mining in transportation networks (DMTNs) refers to using diverse types of spatio-temporal data for various transportation tasks, including pattern analysis, traffic prediction, and traffic controls. Graph neural networks (GNNs) are essential in many DMTN problems due to their capability to represent spatial correlations between entities. Between 2016 and 2024, the notable applications of GNNs in DMTNs have extended to multiple fields such as traffic prediction and operation. However, existing reviews have primarily focused on traffic prediction tasks. To fill this gap, this study provides a timely and insightful summary of GNNs in DMTNs, highlighting new progress in prediction and operation from academic and industry perspectives since 2023. First, we present and analyze various DMTN problems, followed by classical and recent GNN models. Second, we delve into key works in three areas: (1) traffic prediction, (2) traffic operation, and (3) industry involvement, such as Google Maps, Amap, and Baidu Maps. Along these directions, we discuss new research opportunities based on the significance of transportation problems and data availability. Finally, we compile resources such as data, code, and other learning materials to foster interdisciplinary communication. This review, driven by recent trends in GNNs in DMTN studies since 2023, could democratize abundant datasets and efficient GNN methods for various transportation problems including prediction and operation.
Authors: William Marfo, Deepak K. Tosh, Shirley V. Moore
Abstract: Detecting and localizing anomalies in cyber-physical systems (CPS) has become increasingly challenging as systems grow in complexity, particularly due to varying sensor reliability and node failures in distributed environments. While federated learning (FL) provides a foundation for distributed model training, existing approaches often lack mechanisms to address these CPS-specific challenges. This paper introduces an enhanced FL framework with three key innovations: adaptive model aggregation based on sensor reliability, dynamic node selection for resource optimization, and Weibull-based checkpointing for fault tolerance. The proposed framework ensures reliable condition monitoring while tackling the computational and reliability challenges of industrial CPS deployments. Experiments on the NASA Bearing and Hydraulic System datasets demonstrate superior performance compared to state-of-the-art FL methods, achieving 99.5% AUC-ROC in anomaly detection and maintaining accuracy even under node failures. Statistical validation using the Mann-Whitney U test confirms significant improvements, with a p-value less than 0.05, in both detection accuracy and computational efficiency across various operational scenarios.
Authors: Hengzhuang Li, Teng Zhang
Abstract: Out-of-distribution (OOD) detection is crucial for developing trustworthy and reliable machine learning systems. Recent advances in training with auxiliary OOD data demonstrate efficacy in enhancing detection capabilities. Nonetheless, these methods heavily rely on acquiring a large pool of high-quality natural outliers. Some prior methods try to alleviate this problem by synthesizing virtual outliers but suffer from either poor quality or high cost due to the monotonous sampling strategy and the heavy-parameterized generative models. In this paper, we overcome all these problems by proposing the Hamiltonian Monte Carlo Outlier Synthesis (HamOS) framework, which views the synthesis process as sampling from Markov chains. Based solely on the in-distribution data, the Markov chains can extensively traverse the feature space and generate diverse and representative outliers, hence exposing the model to miscellaneous potential OOD scenarios. The Hamiltonian Monte Carlo with sampling acceptance rate almost close to 1 also makes our framework enjoy great efficiency. By empirically competing with SOTA baselines on both standard and large-scale benchmarks, we verify the efficacy and efficiency of our proposed HamOS.
Authors: Fatima Davelouis, John D. Martin, Michael Bowling
Abstract: We study the benefits of different sparse architectures for deep reinforcement learning. In particular, we focus on image-based domains where spatially-biased and fully-connected architectures are common. Using these and several other architectures of equal capacity, we show that sparse structure has a significant effect on learning performance. We also observe that choosing the best sparse architecture for a given domain depends on whether the hidden layer weights are fixed or learned.
Authors: Lin William Cong, Guanhao Feng, Jingyu He, Xin He
Abstract: We introduce a new class of tree-based models, P-Trees, for analyzing (unbalanced) panel of individual asset returns, generalizing high-dimensional sorting with economic guidance and interpretability. Under the mean-variance efficient framework, P-Trees construct test assets that significantly advance the efficient frontier compared to commonly used test assets, with alphas unexplained by benchmark pricing models. P-Tree tangency portfolios also constitute traded factors, recovering the pricing kernel and outperforming popular observable and latent factor models for investments and cross-sectional pricing. Finally, P-Trees capture the complexity of asset returns with sparsity, achieving out-of-sample Sharpe ratios close to those attained only by over-parameterized large models.
Authors: Nimesh Jha, Shuxin Lin, Srideepika Jayaraman, Kyle Frohling, Christodoulos Constantinides, Dhaval Patel
Abstract: This paper introduces a scalable Anomaly Detection Service with a generalizable API tailored for industrial time-series data, designed to assist Site Reliability Engineers (SREs) in managing cloud infrastructure. The service enables efficient anomaly detection in complex data streams, supporting proactive identification and resolution of issues. Furthermore, it presents an innovative approach to anomaly modeling in cloud infrastructure by utilizing Large Language Models (LLMs) to understand key components, their failure modes, and behaviors. A suite of algorithms for detecting anomalies is offered in univariate and multivariate time series data, including regression-based, mixture-model-based, and semi-supervised approaches. We provide insights into the usage patterns of the service, with over 500 users and 200,000 API calls in a year. The service has been successfully applied in various industrial settings, including IoT-based AI applications. We have also evaluated our system on public anomaly benchmarks to show its effectiveness. By leveraging it, SREs can proactively identify potential issues before they escalate, reducing downtime and improving response times to incidents, ultimately enhancing the overall customer experience. We plan to extend the system to include time series foundation models, enabling zero-shot anomaly detection capabilities.
Authors: Mohammad Hossein Shaker, Eyke H\"ullermeier
Abstract: The Random Forest (RF) classifier is often claimed to be relatively well calibrated when compared with other machine learning methods. Moreover, the existing literature suggests that traditional calibration methods, such as isotonic regression, do not substantially enhance the calibration of RF probability estimates unless supplied with extensive calibration data sets, which can represent a significant obstacle in cases of limited data availability. Nevertheless, there seems to be no comprehensive study validating such claims and systematically comparing state-of-the-art calibration methods specifically for RF. To close this gap, we investigate a broad spectrum of calibration methods tailored to or at least applicable to RF, ranging from scaling techniques to more advanced algorithms. Our results based on synthetic as well as real-world data unravel the intricacies of RF probability estimates, scrutinize the impacts of hyper-parameters, compare calibration methods in a systematic way. We show that a well-optimized RF performs as well as or better than leading calibration approaches.
Authors: Bob Johnson, Michael Geller
Abstract: Efficient management of traffic flow in urban environments presents a significant challenge, exacerbated by dynamic changes and the sheer volume of data generated by modern transportation networks. Traditional centralized traffic management systems often struggle with scalability and privacy concerns, hindering their effectiveness. This paper introduces a novel approach by combining Federated Learning (FL) and Meta-Learning (ML) to create a decentralized, scalable, and adaptive traffic management system. Our approach, termed Meta-Federated Learning, leverages the distributed nature of FL to process data locally at the edge, thereby enhancing privacy and reducing latency. Simultaneously, ML enables the system to quickly adapt to new traffic conditions without the need for extensive retraining. We implement our model across a simulated network of smart traffic devices, demonstrating that Meta-Federated Learning significantly outperforms traditional models in terms of prediction accuracy and response time. Furthermore, our approach shows remarkable adaptability to sudden changes in traffic patterns, suggesting a scalable solution for real-time traffic management in smart cities. This study not only paves the way for more resilient urban traffic systems but also exemplifies the potential of integrated FL and ML in other real-world applications.
Authors: Arik Reuter, Tim G. J. Rudner, Vincent Fortuin, David R\"ugamer
Abstract: Transformers have emerged as the dominant architecture in the field of deep learning, with a broad range of applications and remarkable in-context learning (ICL) capabilities. While not yet fully understood, ICL has already proved to be an intriguing phenomenon, allowing transformers to learn in context -- without requiring further training. In this paper, we further advance the understanding of ICL by demonstrating that transformers can perform full Bayesian inference for commonly used statistical models in context. More specifically, we introduce a general framework that builds on ideas from prior fitted networks and continuous normalizing flows which enables us to infer complex posterior distributions for methods such as generalized linear models and latent factor models. Extensive experiments on real-world datasets demonstrate that our ICL approach yields posterior samples that are similar in quality to state-of-the-art MCMC or variational inference methods not operating in context.
Authors: Spyridon Besias, Ilias Sertaridis, Florentia Afentaki, Konstantinos Balaskas, Georgios Zervakis
Abstract: Printed Electronics (PE) provide a mechanically flexible and cost-effective solution for machine learning (ML) circuits, compared to silicon-based technologies. However, due to large feature sizes, printed classifiers are limited by high power, area, and energy overheads, which restricts the realization of battery-powered systems. In this work, we design sequential printed bespoke Support Vector Machine (SVM) circuits that adhere to the power constraints of existing printed batteries while minimizing energy consumption, thereby boosting battery life. Our results show 6.5x energy savings while maintaining higher accuracy compared to the state of the art.
Authors: Francis Tembo, Federica Bragone, Tor Laneryd, Matthieu Barreau, Kateryna Morozovska
Abstract: Power transformers are subjected to electrical currents and temperature fluctuations that, if not properly controlled, can lead to major deterioration of their insulation system. Therefore, monitoring the temperature of a power transformer is fundamental to ensure a long-term operational life. Models presented in the IEC 60076-7 and IEEE standards, for example, monitor the temperature by calculating the top-oil and the hot-spot temperatures. However, these models are not very accurate and rely on the power transformers' properties. This paper focuses on finding an alternative method to predict the top-oil temperatures given previous measurements. Given the large quantities of data available, machine learning methods for time series forecasting are analyzed and compared to the real measurements and the corresponding prediction of the IEC standard. The methods tested are Artificial Neural Networks (ANNs), Time-series Dense Encoder (TiDE), and Temporal Convolutional Networks (TCN) using different combinations of historical measurements. Each of these methods outperformed the IEC 60076-7 model and they are extended to estimate the temperature rise over ambient. To enhance prediction reliability, we explore the application of quantile regression to construct prediction intervals for the expected top-oil temperature ranges. The best-performing model successfully estimates conditional quantiles that provide sufficient coverage.
Authors: Christian Wald, Gabriele Steidl
Abstract: Among generative neural models, flow matching techniques stand out for their simple applicability and good scaling properties. Here, velocity fields of curves connecting a simple latent and a target distribution are learned. Then the corresponding ordinary differential equation can be used to sample from a target distribution, starting in samples from the latent one. This paper reviews from a mathematical point of view different techniques to learn the velocity fields of absolutely continuous curves in the Wasserstein geometry. We show how the velocity fields can be characterized and learned via i) transport plans (couplings) between latent and target distributions, ii) Markov kernels and iii) stochastic processes, where the latter two include the coupling approach, but are in general broader. Besides this main goal, we show how flow matching can be used for solving Bayesian inverse problems, where the definition of conditional Wasserstein distances plays a central role. Finally, we briefly address continuous normalizing flows and score matching techniques, which approach the learning of velocity fields of curves from other directions.
Authors: Ron van Bree, Diego Marcos, Ioannis Athanasiadis
Abstract: Biophysical models offer valuable insights into climate-phenology relationships in both natural and agricultural settings. However, there are substantial structural discrepancies across models which require site-specific recalibration, often yielding inconsistent predictions under similar climate scenarios. Machine learning methods offer data-driven solutions, but often lack interpretability and alignment with existing knowledge. We present a phenology model describing dormancy in fruit trees, integrating conventional biophysical models with a neural network to address their structural disparities. We evaluate our hybrid model in an extensive case study predicting cherry tree phenology in Japan, South Korea and Switzerland. Our approach consistently outperforms both traditional biophysical and machine learning models in predicting blooming dates across years. Additionally, the neural network's adaptability facilitates parameter learning for specific tree varieties, enabling robust generalization to new sites without site-specific recalibration. This hybrid model leverages both biophysical constraints and data-driven flexibility, offering a promising avenue for accurate and interpretable phenology modeling.
Authors: Marco Angioli, Antonello Rosato, Marcello Barbirotta, Rocco Martino, Francesco Menichelli, Mauro Olivieri
Abstract: Hyperdimensional Computing (HDC), also known as Vector Symbolic Architectures, is a computing paradigm that combines the strengths of symbolic reasoning with the efficiency and scalability of distributed connectionist models in artificial intelligence. HDC has recently emerged as a promising alternative for performing learning tasks in resource-constrained environments thanks to its energy and computational efficiency, inherent parallelism, and resilience to noise and hardware faults. This work introduces the Hyperdimensional Contextual Bandits (HD-CB): the first exploration of HDC to model and automate sequential decision-making Contextual Bandits (CB) problems. The proposed approach maps environmental states in a high-dimensional space and represents each action with dedicated hypervectors (HVs). At each iteration, these HVs are used to select the optimal action for the given context and are updated based on the received reward, replacing computationally expensive ridge regression procedures required by traditional linear CB algorithms with simple, highly parallel vector operations. We propose four HD-CB variants, demonstrating their flexibility in implementing different exploration strategies, as well as techniques to reduce memory overhead and the number of hyperparameters. Extensive simulations on synthetic datasets and a real-world benchmark reveal that HD-CB consistently achieves competitive or superior performance compared to traditional linear CB algorithms, while offering faster convergence time, lower computational complexity, improved scalability, and high parallelism.
Authors: Xander M. de Wit, Alessandro Gabbana
Abstract: Many scientific problems involve data that is embedded in a space with periodic boundary conditions. This can for instance be related to an inherent cyclic or rotational symmetry in the data or a spatially extended periodicity. When analyzing such data, well-tailored methods are needed to obtain efficient approaches that obey the periodic boundary conditions of the problem. In this work, we present a method for applying a clustering algorithm to data embedded in a periodic domain based on the DBSCAN algorithm, a widely used unsupervised machine learning method that identifies clusters in data. The proposed method internally leverages the conventional DBSCAN algorithm for domains with open boundaries, such that it remains compatible with all optimized implementations for neighborhood searches in open domains. In this way, it retains the same optimized runtime complexity of $O(N\log N)$. We demonstrate the workings of the proposed method using synthetic data in one, two and three dimensions and also apply it to a real-world example involving the clustering of bubbles in a turbulent flow. The proposed approach is implemented in a ready-to-use Python package that we make publicly available.
Authors: Zhenqi Li, Junhao Zhong, Hewei Wang, Jinfeng Xu, Yijie Li, Jinjiang You, Jiayi Zhang, Runzhi Wu, Soumyabrata Dev
Abstract: Rainfall prediction remains a persistent challenge due to the highly nonlinear and complex nature of meteorological data. Existing approaches lack systematic utilization of grid search for optimal hyperparameter tuning, relying instead on heuristic or manual selection, frequently resulting in sub-optimal results. Additionally, these methods rarely incorporate newly constructed meteorological features such as differences between temperature and humidity to capture critical weather dynamics. Furthermore, there is a lack of systematic evaluation of ensemble learning techniques and limited exploration of diverse advanced models introduced in the past one or two years. To address these limitations, we propose a robust ensemble learning grid search-tuned framework (RAINER) for rainfall prediction. RAINER incorporates a comprehensive feature engineering pipeline, including outlier removal, imputation of missing values, feature reconstruction, and dimensionality reduction via Principal Component Analysis (PCA). The framework integrates novel meteorological features to capture dynamic weather patterns and systematically evaluates non-learning mathematical-based methods and a variety of machine learning models, from weak classifiers to advanced neural networks such as Kolmogorov-Arnold Networks (KAN). By leveraging grid search for hyperparameter tuning and ensemble voting techniques, RAINER achieves promising results within real-world datasets.
Authors: Shireen Kudukkil Manchingal, Muhammad Mubashar, Kaizheng Wang, Fabio Cuzzolin
Abstract: Predictions of uncertainty-aware models are diverse, ranging from single point estimates (often averaged over prediction samples) to predictive distributions, to set-valued or credal-set representations. We propose a novel unified evaluation framework for uncertainty-aware classifiers, applicable to a wide range of model classes, which allows users to tailor the trade-off between accuracy and precision of predictions via a suitably designed performance metric. This makes possible the selection of the most suitable model for a particular real-world application as a function of the desired trade-off. Our experiments, concerning Bayesian, ensemble, evidential, deterministic, credal and belief function classifiers on the CIFAR-10, MNIST and CIFAR-100 datasets, show that the metric behaves as desired.
Authors: Bernd Frauenknecht, Devdutt Subhasish, Friedrich Solowjow, Sebastian Trimpe
Abstract: Model-based reinforcement learning (MBRL) seeks to enhance data efficiency by learning a model of the environment and generating synthetic rollouts from it. However, accumulated model errors during these rollouts can distort the data distribution, negatively impacting policy learning and hindering long-term planning. Thus, the accumulation of model errors is a key bottleneck in current MBRL methods. We propose Infoprop, a model-based rollout mechanism that separates aleatoric from epistemic model uncertainty and reduces the influence of the latter on the data distribution. Further, Infoprop keeps track of accumulated model errors along a model rollout and provides termination criteria to limit data corruption. We demonstrate the capabilities of Infoprop in the Infoprop-Dyna algorithm, reporting state-of-the-art performance in Dyna-style MBRL on common MuJoCo benchmark tasks while substantially increasing rollout length and data quality.
Authors: Dhruv Sarkar, Aprameyo Chakrabartty, Subhamon Supantha, Palash Dey, Abhishek Sinha
Abstract: We study a generalization of the Online Convex Optimization (OCO) framework with time-varying adversarial constraints. In this problem, after selecting a feasible action from the convex decision set $X,$ a convex constraint function is revealed alongside the cost function in each round. Our goal is to design a computationally efficient learning policy that achieves a small regret with respect to the cost functions and a small cumulative constraint violation (CCV) with respect to the constraint functions over a horizon of length $T$. It is well-known that the projection step constitutes the major computational bottleneck of the standard OCO algorithms. However, for many structured decision sets, linear functions can be efficiently optimized over the decision set. We propose a *projection-free* online policy which makes a single call to a Linear Program (LP) solver per round. Our method outperforms state-of-the-art projection-free online algorithms with adversarial constraints, achieving improved bounds of $\tilde{O}(T^{\frac{3}{4}})$ for both regret and CCV. The proposed algorithm is conceptually simple - it first constructs a surrogate cost function as a non-negative linear combination of the cost and constraint functions. Then, it passes the surrogate costs to a new, adaptive version of the online conditional gradient subroutine, which we propose in this paper.
Authors: Christoph Lehmann, Yahor Paromau
Abstract: Machine learning models are widely used in applications where reliability and robustness are critical. Model evaluation often relies on single-point estimates of performance metrics such as accuracy, F1 score, or mean squared error, that fail to capture the inherent variability in model performance. This variability arises from multiple sources, including train-test split, weights initialization, and hyperparameter tuning. Investigating the characteristics of performance metric distributions, rather than focusing on a single point only, is essential for informed decision-making during model selection and optimization, especially in high-stakes settings. How does the performance metric vary due to intrinsic uncertainty in the selected modeling approach? For example, train-test split is modified, initial weights for optimization are modified or hyperparameter tuning is done using an algorithm with probabilistic nature? This is shifting the focus from identifying a single best model to understanding a distribution of the performance metric that captures variability across different training conditions. By running multiple experiments with varied settings, empirical distributions of performance metrics can be generated. Analyzing these distributions can lead to more robust models that generalize well across diverse scenarios. This contribution explores the use of quantiles and confidence intervals to analyze such distributions, providing a more complete understanding of model performance and its uncertainty. Aimed at a statistically interested audience within the machine learning community, the suggested approaches are easy to implement and apply to various performance metrics for classification and regression problems. Given the often long training times in ML, particular attention is given to small sample sizes (in the order of 10-25).
Authors: Chunyu Lei, Guang-Ze Chen, C. L. Philip Chen, Tong Zhang
Abstract: The state-of-the-art online learning models generally conduct a single online gradient descent when a new sample arrives and thus suffer from suboptimal model weights. To this end, we introduce an online broad learning system framework with closed-form solutions for each online update. Different from employing existing incremental broad learning algorithms for online learning tasks, which tend to incur degraded accuracy and expensive online update overhead, we design an effective weight estimation algorithm and an efficient online updating strategy to remedy the above two deficiencies, respectively. Specifically, an effective weight estimation algorithm is first developed by replacing notorious matrix inverse operations with Cholesky decomposition and forward-backward substitution to improve model accuracy. Second, we devise an efficient online updating strategy that dramatically reduces online update time. Theoretical analysis exhibits the splendid error bound and low time complexity of our model. The most popular test-then-training evaluation experiments on various real-world datasets prove its superiority and efficiency. Furthermore, our framework is naturally extended to data stream scenarios with concept drift and exceeds state-of-the-art baselines.
Authors: Makoto Shing, Kou Misaki, Han Bao, Sho Yokoi, Takuya Akiba
Abstract: Causal language models have demonstrated remarkable capabilities, but their size poses significant challenges for deployment in resource-constrained environments. Knowledge distillation, a widely-used technique for transferring knowledge from a large teacher model to a small student model, presents a promising approach for model compression. A significant remaining issue lies in the major differences between teacher and student models, namely the substantial capacity gap, mode averaging, and mode collapse, which pose barriers during distillation. To address these issues, we introduce $\textit{Temporally Adaptive Interpolated Distillation (TAID)}$, a novel knowledge distillation approach that dynamically interpolates student and teacher distributions through an adaptive intermediate distribution, gradually shifting from the student's initial distribution towards the teacher's distribution. We provide a theoretical analysis demonstrating TAID's ability to prevent mode collapse and empirically show its effectiveness in addressing the capacity gap while balancing mode averaging and mode collapse. Our comprehensive experiments demonstrate TAID's superior performance across various model sizes and architectures in both instruction tuning and pre-training scenarios. Furthermore, we showcase TAID's practical impact by developing two state-of-the-art compact foundation models: $\texttt{TAID-LLM-1.5B}$ for language tasks and $\texttt{TAID-VLM-2B}$ for vision-language tasks. These results demonstrate TAID's effectiveness in creating high-performing and efficient models, advancing the development of more accessible AI technologies.
Authors: Fabian Fumagalli, Maximilian Muschalik, Paolo Frazzetto, Janine Strotherm, Luca Hermes, Alessandro Sperduti, Eyke H\"ullermeier, Barbara Hammer
Abstract: Albeit the ubiquitous use of Graph Neural Networks (GNNs) in machine learning (ML) prediction tasks involving graph-structured data, their interpretability remains challenging. In explainable artificial intelligence (XAI), the Shapley Value (SV) is the predominant method to quantify contributions of individual features to a ML model's output. Addressing the limitations of SVs in complex prediction models, Shapley Interactions (SIs) extend the SV to groups of features. In this work, we explain single graph predictions of GNNs with SIs that quantify node contributions and interactions among multiple nodes. By exploiting the GNN architecture, we show that the structure of interactions in node embeddings are preserved for graph prediction. As a result, the exponential complexity of SIs depends only on the receptive fields, i.e. the message-passing ranges determined by the connectivity of the graph and the number of convolutional layers. Based on our theoretical results, we introduce GraphSHAP-IQ, an efficient approach to compute any-order SIs exactly. GraphSHAP-IQ is applicable to popular message passing techniques in conjunction with a linear global pooling and output layer. We showcase that GraphSHAP-IQ substantially reduces the exponential complexity of computing exact SIs on multiple benchmark datasets. Beyond exact computation, we evaluate GraphSHAP-IQ's approximation of SIs on popular GNN architectures and compare with existing baselines. Lastly, we visualize SIs of real-world water distribution networks and molecule structures using a SI-Graph.
Authors: Xinyi Ni (Brandeis University), Qiuyang Wang (Brandeis University), Yukun Zhang (Brandeis University), Pengyu Hong (Brandeis University)
Abstract: LLM-based tool agents offer natural language interfaces, enabling users to seamlessly interact with computing services. While REST APIs are valuable resources for building such agents, they must first be transformed into AI-compatible tools. Automatically generating AI-compatible tools from REST API documents can greatly streamline tool agent development and minimize user learning curves. However, API documentation often suffers from a lack of standardization, inconsistent schemas, and incomplete information. To address these issues, we developed \textbf{ToolFactory}, an open-source pipeline for automating tool generation from unstructured API documents. To enhance the reliability of the developed tools, we implemented an evaluation method to diagnose errors. Furthermore, we built a knowledge base of verified tools, which we leveraged to infer missing information from poorly documented APIs. We developed the API Extraction Benchmark, comprising 167 API documents and 744 endpoints in various formats, and designed a JSON schema to annotate them. This annotated dataset was utilized to train and validate ToolFactory. The experimental results highlight the effectiveness of ToolFactory. We also demonstrated ToolFactory by creating a domain-specific AI agent for glycomaterials research. ToolFactory exhibits significant potential for facilitating the seamless integration of scientific REST APIs into AI workflows.
Authors: Tristan Bilot, Nour El Madhoun, Khaldoun Al Agha, Anis Zouaoui
Abstract: Detecting cyberattacks using Graph Neural Networks (GNNs) has seen promising results recently. Most of the state-of-the-art models that leverage these techniques require labeled examples, hard to obtain in many real-world scenarios. To address this issue, unsupervised learning and Self-Supervised Learning (SSL) have emerged as interesting approaches to reduce the dependency on labeled data. Nonetheless, these methods tend to yield more anomalous detection algorithms rather than effective attack detection systems. This paper introduces Few Edges Are Enough (FEAE), a GNN-based architecture trained with SSL and Few-Shot Learning (FSL) to better distinguish between false positive anomalies and actual attacks. To maximize the potential of few-shot examples, our model employs a hybrid self-supervised objective that combines the advantages of contrastive-based and reconstruction-based SSL. By leveraging only a minimal number of labeled attack events, represented as attack edges, FEAE achieves competitive performance on two well-known network datasets compared to both supervised and unsupervised methods. Remarkably, our experimental results unveil that employing only 1 malicious event for each attack type in the dataset is sufficient to achieve substantial improvements. FEAE not only outperforms self-supervised GNN baselines but also surpasses some supervised approaches on one of the datasets.
Authors: Xi Chen, Qin Li, Haibin Cai, Ting Wang
Abstract: Federated Learning (FL) empowers multiple clients to collaboratively train machine learning models without sharing local data, making it highly applicable in heterogeneous Internet of Things (IoT) environments. However, intrinsic heterogeneity in clients' model architectures and computing capabilities often results in model accuracy loss and the intractable straggler problem, which significantly impairs training effectiveness. To tackle these challenges, this paper proposes a novel Heterogeneity-aware Personalized Federated Learning method, named HAPFL, via multi-level Reinforcement Learning (RL) mechanisms. HAPFL optimizes the training process by incorporating three strategic components: 1) An RL-based heterogeneous model allocation mechanism. The parameter server employs a Proximal Policy Optimization (PPO)-based RL agent to adaptively allocate appropriately sized, differentiated models to clients based on their performance, effectively mitigating performance disparities. 2) An RL-based training intensity adjustment scheme. The parameter server leverages another PPO-based RL agent to dynamically fine-tune the training intensity for each client to further enhance training efficiency and reduce straggling latency. 3) A knowledge distillation-based mutual learning mechanism. Each client deploys both a heterogeneous local model and a homogeneous lightweight model named LiteModel, where these models undergo mutual learning through knowledge distillation. This uniform LiteModel plays a pivotal role in aggregating and sharing global knowledge, significantly enhancing the effectiveness of personalized local training. Experimental results across multiple benchmark datasets demonstrate that HAPFL not only achieves high accuracy but also substantially reduces the overall training time by 20.9%-40.4% and decreases straggling latency by 19.0%-48.0% compared to existing solutions.
Authors: Manojkumar Parmar, Yuvaraj Govindarajulu
Abstract: Large Language Models (LLMs) have achieved remarkable progress in reasoning, alignment, and task-specific performance. However, ensuring harmlessness in these systems remains a critical challenge, particularly in advanced models like DeepSeek-R1. This paper examines the limitations of Reinforcement Learning (RL) as the primary approach for reducing harmful outputs in DeepSeek-R1 and compares it with Supervised Fine-Tuning (SFT). While RL improves reasoning capabilities, it faces challenges such as reward hacking, generalization failures, language mixing, and high computational costs. We propose hybrid training approaches combining RL and SFT to achieve robust harmlessness reduction. Usage recommendations and future directions for deploying DeepSeek-R1 responsibly are also presented.
Authors: Kanishk Chaturvedi, Johannes Gasthuber, Mohamed Abdelaal
Abstract: This paper introduces EdgeMLOps, a framework leveraging Cumulocity IoT and thin-edge.io for deploying and managing machine learning models on resource-constrained edge devices. We address the challenges of model optimization, deployment, and lifecycle management in edge environments. The framework's efficacy is demonstrated through a visual quality inspection (VQI) use case where images of assets are processed on edge devices, enabling real-time condition updates within an asset management system. Furthermore, we evaluate the performance benefits of different quantization methods, specifically static and dynamic signed-int8, on a Raspberry Pi 4, demonstrating significant inference time reductions compared to FP32 precision. Our results highlight the potential of EdgeMLOps to enable efficient and scalable AI deployments at the edge for industrial applications.
Authors: Anna Soligo, Pietro Ferraro, David Boyle
Abstract: Interpretability in reinforcement learning is crucial for ensuring AI systems align with human values and fulfill the diverse related requirements including safety, robustness and fairness. Building on recent approaches to encouraging sparsity and locality in neural networks, we demonstrate how the penalisation of non-local weights leads to the emergence of functionally independent modules in the policy network of a reinforcement learning agent. To illustrate this, we demonstrate the emergence of two parallel modules for assessment of movement along the X and Y axes in a stochastic Minigrid environment. Through the novel application of community detection algorithms, we show how these modules can be automatically identified and their functional roles verified through direct intervention on the network weights prior to inference. This establishes a scalable framework for reinforcement learning interpretability through functional modularity, addressing challenges regarding the trade-off between completeness and cognitive tractability of reinforcement learning explanations.
Authors: Gregory Duth\'e, Imad Abdallah, Eleni Chatzi
Abstract: We introduce a Graph Transformer framework that serves as a general inverse physics engine on meshes, demonstrated through the challenging task of reconstructing aerodynamic flow fields from sparse surface measurements. While deep learning has shown promising results in forward physics simulation, inverse problems remain particularly challenging due to their ill-posed nature and the difficulty of propagating information from limited boundary observations. Our approach addresses these challenges by combining the geometric expressiveness of message-passing neural networks with the global reasoning of Transformers, enabling efficient learning of inverse mappings from boundary conditions to complete states. We evaluate this framework on a comprehensive dataset of steady-state RANS simulations around diverse airfoil geometries, where the task is to reconstruct full pressure and velocity fields from surface pressure measurements alone. The architecture achieves high reconstruction accuracy while maintaining fast inference times. We conduct experiments and provide insights into the relative importance of local geometric processing and global attention mechanisms in mesh-based inverse problems. We also find that the framework is robust to reduced sensor coverage. These results suggest that Graph Transformers can serve as effective inverse physics engines across a broader range of applications where complete system states must be reconstructed from limited boundary observations.
Authors: Evgenii Evstafev
Abstract: Large language models (LLMs) excel in many natural language tasks, yet they struggle with complex mathemat-ical problem-solving, particularly in symbolic reasoning and maintaining consistent output. This study evalu-ates 10 LLMs with 7 to 8 billion parameters using 945 competition-level problems from the MATH dataset. The focus is on their ability to generate executable Python code as a step in their reasoning process, involving over 9,450 code executions. The research introduces an evaluation framework using mistral-large-2411 to rate answers on a 5-point scale, which helps address inconsistencies in mathematical notation. It also examines the impact of regenerating output token-by-token on refining results. The findings reveal a significant 34.5% per-formance gap between the top commercial model (gpt-4o-mini, scoring 83.7%) and the least effective open-source model (open-codestral-mamba:v0.1, scoring 49.2%). This disparity is especially noticeable in complex areas like Number Theory. While token-by-token regeneration slightly improved accuracy (+0.8%) for the model llama3.1:8b, it also reduced code execution time by 36.7%, highlighting a trade-off between efficiency and precision. The study also noted a consistent trend where harder problems correlated with lower accuracy across all models. Despite using controlled execution environments, less than 1% of the generated code was unsafe, and 3.17% of problems remained unsolved after 10 attempts, suggesting that hybrid reasoning methods may be beneficial.
Authors: Erwan Fagnou, Paul Caillon, Blaise Delattre, Alexandre Allauzen
Abstract: Despite being the cornerstone of deep learning, backpropagation is criticized for its inherent sequentiality, which can limit the scalability of very deep models. Such models faced convergence issues due to vanishing gradient, later resolved using residual connections. Variants of these are now widely used in modern architecture. However, the computational cost of backpropagation remains a major burden, accounting for most of the training time. Taking advantage of residual-like architectural designs, we introduce Highway backpropagation, a parallelizable iterative algorithm that approximates backpropagation, by alternatively i) accumulating the gradient estimates along the residual path, and ii) backpropagating them through every layer in parallel. This algorithm is naturally derived from a decomposition of the gradient as the sum of gradients flowing through all paths and is adaptable to a diverse set of common architectures, ranging from ResNets and Transformers to recurrent neural networks. Through an extensive empirical study on a large selection of tasks and models, we evaluate Highway-BP and show that major speedups can be achieved with minimal performance degradation.
Authors: J. Pablo Mu\~noz, Jinjie Yuan, Nilesh Jain
Abstract: Large pre-trained models have achieved outstanding results in sequence modeling. The Transformer block and its attention mechanism have been the main drivers of the success of these models. Recently, alternative architectures, such as Selective Structured State Space Models (SSMs), have been proposed to address the inefficiencies of Transformers. This paper explores the compression of SSM-based models, particularly Mamba and its hybrids. We study the sensitivity of these models to the removal of selected components at different granularities to reduce the model size and computational overhead, thus improving their efficiency while maintaining accuracy. The proposed solutions, collectively referred to as Mamba-Shedder, achieve a speedup of up to 1.4x during inference, demonstrating that model efficiency can be improved by eliminating several redundancies with minimal impact on the overall model performance. The code is available at https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning.
URLs: https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning.
Authors: Carl-Leander Henneking, Claas Beger
Abstract: Traditional methods for aligning Large Language Models (LLMs), such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO), rely on implicit principles, limiting interpretability. Constitutional AI (CAI) offers an explicit, rule-based framework for guiding model outputs. Building on this, we refine the Inverse Constitutional AI (ICAI) algorithm, which extracts constitutions from preference datasets. By improving principle generation, clustering, and embedding processes, our approach enhances the accuracy and generalizability of extracted principles across synthetic and real-world datasets. While in-context alignment yields modest improvements, our results highlight the potential of these principles to foster more transparent and adaptable alignment methods, offering a promising direction for future advancements beyond traditional fine-tuning.
Authors: R\'emy Hosseinkhan Boucher (Universit\'e Paris-Saclay, CNRS), Onofrio Semeraro (Universit\'e Paris-Saclay, CNRS), Lionel Mathelin (Universit\'e Paris-Saclay, CNRS)
Abstract: The generalisation and robustness properties of policies learnt through Maximum-Entropy Reinforcement Learning are investigated on chaotic dynamical systems with Gaussian noise on the observable. First, the robustness under noise contamination of the agent's observation of entropy regularised policies is observed. Second, notions of statistical learning theory, such as complexity measures on the learnt model, are borrowed to explain and predict the phenomenon. Results show the existence of a relationship between entropy-regularised policy optimisation and robustness to noise, which can be described by the chosen complexity measures.
Authors: Ruizhe Wang, Yeyun Gong, Xiao Liu, Guoshuai Zhao, Ziyue Yang, Baining Guo, Zhengjun Zha, Peng Cheng
Abstract: The growing computational demands of training large language models (LLMs) necessitate more efficient methods. Quantized training presents a promising solution by enabling low-bit arithmetic operations to reduce these costs. While FP8 precision has demonstrated feasibility, leveraging FP4 remains a challenge due to significant quantization errors and limited representational capacity. This work introduces the first FP4 training framework for LLMs, addressing these challenges with two key innovations: a differentiable quantization estimator for precise weight updates and an outlier clamping and compensation strategy to prevent activation collapse. To ensure stability, the framework integrates a mixed-precision training scheme and vector-wise quantization. Experimental results demonstrate that our FP4 framework achieves accuracy comparable to BF16 and FP8, with minimal degradation, scaling effectively to 13B-parameter LLMs trained on up to 100B tokens. With the emergence of next-generation hardware supporting FP4, our framework sets a foundation for efficient ultra-low precision training.
Authors: Muhammad Uzair Zahid, Serkan Kiranyaz, Alper Yildirim, Moncef Gabbouj
Abstract: Real-world radar signals are frequently corrupted by various artifacts, including sensor noise, echoes, interference, and intentional jamming, differing in type, severity, and duration. This pilot study introduces a novel model, called Co-Operational Regressor Network (CoRe-Net) for blind radar signal restoration, designed to address such limitations and drawbacks. CoRe-Net replaces adversarial training with a novel cooperative learning strategy, leveraging the complementary roles of its Apprentice Regressor (AR) and Master Regressor (MR). The AR restores radar signals corrupted by various artifacts, while the MR evaluates the quality of the restoration and provides immediate and task-specific feedback, ensuring stable and efficient learning. The AR, therefore, has the advantage of both self-learning and assistive learning by the MR. The proposed model has been extensively evaluated over the benchmark Blind Radar Signal Restoration (BRSR) dataset, which simulates diverse real-world artifact scenarios. Under the fair experimental setup, this study shows that the CoRe-Net surpasses the Op-GANs over a 1 dB mean SNR improvement. To further boost the performance gain, this study proposes multi-pass restoration by cascaded CoRe-Nets trained with a novel paradigm called Progressive Transfer Learning (PTL), which enables iterative refinement, thus achieving an additional 2 dB mean SNR enhancement. Multi-pass CoRe-Net training by PTL consistently yields incremental performance improvements through successive restoration passes whilst highlighting CoRe-Net ability to handle such a complex and varying blend of artifacts.
Authors: Hossein Mirzaei, Ali Ansari, Bahar Dibaei Nia, Mojtaba Nafez, Moein Madadi, Sepehr Rezaee, Zeinab Sadat Taghavi, Arad Maleki, Kian Shamsaie, Mahdi Hajialilue, Jafar Habibi, Mohammad Sabokrou, Mohammad Hossein Rohban
Abstract: Scanning for trojan (backdoor) in deep neural networks is crucial due to their significant real-world applications. There has been an increasing focus on developing effective general trojan scanning methods across various trojan attacks. Despite advancements, there remains a shortage of methods that perform effectively without preconceived assumptions about the backdoor attack method. Additionally, we have observed that current methods struggle to identify classifiers trojaned using adversarial training. Motivated by these challenges, our study introduces a novel scanning method named TRODO (TROjan scanning by Detection of adversarial shifts in Out-of-distribution samples). TRODO leverages the concept of "blind spots"--regions where trojaned classifiers erroneously identify out-of-distribution (OOD) samples as in-distribution (ID). We scan for these blind spots by adversarially shifting OOD samples towards in-distribution. The increased likelihood of perturbed OOD samples being classified as ID serves as a signature for trojan detection. TRODO is both trojan and label mapping agnostic, effective even against adversarially trained trojaned classifiers. It is applicable even in scenarios where training data is absent, demonstrating high accuracy and adaptability across various scenarios and datasets, highlighting its potential as a robust trojan scanning strategy.
Authors: Mathan Kumar Mounagurusamy, Thiyagarajan V S, Abdur Rahman, Shravan Chandak, D. Balaji, Venkateswara Rao Jallepalli
Abstract: Early management and better clinical outcomes for epileptic patients depend on seizure prediction. The accuracy and false alarm rates of existing systems are often compromised by their dependence on static thresholds and basic Electroencephalogram (EEG) properties. A novel Recurrent Neural Network (RNN)-based method for seizure start prediction is proposed in the article to overcome these limitations. As opposed to conventional techniques, the proposed system makes use of Long Short-Term Memory (LSTM) networks to extract temporal correlations from unprocessed EEG data. It enables the system to adapt dynamically to the unique EEG patterns of each patient, improving prediction accuracy. The methodology of the system comprises thorough data collecting, preprocessing, and LSTM-based feature extraction. Annotated EEG datasets are then used for model training and validation. Results show a considerable reduction in false alarm rates (average of 6.8%) and an improvement in prediction accuracy (90.2% sensitivity, 88.9% specificity, and AUC-ROC of 93). Additionally, computational efficiency is significantly higher than that of existing systems (12 ms processing time, 45 MB memory consumption). About improving seizure prediction reliability, these results demonstrate the effectiveness of the proposed RNN-based strategy, opening up possibilities for its practical application to improve epilepsy treatment.
Authors: Ivan Knunyants, Maryam Tavakol, Manolis Sifalakis, Yingfu Xu, Amirreza Yousefzadeh, Guangzhi Tang
Abstract: The recent rise of Large Language Models (LLMs) has revolutionized the deep learning field. However, the desire to deploy LLMs on edge devices introduces energy efficiency and latency challenges. Recurrent LLM (R-LLM) architectures have proven effective in mitigating the quadratic complexity of self-attention, making them a potential paradigm for computing on-edge neuromorphic processors. In this work, we propose a low-cost, training-free algorithm to sparsify R-LLMs' activations to enhance energy efficiency on neuromorphic hardware. Our approach capitalizes on the inherent structure of these models, rendering them well-suited for energy-constrained environments. Although primarily designed for R-LLMs, this method can be generalized to other LLM architectures, such as transformers, as demonstrated on the OPT model, achieving comparable sparsity and efficiency improvements. Empirical studies illustrate that our method significantly reduces computational demands while maintaining competitive accuracy across multiple zero-shot learning benchmarks. Additionally, hardware simulations with the SENECA neuromorphic processor underscore notable energy savings and latency improvements. These results pave the way for low-power, real-time neuromorphic deployment of LLMs and demonstrate the feasibility of training-free on-chip adaptation using activation sparsity.
Authors: S. Muhammad Hossein Mousavi
Abstract: Data scarcity remains a significant challenge in the field of emotion recognition using physiological signals, as acquiring comprehensive and diverse datasets is often prevented by privacy concerns and logistical constraints. This limitation restricts the development and generalization of robust emotion recognition models, making the need for effective synthetic data generation methods more critical. Emotion recognition from physiological signals such as EEG, ECG, and GSR plays a pivotal role in enhancing human-computer interaction and understanding human affective states. Utilizing these signals, this study introduces an innovative approach to synthetic data generation using a Supervised Neural Gas (SNG) network, which has demonstrated noteworthy speed advantages over established models like Conditional VAE, Conditional GAN, diffusion model, and Variational LSTM. The Neural Gas network, known for its adaptability in organizing data based on topological and feature-space proximity, provides a robust framework for generating real-world-like synthetic datasets that preserve the intrinsic patterns of physiological emotion data. Our implementation of the SNG efficiently processes the input data, creating synthetic instances that closely mimic the original data distributions, as demonstrated through comparative accuracy assessments. In experiments, while our approach did not universally outperform all models, it achieved superior performance against most of the evaluated models and offered significant improvements in processing time. These outcomes underscore the potential of using SNG networks for fast, efficient, and effective synthetic data generation in emotion recognition applications.
Authors: Ziwen Li, Xiang 'Anthony' Chen, Youngseung Jeon
Abstract: Drug discovery (DD) has tremendously contributed to maintaining and improving public health. Hypothesizing that inhibiting protein misfolding can slow disease progression, researchers focus on target identification (Target ID) to find protein structures for drug binding. While Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) frameworks have accelerated drug discovery, integrating models into cohesive workflows remains challenging. We conducted a user study with drug discovery researchers to identify the applicability of LLMs and RAGs in Target ID. We identified two main findings: 1) an LLM should provide multiple Protein-Protein Interactions (PPIs) based on an initial protein and protein candidates that have a therapeutic impact; 2) the model must provide the PPI and relevant explanations for better understanding. Based on these observations, we identified three limitations in previous approaches for Target ID: 1) semantic ambiguity, 2) lack of explainability, and 3) short retrieval units. To address these issues, we propose GraPPI, a large-scale knowledge graph (KG)-based retrieve-divide-solve agent pipeline RAG framework to support large-scale PPI signaling pathway exploration in understanding therapeutic impacts by decomposing the analysis of entire PPI pathways into sub-tasks focused on the analysis of PPI edges.
Authors: Sai Tarun Inaganti, Gennady Petrenko
Abstract: Point cloud enhancement is the process of generating a high-quality point cloud from an incomplete input. This is done by filling in the missing details from a reference like the ground truth via regression, for example. In addition to unimodal image and point cloud reconstruction, we focus on the task of view-guided point cloud completion, where we gather the missing information from an image, which represents a view of the point cloud and use it to generate the output point cloud. With the recent research efforts surrounding state-space models, originally in natural language processing and now in 2D and 3D vision, Mamba has shown promising results as an efficient alternative to the self-attention mechanism. However, there is limited research towards employing Mamba for cross-attention between the image and the input point cloud, which is crucial in multi-modal problems. In this paper, we introduce MambaTron, a Mamba-Transformer cell that serves as a building block for our network which is capable of unimodal and cross-modal reconstruction which includes view-guided point cloud completion.We explore the benefits of Mamba's long-sequence efficiency coupled with the Transformer's excellent analytical capabilities through MambaTron. This approach is one of the first attempts to implement a Mamba-based analogue of cross-attention, especially in computer vision. Our model demonstrates a degree of performance comparable to the current state-of-the-art techniques while using a fraction of the computation resources.
Authors: Binjian Wu, Qian Li, Zhe Kuang, Hongyuan Gao, Xinyi Liu, Haiyan Guo, Qiuju Chen, Xinyi Liu, Yangruizhe Jiang, Yuqi Zhang, Jinyin Zha, Mingyu Li, Qiuhan Ren, Sishuo Feng, Haicang Zhang, Xuefeng Lu, Jian Zhang
Abstract: In vitro fertilization-embryo transfer (IVF-ET) stands as one of the most prevalent treatments for infertility. During an IVF-ET cycle, the time interval between trigger shot and oocyte pickup (OPU) is a pivotal period for follicular maturation, which determines mature oocytes yields and impacts the success of subsequent procedures. However, accurately predicting this interval is severely hindered by the variability of clinicians'experience that often leads to suboptimal oocyte retrieval rate. To address this challenge, we propose ILETIA, the first machine learning-based method that could predict the optimal trigger-OPU interval for patients receiving progestin-primed ovarian stimulation (PPOS) protocol. Specifically, ILETIA leverages a Transformer to learn representations from clinical tabular data, and then employs gradient-boosted trees for interval prediction. For model training and evaluating, we compiled a dataset PPOS-DS of nearly ten thousand patients receiving PPOS protocol, the largest such dataset to our knowledge. Experimental results demonstrate that our method achieves strong performance (AUROC = 0.889), outperforming both clinicians and other widely used computational models. Moreover, ILETIA also supports premature ovulation risk prediction in a specific OPU time (AUROC = 0.838). Collectively, by enabling more precise and individualized decisions, ILETIA has the potential to improve clinical outcomes and lay the foundation for future IVF-ET research.
Authors: George Wright, Slawomir Michniewski, Eleanor Jameson, Fayyaz ul Amir Afsar Minhas
Abstract: Background: Phage therapy shows promise for treating antibiotic-resistant Klebsiella infections. Identifying phage depolymerases that target Klebsiella capsular polysaccharides is crucial, as these capsules contribute to biofilm formation and virulence. However, homology-based searches have limitations in novel depolymerase discovery. Objective: To develop a machine learning model for identifying and ranking potential phage depolymerases targeting Klebsiella. Methods: We developed DepoRanker, a machine learning algorithm to rank proteins by their likelihood of being depolymerases. The model was experimentally validated on 5 newly characterized proteins and compared to BLAST. Results: DepoRanker demonstrated superior performance to BLAST in identifying potential depolymerases. Experimental validation confirmed its predictive ability on novel proteins. Conclusions: DepoRanker provides an accurate and functional tool to expedite depolymerase discovery for phage therapy against Klebsiella. It is available as a webserver and open-source software. Availability: Webserver: https://deporanker.dcs.warwick.ac.uk/ Source code: https://github.com/wgrgwrght/deporanker
URLs: https://deporanker.dcs.warwick.ac.uk/, https://github.com/wgrgwrght/deporanker
Authors: Wei Chow, Jiageng Mao, Boyi Li, Daniel Seita, Vitor Guizilini, Yue Wang
Abstract: Understanding the physical world is a fundamental challenge in embodied AI, critical for enabling agents to perform complex tasks and operate safely in real-world environments. While Vision-Language Models (VLMs) have shown great promise in reasoning and task planning for embodied agents, their ability to comprehend physical phenomena remains extremely limited. To close this gap, we introduce PhysBench, a comprehensive benchmark designed to evaluate VLMs' physical world understanding capability across a diverse set of tasks. PhysBench contains 100,000 entries of interleaved video-image-text data, categorized into four major domains: physical object properties, physical object relationships, physical scene understanding, and physics-based dynamics, further divided into 19 subclasses and 8 distinct capability dimensions. Our extensive experiments, conducted on 75 representative VLMs, reveal that while these models excel in common-sense reasoning, they struggle with understanding the physical world -- likely due to the absence of physical knowledge in their training data and the lack of embedded physical priors. To tackle the shortfall, we introduce PhysAgent, a novel framework that combines the generalization strengths of VLMs with the specialized expertise of vision models, significantly enhancing VLMs' physical understanding across a variety of tasks, including an 18.4\% improvement on GPT-4o. Furthermore, our results demonstrate that enhancing VLMs' physical world understanding capabilities can help embodied agents such as MOKA. We believe that PhysBench and PhysAgent offer valuable insights and contribute to bridging the gap between VLMs and physical world understanding.
Authors: Robin Young
Abstract: "First, do no harm" faces a fundamental challenge in artificial intelligence: how can we specify what constitutes harm? While prior work treats harm specification as a technical hurdle to be overcome through better algorithms or more data, we argue this assumption is unsound. Drawing on information theory, we demonstrate that complete harm specification is fundamentally impossible for any system where harm is defined external to its specifications. This impossibility arises from an inescapable information-theoretic gap: the entropy of harm H(O) always exceeds the mutual information I(O;I) between ground truth harm O and a system's specifications I. We introduce two novel metrics: semantic entropy H(S) and the safety-capability ratio I(O;I)/H(O), to quantify these limitations. Through a progression of increasingly sophisticated specification attempts, we show why each approach must fail and why the resulting gaps are not mere engineering challenges but fundamental constraints akin to the halting problem. These results suggest a paradigm shift: rather than pursuing complete specifications, AI alignment research should focus on developing systems that can operate safely despite irreducible specification uncertainty.
Authors: Weijie He, Yuwei Zhang, Ting Xu, Tai An, Yingbin Liang, Bo Zhang
Abstract: Deep learning has emerged as a transformative approach for solving complex pattern recognition and object detection challenges. This paper focuses on the application of a novel detection framework based on the RT-DETR model for analyzing intricate image data, particularly in areas such as diabetic retinopathy detection. Diabetic retinopathy, a leading cause of vision loss globally, requires accurate and efficient image analysis to identify early-stage lesions. The proposed RT-DETR model, built on a Transformer-based architecture, excels at processing high-dimensional and complex visual data with enhanced robustness and accuracy. Comparative evaluations with models such as YOLOv5, YOLOv8, SSD, and DETR demonstrate that RT-DETR achieves superior performance across precision, recall, mAP50, and mAP50-95 metrics, particularly in detecting small-scale objects and densely packed targets. This study underscores the potential of Transformer-based models like RT-DETR for advancing object detection tasks, offering promising applications in medical imaging and beyond.
Authors: Boya Hou, Sina Sanjari, Nathan Dahlin, Alec Koppel, Subhonmesh Bose
Abstract: The Koopman operator provides a powerful framework for representing the dynamics of general nonlinear dynamical systems. Data-driven techniques to learn the Koopman operator typically assume that the chosen function space is closed under system dynamics. In this paper, we study the Koopman operator via its action on the reproducing kernel Hilbert space (RKHS), and explore the mis-specified scenario where the dynamics may escape the chosen function space. We relate the Koopman operator to the conditional mean embeddings (CME) operator and then present an operator stochastic approximation algorithm to learn the Koopman operator iteratively with control over the complexity of the representation. We provide both asymptotic and finite-time last-iterate guarantees of the online sparse learning algorithm with trajectory-based sampling with an analysis that is substantially more involved than that for finite-dimensional stochastic approximation. Numerical examples confirm the effectiveness of the proposed algorithm.
Authors: Emad Efatinasab, Alessandro Brighente, Denis Donadel, Mauro Conti, Mirco Rampazzo
Abstract: Smart grids are critical for addressing the growing energy demand due to global population growth and urbanization. They enhance efficiency, reliability, and sustainability by integrating renewable energy. Ensuring their availability and safety requires advanced operational control and safety measures. Researchers employ AI and machine learning to assess grid stability, but challenges like the lack of datasets and cybersecurity threats, including adversarial attacks, persist. In particular, data scarcity is a key issue: obtaining grid instability instances is tough due to the need for significant expertise, resources, and time. However, they are essential to test novel research advancements and security mitigations. In this paper, we introduce a novel framework to detect instability in smart grids by employing only stable data. It relies on a Generative Adversarial Network (GAN) where the generator is trained to create instability data that are used along with stable data to train the discriminator. Moreover, we include a new adversarial training layer to improve robustness against adversarial attacks. Our solution, tested on a dataset composed of real-world stable and unstable samples, achieve accuracy up to 97.5\% in predicting grid stability and up to 98.9\% in detecting adversarial attacks. Moreover, we implemented our model in a single-board computer demonstrating efficient real-time decision-making with an average response time of less than 7ms. Our solution improves prediction accuracy and resilience while addressing data scarcity in smart grid management.
Authors: Sina Sharifi, Nazanin Abolfazli, Erfan Yazdandoost Hamedani, Mahyar Fazlyab
Abstract: Bilevel optimization is a key framework in hierarchical decision-making, where one problem is embedded within the constraints of another. In this work, we propose a control-theoretic approach to solving bilevel optimization problems. Our method consists of two components: a gradient flow mechanism to minimize the upper-level objective and a safety filter to enforce the constraints imposed by the lower-level problem. Together, these components form a safe gradient flow that solves the bilevel problem in a single loop. To improve scalability with respect to the lower-level problem's dimensions, we introduce a relaxed formulation and design a compact variant of the safe gradient flow. This variant minimizes the upper-level objective while ensuring the lower-level solution remains within a user-defined distance. Using Lyapunov analysis, we establish convergence guarantees for the dynamics, proving that they converge to a neighborhood of the optimal solution. Numerical experiments further validate the effectiveness of the proposed approaches. Our contributions provide both theoretical insights and practical tools for efficiently solving bilevel optimization problems.
Authors: Jorge del Pozo L\'erida, Kamil Kojs, J\'anos M\'at\'e, Miko{\l}aj Antoni Bara\'nski, Christian Hardmeier
Abstract: Large Language Models (LLMs) have become state-of-the-art in Machine Translation (MT), often trained on massive bilingual parallel corpora scraped from the web, that contain low-quality entries and redundant information, leading to significant computational challenges. Various data filtering methods exist to reduce dataset sizes, but their effectiveness largely varies based on specific language pairs and domains. This paper evaluates the impact of commonly used data filtering techniques, such as LASER, MUSE, and LaBSE, on English-Polish translation within the biomedical domain. By filtering the UFAL Medical Corpus, we created varying dataset sizes to fine-tune the mBART50 model, which was then evaluated using the SacreBLEU metric on the Khresmoi dataset, having the quality of translations assessed by bilingual speakers. Our results show that both LASER and MUSE can significantly reduce dataset sizes while maintaining or even enhancing performance. We recommend the use of LASER, as it consistently outperforms the other methods and provides the most fluent and natural-sounding translations.
Authors: Mufan Sang, John H. L. Hansen
Abstract: With excellent generalization ability, SSL speech models have shown impressive performance on various downstream tasks in the pre-training and fine-tuning paradigm. However, as the size of pre-trained models grows, fine-tuning becomes practically unfeasible due to expanding computation and storage requirements and the risk of overfitting. This study explores parameter-efficient tuning (PET) methods for adapting large-scale pre-trained SSL speech models to speaker verification task. Correspondingly, we propose three PET methods: (i)an adapter-tuning method, (ii)a prompt-tuning method, and (iii)a unified framework that effectively incorporates adapter-tuning and prompt-tuning with a dynamically learnable gating mechanism. First, we propose the Inner+Inter Adapter framework, which inserts two types of adapters into pre-trained models, allowing for adaptation of latent features within the intermediate Transformer layers and output embeddings from all Transformer layers, through a parallel adapter design. Second, we propose the Deep Speaker Prompting method that concatenates trainable prompt tokens into the input space of pre-trained models to guide adaptation. Lastly, we propose the UniPET-SPK, a unified framework that effectively incorporates these two alternate PET methods into a single framework with a dynamic trainable gating mechanism. The proposed UniPET-SPK learns to find the optimal mixture of PET methods to match different datasets and scenarios. We conduct a comprehensive set of experiments on several datasets to validate the effectiveness of the proposed PET methods. Experimental results on VoxCeleb, CN-Celeb, and 1st 48-UTD forensic datasets demonstrate that the proposed UniPET-SPK consistently outperforms the two PET methods, fine-tuning, and other parameter-efficient tuning methods, achieving superior performance while updating only 5.4% of the parameters.
Authors: Tina Behzad, S\'ilvia Casacuberta, Emily Ruth Diana, Alexander Williams Tolbert
Abstract: Many machine learning applications predict individual probabilities, such as the likelihood that a person develops a particular illness. Since these probabilities are unknown, a key question is how to address situations in which different models trained on the same dataset produce varying predictions for certain individuals. This issue is exemplified by the model multiplicity (MM) phenomenon, where a set of comparable models yield inconsistent predictions. Roth, Tolbert, and Weinstein recently introduced a reconciliation procedure, the Reconcile algorithm, to address this problem. Given two disagreeing models, the algorithm leverages their disagreement to falsify and improve at least one of the models. In this paper, we empirically analyze the Reconcile algorithm using five widely-used fairness datasets: COMPAS, Communities and Crime, Adult, Statlog (German Credit Data), and the ACS Dataset. We examine how Reconcile fits within the model multiplicity literature and compare it to existing MM solutions, demonstrating its effectiveness. We also discuss potential improvements to the Reconcile algorithm theoretically and practically. Finally, we extend the Reconcile algorithm to the setting of causal inference, given that different competing estimators can again disagree on specific causal average treatment effect (CATE) values. We present the first extension of the Reconcile algorithm in causal inference, analyze its theoretical properties, and conduct empirical tests. Our results confirm the practical effectiveness of Reconcile and its applicability across various domains.
Authors: Zhongyu Jiang, Wenhao Chai, Zhuoran Zhou, Cheng-Yen Yang, Hsiang-Wei Huang, Jenq-Neng Hwang
Abstract: Human motion generation has advanced markedly with the advent of diffusion models. Most recent studies have concentrated on generating motion sequences based on text prompts, commonly referred to as text-to-motion generation. However, the bidirectional generation of motion and text, enabling tasks such as motion-to-text alongside text-to-motion, has been largely unexplored. This capability is essential for aligning diverse modalities and supports unconditional generation. In this paper, we introduce PackDiT, the first diffusion-based generative model capable of performing various tasks simultaneously, including motion generation, motion prediction, text generation, text-to-motion, motion-to-text, and joint motion-text generation. Our core innovation leverages mutual blocks to integrate multiple diffusion transformers (DiTs) across different modalities seamlessly. We train PackDiT on the HumanML3D dataset, achieving state-of-the-art text-to-motion performance with an FID score of 0.106, along with superior results in motion prediction and in-between tasks. Our experiments further demonstrate that diffusion models are effective for motion-to-text generation, achieving performance comparable to that of autoregressive models.
Authors: Haiyun He, Yepeng Liu, Ziqiao Wang, Yongyi Mao, Yuheng Bu
Abstract: This paper introduces a novel problem, distributional information embedding, motivated by the practical demands of multi-bit watermarking for large language models (LLMs). Unlike traditional information embedding, which embeds information into a pre-existing host signal, LLM watermarking actively controls the text generation process--adjusting the token distribution--to embed a detectable signal. We develop an information-theoretic framework to analyze this distributional information embedding problem, characterizing the fundamental trade-offs among three critical performance metrics: text quality, detectability, and information rate. In the asymptotic regime, we demonstrate that the maximum achievable rate with vanishing error corresponds to the entropy of the LLM's output distribution and increases with higher allowable distortion. We also characterize the optimal watermarking scheme to achieve this rate. Extending the analysis to the finite-token case, we identify schemes that maximize detection probability while adhering to constraints on false alarm and distortion.
Authors: Wataru Masaka, Mitsuki Sakamoto, Kenshi Abe, Kaito Ariu, Tuomas Sandholm, Atsushi Iwasaki
Abstract: This paper investigates how perturbation does and does not improve the Follow-the-Regularized-Leader (FTRL) algorithm in imperfect-information extensive-form games. Perturbing the expected payoffs guarantees that the FTRL dynamics reach an approximate equilibrium, and proper adjustments of the magnitude of the perturbation lead to a Nash equilibrium (\textit{last-iterate convergence}). This approach is robust even when payoffs are estimated using sampling -- as is the case for large games -- while the optimistic approach often becomes unstable. Building upon those insights, we first develop a general framework for perturbed FTRL algorithms under \textit{sampling}. We then empirically show that in the last-iterate sense, the perturbed FTRL consistently outperforms the non-perturbed FTRL. We further identify a divergence function that reduces the variance of the estimates for perturbed payoffs, with which it significantly outperforms the prior algorithms on Leduc poker (whose structure is more asymmetric in a sense than that of the other benchmark games) and consistently performs smooth convergence behavior on all the benchmark games.
Authors: Alexandros E. Tzikas, Mykel J. Kochenderfer
Abstract: We tackle the problem of informative input design for system identification, where we select inputs, observe the corresponding outputs from the true system, and optimize the parameters of our model to best fit the data. We propose a methodology that is compatible with any system and parametric family of models. Our approach only requires input-output data from the system and first-order information from the model with respect to the parameters. Our algorithm consists of two modules. First, we formulate the problem of system identification from a Bayesian perspective and propose an approximate iterative method to optimize the model's parameters. Based on this Bayesian formulation, we are able to define a Gaussian-based uncertainty measure for the model parameters, which we can then minimize with respect to the next selected input. Our method outperforms model-free baselines with various linear and nonlinear dynamics.
Authors: Aditya Mishra, Ahnaf Mozib Samin, Ali Etemad, Javad Hashemi
Abstract: We propose GC-VASE, a graph convolutional-based variational autoencoder that leverages contrastive learning for subject representation learning from EEG data. Our method successfully learns robust subject-specific latent representations using the split-latent space architecture tailored for subject identification. To enhance the model's adaptability to unseen subjects without extensive retraining, we introduce an attention-based adapter network for fine-tuning, which reduces the computational cost of adapting the model to new subjects. Our method significantly outperforms other deep learning approaches, achieving state-of-the-art results with a subject balanced accuracy of 89.81% on the ERP-Core dataset and 70.85% on the SleepEDFx-20 dataset. After subject adaptive fine-tuning using adapters and attention layers, GC-VASE further improves the subject balanced accuracy to 90.31% on ERP-Core. Additionally, we perform a detailed ablation study to highlight the impact of the key components of our method.
Authors: Siyi Chen, Yixuan Jia, Qing Qu, He Sun, Jeffrey A Fessler
Abstract: Data assimilation (DA) is crucial for improving the accuracy of state estimation in complex dynamical systems by integrating observational data with physical models. Traditional solutions rely on either pure model-driven approaches, such as Bayesian filters that struggle with nonlinearity, or data-driven methods using deep learning priors, which often lack generalizability and physical interpretability. Recently, score-based DA methods have been introduced, focusing on learning prior distributions but neglecting explicit state transition dynamics, leading to limited accuracy improvements. To tackle the challenge, we introduce FlowDAS, a novel generative model-based framework using the stochastic interpolants to unify the learning of state transition dynamics and generative priors. FlowDAS achieves stable and observation-consistent inference by initializing from proximal previous states, mitigating the instability seen in score-based methods. Our extensive experiments demonstrate FlowDAS's superior performance on various benchmarks, from the Lorenz system to high-dimensional fluid super-resolution tasks. FlowDAS also demonstrates improved tracking accuracy on practical Particle Image Velocimetry (PIV) task, showcasing its effectiveness in complex flow field reconstruction.
Authors: Yanjiang Guo, Jianke Zhang, Xiaoyu Chen, Xiang Ji, Yen-Jen Wang, Yucheng Hu, Jianyu Chen
Abstract: Recent studies have successfully integrated large vision-language models (VLMs) into low-level robotic control by supervised fine-tuning (SFT) with expert robotic datasets, resulting in what we term vision-language-action (VLA) models. Although the VLA models are powerful, how to improve these large models during interaction with environments remains an open question. In this paper, we explore how to further improve these VLA models via Reinforcement Learning (RL), a commonly used fine-tuning technique for large models. However, we find that directly applying online RL to large VLA models presents significant challenges, including training instability that severely impacts the performance of large models, and computing burdens that exceed the capabilities of most local machines. To address these challenges, we propose iRe-VLA framework, which iterates between Reinforcement Learning and Supervised Learning to effectively improve VLA models, leveraging the exploratory benefits of RL while maintaining the stability of supervised learning. Experiments in two simulated benchmarks and a real-world manipulation suite validate the effectiveness of our method.
Authors: Kevin Rojas, Yixin Tan, Molei Tao, Yuriy Nevmyvaka, Wei Deng
Abstract: The momentum Schr\"odinger Bridge (mSB) has emerged as a leading method for accelerating generative diffusion processes and reducing transport costs. However, the lack of simulation-free properties inevitably results in high training costs and affects scalability. To obtain a trade-off between transport properties and scalability, we introduce variational Schr\"odinger momentum diffusion (VSMD), which employs linearized forward score functions (variational scores) to eliminate the dependence on simulated forward trajectories. Our approach leverages a multivariate diffusion process with adaptively transport-optimized variational scores. Additionally, we apply a critical-damping transform to stabilize training by removing the need for score estimations for both velocity and samples. Theoretically, we prove the convergence of samples generated with optimal variational scores and momentum diffusion. Empirical results demonstrate that VSMD efficiently generates anisotropic shapes while maintaining transport efficacy, outperforming overdamped alternatives, and avoiding complex denoising processes. Our approach also scales effectively to real-world data, achieving competitive results in time series and image generation.
Authors: MD Sadik Hossain Shanto, Mahir Labib Dihan, Souvik Ghosh, Riad Ahmed Anonto, Hafijul Hoque Chowdhury, Abir Muhtasim, Rakib Ahsan, MD Tanvir Hassan, MD Roqunuzzaman Sojib, Sheikh Azizul Hakim, M. Saifur Rahman
Abstract: This report presents our approach for the IEEE SP Cup 2025: Deepfake Face Detection in the Wild (DFWild-Cup), focusing on detecting deepfakes across diverse datasets. Our methodology employs advanced backbone models, including MaxViT, CoAtNet, and EVA-02, fine-tuned using supervised contrastive loss to enhance feature separation. These models were specifically chosen for their complementary strengths. Integration of convolution layers and strided attention in MaxViT is well-suited for detecting local features. In contrast, hybrid use of convolution and attention mechanisms in CoAtNet effectively captures multi-scale features. Robust pretraining with masked image modeling of EVA-02 excels at capturing global features. After training, we freeze the parameters of these models and train the classification heads. Finally, a majority voting ensemble is employed to combine the predictions from these models, improving robustness and generalization to unseen scenarios. The proposed system addresses the challenges of detecting deepfakes in real-world conditions and achieves a commendable accuracy of 95.83% on the validation dataset.
Authors: Darnbi Sakong, Thanh Trung Huynh, Jun Jo
Abstract: Recommender systems rely on Collaborative Filtering (CF) to predict user preferences by leveraging patterns in historical user-item interactions. While traditional CF methods primarily focus on learning compact vector embeddings for users and items, graph neural network (GNN)-based approaches have emerged as a powerful alternative, utilizing the structure of user-item interaction graphs to enhance recommendation accuracy. However, existing GNN-based models, such as LightGCN and UltraGCN, often struggle with two major limitations: an inability to fully account for heterophilic interactions, where users engage with diverse item categories, and the over-smoothing problem in multi-layer GNNs, which hinders their ability to model complex, high-order relationships. To address these gaps, we introduce WaveHDNN, an innovative wavelet-enhanced hypergraph diffusion framework. WaveHDNN integrates a Heterophily-aware Collaborative Encoder, designed to capture user-item interactions across diverse categories, with a Multi-scale Group-wise Structure Encoder, which leverages wavelet transforms to effectively model localized graph structures. Additionally, cross-view contrastive learning is employed to maintain robust and consistent representations. Experiments on benchmark datasets validate the efficacy of WaveHDNN, demonstrating its superior ability to capture both heterophilic and localized structural information, leading to improved recommendation performance.
Authors: Yinfeng Gao, Qichao Zhang, Da-wei Ding, Dongbin Zhao
Abstract: It is still a challenging topic to make reactive driving behaviors in complex urban environments as road users' intentions are unknown. Model-based reinforcement learning (MBRL) offers great potential to learn a reactive policy by constructing a world model that can provide informative states and imagination training. However, a critical limitation in relevant research lies in the scene-level reconstruction representation learning, which may overlook key interactive vehicles and hardly model the interactive features among vehicles and their long-term intentions. Therefore, this paper presents a novel MBRL method with a predictive individual world model (PIWM) for autonomous driving. PIWM describes the driving environment from an individual-level perspective and captures vehicles' interactive relations and their intentions via trajectory prediction task. Meanwhile, a behavior policy is learned jointly with PIWM. It is trained in PIWM's imagination and effectively navigates in the urban driving scenes leveraging intention-aware latent states. The proposed method is trained and evaluated on simulation environments built upon real-world challenging interactive scenarios. Compared with popular model-free and state-of-the-art model-based reinforcement learning methods, experimental results show that the proposed method achieves the best performance in terms of safety and efficiency.
Authors: Xinyue Shen, Yixin Wu, Yiting Qu, Michael Backes, Savvas Zannettou, Yang Zhang
Abstract: Large Language Models (LLMs) have raised increasing concerns about their misuse in generating hate speech. Among all the efforts to address this issue, hate speech detectors play a crucial role. However, the effectiveness of different detectors against LLM-generated hate speech remains largely unknown. In this paper, we propose HateBench, a framework for benchmarking hate speech detectors on LLM-generated hate speech. We first construct a hate speech dataset of 7,838 samples generated by six widely-used LLMs covering 34 identity groups, with meticulous annotations by three labelers. We then assess the effectiveness of eight representative hate speech detectors on the LLM-generated dataset. Our results show that while detectors are generally effective in identifying LLM-generated hate speech, their performance degrades with newer versions of LLMs. We also reveal the potential of LLM-driven hate campaigns, a new threat that LLMs bring to the field of hate speech detection. By leveraging advanced techniques like adversarial attacks and model stealing attacks, the adversary can intentionally evade the detector and automate hate campaigns online. The most potent adversarial attack achieves an attack success rate of 0.966, and its attack efficiency can be further improved by $13-21\times$ through model stealing attacks with acceptable attack performance. We hope our study can serve as a call to action for the research community and platform moderators to fortify defenses against these emerging threats.
Authors: Surojit Saha, Ross Whitaker
Abstract: Automated interpretation of seismic images using deep learning methods is challenging because of the limited availability of training data. Few-shot learning is a suitable learning paradigm in such scenarios due to its ability to adapt to a new task with limited supervision (small training budget). Existing few-shot semantic segmentation (FSSS) methods fix the number of target classes. Therefore, they do not support joint training on multiple datasets varying in the number of classes. In the context of the interpretation of seismic facies, fixing the number of target classes inhibits the generalization capability of a model trained on one facies dataset to another, which is likely to have a different number of facies. To address this shortcoming, we propose a few-shot semantic segmentation method for interpreting seismic facies that can adapt to the varying number of facies across the dataset, dubbed the AdaSemSeg. In general, the backbone network of FSSS methods is initialized with the statistics learned from the ImageNet dataset for better performance. The lack of such a huge annotated dataset for seismic images motivates using a self-supervised algorithm on seismic datasets to initialize the backbone network. We have trained the AdaSemSeg on three public seismic facies datasets with different numbers of facies and evaluated the proposed method on multiple metrics. The performance of the AdaSemSeg on unseen datasets (not used in training) is better than the prototype-based few-shot method and baselines.
Authors: Wen Wen, Tieliang Gong, Yuxin Dong, Shujian Yu, Weizhan Zhang
Abstract: Multiview learning has drawn widespread attention for its efficacy in leveraging cross-view consensus and complementarity information to achieve a comprehensive representation of data. While multi-view learning has undergone vigorous development and achieved remarkable success, the theoretical understanding of its generalization behavior remains elusive. This paper aims to bridge this gap by developing information-theoretic generalization bounds for multi-view learning, with a particular focus on multi-view reconstruction and classification tasks. Our bounds underscore the importance of capturing both consensus and complementary information from multiple different views to achieve maximally disentangled representations. These results also indicate that applying the multi-view information bottleneck regularizer is beneficial for satisfactory generalization performance. Additionally, we derive novel data-dependent bounds under both leave-one-out and supersample settings, yielding computational tractable and tighter bounds. In the interpolating regime, we further establish the fast-rate bound for multi-view learning, exhibiting a faster convergence rate compared to conventional square-root bounds. Numerical results indicate a strong correlation between the true generalization gap and the derived bounds across various learning scenarios.
Authors: Arvin Tashakori, Arash Tashakori, Gongbo Yang, Z. Jane Wang, Peyman Servati
Abstract: Lightweight, controllable, and physically plausible human motion synthesis is crucial for animation, virtual reality, robotics, and human-computer interaction applications. Existing methods often compromise between computational efficiency, physical realism, or spatial controllability. We propose FlexMotion, a novel framework that leverages a computationally lightweight diffusion model operating in the latent space, eliminating the need for physics simulators and enabling fast and efficient training. FlexMotion employs a multimodal pre-trained Transformer encoder-decoder, integrating joint locations, contact forces, joint actuations and muscle activations to ensure the physical plausibility of the generated motions. FlexMotion also introduces a plug-and-play module, which adds spatial controllability over a range of motion parameters (e.g., joint locations, joint actuations, contact forces, and muscle activations). Our framework achieves realistic motion generation with improved efficiency and control, setting a new benchmark for human motion synthesis. We evaluate FlexMotion on extended datasets and demonstrate its superior performance in terms of realism, physical plausibility, and controllability.
Authors: Kevin Christian Wibisono, Yixin Wang
Abstract: The self-attention mechanism is the backbone of the transformer neural network underlying most large language models. It can capture complex word patterns and long-range dependencies in natural language. This paper introduces exponential family attention (EFA), a probabilistic generative model that extends self-attention to handle high-dimensional sequence, spatial, or spatial-temporal data of mixed data types, including both discrete and continuous observations. The key idea of EFA is to model each observation conditional on all other existing observations, called the context, whose relevance is learned in a data-driven way via an attention-based latent factor model. In particular, unlike static latent embeddings, EFA uses the self-attention mechanism to capture dynamic interactions in the context, where the relevance of each context observations depends on other observations. We establish an identifiability result and provide a generalization guarantee on excess loss for EFA. Across real-world and synthetic data sets -- including U.S. city temperatures, Instacart shopping baskets, and MovieLens ratings -- we find that EFA consistently outperforms existing models in capturing complex latent structures and reconstructing held-out data.
Authors: Sahar Moghimian Hoosh, Ilia Kamyshev, Henni Ouerdane
Abstract: In this paper, a novel neural network architecture is proposed to address the challenges in energy disaggregation algorithms. These challenges include the limited availability of data and the complexity of disaggregating a large number of appliances operating simultaneously. The proposed model utilizes independent component analysis as the backbone of the neural network and is evaluated using the F1-score for varying numbers of appliances working concurrently. Our results demonstrate that the model is less prone to overfitting, exhibits low complexity, and effectively decomposes signals with many individual components. Furthermore, we show that the proposed model outperforms existing algorithms when applied to real-world data.
Authors: Raul Lara-Cabrera, Antonio Gonzalez-Pardo, David Camacho
Abstract: Nowadays, Social Networks have become an essential communication tools producing a large amount of information about their users and their interactions, which can be analysed with Data Mining methods. In the last years, Social Networks are being used to radicalise people. In this paper, we study the performance of a set of indicators and their respective metrics, devoted to assess the risk of radicalisation of a precise individual on three different datasets. Keyword-based metrics, even though depending on the written language, performs well when measuring frustration, perception of discrimination as well as declaration of negative and positive ideas about Western society and Jihadism, respectively. However, metrics based on frequent habits such as writing ellipses are not well enough to characterise a user in risk of radicalisation. The paper presents a detailed description of both, the set of indicators used to asses the radicalisation in Social Networks and the set of datasets used to evaluate them. Finally, an experimental study over these datasets are carried out to evaluate the performance of the metrics considered.
Authors: Diego Deplano, Nicola Bastianello, Mauro Franceschelli, Karl H. Johansson
Abstract: Modern artificial intelligence relies on networks of agents that collect data, process information, and exchange it with neighbors to collaboratively solve optimization and learning problems. This article introduces a novel distributed algorithm to address a broad class of these problems in "open networks", where the number of participating agents may vary due to several factors, such as autonomous decisions, heterogeneous resource availability, or DoS attacks. Extending the current literature, the convergence analysis of the proposed algorithm is based on the newly developed "Theory of Open Operators", which characterizes an operator as open when the set of components to be updated changes over time, yielding to time-varying operators acting on sequences of points of different dimensions and compositions. The mathematical tools and convergence results developed here provide a general framework for evaluating distributed algorithms in open networks, allowing to characterize their performance in terms of the punctual distance from the optimal solution, in contrast with regret-based metrics that assess cumulative performance over a finite-time horizon. As illustrative examples, the proposed algorithm is used to solve dynamic consensus or tracking problems on different metrics of interest, such as average, median, and min/max value, as well as classification problems with logistic loss functions.
Authors: Vijay Kuberan, Sateesh Gedupudi
Abstract: Micro-structured surfaces influence nucleation characteristics and bubble dynamics besides increasing the heat transfer surface area, thus enabling efficient nucleate boiling heat transfer. Modeling the pool boiling heat transfer characteristics of these surfaces under varied conditions is essential in diverse applications. A new empirical correlation for nucleate boiling on microchannel structured surfaces has been proposed with the data collected from various experiments in previous studies since the existing correlations are limited by their accuracy and narrow operating ranges. This study also examines various Machine Learning (ML) algorithms and Deep Neural Networks (DNN) on the microchannel structured surfaces dataset to predict the nucleate pool boiling Heat Transfer Coefficient (HTC). With the aim to integrate both the ML and domain knowledge, a Physics-Informed Machine Learning Aided Framework (PIMLAF) is proposed. The proposed correlation in this study is employed as the prior physics-based model for PIMLAF, and a DNN is employed to model the residuals of the prior model. This hybrid framework achieved the best performance in comparison to the other ML models and DNNs. This framework is able to generalize well for different datasets because the proposed correlation provides the baseline knowledge of the boiling behavior. Also, SHAP interpretation analysis identifies the critical parameters impacting the model predictions and their effect on HTC prediction. This analysis further makes the model more robust and reliable. Keywords: Pool boiling, Microchannels, Heat transfer coefficient, Correlation analysis, Machine learning, Deep neural network, Physics-informed machine learning aided framework, SHAP analysis
Authors: Xixuan Yang, Xin Huang, Chiming Duan, Tong Jia, Shandong Dong, Ying Li, Gang Huang
Abstract: Anomaly detection is crucial for ensuring the stability and reliability of web service systems. Logs and metrics contain multiple information that can reflect the system's operational state and potential anomalies. Thus, existing anomaly detection methods use logs and metrics to detect web service systems' anomalies through data fusion approaches. They associate logs and metrics using coarse-grained time window alignment and capture the normal patterns of system operation through reconstruction. However, these methods have two issues that limit their performance in anomaly detection. First, due to asynchrony between logs and metrics, coarse-grained time window alignment cannot achieve a precise association between the two modalities. Second, reconstruction-based methods suffer from severe overgeneralization problems, resulting in anomalies being accurately reconstructed. In this paper, we propose a novel anomaly detection method named FFAD to address these two issues. On the one hand, FFAD employs graph-based alignment to mine and extract associations between the modalities from the constructed log-metric relation graph, achieving precise associations between logs and metrics. On the other hand, we improve the model's fit to normal data distributions through Fourier Frequency Focus, thereby enhancing the effectiveness of anomaly detection. We validated the effectiveness of our model on two real-world industrial datasets and one open-source dataset. The results show that our method achieves an average anomaly detection F1-score of 93.6%, representing an 8.8% improvement over previous state-of-the-art methods.
Authors: Zeki Doruk Erden, Boi Faltings
Abstract: Contemporary machine learning paradigm excels in statistical data analysis, solving problems that classical AI couldn't. However, it faces key limitations, such as a lack of integration with planning, incomprehensible internal structure, and inability to learn continually. We present the initial design for an AI system, Agential AI (AAI), in principle operating independently or on top of statistical methods, designed to overcome these issues. AAI's core is a learning method that models temporal dynamics with guarantees of completeness, minimality, and continual learning, using component-level variation and selection to learn the structure of the environment. It integrates this with a behavior algorithm that plans on a learned model and encapsulates high-level behavior patterns. Preliminary experiments on a simple environment show AAI's effectiveness and potential.
Authors: Zheng Zheng (Brandeis University), Xinyi Ni (Brandeis University), Pengyu Hong (Brandeis University)
Abstract: A Retrieval-Augmented Generation (RAG) model powered by a large language model (LLM) provides a faster and more cost-effective solution for adapting to new data and knowledge. It also delivers more specialized responses compared to pre-trained LLMs. However, most existing approaches rely on retrieving prefix-sized chunks as references to support question-answering (Q/A). This approach is often deployed to address information needs at a single level of abstraction, as it struggles to generate answers across multiple levels of abstraction. In an RAG setting, while LLMs can summarize and answer questions effectively when provided with sufficient details, retrieving excessive information often leads to the 'lost in the middle' problem and exceeds token limitations. We propose a novel RAG approach that uses chunks of multiple abstraction levels (MAL), including multi-sentence-level, paragraph-level, section-level, and document-level. The effectiveness of our approach is demonstrated in an under-explored scientific domain of Glycoscience. Compared to traditional single-level RAG approaches, our approach improves AI evaluated answer correctness of Q/A by 25.739\% on Glyco-related papers.
Authors: Hossein Mirzaei, Mohammad Jafari, Hamid Reza Dehbashi, Ali Ansari, Sepehr Ghobadi, Masoud Hadi, Arshia Soltani Moakhar, Mohammad Azizmalayeri, Mahdieh Soleymani Baghshah, Mohammad Hossein Rohban
Abstract: In recent years, there have been significant improvements in various forms of image outlier detection. However, outlier detection performance under adversarial settings lags far behind that in standard settings. This is due to the lack of effective exposure to adversarial scenarios during training, especially on unseen outliers, leading to detection models failing to learn robust features. To bridge this gap, we introduce RODEO, a data-centric approach that generates effective outliers for robust outlier detection. More specifically, we show that incorporating outlier exposure (OE) and adversarial training can be an effective strategy for this purpose, as long as the exposed training outliers meet certain characteristics, including diversity, and both conceptual differentiability and analogy to the inlier samples. We leverage a text-to-image model to achieve this goal. We demonstrate both quantitatively and qualitatively that our adaptive OE method effectively generates ``diverse'' and ``near-distribution'' outliers, leveraging information from both text and image domains. Moreover, our experimental results show that utilizing our synthesized outliers significantly enhances the performance of the outlier detector, particularly in adversarial settings.
Authors: Maximilian X. Tiefenbacher, Brigitta Bachmair, Cheng Giuseppe Chen, Julia Westermayr, Philipp Marquetand, Johannes C. B. Dietschreit, Leticia Gonz\'alez
Abstract: Excited-state nonadiabatic simulations with quantum mechanics/molecular mechanics (QM/MM) are essential to understand photoinduced processes in explicit environments. However, the high computational cost of the underlying quantum chemical calculations limits its application in combination with trajectory surface hopping methods. Here, we use FieldSchNet, a machine-learned interatomic potential capable of incorporating electric field effects into the electronic states, to replace traditional QM/MM electrostatic embedding with its ML/MM counterpart for nonadiabatic excited state trajectories. The developed method is applied to furan in water, including five coupled singlet states. Our results demonstrate that with sufficiently curated training data, the ML/MM model reproduces the electronic kinetics and structural rearrangements of QM/MM surface hopping reference simulations. Furthermore, we identify performance metrics that provide robust and interpretable validation of model accuracy.
Authors: Hongzhi Huang, Defa Zhu, Banggu Wu, Yutao Zeng, Ya Wang, Qiyang Min, Xun Zhou
Abstract: Tokenization is a fundamental component of large language models (LLMs), yet its influence on model scaling and performance is not fully explored. In this paper, we introduce Over-Tokenized Transformers, a novel framework that decouples input and output vocabularies to improve language modeling performance. Specifically, our approach scales up input vocabularies to leverage multi-gram tokens. Through extensive experiments, we uncover a log-linear relationship between input vocabulary size and training loss, demonstrating that larger input vocabularies consistently enhance model performance, regardless of model size. Using a large input vocabulary, we achieve performance comparable to double-sized baselines with no additional cost. Our findings highlight the importance of tokenization in scaling laws and provide practical insight for tokenizer design, paving the way for more efficient and powerful LLMs.
Authors: Shunya Minami, Kouhei Nakaji, Yohichi Suzuki, Al\'an Aspuru-Guzik, Tadashi Kadowaki
Abstract: Quantum computing is entering a transformative phase with the emergence of logical quantum processors, which hold the potential to tackle complex problems beyond classical capabilities. While significant progress has been made, applying quantum algorithms to real-world problems remains challenging. Hybrid quantum-classical techniques have been explored to bridge this gap, but they often face limitations in expressiveness, trainability, or scalability. In this work, we introduce conditional Generative Quantum Eigensolver (conditional-GQE), a context-aware quantum circuit generator powered by an encoder-decoder Transformer. Focusing on combinatorial optimization, we train our generator for solving problems with up to 10 qubits, exhibiting nearly perfect performance on new problems. By leveraging the high expressiveness and flexibility of classical generative models, along with an efficient preference-based training scheme, conditional-GQE provides a generalizable and scalable framework for quantum circuit generation. Our approach advances hybrid quantum-classical computing and contributes to accelerate the transition toward fault-tolerant quantum computing.
Authors: Mohammad Kaviul Anam Khan, Olli Saarela, Rafal Kustra
Abstract: Interpreting black-box machine learning models is challenging due to their strong dependence on data and inherently non-parametric nature. This paper reintroduces the concept of importance through "Marginal Variable Importance Metric" (MVIM), a model-agnostic measure of predictor importance based on the true conditional expectation function. MVIM evaluates predictors' influence on continuous or discrete outcomes. A permutation-based estimation approach, inspired by \citet{breiman2001random} and \citet{fisher2019all}, is proposed to estimate MVIM. MVIM estimator is biased when predictors are highly correlated, as black-box models struggle to extrapolate in low-probability regions. To address this, we investigated the bias-variance decomposition of MVIM to understand the source and pattern of the bias under high correlation. A Conditional Variable Importance Metric (CVIM), adapted from \citet{strobl2008conditional}, is introduced to reduce this bias. Both MVIM and CVIM exhibit a quadratic relationship with the conditional average treatment effect (CATE).
Authors: Shreyam Gupta (Indian Institute of Technology), P. Agrawal (University of Colorado, Boulder, USA), Priyam Gupta (Intelligent Field Robotic Systems)
Abstract: Temporal sequence modeling stands as the fundamental foundation for video prediction systems and real-time forecasting operations as well as anomaly detection applications. The achievement of accurate predictions through efficient resource consumption remains an ongoing issue in contemporary temporal sequence modeling. We introduce the Multi-Attention Unit (MAUCell) which combines Generative Adversarial Networks (GANs) and spatio-temporal attention mechanisms to improve video frame prediction capabilities. Our approach implements three types of attention models to capture intricate motion sequences. A dynamic combination of these attention outputs allows the model to reach both advanced decision accuracy along with superior quality while remaining computationally efficient. The integration of GAN elements makes generated frames appear more true to life therefore the framework creates output sequences which mimic real-world footage. The new design system maintains equilibrium between temporal continuity and spatial accuracy to deliver reliable video prediction. Through a comprehensive evaluation methodology which merged the perceptual LPIPS measurement together with classic tests MSE, MAE, SSIM and PSNR exhibited enhancing capabilities than contemporary approaches based on direct benchmark tests of Moving MNIST, KTH Action, and CASIA-B (Preprocessed) datasets. Our examination indicates that MAUCell shows promise for operational time requirements. The research findings demonstrate how GANs work best with attention mechanisms to create better applications for predicting video sequences.
Authors: Philippe Pasquier, Jeff Ens, Nathan Fradet, Paul Triana, Davide Rizzotti, Jean-Baptiste Rolland, Maryam Safi
Abstract: We present and release MIDI-GPT, a generative system based on the Transformer architecture that is designed for computer-assisted music composition workflows. MIDI-GPT supports the infilling of musical material at the track and bar level, and can condition generation on attributes including: instrument type, musical style, note density, polyphony level, and note duration. In order to integrate these features, we employ an alternative representation for musical material, creating a time-ordered sequence of musical events for each track and concatenating several tracks into a single sequence, rather than using a single time-ordered sequence where the musical events corresponding to different tracks are interleaved. We also propose a variation of our representation allowing for expressiveness. We present experimental results that demonstrate that MIDI-GPT is able to consistently avoid duplicating the musical material it was trained on, generate music that is stylistically similar to the training dataset, and that attribute controls allow enforcing various constraints on the generated material. We also outline several real-world applications of MIDI-GPT, including collaborations with industry partners that explore the integration and evaluation of MIDI-GPT into commercial products, as well as several artistic works produced using it.
Authors: Max Dax, Jordi Berbel, Jan Stria, Leonidas Guibas, Urs Bergmann
Abstract: We generate abstractions of buildings, reflecting the essential aspects of their geometry and structure, by learning to invert procedural models. We first build a dataset of abstract procedural building models paired with simulated point clouds and then learn the inverse mapping through a transformer. Given a point cloud, the trained transformer then infers the corresponding abstracted building in terms of a programmatic language description. This approach leverages expressive procedural models developed for gaming and animation, and thereby retains desirable properties such as efficient rendering of the inferred abstractions and strong priors for regularity and symmetry. Our approach achieves good reconstruction accuracy in terms of geometry and structure, as well as structurally consistent inpainting.
Authors: Alexander Mielke, Jia-Jie Zhu
Abstract: We investigate a family of gradient flows of positive and probability measures, focusing on the Hellinger-Kantorovich (HK) geometry, which unifies transport mechanism of Otto-Wasserstein, and the birth-death mechanism of Hellinger (or Fisher-Rao). A central contribution is a complete characterization of global exponential decay behaviors of entropy functionals (e.g. KL, $\chi^2$) under Otto-Wasserstein and Hellinger-type gradient flows. In particular, for the more challenging analysis of HK gradient flows on positive measures -- where the typical log-Sobolev arguments fail -- we develop a specialized shape-mass decomposition that enables new analysis results. Our approach also leverages the (Polyak-)\L{}ojasiewicz-type functional inequalities and a careful extension of classical dissipation estimates. These findings provide a unified and complete theoretical framework for gradient flows and underpin applications in computational algorithms for statistical inference, optimization, and machine learning.
Authors: Fei Cao (University of Massachusetts Amherst), Kimball Johnston (Arizona State University), Thomas Laurent (Loyola Marymount University), Justin Le (Arizona State University), S\'ebastien Motsch (Arizona State University)
Abstract: Diffusion models have become the de facto framework for generating new datasets. The core of these models lies in the ability to reverse a diffusion process in time. The goal of this manuscript is to explain, from a PDE perspective, how this method works and how to derive the PDE governing the reverse dynamics as well as to study its solution analytically. By linking forward and reverse dynamics, we show that the reverse process's distribution has its support contained within the original distribution. Consequently, diffusion methods, in their analytical formulation, do not inherently regularize the original distribution, and thus, there is no generalization principle. This raises a question: where does generalization arise, given that in practice it does occur? Moreover, we derive an explicit solution to the reverse process's SDE under the assumption that the starting point of the forward process is fixed. This provides a new derivation that links two popular approaches to generative diffusion models: stable diffusion (discrete dynamics) and the score-based approach (continuous dynamics). Finally, we explore the case where the original distribution consists of a finite set of data points. In this scenario, the reverse dynamics are explicit (i.e., the loss function has a clear minimizer), and solving the dynamics fails to generate new samples: the dynamics converge to the original samples. In a sense, solving the minimization problem exactly is "too good for its own good" (i.e., an overfitting regime).
Authors: Lillian Tsai, Eugene Bagdasarian
Abstract: Judging the safety of an action, whether taken by a human or a system, must take into account the context in which the action takes place. Deleting an email from user's mailbox may or may not be appropriate depending on email's content, user's goals, or even available space. Systems today that make these judgements -- providing security against harmful or inappropriate actions -- rely on manually-crafted policies or user confirmation for each relevant context. With the upcoming deployment of systems like generalist agents, we argue that we must rethink security designs to adapt to the scale of contexts and capabilities of these systems. As a first step, this paper explores contextual security in the domain of agents and proposes contextual security for agents (Conseca), a framework to generate just-in-time, contextual, and human-verifiable security policies.
Authors: Christian Fabian, Kai Cui, Heinz Koeppl
Abstract: Large agent networks are abundant in applications and nature and pose difficult challenges in the field of multi-agent reinforcement learning (MARL) due to their computational and theoretical complexity. While graphon mean field games and their extensions provide efficient learning algorithms for dense and moderately sparse agent networks, the case of realistic sparser graphs remains largely unsolved. Thus, we propose a novel mean field control model inspired by local weak convergence to include sparse graphs such as power law networks with coefficients above two. Besides a theoretical analysis, we design scalable learning algorithms which apply to the challenging class of graph sequences with finite first moment. We compare our model and algorithms for various examples on synthetic and real world networks with mean field algorithms based on Lp graphons and graphexes. As it turns out, our approach outperforms existing methods in many examples and on various networks due to the special design aiming at an important, but so far hard to solve class of MARL problems.
Authors: Nuwan T. Attygalle, Matja\v{z} Kljun, Aaron Quigley, Klen \v{c}Opi\v{c} Pucihar, Jens Grubert, Verena Biener, Luis A. Leiva, Juri Yoneyama, Alice Toniolo, Angela Miguel, Hirokazu Kato, Maheshya Weerasinghe
Abstract: The 'keyword method' is an effective technique for learning vocabulary of a foreign language. It involves creating a memorable visual link between what a word means and what its pronunciation in a foreign language sounds like in the learner's native language. However, these memorable visual links remain implicit in the people's mind and are not easy to remember for a large set of words. To enhance the memorisation and recall of the vocabulary, we developed an application that combines the keyword method with text-to-image generators to externalise the memorable visual links into visuals. These visuals represent additional stimuli during the memorisation process. To explore the effectiveness of this approach we first run a pilot study to investigate how difficult it is to externalise the descriptions of mental visualisations of memorable links, by asking participants to write them down. We used these descriptions as prompts for text-to-image generator (DALL-E2) to convert them into images and asked participants to select their favourites. Next, we compared different text-to-image generators (DALL-E2, Midjourney, Stable and Latent Diffusion) to evaluate the perceived quality of the generated images by each. Despite heterogeneous results, participants mostly preferred images generated by DALL-E2, which was used also for the final study. In this study, we investigated whether providing such images enhances the retention of vocabulary being learned, compared to the keyword method only. Our results indicate that people did not encounter difficulties describing their visualisations of memorable links and that providing corresponding images significantly improves memory retention.
Authors: Matthieu Darcy, Edoardo Calvello, Ricardo Baptista, Houman Owhadi, Andrew M. Stuart, Xianjin Yang
Abstract: We consider the use of Gaussian Processes (GPs) or Neural Networks (NNs) to numerically approximate the solutions to nonlinear partial differential equations (PDEs) with rough forcing or source terms, which commonly arise as pathwise solutions to stochastic PDEs. Kernel methods have recently been generalized to solve nonlinear PDEs by approximating their solutions as the maximum a posteriori estimator of GPs that are conditioned to satisfy the PDE at a finite set of collocation points. The convergence and error guarantees of these methods, however, rely on the PDE being defined in a classical sense and its solution possessing sufficient regularity to belong to the associated reproducing kernel Hilbert space. We propose a generalization of these methods to handle roughly forced nonlinear PDEs while preserving convergence guarantees with an oversmoothing GP kernel that is misspecified relative to the true solution's regularity. This is achieved by conditioning a regular GP to satisfy the PDE with a modified source term in a weak sense (when integrated against a finite number of test functions). This is equivalent to replacing the empirical $L^2$-loss on the PDE constraint by an empirical negative-Sobolev norm. We further show that this loss function can be used to extend physics-informed neural networks (PINNs) to stochastic equations, thereby resulting in a new NN-based variant termed Negative Sobolev Norm-PINN (NeS-PINN).
Authors: Jing An, Jianfeng Lu
Abstract: The two-timescale gradient descent-ascent (GDA) is a canonical gradient algorithm designed to find Nash equilibria in min-max games. We analyze the two-timescale GDA by investigating the effects of learning rate ratios on convergence behavior in both finite-dimensional and mean-field settings. In particular, for finite-dimensional quadratic min-max games, we obtain long-time convergence in near quasi-static regimes through the hypocoercivity method. For mean-field GDA dynamics, we investigate convergence under a finite-scale ratio using a mixed synchronous-reflection coupling technique.
Authors: Zhengxuan Wu, Aryaman Arora, Atticus Geiger, Zheng Wang, Jing Huang, Dan Jurafsky, Christopher D. Manning, Christopher Potts
Abstract: Fine-grained steering of language model outputs is essential for safety and reliability. Prompting and finetuning are widely used to achieve these goals, but interpretability researchers have proposed a variety of representation-based techniques as well, including sparse autoencoders (SAEs), linear artificial tomography, supervised steering vectors, linear probes, and representation finetuning. At present, there is no benchmark for making direct comparisons between these proposals. Therefore, we introduce AxBench, a large-scale benchmark for steering and concept detection, and report experiments on Gemma-2-2B and 9B. For steering, we find that prompting outperforms all existing methods, followed by finetuning. For concept detection, representation-based methods such as difference-in-means, perform the best. On both evaluations, SAEs are not competitive. We introduce a novel weakly-supervised representational method (Rank-1 Representation Finetuning; ReFT-r1), which is competitive on both tasks while providing the interpretability advantages that prompting lacks. Along with AxBench, we train and publicly release SAE-scale feature dictionaries for ReFT-r1 and DiffMean.
Authors: Tianzhe Chu, Yuexiang Zhai, Jihan Yang, Shengbang Tong, Saining Xie, Dale Schuurmans, Quoc V. Le, Sergey Levine, Yi Ma
Abstract: Supervised fine-tuning (SFT) and reinforcement learning (RL) are widely used post-training techniques for foundation models. However, their roles in enhancing model generalization capabilities remain unclear. This paper studies the difference between SFT and RL on generalization and memorization, focusing on text-based rule variants and visual variants. We introduce GeneralPoints, an arithmetic reasoning card game, and adopt V-IRL, a real-world navigation environment, to assess how models trained with SFT and RL generalize to unseen variants in both textual and visual domains. We show that RL, especially when trained with an outcome-based reward, generalizes across both rule-based textual and visual variants. SFT, in contrast, tends to memorize training data and struggles to generalize out-of-distribution scenarios. Further analysis reveals that RL improves the model's underlying visual recognition capabilities, contributing to its enhanced generalization in the visual domain. Despite RL's superior generalization, we show that SFT remains essential for effective RL training; SFT stabilizes the model's output format, enabling subsequent RL to achieve its performance gains. These findings demonstrates the capability of RL for acquiring generalizable knowledge in complex, multi-modal tasks.
Authors: Nikolai Kalischek, Michael Oechsle, Fabian Manhardt, Philipp Henzler, Konrad Schindler, Federico Tombari
Abstract: We introduce a novel method for generating 360{\deg} panoramas from text prompts or images. Our approach leverages recent advances in 3D generation by employing multi-view diffusion models to jointly synthesize the six faces of a cubemap. Unlike previous methods that rely on processing equirectangular projections or autoregressive generation, our method treats each face as a standard perspective image, simplifying the generation process and enabling the use of existing multi-view diffusion models. We demonstrate that these models can be adapted to produce high-quality cubemaps without requiring correspondence-aware attention layers. Our model allows for fine-grained text control, generates high resolution panorama images and generalizes well beyond its training set, whilst achieving state-of-the-art results, both qualitatively and quantitatively. Project page: https://cubediff.github.io/
Authors: Javier Garcia-Barcos, Ruben Martinez-Cantin
Abstract: Complex robot navigation and control problems can be framed as policy search problems. However, interactive learning in uncertain environments can be expensive, requiring the use of data-efficient methods. Bayesian optimization is an efficient nonlinear optimization method where queries are carefully selected to gather information about the optimum location. This is achieved by a surrogate model, which encodes past information, and the acquisition function for query selection. Bayesian optimization can be very sensitive to uncertainty in the input data or prior assumptions. In this work, we incorporate both robust optimization and statistical robustness, showing that both types of robustness are synergistic. For robust optimization we use an improved version of unscented Bayesian optimization which provides safe and repeatable policies in the presence of policy uncertainty. We also provide new theoretical insights. For statistical robustness, we use an adaptive surrogate model and we introduce the Boltzmann selection as a stochastic acquisition method to have convergence guarantees and improved performance even with surrogate modeling errors. We present results in several optimization benchmarks and robot tasks.
Authors: Hanrui Wang, Jiaqi Gu, Yongshan Ding, Zirui Li, Frederic T. Chong, David Z. Pan, Song Han
Abstract: Parameterized Quantum Circuits (PQC) are promising towards quantum advantage on near-term quantum hardware. However, due to the large quantum noises (errors), the performance of PQC models has a severe degradation on real quantum devices. Take Quantum Neural Network (QNN) as an example, the accuracy gap between noise-free simulation and noisy results on IBMQ-Yorktown for MNIST-4 classification is over 60%. Existing noise mitigation methods are general ones without leveraging unique characteristics of PQC; on the other hand, existing PQC work does not consider noise effect. To this end, we present QuantumNAT, a PQC-specific framework to perform noise-aware optimizations in both training and inference stages to improve robustness. We experimentally observe that the effect of quantum noise to PQC measurement outcome is a linear map from noise-free outcome with a scaling and a shift factor. Motivated by that, we propose post-measurement normalization to mitigate the feature distribution differences between noise-free and noisy scenarios. Furthermore, to improve the robustness against noise, we propose noise injection to the training process by inserting quantum error gates to PQC according to realistic noise models of quantum hardware. Finally, post-measurement quantization is introduced to quantize the measurement outcomes to discrete values, achieving the denoising effect. Extensive experiments on 8 classification tasks using 6 quantum devices demonstrate that QuantumNAT improves accuracy by up to 43%, and achieves over 94% 2-class, 80% 4-class, and 34% 10-class classification accuracy measured on real quantum computers. The code for construction and noise-aware training of PQC is available in the TorchQuantum library.
Authors: Felix Mohr, Jan N. van Rijn
Abstract: Learning curves are a concept from social sciences that has been adopted in the context of machine learning to assess the performance of a learning algorithm with respect to a certain resource, e.g., the number of training examples or the number of training iterations. Learning curves have important applications in several machine learning contexts, most notably in data acquisition, early stopping of model training, and model selection. For instance, learning curves can be used to model the performance of the combination of an algorithm and its hyperparameter configuration, providing insights into their potential suitability at an early stage and often expediting the algorithm selection process. Various learning curve models have been proposed to use learning curves for decision making. Some of these models answer the binary decision question of whether a given algorithm at a certain budget will outperform a certain reference performance, whereas more complex models predict the entire learning curve of an algorithm. We contribute a framework that categorises learning curve approaches using three criteria: the decision-making situation they address, the intrinsic learning curve question they answer and the type of resources they use. We survey papers from the literature and classify them into this framework.
Authors: Shireen Kudukkil Manchingal, Muhammad Mubashar, Kaizheng Wang, Keivan Shariatmadar, Fabio Cuzzolin
Abstract: Machine learning is increasingly deployed in safety-critical domains where erroneous predictions may lead to potentially catastrophic consequences, highlighting the need for learning systems to be aware of how confident they are in their own predictions: in other words, 'to know when they do not know'. In this paper, we propose a novel Random-Set Neural Network (RS-NN) approach to classification which predicts belief functions (rather than classical probability vectors) over the class list using the mathematics of random sets, i.e., distributions over the collection of sets of classes. RS-NN encodes the 'epistemic' uncertainty induced by training sets that are insufficiently representative or limited in size via the size of the convex set of probability vectors associated with a predicted belief function. Our approach outperforms state-of-the-art Bayesian and Ensemble methods in terms of accuracy, uncertainty estimation and out-of-distribution (OoD) detection on multiple benchmarks (CIFAR-10 vs SVHN/Intel-Image, MNIST vs FMNIST/KMNIST, ImageNet vs ImageNet-O). RS-NN also scales up effectively to large-scale architectures (e.g. WideResNet-28-10, VGG16, Inception V3, EfficientNetB2 and ViT-Base-16), exhibits remarkable robustness to adversarial attacks and can provide statistical guarantees in a conformal learning setting.
Authors: Khashayar Khosravi, Renato Paes Leme, Chara Podimata, Apostolis Tsorvantzis
Abstract: We propose a model for learning with bandit feedback while accounting for deterministically evolving and unobservable states that we call Bandits with Deterministically Evolving States ($B$-$DES$). The workhorse applications of our model are learning for recommendation systems and learning for online ads. In both cases, the reward that the algorithm obtains at each round is a function of the short-term reward of the action chosen and how "healthy" the system is (i.e., as measured by its state). For example, in recommendation systems, the reward that the platform obtains from a user's engagement with a particular type of content depends not only on the inherent features of the specific content, but also on how the user's preferences have evolved as a result of interacting with other types of content on the platform. Our general model accounts for the different rate $\lambda \in [0,1]$ at which the state evolves (e.g., how fast a user's preferences shift as a result of previous content consumption) and encompasses standard multi-armed bandits as a special case. The goal of the algorithm is to minimize a notion of regret against the best-fixed sequence of arms pulled, which is significantly harder to attain compared to standard benchmark of the best-fixed action in hindsight. We present online learning algorithms for any possible value of the evolution rate $\lambda$ and we show the robustness of our results to various model misspecifications.
Authors: Corentin Sala\"un, Xingchang Huang, Iliyan Georgiev, Niloy J. Mitra, Gurprit Singh
Abstract: Machine learning optimization often depends on stochastic gradient descent, where the precision of gradient estimation is vital for model performance. Gradients are calculated from mini-batches formed by uniformly selecting data samples from the training dataset. However, not all data samples contribute equally to gradient estimation. To address this, various importance sampling strategies have been developed to prioritize more significant samples. Despite these advancements, all current importance sampling methods encounter challenges related to computational efficiency and seamless integration into practical machine learning pipelines. In this work, we propose a practical algorithm that efficiently computes data importance on-the-fly during training, eliminating the need for dataset preprocessing. We also introduce a novel metric based on the derivative of the loss w.r.t. the network output, designed for mini-batch importance sampling. Our metric prioritizes influential data points, thereby enhancing gradient estimation accuracy. We demonstrate the effectiveness of our approach across various applications. We first perform classification and regression tasks to demonstrate improvements in accuracy. Then, we show how our approach can also be used for online data pruning by identifying and discarding data samples that contribute minimally towards the training loss. This significantly reduce training time with negligible loss in the accuracy of the model.
Authors: Vivswan Shah, Nathan Youngblood
Abstract: Real-world analog systems intrinsically suffer from noise that can impede model convergence and accuracy on a variety of deep learning models. We demonstrate that differentiable activations like GELU and SiLU enable robust propagation of gradients which help to mitigate analog quantization error that is ubiquitous to all analog systems. We perform analysis and training of convolutional, linear, and transformer networks in the presence of quantized noise. Here, we are able to demonstrate that continuously differentiable activation functions are significantly more noise resilient over conventional rectified activations. As in the case of ReLU, the error in gradients are 100x higher than those in GELU near zero. Our findings provide guidance for selecting appropriate activations to realize performant and reliable hardware implementations across several machine learning domains such as computer vision, signal processing, and beyond. Code available at: \href{https://github.com/Vivswan/GeLUReLUInterpolation}{https://github.com/Vivswan/GeLUReLUInterpolation}.}
URLs: https://github.com/Vivswan/GeLUReLUInterpolation, https://github.com/Vivswan/GeLUReLUInterpolation
Authors: Wenhao Zheng, Liaoyaqi Wang, Dongshen Peng, Hongxia Xu, Yun Li, Hongtu Zhu, Tianfan Fu, Huaxiu Yao
Abstract: The clinical trial is a pivotal and costly process, often spanning multiple years and requiring substantial financial resources. Therefore, the development of clinical trial outcome prediction models aims to exclude drugs likely to fail and holds the potential for significant cost savings. Recent data-driven attempts leverage deep learning methods to integrate multimodal data for predicting clinical trial outcomes. However, these approaches rely on manually designed modal-specific encoders, which limits both the extensibility to adapt new modalities and the ability to discern similar information patterns across different modalities. To address these issues, we propose a multimodal mixture-of-experts (LIFTED) approach for clinical trial outcome prediction. Specifically, LIFTED unifies different modality data by transforming them into natural language descriptions. Then, LIFTED constructs unified noise-resilient encoders to extract information from modal-specific language descriptions. Subsequently, a sparse Mixture-of-Experts framework is employed to further refine the representations, enabling LIFTED to identify similar information patterns across different modalities and extract more consistent representations from those patterns using the same expert model. Finally, a mixture-of-experts module is further employed to dynamically integrate different modality representations for prediction, which gives LIFTED the ability to automatically weigh different modalities and pay more attention to critical information. The experiments demonstrate that LIFTED significantly enhances performance in predicting clinical trial outcomes across all three phases compared to the best baseline, showcasing the effectiveness of our proposed key components.
Authors: Zhe Li, Bicheng Ying, Zidong Liu, Chaosheng Dong, Haibo Yang
Abstract: Federated Learning (FL) offers a promising framework for collaborative and privacy-preserving machine learning across distributed data sources. However, the substantial communication costs associated with FL significantly challenge its efficiency. Specifically, in each communication round, the communication costs scale linearly with the model's dimension, which presents a formidable obstacle, especially in large model scenarios. Despite various communication-efficient strategies, the intrinsic dimension-dependent communication cost remains a major bottleneck for current FL implementations. This paper proposes a novel dimension-free communication algorithm - DeComFL, which leverages the zeroth-order optimization techniques and reduces the communication cost from $\mathscr{O}(d)$ to $\mathscr{O}(1)$ by transmitting only a constant number of scalar values between clients and the server in each round, regardless of the dimension $d$ of the model parameters. Theoretically, in non-convex functions, we prove that our algorithm achieves state-of-the-art rates, which show a linear speedup of the number of clients and local steps under standard assumptions. With additional low effective rank assumption, we can further show the convergence rate is independent of the model dimension $d$ as well. Empirical evaluations, encompassing both classic deep learning training and large language model fine-tuning, demonstrate significant reductions in communication overhead. Notably, DeComFL achieves this by transmitting only around 1MB of data in total between the server and a client to fine-tune a model with billions of parameters. Our code is available at https://github.com/ZidongLiu/DeComFL.
Authors: Deng Pan, Nuno Moniz, Nitesh Chawla
Abstract: The challenge of delivering efficient explanations is a critical barrier that prevents the adoption of model explanations in real-world applications. Existing approaches often depend on extensive model queries for sample-level explanations or rely on expert's knowledge of specific model structures that trade general applicability for efficiency. To address these limitations, this paper introduces a novel framework Fast Explanation (FEX) that represents attribution-based explanations via probability distributions, which are optimized by leveraging the policy gradient method. The proposed framework offers a robust, scalable solution for real-time, large-scale model explanations, bridging the gap between efficiency and applicability. We validate our framework on image and text classification tasks and the experiments demonstrate that our method reduces inference time by over 97% and memory usage by 70% compared to traditional model-agnostic approaches while maintaining high-quality explanations and broad applicability.
Authors: Simla Burcu Harma, Ayan Chakraborty, Elizaveta Kostenok, Danila Mishin, Dongho Ha, Babak Falsafi, Martin Jaggi, Ming Liu, Yunho Oh, Suvinay Subramanian, Amir Yazdanbakhsh
Abstract: The increasing size of deep neural networks (DNNs) necessitates effective model compression to reduce their computational and memory footprints. Sparsity and quantization are two prominent compression methods that have been shown to reduce DNNs' computational and memory footprints significantly while preserving model accuracy. However, how these two methods interact when combined together remains a key question for developers, as many tacitly assume that they are orthogonal, meaning that their combined use does not introduce additional errors beyond those introduced by each method independently. In this paper, we provide the first mathematical proof that sparsity and quantization are non-orthogonal. We corroborate these results with experiments spanning a range of large language models, including the OPT and LLaMA model families (with 125M to 8B parameters), and vision models like ViT and ResNet. We show that the order in which we apply these methods matters because applying quantization before sparsity may disrupt the relative importance of tensor elements, which may inadvertently remove significant elements from a tensor. More importantly, we show that even if applied in the correct order, the compounded errors from sparsity and quantization can significantly harm accuracy. Our findings extend to the efficient deployment of large models in resource-constrained compute platforms to reduce serving cost, offering insights into best practices for applying these compression methods to maximize hardware resource efficiency without compromising accuracy.
Authors: Corentin Sala\"un, Xingchang Huang, Iliyan Georgiev, Niloy J. Mitra, Gurprit Singh
Abstract: We introduce a theoretical and practical framework for efficient importance sampling of mini-batch samples for gradient estimation from single and multiple probability distributions. To handle noisy gradients, our framework dynamically evolves the importance distribution during training by utilizing a self-adaptive metric. Our framework combines multiple, diverse sampling distributions, each tailored to specific parameter gradients. This approach facilitates the importance sampling of vector-valued gradient estimation. Rather than naively combining multiple distributions, our framework involves optimally weighting data contribution across multiple distributions. This adapted combination of multiple importance yields superior gradient estimates, leading to faster training convergence. We demonstrate the effectiveness of our approach through empirical evaluations across a range of optimization tasks like classification and regression on both image and point cloud datasets.
Authors: Minheng Xiao, Shi Bo
Abstract: Imbalanced datasets pose significant challenges in areas including neuroscience, cognitive science, and medical diagnostics, where accurately detecting minority classes is essential for robust model performance. This study addresses the issue of class imbalance, using the `Liking' label in the DEAP dataset as an example. Such imbalances are often overlooked by prior research, which typically focuses on the more balanced arousal and valence labels and predominantly uses accuracy metrics to measure model performance. To tackle this issue, we adopt numerical optimization techniques aimed at maximizing the area under the curve (AUC), thus enhancing the detection of underrepresented classes. Our approach, which begins with a linear classifier, is compared against traditional linear classifiers, including logistic regression and support vector machines (SVM). Our method significantly outperforms these models, increasing recall from 41.6\% to 79.7\% and improving the F1-score from 0.506 to 0.632. These results highlight the efficacy of AUC maximization via numerical optimization in managing imbalanced datasets, providing an effective solution for enhancing predictive accuracy in detecting minority but crucial classes in out-of-sample datasets.
Authors: Xin Li, Zhihong Xia, Hongkun Zhang
Abstract: We have developed a novel activation function, named the Cauchy Activation Function. This function is derived from the Cauchy Integral Theorem in complex analysis and is specifically tailored for problems requiring high precision. This innovation has led to the creation of a new class of neural networks, which we call (Comple)XNet, or simply XNet. We will demonstrate that XNet is particularly effective for high-dimensional challenges such as image classification and solving Partial Differential Equations (PDEs). Our evaluations show that XNet significantly outperforms established benchmarks like MNIST and CIFAR-10 in computer vision, and offers substantial advantages over Physics-Informed Neural Networks (PINNs) in both low-dimensional and high-dimensional PDE scenarios.
Authors: Alfredo Ibias, Hector Antona, Guillem Ramirez-Miranda, Enric Guinovart
Abstract: Knowledge discovery is key to understand and interpret a dataset, as well as to find the underlying relationships between its components. Unsupervised Cognition is a novel unsupervised learning algorithm that focus on modelling the learned data. This paper presents three techniques to perform knowledge discovery over an already trained Unsupervised Cognition model. Specifically, we present a technique for pattern mining, a technique for feature selection based on the previous pattern mining technique, and a technique for dimensionality reduction based on the previous feature selection technique. The final goal is to distinguish between relevant and irrelevant features and use them to build a model from which to extract meaningful patterns. We evaluated our proposals with empirical experiments and found that they overcome the state-of-the-art in knowledge discovery.
Authors: Jiayi Han, Liang Du, Hongwei Du, Xiangguo Zhou, Yiwen Wu, Weibo Zheng, Donghong Han
Abstract: Although many efforts have been made, it is still a challenge to balance the training budget, downstream performance, and the general capabilities of the LLMs in many applications. Training the whole model for downstream tasks is expensive, and could easily result in catastrophic forgetting. By introducing parameter-efficient fine-tuning (PEFT), the training cost could be reduced, but it still suffers from forgetting, and limits the learning on the downstream tasks. To efficiently fine-tune the LLMs with less limitation to their downstream performance while mitigating the forgetting of general capabilities, we propose a novel mixture of expert (MoE) framework based on Soft LoRA and Identity Mixture (SLIM), that allows dynamic routing between LoRA adapters and skipping connection, enables the suppression of forgetting. We adopt weight-yielding with sliding clustering for better out-of-domain distinguish to enhance the routing. We also propose to convert the mixture of low-rank adapters to the model merging formulation and introduce fast dynamic merging of LoRA adapters to keep the general capabilities of the base model. Extensive experiments demonstrate that the proposed SLIM is comparable to the state-of-the-art PEFT approaches on the downstream tasks while achieving the leading performance in mitigating catastrophic forgetting.
Authors: Josiah C. Kratz, Jacob Adamczyk
Abstract: Many organisms and cell types, from bacteria to cancer cells, exhibit a remarkable ability to adapt to fluctuating environments. Additionally, cells can leverage a memory of past environments to better survive previously-encountered stressors. From a control perspective, this adaptability poses significant challenges in driving cell populations toward extinction, and thus poses an open question with great clinical significance. In this work, we focus on drug dosing in cell populations exhibiting phenotypic plasticity. For specific dynamical models switching between resistant and susceptible states, exact solutions are known. However, when the underlying system parameters are unknown, and for complex memory-based systems, obtaining the optimal solution is currently intractable. To address this challenge, we apply reinforcement learning (RL) to identify informed dosing strategies to control cell populations evolving under novel non-Markovian dynamics. We find that model-free deep RL is able to recover exact solutions and control cell populations even in the presence of long-range temporal dynamics. To further test our approach in more realistic settings, we demonstrate robust RL-based control strategies in environments with measurement noise and dynamic memory strength.
Authors: Lukas Tatzel, B\'alint Mucs\'anyi, Osane Hackel, Philipp Hennig
Abstract: Quadratic approximations form a fundamental building block of machine learning methods. E.g., second-order optimizers try to find the Newton step into the minimum of a local quadratic proxy to the objective function; and the second-order approximation of a network's loss function can be used to quantify the uncertainty of its outputs via the Laplace approximation. When computations on the entire training set are intractable - typical for deep learning - the relevant quantities are computed on mini-batches. This, however, distorts and biases the shape of the associated stochastic quadratic approximations in an intricate way with detrimental effects on applications. In this paper, we (i) show that this bias introduces a systematic error, (ii) provide a theoretical explanation for it, (iii) explain its relevance for second-order optimization and uncertainty quantification via the Laplace approximation in deep learning, and (iv) develop and evaluate debiasing strategies.
Authors: Shpresim Sadiku, Moritz Wagner, Sai Ganesh Nagarajan, Sebastian Pokutta
Abstract: We study the problem of finding optimal sparse, manifold-aligned counterfactual explanations for classifiers. Canonically, this can be formulated as an optimization problem with multiple non-convex components, including classifier loss functions and manifold alignment (or \emph{plausibility}) metrics. The added complexity of enforcing \emph{sparsity}, or shorter explanations, complicates the problem further. Existing methods often focus on specific models and plausibility measures, relying on convex $\ell_1$ regularizers to enforce sparsity. In this paper, we tackle the canonical formulation using the accelerated proximal gradient (APG) method, a simple yet efficient first-order procedure capable of handling smooth non-convex objectives and non-smooth $\ell_p$ (where $0 \leq p < 1$) regularizers. This enables our approach to seamlessly incorporate various classifiers and plausibility measures while producing sparser solutions. Our algorithm only requires differentiable data-manifold regularizers and supports box constraints for bounded feature ranges, ensuring the generated counterfactuals remain \emph{actionable}. Finally, experiments on real-world datasets demonstrate that our approach effectively produces sparse, manifold-aligned counterfactual explanations while maintaining proximity to the factual data and computational efficiency.
Authors: Ferdi Kossmann, Bruce Fontaine, Daya Khudia, Michael Cafarella, Samuel Madden
Abstract: Serving systems for Large Language Models (LLMs) improve throughput by processing several requests concurrently. However, multiplexing hardware resources between concurrent requests involves non-trivial scheduling decisions. Practical serving systems typically implement these decisions at two levels: First, a load balancer routes requests to different servers which each hold a replica of the LLM. Then, on each server, an engine-level scheduler decides when to run a request, or when to queue or preempt it. Improved scheduling policies may benefit a wide range of LLM deployments and can often be implemented as "drop-in replacements" to a system's current policy. In this work, we survey scheduling techniques from the literature and from practical serving systems. We find that schedulers from the literature often achieve good performance but introduce significant complexity. In contrast, schedulers in practical deployments often leave easy performance gains on the table but are easy to implement, deploy and configure. This finding motivates us to introduce two new scheduling techniques, which are both easy to implement, and outperform current techniques on production workload traces.
Authors: Thomas Marshall, Adam Scherlis, Nora Belrose
Abstract: We propose affine concept editing (ACE) as an approach for steering language models' behavior by intervening directly in activations. We begin with an affine decomposition of model activation vectors and show that prior methods for steering model behavior correspond to subsets of terms of this decomposition. We then provide a derivation of ACE and use it to control refusal behavior on ten different models, including Llama 3 70B. ACE combines affine subspace projection and activation addition to reliably control the model's refusal responses across prompt types. We evaluate the results using LLM-based scoring on a collection of harmful and harmless prompts. Our experiments demonstrate that ACE consistently achieves more precise control over model behavior than existing methods and generalizes to models where directional ablation via affine subspace projection alone produces incoherent outputs. Code for reproducing our results is available at https://github.com/EleutherAI/steering-llama3 .
Authors: Jie Chen, Hua Mao, Yuanbiao Gou, Zhu Wang, Xi Peng
Abstract: Leveraging the diversity and quantity of data provided by various graph-structured data augmentations while preserving intrinsic semantic information is challenging. Additionally, successive layers in graph neural network (GNN) tend to produce more similar node embeddings, while graph contrastive learning aims to increase the dissimilarity between negative pairs of node embeddings. This inevitably results in a conflict between the message-passing mechanism (MPM) of GNNs and the contrastive learning (CL) of negative pairs via intraviews. In this paper, we propose a conditional distribution learning (CDL) method that learns graph representations from graph-structured data for semisupervised graph classification. Specifically, we present an end-to-end graph representation learning model to align the conditional distributions of weakly and strongly augmented features over the original features. This alignment enables the CDL model to effectively preserve intrinsic semantic information when both weak and strong augmentations are applied to graph-structured data. To avoid the conflict between the MPM and the CL of negative pairs, positive pairs of node representations are retained for measuring the similarity between the original features and the corresponding weakly augmented features. Extensive experiments with several benchmark graph datasets demonstrate the effectiveness of the proposed CDL method.
Authors: Fuqiang Liu, Sicong Jiang, Luis Miranda-Moreno, Seongjin Choi, Lijun Sun
Abstract: Large Language Models (LLMs) have recently demonstrated significant potential in the field of time series forecasting, offering impressive capabilities in handling complex temporal data. However, their robustness and reliability in real-world applications remain under-explored, particularly concerning their susceptibility to adversarial attacks. In this paper, we introduce a targeted adversarial attack framework for LLM-based time series forecasting. By employing both gradient-free and black-box optimization methods, we generate minimal yet highly effective perturbations that significantly degrade the forecasting accuracy across multiple datasets and LLM architectures. Our experiments, which include models like TimeGPT and LLM-Time with GPT-3.5, GPT-4, LLaMa, and Mistral, show that adversarial attacks lead to much more severe performance degradation than random noise, and demonstrate the broad effectiveness of our attacks across different LLMs. The results underscore the critical vulnerabilities of LLMs in time series forecasting, highlighting the need for robust defense mechanisms to ensure their reliable deployment in practical applications.
Authors: Jonathan Schmidt, Luca Schmidt, Felix Strnad, Nicole Ludwig, Philipp Hennig
Abstract: Local climate information is crucial for impact assessment and decision-making, yet coarse global climate simulations cannot capture small-scale phenomena. Current statistical downscaling methods infer these phenomena as temporally decoupled spatial patches. However, to preserve physical properties, estimating spatio-temporally coherent high-resolution weather dynamics for multiple variables across long time horizons is crucial. We present a novel generative framework that uses a score-based diffusion model trained on high-resolution reanalysis data to capture the statistical properties of local weather dynamics. After training, we condition on coarse climate model data to generate weather patterns consistent with the aggregate information. As this predictive task is inherently uncertain, we leverage the probabilistic nature of diffusion models and sample multiple trajectories. We evaluate our approach with high-resolution reanalysis information before applying it to the climate model downscaling task. We then demonstrate that the model generates spatially and temporally coherent weather dynamics that align with global climate output.
Authors: Jianqing Liang, Xinkai Wei, Min Chen, Zhiqiang Wang, Jiye Liang
Abstract: Graph contrastive learning (GCL) has become a hot topic in the field of graph representation learning. In contrast to traditional supervised learning relying on a large number of labels, GCL exploits augmentation strategies to generate multiple views and positive/negative pairs, both of which greatly influence the performance. Unfortunately, commonly used random augmentations may disturb the underlying semantics of graphs. Moreover, traditional GNNs, a type of widely employed encoders in GCL, are inevitably confronted with over-smoothing and over-squashing problems. To address these issues, we propose GNN-Transformer Cooperative Architecture for Trustworthy Graph Contrastive Learning (GTCA), which inherits the advantages of both GNN and Transformer, incorporating graph topology to obtain comprehensive graph representations. Theoretical analysis verifies the trustworthiness of the proposed method. Extensive experiments on benchmark datasets demonstrate state-of-the-art empirical performance.
Authors: Aditya Prakash
Abstract: Graph classification plays a pivotal role in various domains, including pathology, where images can be represented as graphs. In this domain, images can be represented as graphs, where nodes might represent individual nuclei, and edges capture the spatial or functional relationships between them. Often, the overall label of the graph, such as a cancer type or disease state, is determined by patterns within smaller, localized regions of the image. This work introduces a weakly-supervised graph classification framework leveraging two subgraph extraction techniques: (1) Sliding-window approach (2) BFS-based approach. Subgraphs are processed using a Graph Attention Network (GAT), which employs attention mechanisms to identify the most informative subgraphs for classification. Weak supervision is achieved by propagating graph-level labels to subgraphs, eliminating the need for detailed subgraph annotations.
Authors: Dareen Alharthi, Mahsa Zamani, Bhiksha Raj, Rita Singh
Abstract: Voice biometric tasks, such as age estimation require modeling the often complex relationship between voice features and the biometric variable. While deep learning models can handle such complexity, they typically require large amounts of accurately labeled data to perform well. Such data are often scarce for biometric tasks such as voice-based age prediction. On the other hand, simpler models like linear regression can work with smaller datasets but often fail to generalize to the underlying non-linear patterns present in the data. In this paper we propose the Tessellated Linear Model (TLM), a piecewise linear approach that combines the simplicity of linear models with the capacity of non-linear functions. TLM tessellates the feature space into convex regions and fits a linear model within each region. We optimize the tessellation and the linear models using a hierarchical greedy partitioning. We evaluated TLM on the TIMIT dataset on the task of age prediction from voice, where it outperformed state-of-the-art deep learning models.
Authors: Yorgos Tsitsikas, Evangelos E. Papalexakis
Abstract: Despite the fundamental importance of clustering, to this day, much of the relevant research is still based on ambiguous foundations, leading to an unclear understanding of whether or how the various clustering methods are connected with each other. In this work, we provide an additional stepping stone towards resolving such ambiguities by presenting a general clustering framework that subsumes a series of seemingly disparate clustering methods, including various methods belonging to the widely popular spectral clustering framework. In fact, the generality of the proposed framework is additionally capable of shedding light to the largely unexplored area of multi-view graphs where each view may have differently clustered nodes. In turn, we propose GenClus: a method that is simultaneously an instance of this framework and a generalization of spectral clustering, while also being closely related to k-means as well. This results in a principled alternative to the few existing methods studying this special type of multi-view graphs. Then, we conduct in-depth experiments, which demonstrate that GenClus is more computationally efficient than existing methods, while also attaining similar or better clustering performance. Lastly, a qualitative real-world case-study further demonstrates the ability of GenClus to produce meaningful clusterings.
Authors: Thejan Rajapakshe, Rajib Rana, Farina Riaz, Sara Khalifa, Bj\"orn W. Schuller
Abstract: Speech Emotion Recognition (SER) is a complex and challenging task in human-computer interaction due to the intricate dependencies of features and the overlapping nature of emotional expressions conveyed through speech. Although traditional deep learning methods have shown effectiveness, they often struggle to capture subtle emotional variations and overlapping states. This paper introduces a hybrid classical-quantum framework that integrates Parameterised Quantum Circuits (PQCs) with conventional Convolutional Neural Network (CNN) architectures. By leveraging quantum properties such as superposition and entanglement, the proposed model enhances feature representation and captures complex dependencies more effectively than classical methods. Experimental evaluations conducted on benchmark datasets, including IEMOCAP, RECOLA, and MSP-Improv, demonstrate that the hybrid model achieves higher accuracy in both binary and multi-class emotion classification while significantly reducing the number of trainable parameters. While a few existing studies have explored the feasibility of using Quantum Circuits to reduce model complexity, none have successfully shown how they can enhance accuracy. This study is the first to demonstrate that Quantum Circuits has the potential to improve the accuracy of SER. The findings highlight the promise of QML to transform SER, suggesting a promising direction for future research and practical applications in emotion-aware systems.
Authors: KaiHui Huang, RunQing Wu, Fei Ye
Abstract: Continual learning has emerged as a pivotal area of research, primarily due to its advantageous characteristic that allows models to persistently acquire and retain information. However, catastrophic forgetting can severely impair model performance. In this study, we address network forgetting by introducing a novel framework termed Optimally-Weighted Maximum Mean Discrepancy (OWMMD), which imposes penalties on representation alterations via a Multi-Level Feature Matching Mechanism (MLFMM). Furthermore, we propose an Adaptive Regularization Optimization (ARO) strategy to refine the adaptive weight vectors, which autonomously assess the significance of each feature layer throughout the optimization process, The proposed ARO approach can relieve the over-regularization problem and promote the future task learning. We conduct a comprehensive series of experiments, benchmarking our proposed method against several established baselines. The empirical findings indicate that our approach achieves state-of-the-art performance.
Authors: Linh Tran, Wei Sun, Stacy Patterson, Ana Milanova
Abstract: Multimodal Large Language Models (LLMs) are pivotal in revolutionizing customer support and operations by integrating multiple modalities such as text, images, and audio. Federated Prompt Learning (FPL) is a recently proposed approach that combines pre-trained multimodal LLMs such as vision-language models with federated learning to create personalized, privacy-preserving AI systems. However, balancing the competing goals of personalization, generalization, and privacy remains a significant challenge. Over-personalization can lead to overfitting, reducing generalizability, while stringent privacy measures, such as differential privacy, can hinder both personalization and generalization. In this paper, we propose a Differentially Private Federated Prompt Learning (DP-FPL) approach to tackle this challenge by leveraging a low-rank adaptation scheme to capture generalization while maintaining a residual term that preserves expressiveness for personalization. To ensure privacy, we introduce a novel method where we apply local differential privacy to the two low-rank components of the local prompt, and global differential privacy to the global prompt. Our approach mitigates the impact of privacy noise on the model performance while balancing the tradeoff between personalization and generalization. Extensive experiments demonstrate the effectiveness of our approach over other benchmarks.
Authors: Linh Tran, Timothy Castiglia, Stacy Patterson, Ana Milanova
Abstract: We present Poisson Binomial Mechanism Vertical Federated Learning (PBM-VFL), a communication-efficient Vertical Federated Learning algorithm with Differential Privacy guarantees. PBM-VFL combines Secure Multi-Party Computation with the recently introduced Poisson Binomial Mechanism to protect parties' private datasets during model training. We define the novel concept of feature privacy and analyze end-to-end feature and sample privacy of our algorithm. We compare sample privacy loss in VFL with privacy loss in HFL. We also provide the first theoretical characterization of the relationship between privacy budget, convergence error, and communication cost in differentially-private VFL. Finally, we empirically show that our model performs well with high levels of privacy.
Authors: Michael Fuest, Alfredo Cuesta, Kalyan Veeramachaneni
Abstract: Recent breakthroughs in large-scale generative modeling have demonstrated the potential of foundation models in domains such as natural language, computer vision, and protein structure prediction. However, their application in the energy and smart grid sector remains limited due to the scarcity and heterogeneity of high-quality data. In this work, we propose a method for creating high-fidelity electricity consumption time series data for rare and unseen context variables (e.g. location, building type, photovoltaics). Our approach, Context Encoding and Normalizing Time Series Generation, or CENTS, includes three key innovations: (i) A context normalization approach that enables inverse transformation for time series context variables unseen during training, (ii) a novel context encoder to condition any state-of-the-art time-series generator on arbitrary numbers and combinations of context variables, (iii) a framework for training this context encoder jointly with a time-series generator using an auxiliary context classification loss designed to increase expressivity of context embeddings and improve model performance. We further provide a comprehensive overview of different evaluation metrics for generative time series models. Our results highlight the efficacy of the proposed method in generating realistic household-level electricity consumption data, paving the way for training larger foundation models in the energy domain on synthetic as well as real-world data.
Authors: Dan Braun, Lucius Bushnaq, Stefan Heimersheim, Jake Mendel, Lee Sharkey
Abstract: Mechanistic interpretability aims to understand the internal mechanisms learned by neural networks. Despite recent progress toward this goal, it remains unclear how best to decompose neural network parameters into mechanistic components. We introduce Attribution-based Parameter Decomposition (APD), a method that directly decomposes a neural network's parameters into components that (i) are faithful to the parameters of the original network, (ii) require a minimal number of components to process any input, and (iii) are maximally simple. Our approach thus optimizes for a minimal length description of the network's mechanisms. We demonstrate APD's effectiveness by successfully identifying ground truth mechanisms in multiple toy experimental settings: Recovering features from superposition; separating compressed computations; and identifying cross-layer distributed representations. While challenges remain to scaling APD to non-toy models, our results suggest solutions to several open problems in mechanistic interpretability, including identifying minimal circuits in superposition, offering a conceptual foundation for 'features', and providing an architecture-agnostic framework for neural network decomposition.
Authors: Ajesh Koyatan Chathoth, Stephen Lee
Abstract: The rapid expansion of connected devices has made them prime targets for cyberattacks. To address these threats, deep learning-based, data-driven intrusion detection systems (IDS) have emerged as powerful tools for detecting and mitigating such attacks. These IDSs analyze network traffic to identify unusual patterns and anomalies that may indicate potential security breaches. However, prior research has shown that deep learning models are vulnerable to backdoor attacks, where attackers inject triggers into the model to manipulate its behavior and cause misclassifications of network traffic. In this paper, we explore the susceptibility of deep learning-based IDS systems to backdoor attacks in the context of network traffic analysis. We introduce \texttt{PCAP-Backdoor}, a novel technique that facilitates backdoor poisoning attacks on PCAP datasets. Our experiments on real-world Cyber-Physical Systems (CPS) and Internet of Things (IoT) network traffic datasets demonstrate that attackers can effectively backdoor a model by poisoning as little as 1\% or less of the entire training dataset. Moreover, we show that an attacker can introduce a trigger into benign traffic during model training yet cause the backdoored model to misclassify malicious traffic when the trigger is present. Finally, we highlight the difficulty of detecting this trigger-based backdoor, even when using existing backdoor defense techniques.
Authors: Jacopo Di Ventura, Dylan R. Ashley, Vincent Herrmann, Francesco Faccio, J\"urgen Schmidhuber
Abstract: Upside Down Reinforcement Learning (UDRL) is a promising framework for solving reinforcement learning problems which focuses on learning command-conditioned policies. In this work, we extend UDRL to the task of learning a command-conditioned generator of deep neural network policies. We accomplish this using Hypernetworks - a variant of Fast Weight Programmers, which learn to decode input commands representing a desired expected return into command-specific weight matrices. Our method, dubbed Upside Down Reinforcement Learning with Policy Generators (UDRLPG), streamlines comparable techniques by removing the need for an evaluator or critic to update the weights of the generator. To counteract the increased variance in last returns caused by not having an evaluator, we decouple the sampling probability of the buffer from the absolute number of policies in it, which, together with a simple weighting strategy, improves the empirical convergence of the algorithm. Compared with existing algorithms, UDRLPG achieves competitive performance and high returns, sometimes outperforming more complex architectures. Our experiments show that a trained generator can generalize to create policies that achieve unseen returns zero-shot. The proposed method appears to be effective in mitigating some of the challenges associated with learning highly multimodal functions. Altogether, we believe that UDRLPG represents a promising step forward in achieving greater empirical sample efficiency in RL. A full implementation of UDRLPG is publicly available at https://github.com/JacopoD/udrlpg_
Authors: Hanrui Wang, Zirui Li, Jiaqi Gu, Yongshan Ding, David Z. Pan, Song Han
Abstract: Parameterized Quantum Circuits (PQC) are drawing increasing research interest thanks to its potential to achieve quantum advantages on near-term Noisy Intermediate Scale Quantum (NISQ) hardware. In order to achieve scalable PQC learning, the training process needs to be offloaded to real quantum machines instead of using exponential-cost classical simulators. One common approach to obtain PQC gradients is parameter shift whose cost scales linearly with the number of qubits. We present QOC, the first experimental demonstration of practical on-chip PQC training with parameter shift. Nevertheless, we find that due to the significant quantum errors (noises) on real machines, gradients obtained from naive parameter shift have low fidelity and thus degrading the training accuracy. To this end, we further propose probabilistic gradient pruning to firstly identify gradients with potentially large errors and then remove them. Specifically, small gradients have larger relative errors than large ones, thus having a higher probability to be pruned. We perform extensive experiments with the Quantum Neural Network (QNN) benchmarks on 5 classification tasks using 5 real quantum machines. The results demonstrate that our on-chip training achieves over 90% and 60% accuracy for 2-class and 4-class image classification tasks. The probabilistic gradient pruning brings up to 7% PQC accuracy improvements over no pruning. Overall, we successfully obtain similar on-chip training accuracy compared with noise-free simulation but have much better training scalability. The QOC code is available in the TorchQuantum library.
Authors: Hanrui Wang, Pengyu Liu, Jinglei Cheng, Zhiding Liang, Jiaqi Gu, Zirui Li, Yongshan Ding, Weiwen Jiang, Yiyu Shi, Xuehai Qian, David Z. Pan, Frederic T. Chong, Song Han
Abstract: Among different quantum algorithms, PQC for QML show promises on near-term devices. To facilitate the QML and PQC research, a recent python library called TorchQuantum has been released. It can construct, simulate, and train PQC for machine learning tasks with high speed and convenient debugging supports. Besides quantum for ML, we want to raise the community's attention on the reversed direction: ML for quantum. Specifically, the TorchQuantum library also supports using data-driven ML models to solve problems in quantum system research, such as predicting the impact of quantum noise on circuit fidelity and improving the quantum circuit compilation efficiency. This paper presents a case study of the ML for quantum part. Since estimating the noise impact on circuit reliability is an essential step toward understanding and mitigating noise, we propose to leverage classical ML to predict noise impact on circuit fidelity. Inspired by the natural graph representation of quantum circuits, we propose to leverage a graph transformer model to predict the noisy circuit fidelity. We firstly collect a large dataset with a variety of quantum circuits and obtain their fidelity on noisy simulators and real machines. Then we embed each circuit into a graph with gate and noise properties as node features, and adopt a graph transformer to predict the fidelity. Evaluated on 5 thousand random and algorithm circuits, the graph transformer predictor can provide accurate fidelity estimation with RMSE error 0.04 and outperform a simple neural network-based model by 0.02 on average. It can achieve 0.99 and 0.95 R$^2$ scores for random and algorithm circuits, respectively. Compared with circuit simulators, the predictor has over 200X speedup for estimating the fidelity.
Authors: Cornelia Gruber, Patrick Oliver Schenk, Malte Schierholz, Frauke Kreuter, G\"oran Kauermann
Abstract: Supervised machine learning and predictive models have achieved an impressive standard today, enabling us to answer questions that were inconceivable a few years ago. Besides these successes, it becomes clear, that beyond pure prediction, which is the primary strength of most supervised machine learning algorithms, the quantification of uncertainty is relevant and necessary as well. However, before quantification is possible, types and sources of uncertainty need to be defined precisely. While first concepts and ideas in this direction have emerged in recent years, this paper adopts a conceptual, basic science perspective and examines possible sources of uncertainty. By adopting the viewpoint of a statistician, we discuss the concepts of aleatoric and epistemic uncertainty, which are more commonly associated with machine learning. The paper aims to formalize the two types of uncertainty and demonstrates that sources of uncertainty are miscellaneous and can not always be decomposed into aleatoric and epistemic. Drawing parallels between statistical concepts and uncertainty in machine learning, we emphasise the role of data and their influence on uncertainty.
Authors: Riccardo Barbano, Alexander Denker, Hyungjin Chung, Tae Hoon Roh, Simon Arridge, Peter Maass, Bangti Jin, Jong Chul Ye
Abstract: Denoising diffusion models have emerged as the go-to generative framework for solving inverse problems in imaging. A critical concern regarding these models is their performance on out-of-distribution tasks, which remains an under-explored challenge. Using a diffusion model on an out-of-distribution dataset, realistic reconstructions can be generated, but with hallucinating image features that are uniquely present in the training dataset. To address this discrepancy during train-test time and improve reconstruction accuracy, we introduce a novel sampling framework called Steerable Conditional Diffusion. Specifically, this framework adapts the diffusion model, concurrently with image reconstruction, based solely on the information provided by the available measurement. Utilising our proposed method, we achieve substantial enhancements in out-of-distribution performance across diverse imaging modalities, advancing the robust deployment of denoising diffusion models in real-world applications.
Authors: Olatunji Mumini Omisore, Toluwanimi Akinyemi, Anh Nguyen, Lei Wang
Abstract: Robot-assisted catheterization has garnered a good attention for its potentials in treating cardiovascular diseases. However, advancing surgeon-robot collaboration still requires further research, particularly on task-specific automation. For instance, automated tool segmentation can assist surgeons in visualizing and tracking of endovascular tools during cardiac procedures. While learning-based models have demonstrated state-of-the-art segmentation performances, generating ground-truth labels for fully-supervised methods is both labor-intensive time consuming, and costly. In this study, we propose a weakly-supervised learning method with multi-lateral pseudo labeling for tool segmentation in cardiovascular angiogram datasets. The method utilizes a modified U-Net architecture featuring one encoder and multiple laterally branched decoders. The decoders generate diverse pseudo labels under different perturbations, augmenting available partial labels. The pseudo labels are self-generated using a mixed loss function with shared consistency across the decoders. The weakly-supervised model was trained end-to-end and validated using partially annotated angiogram data from three cardiovascular catheterization procedures. Validation results show that the model could perform closer to fully-supervised models. Also, the proposed weakly-supervised multi-lateral method outperforms three well known methods used for weakly-supervised learning, offering the highest segmentation performance across the three angiogram datasets. Furthermore, numerous ablation studies confirmed the model's consistent performance under different parameters. Finally, the model was applied for tool segmentation in a robot-assisted catheterization experiments. The model enhanced visualization with high connectivity indices for guidewire and catheter, and a mean processing time of 35 ms per frame.
Authors: Marco Rando, Martin James, Alessandro Verri, Lorenzo Rosasco, Agnese Seminara
Abstract: We consider the problem of olfactory searches in a turbulent environment. We focus on agents that respond solely to odor stimuli, with no access to spatial perception nor prior information about the odor. We ask whether navigation to a target can be learned robustly within a sequential decision making framework. We develop a reinforcement learning algorithm using a small set of interpretable olfactory states and train it with realistic turbulent odor cues. By introducing a temporal memory, we demonstrate that two salient features of odor traces, discretized in few olfactory states, are sufficient to learn navigation in a realistic odor plume. Performance is dictated by the sparse nature of turbulent odors. An optimal memory exists which ignores blanks within the plume and activates a recovery strategy outside the plume. We obtain the best performance by letting agents learn their recovery strategy and show that it is mostly casting cross wind, similar to behavior observed in flying insects. The optimal strategy is robust to substantial changes in the odor plumes, suggesting minor parameter tuning may be sufficient to adapt to different environments.
Authors: Yuichiro Terasaki, Kohei Nakajima
Abstract: A continuous one-dimensional map with period three includes all periods. This raises the following question: Can we obtain any types of periodic orbits solely by learning three data points? In this paper, we report the answer to be yes. Considering a random neural network in its thermodynamic limit, we first show that almost all learned periods are unstable and each network has its characteristic attractors (which can even be untrained ones). The latently acquired dynamics, which are unstable within the trained network, serve as a foundation for the diversity of characteristic attractors and may even lead to the emergence of attractors of all periods after learning. When the neural network interpolation is quadratic, a universal post-learning bifurcation scenario appears, which is consistent with a topological conjugacy between the trained network and the classical logistic map. In addition to universality, we explore specific properties of certain networks, including the singular behavior at the infinite scale of weights limit and the symmetry in learning period three.
Authors: Martin Tveten, Morten Stakkeland
Abstract: Machine learning and statistical methods can improve conventional motor protection systems, providing early warning and detection of emerging failures. Data-driven methods rely on historical data to learn how the system is expected to behave under normal circumstances. An unexpected change in the underlying system may cause a change in the statistical properties of the data, and by this alter the performance of the fault detection algorithm in terms of time to detection and false alarms. This kind of change, called \textit{concept drift}, requires adaptations to maintain constant performance. In this article, we present a machine learning approach for detecting overheating in the stator windings of marine electrical propulsion motors. Using simulated overheating faults injected into operational data, the methods are shown to provide early detection compared to conventional methods based on temperature readings and fixed limits. The proposed monitors are designed to operate for a type of concept drift observed in operational data collected from a specific class of motors in a fleet of ships. Using a mix of real and simulated concept drifts, it is shown that the proposed monitors are able to provide early detections during and after concept drifts, without the need for full model retraining.
Authors: Feijie Wu, Xiaoze Liu, Haoyu Wang, Xingchen Wang, Lu Su, Jing Gao
Abstract: Reinforcement learning with human feedback (RLHF) fine-tunes a pretrained large language model (LLM) using user preference data, enabling it to generate content aligned with human preferences. However, due to privacy concerns, users may be reluctant to share sensitive preference data. To address this, we propose utilizing Federated Learning (FL) techniques, allowing large-scale preference collection from diverse real-world users without requiring them to transmit data to a central server. Our federated RLHF methods (i.e., FedBis and FedBiscuit) encode each client's preferences into binary selectors and aggregate them to capture common preferences. In particular, FedBiscuit overcomes key challenges, such as preference heterogeneity and reward hacking, through innovative solutions like grouping clients with similar preferences to reduce heterogeneity and using multiple binary selectors to enhance LLM output quality. To evaluate the performance of the proposed methods, we establish the first federated RLHF benchmark with a heterogeneous human preference dataset. Experimental results show that by integrating the LLM with aggregated client preferences, FedBis and FedBiscuit significantly enhance the professionalism and readability of the generated content.
Authors: Tingwei Zhang, Collin Zhang, John X. Morris, Eugene Bagdasarian, Vitaly Shmatikov
Abstract: We introduce a new type of indirect, cross-modal injection attacks against visual language models that enable creation of self-interpreting images. These images contain hidden "meta-instructions" that control how models answer users' questions about the image and steer their outputs to express an adversary-chosen style, sentiment, or point of view. Self-interpreting images act as soft prompts, conditioning the model to satisfy the adversary's (meta-)objective while still producing answers based on the image's visual content. Meta-instructions are thus a stronger form of prompt injection. Adversarial images look natural and the model's answers are coherent and plausible--yet they also follow the adversary-chosen interpretation, e.g., political spin, or even objectives that are not achievable with explicit text instructions. We evaluate the efficacy of self-interpreting images for a variety of models, interpretations, and user prompts. We describe how these attacks could cause harm by enabling creation of self-interpreting content that carries spam, misinformation, or spin. Finally, we discuss defenses.
Authors: Anton Zubchenko, Danielle Middlebrooks, Torbj{\o}rn Rasmussen, Lara Lausen, Ferdinand Kuemmeth, Anasua Chatterjee, Justyna P. Zwolak
Abstract: Semiconductor quantum dots (QDs) are a promising platform for multiple different qubit implementations, all of which are voltage controlled by programmable gate electrodes. However, as the QD arrays grow in size and complexity, tuning procedures that can fully autonomously handle the increasing number of control parameters are becoming essential for enabling scalability. We propose a bootstrapping algorithm for initializing a depletion-mode QD device in preparation for subsequent phases of tuning. During bootstrapping, the QD device functionality is validated, all gates are characterized, and the QD charge sensor is made operational. We demonstrate the bootstrapping protocol in conjunction with a coarse-tuning module, showing that the combined algorithm can efficiently and reliably take a cooled-down QD device to a desired global-state configuration in under 8 min with a success rate of 96 %. Finally, by following heuristic approaches to QD device initialization and combining the efficient ray-based measurement with the rapid radio-frequency reflectometry measurements, the proposed algorithm establishes a reference in terms of performance, reliability, and efficiency against which alternative algorithms can be benchmarked.
Authors: Micheline B\'en\'edicte Moumoula, Abdoul Kader Kabore, Jacques Klein, Tegawend\'e Bissyande
Abstract: With the involvement of multiple programming languages in modern software development, cross-lingual code clone detection has gained traction within the software engineering community. Numerous studies have explored this topic, proposing various promising approaches. Inspired by the significant advances in machine learning in recent years, particularly Large Language Models (LLMs), which have demonstrated their ability to tackle various tasks, this paper revisits cross-lingual code clone detection. We evaluate the performance of five (05) LLMs and eight prompts (08) for the identification of cross-lingual code clones. Additionally, we compare these results against two baseline methods. Finally, we evaluate a pre-trained embedding model to assess the effectiveness of the generated representations for classifying clone and non-clone pairs. The studies involving LLMs and Embedding models are evaluated using two widely used cross-lingual datasets, XLCoST and CodeNet. Our results show that LLMs can achieve high F1 scores, up to 0.99, for straightforward programming examples. However, they not only perform less well on programs associated with complex programming challenges but also do not necessarily understand the meaning of "code clones" in a cross-lingual setting. We show that embedding models used to represent code fragments from different programming languages in the same representation space enable the training of a basic classifier that outperforms all LLMs by ~1 and ~20 percentage points on the XLCoST and CodeNet datasets, respectively. This finding suggests that, despite the apparent capabilities of LLMs, embeddings provided by embedding models offer suitable representations to achieve state-of-the-art performance in cross-lingual code clone detection.
Authors: Shi Bo, Minheng Xiao
Abstract: This paper presents a novel approach to root cause attribution of delivery risks within supply chains by integrating causal discovery with reinforcement learning. As supply chains become increasingly complex, traditional methods of root cause analysis struggle to capture the intricate interrelationships between various factors, often leading to spurious correlations and suboptimal decision-making. Our approach addresses these challenges by leveraging causal discovery to identify the true causal relationships between operational variables, and reinforcement learning to iteratively refine the causal graph. This method enables the accurate identification of key drivers of late deliveries, such as shipping mode and delivery status, and provides actionable insights for optimizing supply chain performance. We apply our approach to a real-world supply chain dataset, demonstrating its effectiveness in uncovering the underlying causes of delivery delays and offering strategies for mitigating these risks. The findings have significant implications for improving operational efficiency, customer satisfaction, and overall profitability within supply chains.
Authors: Majid Daliri, Christopher Musco, Ananda Theertha Suresh
Abstract: Suppose Alice has a distribution $P$ and Bob has a distribution $Q$. Alice wants to draw a sample $a\sim P$ and Bob a sample $b \sim Q$ such that $a = b$ with as high of probability as possible. It is well-known that, by sampling from an optimal coupling between the distributions, Alice and Bob can achieve $\Pr[a = b] = 1 - D_{TV}(P,Q)$, where $D_{TV}(P,Q)$ is the total variation distance between $P$ and $Q$. What if Alice and Bob must solve this same problem \emph{without communicating at all?} Perhaps surprisingly, with access to public randomness, they can still achieve $\Pr[a = b] \geq \frac{1 - D_{TV}(P,Q)}{1 + D_{TV}(P,Q)} \geq 1-2D_{TV}(P,Q)$ using a simple protocol based on the Weighted MinHash algorithm. This bound was shown to be optimal in the worst-case by [Bavarian et al., 2020]. In this work, we revisit the communication-free coupling problem. We provide a simpler proof of the optimality result from [Bavarian et al., 2020]. We show that, while the worst-case success probability of Weighted MinHash cannot be improved, an equally simple protocol based on Gumbel sampling offers a Pareto improvement: for every pair of distributions $P, Q$, Gumbel sampling achieves an equal or higher value of $\Pr[a = b]$ than Weighted MinHash. Importantly, this improvement translates to practice. We demonstrate an application of communication-free coupling to \emph{speculative decoding}, a recent method for accelerating autoregressive large language models [Leviathan, Kalman, Matias, ICML 2023]. We show that communication-free protocols can be used to contruct \emph{\CSD{}} schemes, which have the desirable property that their output is fixed given a fixed random seed, regardless of what drafter is used for speculation. In experiments on a language generation task, Gumbel sampling outperforms Weighted MinHash. Code is available at https://github.com/majid-daliri/DISD.
Authors: Zhaorui Tan, Xi Yang, Qiufeng Wang, Anh Nguyen, Kaizhu Huang
Abstract: Vision models excel in image classification but struggle to generalize to unseen data, such as classifying images from unseen domains or discovering novel categories. In this paper, we explore the relationship between logical reasoning and deep learning generalization in visual classification. A logical regularization termed L-Reg is derived which bridges a logical analysis framework to image classification. Our work reveals that L-Reg reduces the complexity of the model in terms of the feature distribution and classifier weights. Specifically, we unveil the interpretability brought by L-Reg, as it enables the model to extract the salient features, such as faces to persons, for classification. Theoretical analysis and experiments demonstrate that L-Reg enhances generalization across various scenarios, including multi-domain generalization and generalized category discovery. In complex real-world scenarios where images span unknown classes and unseen domains, L-Reg consistently improves generalization, highlighting its practical efficacy.
Authors: Jinlin Lai, Yuling Yao
Abstract: Vanilla variational inference finds an optimal approximation to the Bayesian posterior distribution, but even the exact Bayesian posterior is often not meaningful under model misspecification. We propose predictive variational inference (PVI): a general inference framework that seeks and samples from an optimal posterior density such that the resulting posterior predictive distribution is as close to the true data generating process as possible, while this closeness is measured by multiple scoring rules. By optimizing the objective, the predictive variational inference is generally not the same as, or even attempting to approximate, the Bayesian posterior, even asymptotically. Rather, we interpret it as implicit hierarchical expansion. Further, the learned posterior uncertainty detects heterogeneity of parameters among the population, enabling automatic model diagnosis. This framework applies to both likelihood-exact and likelihood-free models. We demonstrate its application in real data examples.
Authors: \.Ilker I\c{s}{\i}k, Ramazan Gokberk Cinbis, Ebru Aydin Gol
Abstract: We propose a novel approach for learning interchangeable tokens in language models to obtain an extendable vocabulary that can generalize to new tokens. Our method addresses alpha-equivalence, the principle that renaming bound variables preserves semantics. This property arises in many formal languages such as temporal logics, where all proposition symbols represent the same concept but remain distinct. To handle such tokens, we develop a dual-part embedding approach. The first part is shared across all interchangeable tokens, enforcing that they represent the same core concept. The second part is randomly generated for each token, enabling distinguishability. As a baseline, we consider a simpler approach that uses alpha-renaming for data augmentation. We also present alpha-covariance, a metric for measuring robustness against alpha-conversions. When evaluated in a Transformer encoder-decoder model for solving linear temporal logic formulae and copying with extendable vocabulary, our method demonstrates promising generalization capabilities as well as a favorable inductive bias for alpha-equivalence.
Authors: Parthasarathy Suryanarayanan, Yunguang Qiu, Shreyans Sethi, Diwakar Mahajan, Hongyang Li, Yuxin Yang, Elif Eyigoz, Aldo Guzman Saenz, Daniel E. Platt, Timothy H. Rumbell, Kenney Ng, Sanjoy Dey, Myson Burch, Bum Chul Kwon, Pablo Meyer, Feixiong Cheng, Jianying Hu, Joseph A. Morrone
Abstract: Foundation models applied to bio-molecular space hold promise to accelerate drug discovery. Molecular representation is key to building such models. Previous works have typically focused on a single representation or view of the molecules. Here, we develop a multi-view foundation model approach, that integrates molecular views of graph, image and text. Single-view foundation models are each pre-trained on a dataset of up to 200M molecules and then aggregated into combined representations. Our multi-view model is validated on a diverse set of 18 tasks, encompassing ligand-protein binding, molecular solubility, metabolism and toxicity. We show that the multi-view models perform robustly and are able to balance the strengths and weaknesses of specific views. We then apply this model to screen compounds against a large (>100 targets) set of G Protein-Coupled receptors (GPCRs). From this library of targets, we identify 33 that are related to Alzheimer's disease. On this subset, we employ our model to identify strong binders, which are validated through structure-based modeling and identification of key binding motifs.
Authors: \'Isak P\'etursson, Mar\'ia \'Oskarsd\'ottir
Abstract: We present a novel approach for predicting the distribution of asset returns using a quantile-based method with Long Short-Term Memory (LSTM) networks. Our model is designed in two stages: the first focuses on predicting the quantiles of normalized asset returns using asset-specific features, while the second stage incorporates market data to adjust these predictions for broader economic conditions. This results in a generalized model that can be applied across various asset classes, including commodities, cryptocurrencies, as well as synthetic datasets. The predicted quantiles are then converted into full probability distributions through kernel density estimation, allowing for more precise return distribution predictions and inferencing. The LSTM model significantly outperforms a linear quantile regression baseline by 98% and a dense neural network model by over 50%, showcasing its ability to capture complex patterns in financial return distributions across both synthetic and real-world data. By using exclusively asset-class-neutral features, our model achieves robust, generalizable results.
Authors: Michele Caprio, David Stutz, Shuo Li, Arnaud Doucet
Abstract: An open question in \emph{Imprecise Probabilistic Machine Learning} is how to empirically derive a credal region (i.e., a closed and convex family of probabilities on the output space) from the available data, without any prior knowledge or assumption. In classification problems, credal regions are a tool that is able to provide provable guarantees under realistic assumptions by characterizing the uncertainty about the distribution of the labels. Building on previous work, we show that credal regions can be directly constructed using conformal methods. This allows us to provide a novel extension of classical conformal prediction to problems with ambiguous ground truth, that is, when the exact labels for given inputs are not exactly known. The resulting construction enjoys desirable practical and theoretical properties: (i) conformal coverage guarantees, (ii) smaller prediction sets (compared to classical conformal prediction regions) and (iii) disentanglement of uncertainty sources (epistemic, aleatoric). We empirically verify our findings on both synthetic and real datasets.
Authors: Zheng Cao, Helyette Geman
Abstract: This article introduces a Hype-Adjusted Probability Measure in the context of a new Natural Language Processing (NLP) approach for stock return and volatility forecasting. A novel sentiment score equation is proposed to represent the impact of intraday news on forecasting next-period stock return and volatility for selected U.S. semiconductor tickers, a very vibrant industry sector. This work improves the forecast accuracy by addressing news bias, memory, and weight, and incorporating shifts in sentiment direction. More importantly, it extends the use of the remarkable tool of change of Probability Measure developed in the finance of Asset Pricing to NLP forecasting by constructing a Hype-Adjusted Probability Measure, obtained from a redistribution of the weights in the probability space, meant to correct for excessive or insufficient news.
Authors: Karishma Thakrar
Abstract: Graph Retrieval-Augmented Generation (GRAG or Graph RAG) architectures aim to enhance language understanding and generation by leveraging external knowledge. However, effectively capturing and integrating the rich semantic information present in textual and structured data remains a challenge. To address this, a novel GRAG framework, Dynamic Graph Retrieval-Agumented Generation (DynaGRAG), is proposed to focus on enhancing subgraph representation and diversity within the knowledge graph. By improving graph density, capturing entity and relation information more effectively, and dynamically prioritizing relevant and diverse subgraphs and information within them, the proposed approach enables a more comprehensive understanding of the underlying semantic structure. This is achieved through a combination of de-duplication processes, two-step mean pooling of embeddings, query-aware retrieval considering unique nodes, and a Dynamic Similarity-Aware BFS (DSA-BFS) traversal algorithm. Integrating Graph Convolutional Networks (GCNs) and Large Language Models (LLMs) through hard prompting further enhances the learning of rich node and edge representations while preserving the hierarchical subgraph structure. Experimental results demonstrate the effectiveness of DynaGRAG, showcasing the significance of enhanced subgraph representation and diversity for improved language understanding and generation.
Authors: Haoran Wang, Pingzhi Li, Min Chen, Jinglei Cheng, Junyu Liu, Tianlong Chen
Abstract: Quantum computing is an exciting non-Von Neumann paradigm, offering provable speedups over classical computing for specific problems. However, the practical limits of classical simulatability for quantum circuits remain unclear, especially with current noisy quantum devices. In this work, we explore the potential of leveraging Large Language Models (LLMs) to simulate the output of a quantum Turing machine using Grover's quantum circuits, known to provide quadratic speedups over classical counterparts. To this end, we developed GroverGPT, a specialized model based on LLaMA's 8-billion-parameter architecture, trained on over 15 trillion tokens. Unlike brute-force state-vector simulations, which demand substantial computational resources, GroverGPT employs pattern recognition to approximate quantum search algorithms without explicitly representing quantum states. Analyzing 97K quantum search instances, GroverGPT consistently outperformed OpenAI's GPT-4o (45\% accuracy), achieving nearly 100\% accuracy on 6- and 10-qubit datasets when trained on 4-qubit or larger datasets. It also demonstrated strong generalization, surpassing 95\% accuracy for systems with over 20 qubits when trained on 3- to 6-qubit data. Analysis indicates GroverGPT captures quantum features of Grover's search rather than classical patterns, supported by novel prompting strategies to enhance performance. Although accuracy declines with increasing system size, these findings offer insights into the practical boundaries of classical simulatability. This work suggests task-specific LLMs can surpass general-purpose models like GPT-4o in quantum algorithm learning and serve as powerful tools for advancing quantum research.
Authors: Sara Abdali, Can Goksen, Saeed Amizadeh, Kazuhito Koishida
Abstract: Investigating NLP through a philosophical lens has recently caught researcher's eyes as it connects computational methods with classical schools of philosophy. This paper introduces a philosophical approach inspired by the Hegelian Dialectic for LLMs' self-reflection, utilizing a self-dialectical approach to emulate internal critiques and then synthesize new ideas by resolving the contradicting points. Moreover, this paper investigates the effect of LLMs' temperature for generation by establishing a dynamic annealing approach, which promotes the creativity in the early stages and gradually refines it by focusing on the nuances, as well as a fixed temperature strategy for generation. Our proposed approach is examined to determine its ability to generate novel ideas from an initial proposition. Additionally, a Multi Agent Majority Voting (MAMV) strategy is leveraged to assess the validity and novelty of the generated ideas, which proves beneficial in the absence of domain experts. Our experiments show promise in generating new ideas and provide a stepping stone for future research.
Authors: Hubert Banville, Yohann Benchetrit, St\'ephane d'Ascoli, J\'er\'emy Rapin, Jean-R\'emi King
Abstract: Generative AI has recently propelled the decoding of images from brain activity. How do these approaches scale with the amount and type of neural recordings? Here, we systematically compare image decoding from four types of non-invasive devices: electroencephalography (EEG), magnetoencephalography (MEG), high-field functional Magnetic Resonance Imaging (3T fMRI) and ultra-high field (7T) fMRI. For this, we evaluate decoding models on the largest benchmark to date, encompassing 8 public datasets, 84 volunteers, 498 hours of brain recording and 2.3 million brain responses to natural images. Unlike previous work, we focus on single-trial decoding performance to simulate real-time settings. This systematic comparison reveals three main findings. First, the most precise neuroimaging devices tend to yield the best decoding performances, when the size of the training sets are similar. However, the gain enabled by deep learning - in comparison to linear models - is obtained with the noisiest devices. Second, we do not observe any plateau of decoding performance as the amount of training data increases. Rather, decoding performance scales log-linearly with the amount of brain recording. Third, this scaling law primarily depends on the amount of data per subject. However, little decoding gain is observed by increasing the number of subjects. Overall, these findings delineate the path most suitable to scale the decoding of images from non-invasive brain recordings.
Authors: Adil Kaan Akan, Yucel Yemez
Abstract: We present SlotAdapt, an object-centric learning method that combines slot attention with pretrained diffusion models by introducing adapters for slot-based conditioning. Our method preserves the generative power of pretrained diffusion models, while avoiding their text-centric conditioning bias. We also incorporate an additional guidance loss into our architecture to align cross-attention from adapter layers with slot attention. This enhances the alignment of our model with the objects in the input image without using external supervision. Experimental results show that our method outperforms state-of-the-art techniques in object discovery and image generation tasks across multiple datasets, including those with real images. Furthermore, we demonstrate through experiments that our method performs remarkably well on complex real-world images for compositional generation, in contrast to other slot-based generative methods in the literature. The project page can be found at https://kaanakan.github.io/SlotAdapt/.