Authors: Jayadratha Gayen, Himanshu Pal, Naresh Manwani, Charu Sharma
Abstract: Many real-world systems can be modeled as dynamic graphs, where nodes and edges evolve over time, requiring specialized models to capture their evolving dynamics in risk-sensitive applications effectively. Temporal graph neural networks (GNNs) are one such category of specialized models. For the first time, our approach integrates a reject option strategy within the framework of GNNs for continuous-time dynamic graphs. This allows the model to strategically abstain from making predictions when the uncertainty is high and confidence is low, thus minimizing the risk of critical misclassification and enhancing the results and reliability. We propose a coverage-based abstention prediction model to implement the reject option that maximizes prediction within a specified coverage. It improves the prediction score for link prediction and node classification tasks. Temporal GNNs deal with extremely skewed datasets for the next state prediction or node classification task. In the case of class imbalance, our method can be further tuned to provide a higher weightage to the minority class. Exhaustive experiments are presented on four datasets for dynamic link prediction and two datasets for dynamic node classification tasks. This demonstrates the effectiveness of our approach in improving the reliability and area under the curve (AUC)/ average precision (AP) scores for predictions in dynamic graph scenarios. The results highlight our model's ability to efficiently handle the trade-offs between prediction confidence and coverage, making it a dependable solution for applications requiring high precision in dynamic and uncertain environments.
Authors: Sina Ehsani, Fenglian Pan, Qingpei Hu, Jian Liu
Abstract: Accurate prediction of spatial-temporal (ST) information in dynamic systems, such as urban mobility and weather patterns, is a crucial yet challenging problem. The complexity stems from the intricate interplay between spatial proximity and temporal relevance, where both long-term trends and short-term fluctuations are present in convoluted patterns. Existing approaches, including traditional statistical methods and conventional neural networks, may provide inaccurate results due to the lack of an effective mechanism that simultaneously incorporates information at variable temporal depths while maintaining spatial context, resulting in a trade-off between comprehensive long-term historical analysis and responsiveness to short-term new information. To bridge this gap, this paper proposes the BiDepth Multimodal Neural Network (BDMNN) with bidirectional depth modulation that enables a comprehensive understanding of both long-term seasonality and short-term fluctuations, adapting to the complex ST context. Case studies with real-world public data demonstrate significant improvements in prediction accuracy, with a 12% reduction in Mean Squared Error for urban traffic prediction and a 15% improvement in rain precipitation forecasting compared to state-of-the-art benchmarks, without demanding extra computational resources.
Authors: Zijiang Yan, Hao Zhou, Jianhua Pei, Aryan Kaushik, Hina Tabassum, Ping Wang
Abstract: Efficient resource allocation is essential for optimizing various tasks in wireless networks, which are usually formulated as generalized assignment problems (GAP). GAP, as a generalized version of the linear sum assignment problem, involves both equality and inequality constraints that add computational challenges. In this work, we present a novel Conditional Value at Risk (CVaR)-based Variational Quantum Eigensolver (VQE) framework to address GAP in vehicular networks (VNets). Our approach leverages a hybrid quantum-classical structure, integrating a tailored cost function that balances both objective and constraint-specific penalties to improve solution quality and stability. Using the CVaR-VQE model, we handle the GAP efficiently by focusing optimization on the lower tail of the solution space, enhancing both convergence and resilience on noisy intermediate-scale quantum (NISQ) devices. We apply this framework to a user-association problem in VNets, where our method achieves 23.5% improvement compared to the deep neural network (DNN) approach.
Authors: Davide Barbieri, Matteo Bonforte, Peio Ibarrondo
Abstract: In this paper we analyze the behaviour of the stochastic gradient descent (SGD), a widely used method in supervised learning for optimizing neural network weights via a minimization of non-convex loss functions. Since the pioneering work of E, Li and Tai (2017), the underlying structure of such processes can be understood via parabolic PDEs of Fokker-Planck type, which are at the core of our analysis. Even if Fokker-Planck equations have a long history and a extensive literature, almost nothing is known when the potential is non-convex or when the diffusion matrix is degenerate, and this is the main difficulty that we face in our analysis. We identify two different regimes: in the initial phase of SGD, the loss function drives the weights to concentrate around the nearest local minimum. We refer to this phase as the drift regime and we provide quantitative estimates on this concentration phenomenon. Next, we introduce the diffusion regime, where stochastic fluctuations help the learning process to escape suboptimal local minima. We analyze the Mean Exit Time (MET) and prove upper and lower bounds of the MET. Finally, we address the asymptotic convergence of SGD, for a non-convex cost function and a degenerate diffusion matrix, that do not allow to use the standard approaches, and require new techniques. For this purpose, we exploit two different methods: duality and entropy methods. We provide new results about the dynamics and effectiveness of SGD, offering a deep connection between stochastic optimization and PDE theory, and some answers and insights to basic questions in the Machine Learning processes: How long does SGD take to escape from a bad minimum? Do neural network parameters converge using SGD? How do parameters evolve in the first stage of training with SGD?
Authors: Sergio Hernan Garrido Mejia, Patrick Bl\"obaum, Bernhard Sch\"olkopf, Dominik Janzing
Abstract: We study the differences arising from merging predictors in the causal and anticausal directions using the same data. In particular we study the asymmetries that arise in a simple model where we merge the predictors using one binary variable as target and two continuous variables as predictors. We use Causal Maximum Entropy (CMAXENT) as inductive bias to merge the predictors, however, we expect similar differences to hold also when we use other merging methods that take into account asymmetries between cause and effect. We show that if we observe all bivariate distributions, the CMAXENT solution reduces to a logistic regression in the causal direction and Linear Discriminant Analysis (LDA) in the anticausal direction. Furthermore, we study how the decision boundaries of these two solutions differ whenever we observe only some of the bivariate distributions implications for Out-Of-Variable (OOV) generalisation.
Authors: Sharmila Karumuri, Lori Graham-Brady, Somdatta Goswami
Abstract: Deep operator network (DeepONet) has shown great promise as a surrogate model for systems governed by partial differential equations (PDEs), learning mappings between infinite-dimensional function spaces with high accuracy. However, achieving low generalization errors often requires highly overparameterized networks, posing significant challenges for large-scale, complex systems. To address these challenges, latent DeepONet was proposed, introducing a two-step approach: first, a reduced-order model is used to learn a low-dimensional latent space, followed by operator learning on this latent space. While effective, this method is inherently data-driven, relying on large datasets and making it difficult to incorporate governing physics into the framework. Additionally, the decoupled nature of these steps prevents end-to-end optimization and the ability to handle data scarcity. This work introduces PI-Latent-NO, a physics-informed latent operator learning framework that overcomes these limitations. Our architecture employs two coupled DeepONets in an end-to-end training scheme: the first, termed Latent-DeepONet, identifies and learns the low-dimensional latent space, while the second, Reconstruction-DeepONet, maps the latent representations back to the original physical space. By integrating governing physics directly into the training process, our approach requires significantly fewer data samples while achieving high accuracy. Furthermore, the framework is computationally and memory efficient, exhibiting nearly constant scaling behavior on a single GPU and demonstrating the potential for further efficiency gains with distributed training. We validate the proposed method on high-dimensional parametric PDEs, demonstrating its effectiveness as a proof of concept and its potential scalability for large-scale systems.
Authors: Svenja Ehlers, Norbert Hoffmann, Tianning Tang, Adrian H. Callaghan, Rui Cao, Enrique M. Padilla, Yuxin Fang, Merten Stender
Abstract: The assimilation and prediction of phase-resolved surface gravity waves are critical challenges in ocean science and engineering. Potential flow theory (PFT) has been widely employed to develop wave models and numerical techniques for wave prediction. However, traditional wave prediction methods are often limited. For example, most simplified wave models have a limited ability to capture strong wave nonlinearity, while fully nonlinear PFT solvers often fail to meet the speed requirements of engineering applications. This computational inefficiency also hinders the development of effective data assimilation techniques, which are required to reconstruct spatial wave information from sparse measurements to initialize the wave prediction. To address these challenges, we propose a novel solver method that leverages physics-informed neural networks (PINNs) that parameterize PFT solutions as neural networks. This provides a computationally inexpensive way to assimilate and predict wave data. The proposed PINN framework is validated through comparisons with analytical linear PFT solutions and experimental data collected in a laboratory wave flume. The results demonstrate that our approach accurately captures and predicts irregular, nonlinear, and dispersive wave surface dynamics. Moreover, the PINN can infer the fully nonlinear velocity potential throughout the entire fluid volume solely from surface elevation measurements, enabling the calculation of fluid velocities that are difficult to measure experimentally.
Authors: R\'emi Genet, Hugo Inzirillo
Abstract: In this paper we introduce Keras Sig a high-performance pythonic library designed to compute path signature for deep learning applications. Entirely built in Keras 3, \textit{Keras Sig} leverages the seamless integration with the mostly used deep learning backends such as PyTorch, JAX and TensorFlow. Inspired by Kidger and Lyons (2021),we proposed a novel approach reshaping signature calculations to leverage GPU parallelism. This adjustment allows us to reduce the training time by 55\% and 5 to 10-fold improvements in direct signature computation compared to existing methods, while maintaining similar CPU performance. Relying on high-level tensor operations instead of low-level C++ code, Keras Sig significantly reduces the versioning and compatibility issues commonly encountered in deep learning libraries, while delivering superior or comparable performance across various hardware configurations. We demonstrate through extensive benchmarking that our approach scales efficiently with the length of input sequences and maintains competitive performance across various signature parameters, though bounded by memory constraints for very large signature dimensions.
Authors: Joao Carmo de Almeida Neto, Claudio Miceli de Farias, Leandro Santiago de Araujo, Leopoldo Andre Dutra Lusquino Filho
Abstract: The research related to digital twins has been increasing in recent years. Besides the mirroring of the physical word into the digital, there is the need of providing services related to the data collected and transferred to the virtual world. One of these services is the forecasting of physical part future behavior, that could lead to applications, like preventing harmful events or designing improvements to get better performance. One strategy used to predict any system operation it is the use of time series models like ARIMA or LSTM, and improvements were implemented using these algorithms. Recently, deep learning techniques based on generative models such as Generative Adversarial Networks (GANs) have been proposed to create time series and the use of LSTM has gained more relevance in time series forecasting, but both have limitations that restrict the forecasting results. Another issue found in the literature is the challenge of handling multivariate environments/applications in time series generation. Therefore, new methods need to be studied in order to fill these gaps and, consequently, provide better resources for creating useful digital twins. In this proposal, it is going to be studied the integration of a BiLSTM layer with a time series obtained by GAN in order to improve the forecasting of all the features provided by the dataset in terms of accuracy and, consequently, improving behaviour prediction.
Authors: Kavita Selva, Satita Vittayaareekul, Brando Miranda
Abstract: Currently, data and model size dominate the narrative in the training of super-large, powerful models. However, there has been a lack of exploration on the effect of other attributes of the training dataset on model performance. We hypothesize that dataset diversity can impact the performance of vision models. Our study shows positive correlations between test set accuracy and data diversity, providing an argument for furthering the research of dataset attributes beyond size. We analyzed pre-training and model-agnostic meta-learning methods on twelve popular visual datasets (e.g., Omniglot, CIFAR-FS, Aircraft) and five model configurations, including MAML variants with different numbers of inner gradient steps and supervised learning. We show moderate to strong positive correlations (R-squared: 0.15-0.42) between accuracy and data diversity and weaker but significant correlations (R-squared: ~0.2) between loss and diversity. These findings support our hypothesis and demonstrate a promising way for a deeper exploration of how formal data diversity influences model performance. This initial study highlights the potential of (Task2Vec) data diversity as a valuable measure in the rapidly evolving field of large-scale learning and emphasizes that understanding the dataset is key to building more powerful and generalizable models.
Authors: Matthieu Kirchmeyer, Pedro O. Pinheiro, Saeed Saremi
Abstract: We introduce a new representation for 3D molecules based on their continuous atomic density fields. Using this representation, we propose a new model based on walk-jump sampling for unconditional 3D molecule generation in the continuous space using neural fields. Our model, FuncMol, encodes molecular fields into latent codes using a conditional neural field, samples noisy codes from a Gaussian-smoothed distribution with Langevin MCMC (walk), denoises these samples in a single step (jump), and finally decodes them into molecular fields. FuncMol performs all-atom generation of 3D molecules without assumptions on the molecular structure and scales well with the size of molecules, unlike most approaches. Our method achieves competitive results on drug-like molecules and easily scales to macro-cyclic peptides, with at least one order of magnitude faster sampling. The code is available at https://github.com/prescient-design/funcmol.
Authors: Hongyi Li, Jun Xu, William Ward Armstrong
Abstract: This paper introduces a novel tree-based model, Learning Hyperplane Tree (LHT), which outperforms state-of-the-art (SOTA) tree models for classification tasks on several public datasets. The structure of LHT is simple and efficient: it partitions the data using several hyperplanes to progressively distinguish between target and non-target class samples. Although the separation is not perfect at each stage, LHT effectively improves the distinction through successive partitions. During testing, a sample is classified by evaluating the hyperplanes defined in the branching blocks and traversing down the tree until it reaches the corresponding leaf block. The class of the test sample is then determined using the piecewise linear membership function defined in the leaf blocks, which is derived through least-squares fitting and fuzzy logic. LHT is highly transparent and interpretable--at each branching block, the contribution of each feature to the classification can be clearly observed.
Authors: Huy Q. Le, Ye Lin Tun, Yu Qiao, Minh N. H. Nguyen, Keon Oh Kim, Choong Seon Hong
Abstract: Federated Learning (FL) has emerged as a decentralized machine learning technique, allowing clients to train a global model collaboratively without sharing private data. However, most FL studies ignore the crucial challenge of heterogeneous domains where each client has a distinct feature distribution, which is common in real-world scenarios. Prototype learning, which leverages the mean feature vectors within the same classes, has become a prominent solution for federated learning under domain skew. However, existing federated prototype learning methods only consider inter-domain prototypes on the server and overlook intra-domain characteristics. In this work, we introduce a novel federated prototype learning method, namely I$^2$PFL, which incorporates $\textbf{I}$ntra-domain and $\textbf{I}$nter-domain $\textbf{P}$rototypes, to mitigate domain shifts and learn a generalized global model across multiple domains in federated learning. To construct intra-domain prototypes, we propose feature alignment with MixUp-based augmented prototypes to capture the diversity of local domains and enhance the generalization of local features. Additionally, we introduce a reweighting mechanism for inter-domain prototypes to generate generalized prototypes to provide inter-domain knowledge and reduce domain skew across multiple clients. Extensive experiments on the Digits, Office-10, and PACS datasets illustrate the superior performance of our method compared to other baselines.
Authors: Haosen Wang, Chenglong Shi, Can Xu, Surong Yan, Pan Tang
Abstract: Heterogeneous graph pre-training (HGP) has demonstrated remarkable performance across various domains. However, the issue of heterophily in real-world heterogeneous graphs (HGs) has been largely overlooked. To bridge this research gap, we proposed a novel heterogeneous graph contrastive learning framework, termed HGMS, which leverages connection strength and multi-view self-expression to learn homophilous node representations. Specifically, we design a heterogeneous edge dropping augmentation strategy that enhances the homophily of augmented views. Moreover, we introduce a multi-view self-expressive learning method to infer the homophily between nodes. In practice, we develop two approaches to solve the self-expressive matrix. The solved self-expressive matrix serves as an additional augmented view to provide homophilous information and is used to identify false negatives in contrastive loss. Extensive experimental results demonstrate the superiority of HGMS across different downstream tasks.
Authors: Jin Chen, Jin Zhang, Xu huang, Yi Yang, Defu Lian, Enhong Chen
Abstract: The softmax function is a cornerstone of multi-class classification, integral to a wide range of machine learning applications, from large-scale retrieval and ranking models to advanced large language models. However, its computational cost grows linearly with the number of classes, which becomes prohibitively expensive in scenarios with millions or even billions of classes. The sampled softmax, which relies on self-normalized importance sampling, has emerged as a powerful alternative, significantly reducing computational complexity. Yet, its estimator remains unbiased only when the sampling distribution matches the true softmax distribution. To improve both approximation accuracy and sampling efficiency, we propose the MIDX Sampler, a novel adaptive sampling strategy based on an inverted multi-index approach. Concretely, we decompose the softmax probability into several multinomial probabilities, each associated with a specific set of codewords and the last associated with the residual score of queries, thus reducing time complexity to the number of codewords instead of the number of classes. To further boost efficiency, we replace the query-specific residual probability with a simple uniform distribution, simplifying the computation while retaining high performance. Our method is backed by rigorous theoretical analysis, addressing key concerns such as sampling bias, gradient bias, convergence rates, and generalization error bounds. The results demonstrate that a smaller divergence from the ideal softmax distribution leads to faster convergence and improved generalization. Extensive experiments on large-scale language models, sequential recommenders, and extreme multi-class classification tasks confirm that the MIDX-Sampler delivers superior effectiveness and efficiency compared to existing approaches.
Authors: Guanlin Liu, Xiaomei Yu, Zihao Liu, Xue Li, Xingxu Fan, Xiangwei Zheng
Abstract: Medication Recommendation (MR) is a promising research topic which booms diverse applications in the healthcare and clinical domains. However, existing methods mainly rely on sequential modeling and static graphs for representation learning, which ignore the dynamic correlations in diverse medical events of a patient's temporal visits, leading to insufficient global structural exploration on nodes. Additionally, mitigating drug-drug interactions (DDIs) is another issue determining the utility of the MR systems. To address the challenges mentioned above, this paper proposes a novel MR method with the integration of dynamic networks and multi-view drug representations (DNMDR). Specifically, weighted snapshot sequences for dynamic heterogeneous networks are constructed based on discrete visits in temporal EHRs, and all the dynamic networks are jointly trained to gain both structural correlations in diverse medical events and temporal dependency in historical health conditions, for achieving comprehensive patient representations with both semantic features and structural relationships. Moreover, combining the drug co-occurrences and adverse drug-drug interactions (DDIs) in internal view of drug molecule structure and interactive view of drug pairs, the safe drug representations are available to obtain high-quality medication combination recommendation. Finally, extensive experiments on real world datasets are conducted for performance evaluation, and the experimental results demonstrate that the proposed DNMDR method outperforms the state-of-the-art baseline models with a large margin on various metrics such as PRAUC, Jaccard, DDI rates and so on.
Authors: Baoming Zhang, MingCai Chen, Jianqing Song, Shuangjie Li, Jie Zhang, Chongjun Wang
Abstract: Graph Neural Networks (GNNs) have demonstrated remarkable ability in semi-supervised node classification. However, most existing GNNs rely heavily on a large amount of labeled data for training, which is labor-intensive and requires extensive domain knowledge. In this paper, we first analyze the restrictions of GNNs generalization from the perspective of supervision signals in the context of few-shot semi-supervised node classification. To address these challenges, we propose a novel algorithm named NormProp, which utilizes the homophily assumption of unlabeled nodes to generate additional supervision signals, thereby enhancing the generalization against label scarcity. The key idea is to efficiently capture both the class information and the consistency of aggregation during message passing, via decoupling the direction and Euclidean norm of node representations. Moreover, we conduct a theoretical analysis to determine the upper bound of Euclidean norm, and then propose homophilous regularization to constraint the consistency of unlabeled nodes. Extensive experiments demonstrate that NormProp achieve state-of-the-art performance under low-label rate scenarios with low computational complexity.
Authors: Xueyuan Chen, Shangzhe Li, Ruomei Liu, Bowen Shi, Jiaheng Liu, Junran Wu, Ke Xu
Abstract: Trapped by the label scarcity in molecular property prediction and drug design, graph contrastive learning (GCL) came forward. Leading contrastive learning works show two kinds of view generators, that is, random or learnable data corruption and domain knowledge incorporation. While effective, the two ways also lead to molecular semantics altering and limited generalization capability, respectively. To this end, we relate the \textbf{L}in\textbf{E} graph with \textbf{MO}lecular graph co\textbf{N}trastive learning and propose a novel method termed \textit{LEMON}. Specifically, by contrasting the given graph with the corresponding line graph, the graph encoder can freely encode the molecular semantics without omission. Furthermore, we present a new patch with edge attribute fusion and two local contrastive losses enhance information transmission and tackle hard negative samples. Compared with state-of-the-art (SOTA) methods for view generation, superior performance on molecular property prediction suggests the effectiveness of our proposed framework.
Authors: Shogo Ito, Tatsuji Takahashi, Yu Kono
Abstract: The contextual bandit problem, which is a type of reinforcement learning tasks, provides an effective framework for solving challenges in recommendation systems, such as satisfying real-time requirements, enabling personalization, addressing cold-start problems. However, contextual bandit algorithms face challenges since they need to handle large state-action spaces sequentially. These challenges include the high costs for learning and balancing exploration and exploitation, as well as large variations in performance that depend on the domain of application. To address these challenges, Tsuboya et~al. proposed the Regional Linear Risk-sensitive Satisficing (RegLinRS) algorithm. RegLinRS switches between exploration and exploitation based on how well the agent has achieved the target. However, the reward expectations in RegLinRS are linearly approximated based on features, which limits its applicability when the relationship between features and reward expectations is non-linear. To handle more complex environments, we proposed Neural Risk-sensitive Satisficing (NeuralRS), which incorporates neural networks into RegLinRS, and demonstrated its utility.
Authors: Zhenxing Niu, Haoxuan Ji, Yuyao Sun, Zheng Lin, Fei Gao, Yuhang Wang, Haichao Gao
Abstract: Modern privacy regulations have spurred the evolution of machine unlearning, a technique enabling a trained model to efficiently forget specific training data. In prior unlearning methods, the concept of "data forgetting" is often interpreted and implemented as achieving zero classification accuracy on such data. Nevertheless, the authentic aim of machine unlearning is to achieve alignment between the unlearned model and the gold model, i.e., encouraging them to have identical classification accuracy. On the other hand, the gold model often exhibits non-zero classification accuracy due to its generalization ability. To achieve aligned data forgetting, we propose a Twin Machine Unlearning (TMU) approach, where a twin unlearning problem is defined corresponding to the original unlearning problem. Consequently, the generalization-label predictor trained on the twin problem can be transferred to the original problem, facilitating aligned data forgetting. Comprehensive empirical experiments illustrate that our approach significantly enhances the alignment between the unlearned model and the gold model.
Authors: Kaiqu Liang, Haimin Hu, Ryan Liu, Thomas L. Griffiths, Jaime Fern\'andez Fisac
Abstract: Generative AI systems like foundation models (FMs) must align well with human values to ensure their behavior is helpful and trustworthy. While Reinforcement Learning from Human Feedback (RLHF) has shown promise for optimizing model performance using human judgments, existing RLHF pipelines predominantly rely on immediate feedback, which can fail to accurately reflect the downstream impact of an interaction on users' utility. We demonstrate that feedback based on evaluators' foresight estimates of downstream consequences systematically induces Goodhart's Law dynamics, incentivizing misaligned behaviors like sycophancy and deception and ultimately degrading user outcomes. To alleviate this, we propose decoupling evaluation from prediction by refocusing RLHF on hindsight feedback. Our theoretical analysis reveals that conditioning evaluator feedback on downstream observations mitigates misalignment and improves expected human utility, even when these observations are simulated by the AI system itself. To leverage this insight in a practical alignment algorithm, we introduce Reinforcement Learning from Hindsight Simulation (RLHS), which first simulates plausible consequences and then elicits feedback to assess what behaviors were genuinely beneficial in hindsight. We apply RLHS to two widely-employed online and offline preference optimization methods -- Proximal Policy Optimization (PPO) and Direct Preference Optimization (DPO) -- and show empirically that misalignment is significantly reduced with both methods. Through an online human user study, we show that RLHS consistently outperforms RLHF in helping users achieve their goals and earns higher satisfaction ratings, despite being trained solely with simulated hindsight feedback. These results underscore the importance of focusing on long-term consequences, even simulated ones, to mitigate misalignment in RLHF.
Authors: Menghao Huo, Kuan Lu, Yuxiao Li, Qiang Zhu
Abstract: Accurately predicting renewable energy output is crucial for the efficient integration of solar and wind power into modern energy systems. This study develops and evaluates an advanced deep learning model, Channel-Time Patch Time-Series Transformer (CT-PatchTST), to forecast the power output of photovoltaic and wind energy systems using annual offshore wind power, onshore wind power, and solar power generation data from Denmark. While the original Patch Time-Series Transformer(PatchTST) model employs a channel-independent (CI) approach, it tends to overlook inter-channel relationships during training, potentially leading to a loss of critical information. To address this limitation and further leverage the benefits of increased data granularity brought by CI, we propose CT-PatchTST. This enhanced model improves the processing of inter-channel information while maintaining the advantages of the channel-independent approach. The predictive performance of CT-PatchTST is rigorously analyzed, demonstrating its ability to provide precise and reliable energy forecasts. This work contributes to improving the predictability of renewable energy systems, supporting their broader adoption and integration into energy grids.
Authors: Charalampos Shimillas, Kleanthis Malialis, Konstantinos Fokianos, Marios M. Polycarpou
Abstract: With the growing complexity of Cyber-Physical Systems (CPS) and the integration of Internet of Things (IoT), the use of sensors for online monitoring generates large volume of multivariate time series (MTS) data. Consequently, the need for robust anomaly diagnosis in MTS is paramount to maintaining system reliability and safety. While significant advancements have been made in anomaly detection, localization remains a largely underexplored area, though crucial for intelligent decision-making. This paper introduces a novel transformer-based model for unsupervised anomaly diagnosis in MTS, with a focus on improving localization performance, through an in-depth analysis of the self-attention mechanism's learning behavior under both normal and anomalous conditions. We formulate the anomaly localization problem as a three-stage process: time-step, window, and segment-based. This leads to the development of the Space-Time Anomaly Score (STAS), a new metric inspired by the connection between transformer latent representations and space-time statistical models. STAS is designed to capture individual anomaly behaviors and inter-series dependencies, delivering enhanced localization performance. Additionally, the Statistical Feature Anomaly Score (SFAS) complements STAS by analyzing statistical features around anomalies, with their combination helping to reduce false alarms. Experiments on real world and synthetic datasets illustrate the model's superiority over state-of-the-art methods in both detection and localization tasks.
Authors: Binrui Zeng, Yongtao Tang, Xiaodong Liu, Xiaopeng Li
Abstract: Large language models (LLMs) have spurred development in multiple industries. However, the growing number of their parameters brings substantial storage and computing burdens, making it essential to explore model compression techniques for parameter reduction and easier deployment. We propose SWSC, an LLM compression method based on the concept of Shared Weight for Similar Channel. It uses the K-Means clustering algorithm to cluster model weights channel-by-channel, generating clusters with highly similar vectors within each. A representative vector from each cluster is selected to approximately replace all vectors in the cluster, significantly reducing the number of model weight parameters. However, approximate restoration will inevitably cause damage to the performance of the model. To tackle this issue, we perform singular value decomposition on the weight error values before and after compression and retain the larger singular values and their corresponding singular vectors to compensate for the accuracy. The experimental results show that our method can effectively ensure the performance of the compressed LLM even under low-precision conditions.
Authors: Naomi Mona Chmielewski (L2S), Nina Amini (L2S, CNRS), Joseph Mikael
Abstract: We propose a way to bound the generalisation errors of several classes of quantum reservoirs using the Rademacher complexity. We give specific, parameter-dependent bounds for two particular quantum reservoir classes. We analyse how the generalisation bounds scale with growing numbers of qubits. Applying our results to classes with polynomial readout functions, we find that the risk bounds converge in the number of training samples. The explicit dependence on the quantum reservoir and readout parameters in our bounds can be used to control the generalisation error to a certain extent. It should be noted that the bounds scale exponentially with the number of qubits $n$. The upper bounds on the Rademacher complexity can be applied to other reservoir classes that fulfill a few hypotheses on the quantum dynamics and the readout function.
Authors: Wang-Tao Zhou, Zhao Kang, Sicong Liu, Lizong Zhang, Ling Tian
Abstract: Event prediction tasks often handle spatio-temporal data distributed in a large spatial area. Different regions in the area exhibit different characteristics while having latent correlations. This spatial heterogeneity and correlations greatly affect the spatio-temporal distributions of event occurrences, which has not been addressed by state-of-the-art models. Learning spatial dependencies of events in a continuous space is challenging due to its fine granularity and a lack of prior knowledge. In this work, we propose a novel Graph Spatio-Temporal Point Process (GSTPP) model for fine-grained event prediction. It adopts an encoder-decoder architecture that jointly models the state dynamics of spatially localized regions using neural Ordinary Differential Equations (ODEs). The state evolution is built on the foundation of a novel Self-Adaptive Anchor Graph (SAAG) that captures spatial dependencies. By adaptively localizing the anchor nodes in the space and jointly constructing the correlation edges between them, the SAAG enhances the model's ability of learning complex spatial event patterns. The proposed GSTPP model greatly improves the accuracy of fine-grained event prediction. Extensive experimental results show that our method greatly improves the prediction accuracy over existing spatio-temporal event prediction approaches.
Authors: Carlo Romeo, Girolamo Macaluso, Alessandro Sestini, Andrew D. Bagdanov
Abstract: A key challenge in Deep Reinforcement Learning is sample efficiency, especially in real-world applications where collecting environment interactions is expensive or risky. Recent off-policy algorithms improve sample efficiency by increasing the Update-To-Data (UTD) ratio and performing more gradient updates per environment interaction. While this improves sample efficiency, it significantly increases computational cost due to the higher number of gradient updates required. In this paper we propose a sample-efficient method to improve computational efficiency by separating training into distinct learning phases in order to exploit gradient updates more effectively. Our approach builds on top of the Dropout Q-Functions (DroQ) algorithm and alternates between an online, low UTD ratio training phase, and an offline stabilization phase. During the stabilization phase, we fine-tune the Q-functions without collecting new environment interactions. This process improves the effectiveness of the replay buffer and reduces computational overhead. Our experimental results on continuous control problems show that our method achieves results comparable to state-of-the-art, high UTD ratio algorithms while requiring 56\% fewer gradient updates and 50\% less training time than DroQ. Our approach offers an effective and computationally economical solution while maintaining the same sample efficiency as the more costly, high UTD ratio state-of-the-art.
Authors: Tobias Rohe, Florian Burger, Michael K\"olle, Sebastian W\"olckert, Maximilian Zorn, Claudia Linnhoff-Popien
Abstract: The demand for artificially generated data for the development, training and testing of new algorithms is omnipresent. Quantum computing (QC), does offer the hope that its inherent probabilistic functionality can be utilised in this field of generative artificial intelligence. In this study, we use quantum-classical hybrid generative adversarial networks (QuGANs) to artificially generate graphs of shipping routes. We create a training dataset based on real shipping data and investigate to what extent QuGANs are able to learn and reproduce inherent distributions and geometric features of this data. We compare hybrid QuGANs with classical Generative Adversarial Networks (GANs), with a special focus on their parameter efficiency. Our results indicate that QuGANs are indeed able to quickly learn and represent underlying geometric properties and distributions, although they seem to have difficulties in introducing variance into the sampled data. Compared to classical GANs of greater size, measured in the number of parameters used, some QuGANs show similar result quality. Our reference to concrete use cases, such as the generation of shipping data, provides an illustrative example and demonstrate the potential and diversity in which QC can be used.
Authors: Yicheng Li, Qian Lin
Abstract: This paper introduces a diagonal adaptive kernel model that dynamically learns kernel eigenvalues and output coefficients simultaneously during training. Unlike fixed-kernel methods tied to the neural tangent kernel theory, the diagonal adaptive kernel model adapts to the structure of the truth function, significantly improving generalization over fixed-kernel methods, especially when the initial kernel is misaligned with the target. Moreover, we show that the adaptivity comes from learning the right eigenvalues during training, showing a feature learning behavior. By extending to deeper parameterization, we further show how extra depth enhances adaptability and generalization. This study combines the insights from feature learning and implicit regularization and provides new perspective into the adaptivity and generalization potential of neural networks beyond the kernel regime.
Authors: Noelle Y. L. Wong, Eng Yeow Cheu, Zhonglin Chiam
Abstract: Conflicting objectives present a considerable challenge in interleaving multi-task learning, necessitating the need for meticulous design and balance to ensure effective learning of a representative latent data space across all tasks without mutual negative impact. Drawing inspiration from the concept of marginal and conditional probability distributions in probability theory, we design a principled and well-founded approach to disentangle the original input into marginal and conditional probability distributions in the latent space of a variational autoencoder. Our proposed model, Deep Disentangled Interleaving Variational Encoding (DeepDIVE) learns disentangled features from the original input to form clusters in the embedding space and unifies these features via the cross-attention mechanism in the fusion stage. We theoretically prove that combining the objectives for reconstruction and forecasting fully captures the lower bound and mathematically derive a loss function for disentanglement using Na\"ive Bayes. Under the assumption that the prior is a mixture of log-concave distributions, we also establish that the Kullback-Leibler divergence between the prior and the posterior is upper bounded by a function minimized by the minimizer of the cross entropy loss, informing our adoption of radial basis functions (RBF) and cross entropy with interleaving training for DeepDIVE to provide a justified basis for convergence. Experiments on two public datasets show that DeepDIVE disentangles the original input and yields forecast accuracies better than the original VAE and comparable to existing state-of-the-art baselines.
Authors: Zerui Tao, Yuhta Takida, Naoki Murata, Qibin Zhao, Yuki Mitsufuji
Abstract: Parameter-Efficient Fine-Tuning (PEFT) of text-to-image models has become an increasingly popular technique with many applications. Among the various PEFT methods, Low-Rank Adaptation (LoRA) and its variants have gained significant attention due to their effectiveness, enabling users to fine-tune models with limited computational resources. However, the approximation gap between the low-rank assumption and desired fine-tuning weights prevents the simultaneous acquisition of ultra-parameter-efficiency and better performance. To reduce this gap and further improve the power of LoRA, we propose a new PEFT method that combines two classes of adaptations, namely, transform and residual adaptations. In specific, we first apply a full-rank and dense transform to the pre-trained weight. This learnable transform is expected to align the pre-trained weight as closely as possible to the desired weight, thereby reducing the rank of the residual weight. Then, the residual part can be effectively approximated by more compact and parameter-efficient structures, with a smaller approximation error. To achieve ultra-parameter-efficiency in practice, we design highly flexible and effective tensor decompositions for both the transform and residual adaptations. Additionally, popular PEFT methods such as DoRA can be summarized under this transform plus residual adaptation scheme. Experiments are conducted on fine-tuning Stable Diffusion models in subject-driven and controllable generation. The results manifest that our method can achieve better performances and parameter efficiency compared to LoRA and several baselines.
Authors: Marco Hoffmann, Hans Hasse, Fabian Jirasek
Abstract: Although the pure component vapor pressure is one of the most important properties for designing chemical processes, no broadly applicable, sufficiently accurate, and open-source prediction method has been available. To overcome this, we have developed GRAPPA - a hybrid graph neural network for predicting vapor pressures of pure components. GRAPPA enables the prediction of the vapor pressure curve of basically any organic molecule, requiring only the molecular structure as input. The new model consists of three parts: A graph attention network for the message passing step, a pooling function that captures long-range interactions, and a prediction head that yields the component-specific parameters of the Antoine equation, from which the vapor pressure can readily and consistently be calculated for any temperature. We have trained and evaluated GRAPPA on experimental vapor pressure data of almost 25,000 pure components. We found excellent prediction accuracy for unseen components, outperforming state-of-the-art group contribution methods and other machine learning approaches in applicability and accuracy. The trained model and its code are fully disclosed, and GRAPPA is directly applicable via the interactive website ml-prop.mv.rptu.de.
Authors: Yichen Li, Yuying Wang, Jiahua Dong, Haozhao Wang, Yining Qi, Rui Zhang, Ruixuan Li
Abstract: Federated Continual Learning (FCL) aims to enable sequentially privacy-preserving model training on streams of incoming data that vary in edge devices by preserving previous knowledge while adapting to new data. Current FCL literature focuses on restricted data privacy and access to previously seen data while imposing no constraints on the training overhead. This is unreasonable for FCL applications in real-world scenarios, where edge devices are primarily constrained by resources such as storage, computational budget, and label rate. We revisit this problem with a large-scale benchmark and analyze the performance of state-of-the-art FCL approaches under different resource-constrained settings. Various typical FCL techniques and six datasets in two incremental learning scenarios (Class-IL and Domain-IL) are involved in our experiments. Through extensive experiments amounting to a total of over 1,000+ GPU hours, we find that, under limited resource-constrained settings, existing FCL approaches, with no exception, fail to achieve the expected performance. Our conclusions are consistent in the sensitivity analysis. This suggests that most existing FCL methods are particularly too resource-dependent for real-world deployment. Moreover, we study the performance of typical FCL techniques with resource constraints and shed light on future research directions in FCL.
Authors: Paul Garnier, Vincent Lannelongue, Jonathan Viquerat, Elie Hachem
Abstract: We introduce a novel masked pre-training technique for graph neural networks (GNNs) applied to computational fluid dynamics (CFD) problems. By randomly masking up to 40\% of input mesh nodes during pre-training, we force the model to learn robust representations of complex fluid dynamics. We pair this masking strategy with an asymmetric encoder-decoder architecture and gated multi-layer perceptrons to further enhance performance. The proposed method achieves state-of-the-art results on seven CFD datasets, including a new challenging dataset of 3D intracranial aneurysm simulations with over 250,000 nodes per mesh. Moreover, it significantly improves model performance and training efficiency across such diverse range of fluid simulation tasks. We demonstrate improvements of up to 60\% in long-term prediction accuracy compared to previous best models, while maintaining similar computational costs. Notably, our approach enables effective pre-training on multiple datasets simultaneously, significantly reducing the time and data required to achieve high performance on new tasks. Through extensive ablation studies, we provide insights into the optimal masking ratio, architectural choices, and training strategies.
Authors: Guilherme S. Varela, Alberto Sardinha, Francisco S. Melo
Abstract: We propose a novel cooperative multi-agent reinforcement learning (MARL) approach for networked agents. In contrast to previous methods that rely on complete state information or joint observations, our agents must learn how to reach shared objectives under partial observability. During training, they collect individual rewards and approximate a team value function through local communication, resulting in cooperative behavior. To describe our problem, we introduce the networked dynamic partially observable Markov game framework, where agents communicate over a switching topology communication network. Our distributed method, DNA-MARL, uses a consensus mechanism for local communication and gradient descent for local computation. DNA-MARL increases the range of the possible applications of networked agents, being well-suited for real world domains that impose privacy and where the messages may not reach their recipients. We evaluate DNA-MARL across benchmark MARL scenarios. Our results highlight the superior performance of DNA-MARL over previous methods.
Authors: Pia Callmer, Mia Bonini, Edward Ferdian, David Nordsletten, Daniel Giese, Alistair A. Young, Alexander Fyrdahl, David Marlevi
Abstract: 4D Flow Magnetic Resonance Imaging (4D Flow MRI) is a non-invasive technique for volumetric, time-resolved blood flow quantification. However, apparent trade-offs between acquisition time, image noise, and resolution limit clinical applicability. In particular, in regions of highly transient flow, coarse temporal resolution can hinder accurate capture of physiologically relevant flow variations. To overcome these issues, post-processing techniques using deep learning have shown promising results to enhance resolution post-scan using so-called super-resolution networks. However, while super-resolution has been focusing on spatial upsampling, temporal super-resolution remains largely unexplored. The aim of this study was therefore to implement and evaluate a residual network for temporal super-resolution 4D Flow MRI. To achieve this, an existing spatial network (4DFlowNet) was re-designed for temporal upsampling, adapting input dimensions, and optimizing internal layer structures. Training and testing were performed using synthetic 4D Flow MRI data originating from patient-specific in-silico models, as well as using in-vivo datasets. Overall, excellent performance was achieved with input velocities effectively denoised and temporally upsampled, with a mean absolute error (MAE) of 1.0 cm/s in an unseen in-silico setting, outperforming deterministic alternatives (linear interpolation MAE = 2.3 cm/s, sinc interpolation MAE = 2.6 cm/s). Further, the network synthesized high-resolution temporal information from unseen low-resolution in-vivo data, with strong correlation observed at peak flow frames. As such, our results highlight the potential of utilizing data-driven neural networks for temporal super-resolution 4D Flow MRI, enabling high-frame-rate flow quantification without extending acquisition times beyond clinically acceptable limits.
Authors: Konstantin Garov, Kamalika Chaudhuri
Abstract: Machine learning algorithms often encounter different or "out-of-distribution" (OOD) data at deployment time, and OOD detection is frequently employed to detect these examples. While it works reasonably well in practice, existing theoretical results on OOD detection are highly pessimistic. In this work, we take a closer look at this problem, and make a distinction between uniform and non-uniform learnability, following PAC learning theory. We characterize under what conditions OOD detection is uniformly and non-uniformly learnable, and we show that in several cases, non-uniform learnability turns a number of negative results into positive. In all cases where OOD detection is learnable, we provide concrete learning algorithms and a sample-complexity analysis.
Authors: Andreas Abildtrup Hansen, Paraskevas Pegios, Anna Calissano, Aasa Feragen
Abstract: Explaining the predictions of a deep neural network is a nontrivial task, yet high-quality explanations for predictions are often a prerequisite for practitioners to trust these models. Counterfactual explanations aim to explain predictions by finding the ''nearest'' in-distribution alternative input whose prediction changes in a pre-specified way. However, it remains an open question how to define this nearest alternative input, whose solution depends on both the domain (e.g. images, graphs, tabular data, etc.) and the specific application considered. For graphs, this problem is complicated i) by their discrete nature, as opposed to the continuous nature of state-of-the-art graph classifiers; and ii) by the node permutation group acting on the graphs. We propose a method to generate counterfactual explanations for any differentiable black-box graph classifier, utilizing a case-specific permutation equivariant graph variational autoencoder. We generate counterfactual explanations in a continuous fashion by traversing the latent space of the autoencoder across the classification boundary of the classifier, allowing for seamless integration of discrete graph structure and continuous graph attributes. We empirically validate the approach on three graph datasets, showing that our model is consistently high-performing and more robust than the baselines.
Authors: Balasundaram Kadirvelu, Teresa Bellido Bel, Aglaia Freccero, Martina Di Simplicio, Dasha Nicholls, A Aldo Faisal
Abstract: Background: Adolescents are particularly vulnerable to mental disorders, with over 75% of cases manifesting before the age of 25. Research indicates that only 18 to 34% of young people experiencing high levels of depression or anxiety symptoms seek support. Digital tools leveraging smartphones offer scalable and early intervention opportunities. Objective: Using a novel machine learning framework, this study evaluated the feasibility of integrating active and passive smartphone data to predict mental disorders in non-clinical adolescents. Specifically, we investigated the utility of the Mindcraft app in predicting risks for internalising and externalising disorders, eating disorders, insomnia and suicidal ideation. Methods: Participants (N=103; mean age 16.1 years) were recruited from three London schools. Participants completed the Strengths and Difficulties Questionnaire, the Eating Disorders-15 Questionnaire, Sleep Condition Indicator Questionnaire and indicated the presence/absence of suicidal ideation. They used the Mindcraft app for 14 days, contributing active data via self-reports and passive data from smartphone sensors. A contrastive pretraining phase was applied to enhance user-specific feature stability, followed by supervised fine-tuning. The model evaluation employed leave-one-subject-out cross-validation using balanced accuracy as the primary metric. Results: The integration of active and passive data achieved superior performance compared to individual data sources, with mean balanced accuracies of 0.71 for SDQ-High risk, 0.67 for insomnia, 0.77 for suicidal ideation and 0.70 for eating disorders. The contrastive learning framework stabilised daily behavioural representations, enhancing predictive robustness. This study demonstrates the potential of integrating active and passive smartphone data with advanced machine-learning techniques for predicting mental health risks.
Authors: Xueluan Gong, Yuji Wang, Yanjiao Chen, Haocheng Dong, Yiming Li, Mengyuan Sun, Shuaike Li, Qian Wang, Chen Chen
Abstract: Private data, when published online, may be collected by unauthorized parties to train deep neural networks (DNNs). To protect privacy, defensive noises can be added to original samples to degrade their learnability by DNNs. Recently, unlearnable examples are proposed to minimize the training loss such that the model learns almost nothing. However, raw data are often pre-processed before being used for training, which may restore the private information of protected data. In this paper, we reveal the data privacy violation induced by data augmentation, a commonly used data pre-processing technique to improve model generalization capability, which is the first of its kind as far as we are concerned. We demonstrate that data augmentation can significantly raise the accuracy of the model trained on unlearnable examples from 21.3% to 66.1%. To address this issue, we propose a defense framework, dubbed ARMOR, to protect data privacy from potential breaches of data augmentation. To overcome the difficulty of having no access to the model training process, we design a non-local module-assisted surrogate model that better captures the effect of data augmentation. In addition, we design a surrogate augmentation selection strategy that maximizes distribution alignment between augmented and non-augmented samples, to choose the optimal augmentation strategy for each class. We also use a dynamic step size adjustment algorithm to enhance the defensive noise generation process. Extensive experiments are conducted on 4 datasets and 5 data augmentation methods to verify the performance of ARMOR. Comparisons with 6 state-of-the-art defense methods have demonstrated that ARMOR can preserve the unlearnability of protected private data under data augmentation. ARMOR reduces the test accuracy of the model trained on augmented protected samples by as much as 60% more than baselines.
Authors: Runqing Wu, Fei Ye, Qihe Liu, Guoxi Huang, Jinyu Guo, Rongyao Hu
Abstract: Continual Learning seeks to develop a model capable of incrementally assimilating new information while retaining prior knowledge. However, current research predominantly addresses a straightforward learning context, wherein all data samples originate from a singular data domain. This paper shifts focus to a more complex and realistic learning environment, characterized by data samples sourced from multiple distinct domains. We tackle this intricate learning challenge by introducing a novel methodology, termed the Multi-Source Dynamic Expansion Model (MSDEM), which leverages various pre-trained models as backbones and progressively establishes new experts based on them to adapt to emerging tasks. Additionally, we propose an innovative dynamic expandable attention mechanism designed to selectively harness knowledge from multiple backbones, thereby accelerating the new task learning. Moreover, we introduce a dynamic graph weight router that strategically reuses all previously acquired parameters and representations for new task learning, maximizing the positive knowledge transfer effect, which further improves generalization performance. We conduct a comprehensive series of experiments, and the empirical findings indicate that our proposed approach achieves state-of-the-art performance.
Authors: Keisuke Kamo, Hideaki Iiduka
Abstract: Stochastic gradient descent with momentum (SGDM), which is defined by adding a momentum term to SGD, has been well studied in both theory and practice. Theoretically investigated results showed that the settings of the learning rate and momentum weight affect the convergence of SGDM. Meanwhile, practical results showed that the setting of batch size strongly depends on the performance of SGDM. In this paper, we focus on mini-batch SGDM with constant learning rate and constant momentum weight, which is frequently used to train deep neural networks in practice. The contribution of this paper is showing theoretically that using a constant batch size does not always minimize the expectation of the full gradient norm of the empirical loss in training a deep neural network, whereas using an increasing batch size definitely minimizes it, that is, increasing batch size improves convergence of mini-batch SGDM. We also provide numerical results supporting our analyses, indicating specifically that mini-batch SGDM with an increasing batch size converges to stationary points faster than with a constant batch size. Python implementations of the optimizers used in the numerical experiments are available at https://anonymous.4open.science/r/momentum-increasing-batch-size-888C/.
URLs: https://anonymous.4open.science/r/momentum-increasing-batch-size-888C/.
Authors: Guillaume O. Berger, Rapha\"el M. Jungers
Abstract: We study the PAC property of scenario decision-making algorithms, that is, the ability to make a decision that has an arbitrarily low risk of violating an unknown safety constraint, provided sufficiently many realizations (called scenarios) of the safety constraint are sampled. Sufficient conditions for scenario decision-making algorithms to be PAC are available in the literature, such as finiteness of the VC dimension of its associated classifier and existence of a compression scheme. We study the question of whether these sufficient conditions are also necessary. We show with counterexamples that this is not the case in general. This contrasts with binary classification learning, for which the analogous conditions are sufficient and necessary. Popular scenario decision-making algorithms, such as scenario optimization, enjoy additional properties, such as stability and consistency. We show that even under these additional assumptions the above conclusions hold. Finally, we derive a necessary condition for scenario decision-making algorithms to be PAC, inspired by the VC dimension and the so-called no-free-lunch theorem.
Authors: Chuan Zhou, Yaxuan Li, Chunyuan Zheng, Haiteng Zhang, Min Zhang, Haoxuan Li, Mingming Gong
Abstract: Estimating the conditional average treatment effect (CATE) from observational data plays a crucial role in areas such as e-commerce, healthcare, and economics. Existing studies mainly rely on the strong ignorability assumption that there are no unmeasured confounders, whose presence cannot be tested from observational data and can invalidate any causal conclusion. In contrast, data collected from randomized controlled trials (RCT) do not suffer from confounding, but are usually limited by a small sample size. In this paper, we propose a two-stage pretraining-finetuning (TSPF) framework using both large-scale observational data and small-scale RCT data to estimate the CATE in the presence of unmeasured confounding. In the first stage, a foundational representation of covariates is trained to estimate counterfactual outcomes through large-scale observational data. In the second stage, we propose to train an augmented representation of the covariates, which is concatenated to the foundational representation obtained in the first stage to adjust for the unmeasured confounding. To avoid overfitting caused by the small-scale RCT data in the second stage, we further propose a partial parameter initialization approach, rather than training a separate network. The superiority of our approach is validated on two public datasets with extensive experiments. The code is available at https://github.com/zhouchuanCN/KDD25-TSPF.
Authors: Xinchen Han, Hossam Afifi, Michel Marot
Abstract: Offline Reinforcement Learning (RL) faces a critical challenge of extrapolation errors caused by out-of-distribution (OOD) actions. Implicit Q-Learning (IQL) algorithm employs expectile regression to achieve in-sample learning, effectively mitigating the risks associated with OOD actions. However, the fixed hyperparameter in policy evaluation and density-based policy improvement method limit its overall efficiency. In this paper, we propose Proj-IQL, a projective IQL algorithm enhanced with the support constraint. In the policy evaluation phase, Proj-IQL generalizes the one-step approach to a multi-step approach through vector projection, while maintaining in-sample learning and expectile regression framework. In the policy improvement phase, Proj-IQL introduces support constraint that is more aligned with the policy evaluation approach. Furthermore, we theoretically demonstrate that Proj-IQL guarantees monotonic policy improvement and enjoys a progressively more rigorous criterion for superior actions. Empirical results demonstrate the Proj-IQL achieves state-of-the-art performance on D4RL benchmarks, especially in challenging navigation domains.
Authors: Olabode T. Ajenifujah, Amir Barati Farimani
Abstract: Additive manufacturing (AM) is a rapidly evolving technology that has attracted applications across a wide range of fields due to its ability to fabricate complex geometries. However, one of the key challenges in AM is achieving consistent print quality. This inconsistency is often attributed to uncontrolled melt pool dynamics, partly caused by spatter which can lead to defects. Therefore, capturing and controlling the evolution of the melt pool is crucial for enhancing process stability and part quality. In this study, we developed a framework to support decision-making in AM operations, facilitating quality control and minimizing defects via machine learning (ML) and polynomial symbolic regression models. We implemented experimentally validated computational tools as a cost-effective approach to collect large datasets from laser powder bed fusion (LPBF) processes. For a dataset consisting of 281 process conditions, parameters such as melt pool dimensions (length, width, depth), melt pool geometry (area, volume), and volume indicated as spatter were extracted. Using machine learning (ML) and polynomial symbolic regression models, a high R2 of over 95 % was achieved in predicting the melt pool dimensions and geometry features for both the training and testing datasets, with either process conditions (power and velocity) or melt pool dimensions as the model inputs. In the case of volume indicated as spatter, R2 improved after logarithmic transforming the model inputs, which was either the process conditions or the melt pool dimensions. Among the investigated ML models, the ExtraTree model achieved the highest R2 values of 96.7 % and 87.5 %.
Authors: Tim Grams, Patrick Betz, Christian Bartelt
Abstract: Exploration is a crucial skill for self-improvement and open-ended problem-solving. However, it remains uncertain whether large language models can effectively explore the state-space. Existing evaluations predominantly focus on the trade-off between exploration and exploitation, often assessed in multi-armed bandit problems. In contrast, this work isolates exploration as the sole objective, tasking the agent with delivering information that enhances future returns. For the evaluation, we propose to decompose missing rewards into exploration and exploitation components by measuring the optimal achievable return for the states already explored. Our experiments with various LLMs reveal that most models struggle to sufficiently explore the state-space and that weak exploration is insufficient. We observe a positive correlation between model size and exploration performance, with larger models demonstrating superior capabilities. Furthermore, we show that our decomposition provides insights into differences in behaviors driven by agent instructions during prompt engineering, offering a valuable tool for refining LLM performance in exploratory tasks.
Authors: Meiliang Liu, Yunfang Xu, Zijin Li, Zhengye Si, Xiaoxiao Yang, Xinyue Yang, Zhiwen Zhao
Abstract: We introduce Granger Causality Kolmogorov-Arnold Networks (GCKAN), an innovative architecture that extends the recently proposed Kolmogorov-Arnold Networks (KAN) to the domain of causal inference. By extracting base weights from KAN layers and incorporating the sparsity-inducing penalty along with ridge regularization, GCKAN infers the Granger causality from time series while enabling automatic time lag selection. Additionally, we propose an algorithm leveraging time-reversed Granger causality to enhance inference accuracy. The algorithm compares prediction and sparse-inducing losses derived from the original and time-reversed series, automatically selecting the casual relationship with the higher score or integrating the results to mitigate spurious connectivities. Comprehensive experiments conducted on Lorenz-96, gene regulatory networks, fMRI BOLD signals, and VAR datasets demonstrate that the proposed model achieves competitive performance to state-of-the-art methods in inferring Granger causality from nonlinear, high-dimensional, and limited-sample time series.
Authors: Kevin He, David Adam, Sarah Han-Oh, Anqi Liu
Abstract: Measurement quality assurance (QA) practices play a key role in the safe use of Intensity Modulated Radiation Therapies (IMRT) for cancer treatment. These practices have reduced measurement-based IMRT QA failure below 1%. However, these practices are time and labor intensive which can lead to delays in patient care. In this study, we examine how conformal prediction methodologies can be used to robustly triage plans. We propose a new training-aware conformal risk control method by combining the benefit of conformal risk control and conformal training. We incorporate the decision making thresholds based on the gamma passing rate, along with the risk functions used in clinical evaluation, into the design of the risk control framework. Our method achieves high sensitivity and specificity and significantly reduces the number of plans needing measurement without generating a huge confidence interval. Our results demonstrate the validity and applicability of conformal prediction methods for improving efficiency and reducing the workload of the IMRT QA process.
Authors: Youssef Abdalla, Marrisa Taub, Eleanor Hilton, Priya Akkaraju, Alexander Milanovic, Mine Orlu, Abdul W. Basit, Michael T Cook, Tapabrata Chakraborty, David Shorthouse
Abstract: Data scarcity in pharmaceutical research has led to reliance on labour-intensive trial and error approaches for development rather than data driven methods. While Machine Learning offers a solution, existing datasets are often small and noisy, limiting their utility. To address this, we developed a Variationally Encoded Conditional Tabular Generative Adversarial Network (VECT GAN), a novel generative model specifically designed for augmenting small, noisy datasets. We introduce a pipeline where data is augmented before regression model development and demonstrate that this consistently and significantly improves performance over other state of the art tabular generative models. We apply this pipeline across six pharmaceutical datasets, and highlight its real-world applicability by developing novel polymers with medically desirable mucoadhesive properties, which we made and experimentally characterised. Additionally, we pre-train the model on the ChEMBL database of drug-like molecules, leveraging knowledge distillation to enhance its generalisability, making it readily available for use on pharmaceutical datasets containing small molecules, which is an extremely common pharmaceutical task. We demonstrate the power of synthetic data for regularising small tabular datasets, highlighting its potential to become standard practice in pharmaceutical model development, and make our method, including VECT GAN pretrained on ChEMBL available as a pip package.
Authors: Christopher Burger, Charles Walter
Abstract: Advances in the effectiveness of machine learning models have come at the cost of enormous complexity resulting in a poor understanding of how they function. Local surrogate methods have been used to approximate the workings of these complex models, but recent work has revealed their vulnerability to adversarial attacks where the explanation produced is appreciably different while the meaning and structure of the complex model's output remains similar. This prior work has focused on the existence of these weaknesses but not on their magnitude. Here we explore using an alternate search method with the goal of finding minimum viable perturbations, the fewest perturbations necessary to achieve a fixed similarity value between the original and altered text's explanation. Intuitively, a method that requires fewer perturbations to expose a given level of instability is inferior to one which requires more. This nuance allows for superior comparisons of the stability of explainability methods.
Authors: Kuanren Qian, Genesis Omana Suarez, Toshihiko Nambara, Takahisa Kanekiyo, Yongjie Jessica Zhang
Abstract: Neurodevelopmental disorders (NDDs) cover a variety of conditions, including autism spectrum disorder, attention-deficit/hyperactivity disorder, and epilepsy, which impair the central and peripheral nervous systems. Their high comorbidity and complex etiologies present significant challenges for accurate diagnosis and effective treatments. Conventional clinical and experimental studies are time-intensive, burdening research progress considerably. This paper introduces a high-throughput digital twin framework for modeling neurite deteriorations associated with NDDs, integrating synthetic data generation, experimental images, and machine learning (ML) models. The synthetic data generator utilizes an isogeometric analysis (IGA)-based phase field model to capture diverse neurite deterioration patterns such as neurite retraction, atrophy, and fragmentation while mitigating the limitations of scarce experimental data. The ML model utilizes MetaFormer-based gated spatiotemporal attention architecture with deep temporal layers and provides fast predictions. The framework effectively captures long-range temporal dependencies and intricate morphological transformations with average errors of 1.9641% and 6.0339% for synthetic and experimental neurite deterioration, respectively. Seamlessly integrating simulations, experiments, and ML, the digital twin framework can guide researchers to make informed experimental decisions by predicting potential experimental outcomes, significantly reducing costs and saving valuable time. It can also advance our understanding of neurite deterioration and provide a scalable solution for exploring complex neurological mechanisms, contributing to the development of targeted treatments.
Authors: Xiguang Yang, Krish Arora, Michael Bachmann
Abstract: We investigate the loss landscape and backpropagation dynamics of convergence for the simplest possible artificial neural network representing the logical exclusive-OR (XOR) gate. Cross-sections of the loss landscape in the nine-dimensional parameter space are found to exhibit distinct features, which help understand why backpropagation efficiently achieves convergence toward zero loss, whereas values of weights and biases keep drifting. Differences in shapes of cross-sections obtained by nonrandomized and randomized batches are discussed. In reference to statistical physics we introduce the microcanonical entropy as a unique quantity that allows to characterize the phase behavior of the network. Learning in neural networks can thus be thought of as an annealing process that experiences the analogue of phase transitions known from thermodynamic systems. It also reveals how the loss landscape simplifies as more hidden neurons are added to the network, eliminating entropic barriers caused by finite-size effects.
Authors: Shijian Xu
Abstract: Empirical risk minimization (ERM) is not robust to changes in the distribution of data. When the distribution of test data is different from that of training data, the problem is known as out-of-distribution generalization. Recently, two techniques have been developed for addressing out-of-distribution generalization in computer vision: weight averaging (WA) and sharpness-aware minimization (SAM). WA involves training multiple models with different hyperparameters and then averaging the weights of these models, which can significantly improve out-of-distribution generalization performance. SAM optimizes a neural network to find minima in flat regions, which have been proven to perform well under distribution shifts. While these techniques have made great progress, there is still room for improvement and further exploration. In this thesis, we propose increasing the model diversity in WA explicitly by introducing gradient similarity as a loss regularizer to further improve out-of-distribution generalization performance. We also propose combining WA and SAM to solve the problem of few-shot domain adaptation. Our extensive experiments on digits datasets (MNIST, SVHN, USPS, MNIST-M) and other domain adaptation datasets (VLCS, PACS) show that combining WA and SAM leads to improved out-of-distribution generalization performance and significantly increases few-shot domain adaptation accuracy.
Authors: Stefan Baack, Stella Biderman, Kasia Odrozek, Aviya Skowron, Ayah Bdeir, Jillian Bommarito, Jennifer Ding, Maximilian Gahntz, Paul Keller, Pierre-Carl Langlais, Greg Lindahl, Sebastian Majstorovic, Nik Marda, Guilherme Penedo, Maarten Van Segbroeck, Jennifer Wang, Leandro von Werra, Mitchell Baker, Julie Beli\~ao, Kasia Chmielinski, Marzieh Fadaee, Lisa Gutermuth, Hynek Kydl\'i\v{c}ek, Greg Leppert, EM Lewis-Jong, Solana Larsen, Shayne Longpre, Angela Oduor Lungati, Cullen Miller, Victor Miller, Max Ryabinin, Kathleen Siminyu, Andrew Strait, Mark Surman, Anna Tumad\'ottir, Maurice Weber, Rebecca Weiss, Lee White, Thomas Wolf
Abstract: Many AI companies are training their large language models (LLMs) on data without the permission of the copyright owners. The permissibility of doing so varies by jurisdiction: in countries like the EU and Japan, this is allowed under certain restrictions, while in the United States, the legal landscape is more ambiguous. Regardless of the legal status, concerns from creative producers have led to several high-profile copyright lawsuits, and the threat of litigation is commonly cited as a reason for the recent trend towards minimizing the information shared about training datasets by both corporate and public interest actors. This trend in limiting data information causes harm by hindering transparency, accountability, and innovation in the broader ecosystem by denying researchers, auditors, and impacted individuals access to the information needed to understand AI models. While this could be mitigated by training language models on open access and public domain data, at the time of writing, there are no such models (trained at a meaningful scale) due to the substantial technical and sociological challenges in assembling the necessary corpus. These challenges include incomplete and unreliable metadata, the cost and complexity of digitizing physical records, and the diverse set of legal and technical skills required to ensure relevance and responsibility in a quickly changing landscape. Building towards a future where AI systems can be trained on openly licensed data that is responsibly curated and governed requires collaboration across legal, technical, and policy domains, along with investments in metadata standards, digitization, and fostering a culture of openness.
Authors: Nastaran Saffaryazdi, Tamil Selvan Gunasekaran, Kate Laveys, Elizabeth Broadbent, Mark Billinghurst
Abstract: Conversational agents (CAs) are revolutionizing human-computer interaction by evolving from text-based chatbots to empathetic digital humans (DHs) capable of rich emotional expressions. This paper explores the integration of neural and physiological signals into the perception module of CAs to enhance empathetic interactions. By leveraging these cues, the study aims to detect emotions in real-time and generate empathetic responses and expressions. We conducted a user study where participants engaged in conversations with a DH about emotional topics. The DH responded and displayed expressions by mirroring detected emotions in real-time using neural and physiological cues. The results indicate that participants experienced stronger emotions and greater engagement during interactions with the Empathetic DH, demonstrating the effectiveness of incorporating neural and physiological signals for real-time emotion recognition. However, several challenges were identified, including recognition accuracy, emotional transition speeds, individual personality effects, and limitations in voice tone modulation. Addressing these challenges is crucial for further refining Empathetic DHs and fostering meaningful connections between humans and artificial entities. Overall, this research advances human-agent interaction and highlights the potential of real-time neural and physiological emotion recognition in creating empathetic DHs.
Authors: Hao Chen, Gonzalo Esteban Constante-Flores, Krishna Sri Ipsit Mantri, Sai Madhukiran Kompalli, Akshdeep Singh Ahluwalia, Can Li
Abstract: Optimization models have been applied to solve a wide variety of decision-making problems. These models are usually developed by optimization experts but are used by practitioners without optimization expertise in various application domains. As a result, practitioners often struggle to interact with and draw useful conclusions from optimization models independently. To fill this gap, we introduce OptiChat, a natural language dialogue system designed to help practitioners interpret model formulation, diagnose infeasibility, analyze sensitivity, retrieve information, evaluate modifications, and provide counterfactual explanations. By augmenting large language models (LLMs) with functional calls and code generation tailored for optimization models, we enable seamless interaction and minimize the risk of hallucinations in OptiChat. We develop a new dataset to evaluate OptiChat's performance in explaining optimization models. Experiments demonstrate that OptiChat effectively bridges the gap between optimization models and practitioners, delivering autonomous, accurate, and instant responses.
Authors: Hansoo Park, Chanwoo Kim, Jihyeon Kim, Hoseong Cho, Nhat Nguyen Bao Truong, Taehwan Kim, Seungryul Baek
Abstract: RGB-based 3D pose estimation methods have been successful with the development of deep learning and the emergence of high-quality 3D pose datasets. However, most existing methods do not operate well for testing images whose distribution is far from that of training data. However, most existing methods do not operate well for testing images whose distribution is far from that of training data. This problem might be alleviated by involving diverse data during training, however it is non-trivial to collect such diverse data with corresponding labels (i.e. 3D pose). In this paper, we introduced an unsupervised domain adaptation framework for 3D pose estimation that utilizes the unlabeled data in addition to labeled data via masked image modeling (MIM) framework. Foreground-centric reconstruction and attention regularization are further proposed to increase the effectiveness of unlabeled data usage. Experiments are conducted on the various datasets in human and hand pose estimation tasks, especially using the cross-domain scenario. We demonstrated the effectiveness of ours by achieving the state-of-the-art accuracy on all datasets.
Authors: Anurag Kumar, Rohit Paturi, Amber Afshan, Sundararajan Srinivasan
Abstract: Speaker Diarization (SD) is a crucial component of modern end-to-end ASR pipelines. Traditional SD systems, which are typically audio-based and operate independently of ASR, often introduce speaker errors, particularly during speaker transitions and overlapping speech. Recently, language models including fine-tuned large language models (LLMs) have shown to be effective as a second-pass speaker error corrector by leveraging lexical context in the transcribed output. In this work, we introduce a novel acoustic conditioning approach to provide more fine-grained information from the acoustic diarizer to the LLM. We also show that a simpler constrained decoding strategy reduces LLM hallucinations, while avoiding complicated post-processing. Our approach significantly reduces the speaker error rates by 24-43% across Fisher, Callhome, and RT03-CTS datasets, compared to the first-pass Acoustic SD.
Authors: William Cole Nockolds, C. G. Krishnanunni, Tan Bui-Thanh
Abstract: Solving stiff ordinary differential equations (StODEs) requires sophisticated numerical solvers, which are often computationally expensive. In particular, StODE's often cannot be solved with traditional explicit time integration schemes and one must resort to costly implicit methods to compute solutions. On the other hand, state-of-the-art machine learning (ML) based methods such as Neural ODE (NODE) poorly handle the timescale separation of various elements of the solutions to StODEs and require expensive implicit solvers for integration at inference time. In this work, we embark on a different path which involves learning a latent dynamics for StODEs, in which one completely avoids numerical integration. To that end, we consider a constant velocity latent dynamical system whose solution is a sequence of straight lines. Given the initial condition and parameters of the ODE, the encoder networks learn the slope (i.e the constant velocity) and the initial condition for the latent dynamics. In other words, the solution of the original dynamics is encoded into a sequence of straight lines which can be decoded back to retrieve the actual solution as and when required. Another key idea in our approach is a nonlinear transformation of time, which allows for the "stretching/squeezing" of time in the latent space, thereby allowing for varying levels of attention to different temporal regions in the solution. Additionally, we provide a simple universal-approximation-type proof showing that our approach can approximate the solution of stiff nonlinear system on a compact set to any degree of accuracy, {\epsilon}. We show that the dimension of the latent dynamical system in our approach is independent of {\epsilon}. Numerical investigation on prototype StODEs suggest that our method outperforms state-of-the art machine learning approaches for handling StODEs.
Authors: Sabri Mustafa Kahya, Boran Hamdi Sivrikaya, Muhammet Sami Yavuz, Eckehard Steinbach
Abstract: In this work, we propose a novel pipeline for face recognition and out-of-distribution (OOD) detection using short-range FMCW radar. The proposed system utilizes Range-Doppler and micro Range-Doppler Images. The architecture features a primary path (PP) responsible for the classification of in-distribution (ID) faces, complemented by intermediate paths (IPs) dedicated to OOD detection. The network is trained in two stages: first, the PP is trained using triplet loss to optimize ID face classification. In the second stage, the PP is frozen, and the IPs-comprising simple linear autoencoder networks-are trained specifically for OOD detection. Using our dataset generated with a 60 GHz FMCW radar, our method achieves an ID classification accuracy of 99.30% and an OOD detection AUROC of 96.91%.
Authors: Xu Li, Yi Zheng, Haotian Chen, Xiaolei Chen, Yuxuan Liang, Chenghang Lai
Abstract: Large Vision-Language Models (LVLMs) have achieved significant success in multimodal tasks by combining pre-trained vision encoders and large language models. However, current LVLMs mainly rely on features from the final layers of the vision encoder, neglecting complementary information in shallower layers. While recent methods have explored multi-layer features, they are often task-agnostic. We investigate the contributions of visual features from different encoder layers across 18 benchmarks and 6 task categories. Our results show that multi-layer features provide complementary strengths with varying task dependencies, and uniform fusion performs suboptimally. Based on these findings, we propose an instruction-guided vision aggregator that dynamically integrates multi-layer features based on textual instructions, without increasing the number of visual tokens. Extensive evaluations show superior performance, and analysis reveals the dominance of mid-to-high-level features in semantic tasks and the critical role of low-level features in fine-grained perception. This work provides valuable insights into the adaptive use of hierarchical visual features in LVLMs, advancing more flexible multimodal systems.
Authors: Weichen Fan, Chenyang Si, Junhao Song, Zhenyu Yang, Yinan He, Long Zhuo, Ziqi Huang, Ziyue Dong, Jingwen He, Dongwei Pan, Yi Wang, Yuming Jiang, Yaohui Wang, Peng Gao, Xinyuan Chen, Hengjie Li, Dahua Lin, Yu Qiao, Ziwei Liu
Abstract: We present Vchitect-2.0, a parallel transformer architecture designed to scale up video diffusion models for large-scale text-to-video generation. The overall Vchitect-2.0 system has several key designs. (1) By introducing a novel Multimodal Diffusion Block, our approach achieves consistent alignment between text descriptions and generated video frames, while maintaining temporal coherence across sequences. (2) To overcome memory and computational bottlenecks, we propose a Memory-efficient Training framework that incorporates hybrid parallelism and other memory reduction techniques, enabling efficient training of long video sequences on distributed systems. (3) Additionally, our enhanced data processing pipeline ensures the creation of Vchitect T2V DataVerse, a high-quality million-scale training dataset through rigorous annotation and aesthetic evaluation. Extensive benchmarking demonstrates that Vchitect-2.0 outperforms existing methods in video quality, training efficiency, and scalability, serving as a suitable base for high-fidelity video generation.
Authors: Arina Kostina, Marios D. Dikaiakos, Dimosthenis Stefanidis, George Pallis
Abstract: Unlocking the potential of Large Language Models (LLMs) in data classification represents a promising frontier in natural language processing. In this work, we evaluate the performance of different LLMs in comparison with state-of-the-art deep-learning and machine-learning models, in two different classification scenarios: i) the classification of employees' working locations based on job reviews posted online (multiclass classification), and 2) the classification of news articles as fake or not (binary classification). Our analysis encompasses a diverse range of language models differentiating in size, quantization, and architecture. We explore the impact of alternative prompting techniques and evaluate the models based on the weighted F1-score. Also, we examine the trade-off between performance (F1-score) and time (inference response time) for each language model to provide a more nuanced understanding of each model's practical applicability. Our work reveals significant variations in model responses based on the prompting strategies. We find that LLMs, particularly Llama3 and GPT-4, can outperform traditional methods in complex classification tasks, such as multiclass classification, though at the cost of longer inference times. In contrast, simpler ML models offer better performance-to-time trade-offs in simpler binary classification tasks.
Authors: El\'eonore V. Lieffrig, Takuya Toyonaga, Jiazhen Zhang, John A. Onofrey
Abstract: Brain positron emission tomography (PET) imaging is broadly used in research and clinical routines to study, diagnose, and stage Alzheimer's disease (AD). However, its potential cannot be fully exploited yet due to the lack of portable motion correction solutions, especially in clinical settings. Head motion during data acquisition has indeed been shown to degrade image quality and induces tracer uptake quantification error. In this study, we demonstrate that it also biases machine learning-based AD classification. We start by proposing a binary classification algorithm solely based on PET images. We find that it reaches a high accuracy in classifying motion corrected images into cognitive normal or AD. We demonstrate that the classification accuracy substantially decreases when images lack motion correction, thereby limiting the algorithm's effectiveness and biasing image interpretation. We validate these findings in cohorts of 128 $^{11}$C-UCB-J and 173 $^{18}$F-FDG scans, two tracers highly relevant to the study of AD. Classification accuracies decreased by 10% and 5% on 20 $^{18}$F-FDG and 20 $^{11}$C-UCB-J testing cases, respectively. Our findings underscore the critical need for efficient motion correction methods to make the most of the diagnostic capabilities of PET-based machine learning.
Authors: Isaac Corley, Simone Fobi Nsutezo, Anthony Ortiz, Caleb Robinson, Rahul Dodhia, Juan M. Lavista Ferres, Peyman Najafirad
Abstract: Remote sensing imagery is dense with objects and contextual visual information. There is a recent trend to combine paired satellite images and text captions for pretraining performant encoders for downstream tasks. However, while contrastive image-text methods like CLIP enable vision-language alignment and zero-shot classification ability, vision-only downstream performance tends to degrade compared to image-only pretraining, such as MAE. In this paper, we propose FLAVARS, a pretraining method that combines the best of both contrastive learning and masked modeling, along with geospatial alignment via contrastive location encoding. We find that FLAVARS significantly outperforms a baseline of SkyCLIP for vision-only tasks such as KNN classification and semantic segmentation, +6\% mIOU on SpaceNet1, while retaining the ability to perform zero-shot classification, unlike MAE pretrained methods.
Authors: Krrish Chawla, Aryan Sahai, Mario DePavia, Sudharsan Sundar, Brando Miranda
Abstract: Contrary to the conventional emphasis on dataset size, we explore the role of data alignment -- an often overlooked aspect of data quality -- in training capable Large Language Models (LLMs). To do so, we use the Task2Vec-based alignment coefficient, a quantitative measure of the similarity between two datasets, to quantify the impact of alignment between training data and evaluation data on downstream performance. In particular, we conduct controlled \textit{interventional} experiments for two settings: 1. the impact of increased alignment coefficients between various pre-training (pt) against evaluation datasets, and 2. the impact of increased alignment coefficients between domain specific fine-tuning (ft) against domain specific evaluation. The domain specific task we explore is Autoformalization -- the machine translation task between natural language and code for formal verification. In both settings, we find a strong, predictable negative correlation between the alignment coefficient of a model's training and evaluation data and the model's loss/perplexity on the respective downstream task. These findings suggest a re-evaluation of LLM training approaches, demonstrating the relevance of data alignment compared to data quantity, especially in specialized downstream tasks such as Autoformalization.
Authors: Zhiwei Gao, George Em Karniadakis
Abstract: Uncertainty quantification (UQ) plays a pivotal role in scientific machine learning, especially when surrogate models are used to approximate complex systems. Although multilayer perceptions (MLPs) are commonly employed as surrogates, they often suffer from overfitting due to their large number of parameters. Kolmogorov-Arnold networks (KANs) offer an alternative solution with fewer parameters. However, gradient-based inference methods, such as Hamiltonian Monte Carlo (HMC), may result in computational inefficiency when applied to KANs, especially for large-scale datasets, due to the high cost of back-propagation.To address these challenges, we propose a novel approach, combining the dropout Tikhonov ensemble Kalman inversion (DTEKI) with Chebyshev KANs. This gradient-free method effectively mitigates overfitting and enhances numerical stability. Additionally, we incorporate the active subspace method to reduce the parameter-space dimensionality, allowing us to improve the accuracy of predictions and obtain more reliable uncertainty estimates.Extensive experiments demonstrate the efficacy of our approach in various test cases, including scenarios with large datasets and high noise levels. Our results show that the new method achieves comparable or better accuracy, much higher efficiency as well as stability compared to HMC, in addition to scalability. Moreover, by leveraging the low-dimensional parameter subspace, our method preserves prediction accuracy while substantially reducing further the computational cost.
Authors: Waqwoya Abebe, Sadegh Jafari, Sixing Yu, Akash Dutta, Jan Strube, Nathan R. Tallent, Luanzheng Guo, Pablo Munoz, Ali Jannesari
Abstract: Neural Architecture Search (NAS) is a powerful approach of automating the design of efficient neural architectures. In contrast to traditional NAS methods, recently proposed one-shot NAS methods prove to be more efficient in performing NAS. One-shot NAS works by generating a singular weight-sharing supernetwork that acts as a search space (container) of subnetworks. Despite its achievements, designing the one-shot search space remains a major challenge. In this work we propose a search space design strategy for Vision Transformer (ViT)-based architectures. In particular, we convert the Segment Anything Model (SAM) into a weight-sharing supernetwork called SuperSAM. Our approach involves automating the search space design via layer-wise structured pruning and parameter prioritization. While the structured pruning applies probabilistic removal of certain transformer layers, parameter prioritization performs weight reordering and slicing of MLP-blocks in the remaining layers. We train supernetworks on several datasets using the sandwich rule. For deployment, we enhance subnetwork discovery by utilizing a program autotuner to identify efficient subnetworks within the search space. The resulting subnetworks are 30-70% smaller in size compared to the original pre-trained SAM ViT-B, yet outperform the pretrained model. Our work introduces a new and effective method for ViT NAS search-space design.
Authors: Zhongwang Zhang, Pengxiao Lin, Zhiwei Wang, Yaoyu Zhang, Zhi-Qin John Xu
Abstract: Transformers have demonstrated impressive capabilities across various tasks, yet their performance on compositional problems remains a subject of debate. In this study, we investigate the internal mechanisms underlying Transformers' behavior in compositional tasks. We find that complexity control strategies significantly influence whether the model learns primitive-level rules that generalize out-of-distribution (reasoning-based solutions) or relies solely on memorized mappings (memory-based solutions). By applying masking strategies to the model's information circuits and employing multiple complexity metrics, we reveal distinct internal working mechanisms associated with different solution types. Further analysis reveals that reasoning-based solutions exhibit a lower complexity bias, which aligns with the well-studied neuron condensation phenomenon. This lower complexity bias is hypothesized to be the key factor enabling these solutions to learn reasoning rules. We validate these conclusions across multiple real-world datasets, including image generation and natural language processing tasks, confirming the broad applicability of our findings.
Authors: Geon-Woo Kim, Donghyun Kim, Jeongyoon Moon, Henry Liu, Tarannum Khan, Anand Iyer, Daehyeok Kim, Aditya Akella
Abstract: Graph Neural Networks (GNNs) have been widely adopted for their ability to compute expressive node representations in graph datasets. However, serving GNNs on large graphs is challenging due to the high communication, computation, and memory overheads of constructing and executing computation graphs, which represent information flow across large neighborhoods. Existing approximation techniques in training can mitigate the overheads but, in serving, still lead to high latency and/or accuracy loss. To this end, we propose OMEGA, a system that enables low-latency GNN serving for large graphs with minimal accuracy loss through two key ideas. First, OMEGA employs selective recomputation of precomputed embeddings, which allows for reusing precomputed computation subgraphs while selectively recomputing a small fraction to minimize accuracy loss. Second, we develop computation graph parallelism, which reduces communication overhead by parallelizing the creation and execution of computation graphs across machines. Our evaluation with large graph datasets and GNN models shows that OMEGA significantly outperforms state-of-the-art techniques.
Authors: Steve Hanneke, Hongao Wang
Abstract: We provide a full characterization of the concept classes that are optimistically universally online learnable with $\{0, 1\}$ labels. The notion of optimistically universal online learning was defined in [Hanneke, 2021] in order to understand learnability under minimal assumptions. In this paper, following the philosophy behind that work, we investigate two questions, namely, for every concept class: (1) What are the minimal assumptions on the data process admitting online learnability? (2) Is there a learning algorithm which succeeds under every data process satisfying the minimal assumptions? Such an algorithm is said to be optimistically universal for the given concept class. We resolve both of these questions for all concept classes, and moreover, as part of our solution, we design general learning algorithms for each case. Finally, we extend these algorithms and results to the agnostic case, showing an equivalence between the minimal assumptions on the data process for learnability in the agnostic and realizable cases, for every concept class, as well as the equivalence of optimistically universal learnability.
Authors: Aniruddha Srinivas Joshi
Abstract: Procedural Content Generation (PCG) is widely used to create scalable and diverse environments in games. However, existing methods, such as the Wave Function Collapse (WFC) algorithm, are often limited to static scenarios and lack the adaptability required for dynamic, narrative-driven applications, particularly in augmented reality (AR) games. This paper presents a reinforcement learning-enhanced WFC framework designed for mobile AR environments. By integrating environment-specific rules and dynamic tile weight adjustments informed by reinforcement learning (RL), the proposed method generates maps that are both contextually coherent and responsive to gameplay needs. Comparative evaluations and user studies demonstrate that the framework achieves superior map quality and delivers immersive experiences, making it well-suited for narrative-driven AR games. Additionally, the method holds promise for broader applications in education, simulation training, and immersive extended reality (XR) experiences, where dynamic and adaptive environments are critical.
Authors: Yiran Tao, Jehan Yang, Dan Ding, Zackory Erickson
Abstract: Teleoperating high degrees-of-freedom (DoF) robotic manipulators via low-DoF controllers like joysticks often requires frequent switching between control modes, where each mode maps controller movements to specific robot actions. Manually performing this frequent switching can make teleoperation cumbersome and inefficient. On the other hand, existing automatic mode-switching solutions, such as heuristic-based or learning-based methods, are often task-specific and lack generalizability. In this paper, we introduce LLM-Driven Automatic Mode Switching (LAMS), a novel approach that leverages Large Language Models (LLMs) to automatically switch control modes based on task context. Unlike existing methods, LAMS requires no prior task demonstrations and incrementally improves by integrating user-generated mode-switching examples. We validate LAMS through an ablation study and a user study with 10 participants on complex, long-horizon tasks, demonstrating that LAMS effectively reduces manual mode switches, is preferred over alternative methods, and improves performance over time. The project website with supplementary materials is at https://lams-assistance.github.io/.
Authors: Safayat Bin Hakim, Muhammad Adil, Alvaro Velasquez, Houbing Herbert Song
Abstract: In this paper, we propose an Adaptive Neuro-Symbolic Learning Framework for digital twin technology called ``ANSR-DT." Our approach combines pattern recognition algorithms with reinforcement learning and symbolic reasoning to enable real-time learning and adaptive intelligence. This integration enhances the understanding of the environment and promotes continuous learning, leading to better and more effective decision-making in real-time for applications that require human-machine collaboration. We evaluated the \textit{ANSR-DT} framework for its ability to learn and adapt to dynamic patterns, observing significant improvements in decision accuracy, reliability, and interpretability when compared to existing state-of-the-art methods. However, challenges still exist in extracting and integrating symbolic rules in complex environments, which limits the full potential of our framework in heterogeneous settings. Moreover, our ongoing research aims to address this issue in the future by ensuring seamless integration of neural models at large. In addition, our open-source implementation promotes reproducibility and encourages future research to build on our foundational work.
Authors: Oscar Ramos-Soto, Jorge Ramos-Frutos, Ezequiel Perez-Zarate, Diego Oliva, Sandra E. Balderas-Mata
Abstract: Feature extraction techniques are crucial in medical image classification; however, classical feature extractors in addition to traditional machine learning classifiers often exhibit significant limitations in providing sufficient discriminative information for complex image sets. While Convolutional Neural Networks (CNNs) and Vision Transformer (ViT) have shown promise in feature extraction, they are prone to overfitting due to the inherent characteristics of medical imaging data, including small sample sizes or high intra-class variance. In this work, the Medical Image Attention-based Feature Extractor (MIAFEx) is proposed, a novel method that employs a learnable refinement mechanism to enhance the classification token within the Transformer encoder architecture. This mechanism adjusts the token based on learned weights, improving the extraction of salient features and enhancing the model's adaptability to the challenges presented by medical imaging data. The MIAFEx output features quality is compared against classical feature extractors using traditional and hybrid classifiers. Also, the performance of these features is compared against modern CNN and ViT models in classification tasks, demonstrating its superiority in accuracy and robustness across multiple complex classification medical imaging datasets. This advantage is particularly pronounced in scenarios with limited training data, where traditional and modern models often struggle to generalize effectively. The source code of this proposal can be found at https://github.com/Oscar-RamosS/Medical-Image-Attention-based-Feature-Extractor-MIAFEx
URLs: https://github.com/Oscar-RamosS/Medical-Image-Attention-based-Feature-Extractor-MIAFEx
Authors: Siqi Zhao (WBooth School of Engineering Practice and Technology, McMaster University, Hamilton, Ontario Canada), Wangyang Li (WBooth School of Engineering Practice and Technology, McMaster University, Hamilton, Ontario Canada), Xiru Wang (WBooth School of Engineering Practice and Technology, McMaster University, Hamilton, Ontario Canada), Stevie Foglia (School of Biomedical Engineering, McMaster University, Hamilton, Ontario, Canada), Hongzhao Tan (WBooth School of Engineering Practice and Technology, McMaster University, Hamilton, Ontario Canada), Bohan Zhang (WBooth School of Engineering Practice and Technology, McMaster University, Hamilton, Ontario Canada), Ameer Hamoodi (School of Biomedical Engineering, McMaster University, Hamilton, Ontario, Canada), Aimee Nelson (School of Biomedical Engineering, McMaster University, Hamilton, Ontario, Canada, Department of Kinesiology, McMaster University, Hamilton, Ontario, Canada), Zhen Gao (WBooth School of Engineering Practice and Technology, McMaster University, Hamilton, Ontario Canada, School of Biomedical Engineering, McMaster University, Hamilton, Ontario, Canada)
Abstract: Machine learning (ML) and deep learning (DL) techniques have been widely applied to analyze electroencephalography (EEG) signals for disease diagnosis and brain-computer interfaces (BCI). The integration of multimodal data has been shown to enhance the accuracy of ML and DL models. Combining EEG with other modalities can improve clinical decision-making by addressing complex tasks in clinical populations. This systematic literature review explores the use of multimodal EEG data in ML and DL models for clinical applications. A comprehensive search was conducted across PubMed, Web of Science, and Google Scholar, yielding 16 relevant studies after three rounds of filtering. These studies demonstrate the application of multimodal EEG data in addressing clinical challenges, including neuropsychiatric disorders, neurological conditions (e.g., seizure detection), neurodevelopmental disorders (e.g., autism spectrum disorder), and sleep stage classification. Data fusion occurred at three levels: signal, feature, and decision levels. The most commonly used ML models were support vector machines (SVM) and decision trees. Notably, 11 out of the 16 studies reported improvements in model accuracy with multimodal EEG data. This review highlights the potential of multimodal EEG-based ML models in enhancing clinical diagnostics and problem-solving.
Authors: Xuanhe Zhou, Wei Zhou, Liguo Qi, Hao Zhang, Dihao Chen, Bingsheng He, Mian Lu, Guoliang Li, Fan Wu, Yuqiang Chen
Abstract: Efficient and consistent feature computation is crucial for a wide range of online ML applications. Typically, feature computation is divided into two distinct phases, i.e., offline stage for model training and online stage for model serving. These phases often rely on execution engines with different interface languages and function implementations, causing significant inconsistencies. Moreover, many online ML features involve complex time-series computations (e.g., functions over varied-length table windows) that differ from standard streaming and analytical queries. Existing data processing systems (e.g., Spark, Flink, DuckDB) often incur multi-second latencies for these computations, making them unsuitable for real-time online ML applications that demand timely feature updates. This paper presents OpenMLDB, a feature computation system deployed in 4Paradigm's SageOne platform and over 100 real scenarios. Technically, OpenMLDB first employs a unified query plan generator for consistent computation results across the offline and online stages, significantly reducing feature deployment overhead. Second, OpenMLDB provides an online execution engine that resolves performance bottlenecks caused by long window computations (via pre-aggregation) and multi-table window unions (via data self-adjusting). It also provides a high-performance offline execution engine with window parallel optimization and time-aware data skew resolving. Third, OpenMLDB features a compact data format and stream-focused indexing to maximize memory usage and accelerate data access. Evaluations in testing and real workloads reveal significant performance improvements and resource savings compared to the baseline systems. The open community of OpenMLDB now has over 150 contributors and gained 1.6k stars on GitHub.
Authors: Jason T. Isa, Lillian J. Ratliff, Samuel A. Burden
Abstract: When humans interact with learning-based control systems, a common goal is to minimize a cost function known only to the human. For instance, an exoskeleton may adapt its assistance in an effort to minimize the human's metabolic cost-of-transport. Conventional approaches to synthesizing the learning algorithm solve an inverse problem to infer the human's cost. However, these problems can be ill-posed, hard to solve, or sensitive to problem data. Here we show a game-theoretic learning algorithm that works solely by observing human actions to find the cost minimum, avoiding the need to solve an inverse problem. We evaluate the performance of our algorithm in an extensive set of human subjects experiments, demonstrating consistent convergence to the minimum of a prescribed human cost function in scalar and multidimensional instantiations of the game. We conclude by outlining future directions for theoretical and empirical extensions of our results.
Authors: Xinya Ji, Gaspard Zoss, Prashanth Chandran, Lingchen Yang, Xun Cao, Barbara Solenthaler, Derek Bradley
Abstract: 2D portrait animation has experienced significant advancements in recent years. Much research has utilized the prior knowledge embedded in large generative diffusion models to enhance high-quality image manipulation. However, most methods only focus on generating RGB images as output, and the co-generation of consistent visual plus 3D output remains largely under-explored. In our work, we propose to jointly learn the visual appearance and depth simultaneously in a diffusion-based portrait image generator. Our method embraces the end-to-end diffusion paradigm and introduces a new architecture suitable for learning this conditional joint distribution, consisting of a reference network and a channel-expanded diffusion backbone. Once trained, our framework can be efficiently adapted to various downstream applications, such as facial depth-to-image and image-to-depth generation, portrait relighting, and audio-driven talking head animation with consistent 3D output.
Authors: Laurenz Nagler, Martin Zach, Thomas Pock
Abstract: Diffusion models have recently shown remarkable results in magnetic resonance imaging reconstruction. However, the employed networks typically are black-box estimators of the (smoothed) prior score with tens of millions of parameters, restricting interpretability and increasing reconstruction time. Furthermore, parallel imaging reconstruction algorithms either rely on off-line coil sensitivity estimation, which is prone to misalignment and restricting sampling trajectories, or perform per-coil reconstruction, making the computational cost proportional to the number of coils. To overcome this, we jointly reconstruct the image and the coil sensitivities using the lightweight, parameter-efficient, and interpretable product of Gaussian mixture diffusion model as an image prior and a classical smoothness priors on the coil sensitivities. The proposed method delivers promising results while allowing for fast inference and demonstrating robustness to contrast out-of-distribution data and sampling trajectories, comparable to classical variational penalties such as total variation. Finally, the probabilistic formulation allows the calculation of the posterior expectation and pixel-wise variance.
Authors: Jaemyung Yu, Jaehyun Choi, Dong-Jae Lee, HyeongGwon Hong, Junmo Kim
Abstract: Unsupervised representation learning has significantly advanced various machine learning tasks. In the computer vision domain, state-of-the-art approaches utilize transformations like random crop and color jitter to achieve invariant representations, embedding semantically the same inputs despite transformations. However, this can degrade performance in tasks requiring precise features, such as localization or flower classification. To address this, recent research incorporates equivariant representation learning, which captures transformation-sensitive information. However, current methods depend on transformation labels and thus struggle with interdependency and complex transformations. We propose Self-supervised Transformation Learning (STL), replacing transformation labels with transformation representations derived from image pairs. The proposed method ensures transformation representation is image-invariant and learns corresponding equivariant transformations, enhancing performance without increased batch complexity. We demonstrate the approach's effectiveness across diverse classification and detection tasks, outperforming existing methods in 7 out of 11 benchmarks and excelling in detection. By integrating complex transformations like AugMix, unusable by prior equivariant methods, this approach enhances performance across tasks, underscoring its adaptability and resilience. Additionally, its compatibility with various base models highlights its flexibility and broad applicability. The code is available at https://github.com/jaemyung-u/stl.
Authors: Tianru Zhang, Li Ju, Prashant Singh, Salman Toor
Abstract: Analyzing large-scale datasets, especially involving complex and high-dimensional data like images, is particularly challenging. While self-supervised learning (SSL) has proven effective for learning representations from unlabelled data, it typically focuses on flat, non-hierarchical structures, missing the multi-level relationships present in many real-world datasets. Hierarchical clustering (HC) can uncover these relationships by organizing data into a tree-like structure, but it often relies on rigid similarity metrics that struggle to capture the complexity of diverse data types. To address these we envision $\texttt{InfoHier}$, a framework that combines SSL with HC to jointly learn robust latent representations and hierarchical structures. This approach leverages SSL to provide adaptive representations, enhancing HC's ability to capture complex patterns. Simultaneously, it integrates HC loss to refine SSL training, resulting in representations that are more attuned to the underlying information hierarchy. $\texttt{InfoHier}$ has the potential to improve the expressiveness and performance of both clustering and representation learning, offering significant benefits for data analysis, management, and information retrieval.
Authors: Yunze Wei, Xiaohui Xie, Yiwei Zuo, Tianshuo Hu, Xinyi Chen, Kaiwen Chi, Yong Cui
Abstract: Configuration translation is a critical and frequent task in network operations. When a network device is damaged or outdated, administrators need to replace it to maintain service continuity. The replacement devices may originate from different vendors, necessitating configuration translation to ensure seamless network operation. However, translating configurations manually is a labor-intensive and error-prone process. In this paper, we propose an intent-based framework for translating network configuration with Large Language Model (LLM) Agents. The core of our approach is an Intent-based Retrieval Augmented Generation (IRAG) module that systematically splits a configuration file into fragments, extracts intents, and generates accurate translations. We also design a two-stage verification method to validate the syntax and semantics correctness of the translated configurations. We implement and evaluate the proposed method on real-world network configurations. Experimental results show that our method achieves 97.74% syntax correctness, outperforming state-of-the-art methods in translation accuracy.
Authors: Sydney Vernon, Eviatar Bach, Oliver R. A. Dunbar
Abstract: Ensemble Kalman inversion (EKI) is a derivative-free, particle-based optimization method for solving inverse problems. It can be shown that EKI approximates a gradient flow, which allows the application of methods for accelerating gradient descent. Here, we show that Nesterov acceleration is effective in speeding up the reduction of the EKI cost function on a variety of inverse problems. We also implement Nesterov acceleration for two EKI variants, unscented Kalman inversion and ensemble transform Kalman inversion. Our specific implementation takes the form of a particle-level nudge that is demonstrably simple to couple in a black-box fashion with any existing EKI variant algorithms, comes with no additional computational expense, and with no additional tuning hyperparameters. This work shows a pathway for future research to translate advances in gradient-based optimization into advances in gradient-free Kalman optimization.
Authors: Zhipeng Ye, Feng Jiang, Qiufeng Wang, Kaizhu Huang, Jiaqi Huang
Abstract: CLIP (Contrastive Language-Image Pre-training) has attained great success in pattern recognition and computer vision. Transferring CLIP to downstream tasks (e.g. zero- or few-shot classification) is a hot topic in multimodal learning. However, current studies primarily focus on either prompt learning for text or adapter tuning for vision, without fully exploiting the complementary information and correlations among image-text pairs. In this paper, we propose an Image Description Enhanced CLIP-Adapter (IDEA) method to adapt CLIP to few-shot image classification tasks. This method captures fine-grained features by leveraging both visual features and textual descriptions of images. IDEA is a training-free method for CLIP, and it can be comparable to or even exceeds state-of-the-art models on multiple tasks. Furthermore, we introduce Trainable-IDEA (T-IDEA), which extends IDEA by adding two lightweight learnable components (i.e., a projector and a learnable latent space), further enhancing the model's performance and achieving SOTA results on 11 datasets. As one important contribution, we employ the Llama model and design a comprehensive pipeline to generate textual descriptions for images of 11 datasets, resulting in a total of 1,637,795 image-text pairs, named "IMD-11". Our code and data are released at https://github.com/FourierAI/IDEA.
Authors: Hamza Bodor, Laurent Carlier
Abstract: The Queue-Reactive model introduced by Huang et al. (2015) has become a standard tool for limit order book modeling, widely adopted by both researchers and practitioners for its simplicity and effectiveness. We present the Multidimensional Deep Queue-Reactive (MDQR) model, which extends this framework in three ways: it relaxes the assumption of queue independence, enriches the state space with market features, and models the distribution of order sizes. Through a neural network architecture, the model learns complex dependencies between different price levels and adapts to varying market conditions, while preserving the interpretable point-process foundation of the original framework. Using data from the Bund futures market, we show that MDQR captures key market properties including the square-root law of market impact, cross-queue correlations, and realistic order size patterns. The model demonstrates particular strength in reproducing both conditional and stationary distributions of order sizes, as well as various stylized facts of market microstructure. The model achieves this while maintaining the computational efficiency needed for practical applications such as strategy development through reinforcement learning or realistic backtesting.
Authors: Carlos G\"uemes-Palau, Miquel Ferriol-Galm\'es, Jordi Paillisse-Vilanova, Albert L\'opez-Bresc\'o, Pere Barlet-Ros, Albert Cabellos-Aparicio
Abstract: Network simulation is pivotal in network modeling, assisting with tasks ranging from capacity planning to performance estimation. Traditional approaches such as Discrete Event Simulation (DES) face limitations in terms of computational cost and accuracy. This paper introduces RouteNet-Gauss, a novel integration of a testbed network with a Machine Learning (ML) model to address these challenges. By using the testbed as a hardware accelerator, RouteNet-Gauss generates training datasets rapidly and simulates network scenarios with high fidelity to real-world conditions. Experimental results show that RouteNet-Gauss significantly reduces prediction errors by up to 95% and achieves a 488x speedup in inference time compared to state-of-the-art DES-based methods. RouteNet-Gauss's modular architecture is dynamically constructed based on the specific characteristics of the network scenario, such as topology and routing. This enables it to understand and generalize to different network configurations beyond those seen during training, including networks up to 10x larger. Additionally, it supports Temporal Aggregated Performance Estimation (TAPE), providing configurable temporal granularity and maintaining high accuracy in flow performance metrics. This approach shows promise in improving both simulation efficiency and accuracy, offering a valuable tool for network operators.
Authors: Guillaume O. Berger, Rapha\"el M. Jungers
Abstract: Scenario decision making offers a flexible way of making decision in an uncertain environment while obtaining probabilistic guarantees on the risk of failure of the decision. The idea of this approach is to draw samples of the uncertainty and make a decision based on the samples, called "scenarios". The probabilistic guarantees take the form of a bound on the probability of sampling a set of scenarios that will lead to a decision whose risk of failure is above a given maximum tolerance. This bound can be expressed as a function of the number of sampled scenarios, the maximum tolerated risk, and some intrinsic property of the problem called the "compression size". Several such bounds have been proposed in the literature under various assumptions on the problem. We propose new bounds that improve upon the existing ones without requiring stronger assumptions on the problem.
Authors: Sneha N. Naik, Elsa D. Angelini, Eric A. Hoffman, Elizabeth C. Oelsner, R. Graham Barr, Benjamin M. Smith, Andrew F. Laine
Abstract: The ratio of airway tree lumen to lung size (ALR), assessed at full inspiration on high resolution full-lung computed tomography (CT), is a major risk factor for chronic obstructive pulmonary disease (COPD). There is growing interest to infer ALR from cardiac CT images, which are widely available in epidemiological cohorts, to investigate the relationship of ALR to severe COVID-19 and post-acute sequelae of SARS-CoV-2 infection (PASC). Previously, cardiac scans included approximately 2/3 of the total lung volume with 5-6x greater slice thickness than high-resolution (HR) full-lung (FL) CT. In this study, we present a novel attention-based Multi-view Swin Transformer to infer FL ALR values from segmented cardiac CT scans. For the supervised training we exploit paired full-lung and cardiac CTs acquired in the Multi-Ethnic Study of Atherosclerosis (MESA). Our network significantly outperforms a proxy direct ALR inference on segmented cardiac CT scans and achieves accuracy and reproducibility comparable with a scan-rescan reproducibility of the FL ALR ground-truth.
Authors: Liam Dugan, Andrew Zhu, Firoj Alam, Preslav Nakov, Marianna Apidianaki, Chris Callison-Burch
Abstract: Recently there have been many shared tasks targeting the detection of generated text from Large Language Models (LLMs). However, these shared tasks tend to focus either on cases where text is limited to one particular domain or cases where text can be from many domains, some of which may not be seen during test time. In this shared task, using the newly released RAID benchmark, we aim to answer whether or not models can detect generated text from a large, yet fixed, number of domains and LLMs, all of which are seen during training. Over the course of three months, our task was attempted by 9 teams with 23 detector submissions. We find that multiple participants were able to obtain accuracies of over 99% on machine-generated text from RAID while maintaining a 5% False Positive Rate -- suggesting that detectors are able to robustly detect text from many domains and models simultaneously. We discuss potential interpretations of this result and provide directions for future research.
Authors: Surya Murthy, John-Paul Clarke, Ufuk Topcu, Zhenyu Gao
Abstract: Urban air mobility (UAM) is a transformative system that operates various small aerial vehicles in urban environments to reshape urban transportation. However, integrating UAM into existing urban environments presents a variety of complex challenges. Recent analyses of UAM's operational constraints highlight aircraft noise and system safety as key hurdles to UAM system implementation. Future UAM air traffic management schemes must ensure that the system is both quiet and safe. We propose a multi-agent reinforcement learning approach to manage UAM traffic, aiming at both vertical separation assurance and noise mitigation. Through extensive training, the reinforcement learning agent learns to balance the two primary objectives by employing altitude adjustments in a multi-layer UAM network. The results reveal the tradeoffs among noise impact, traffic congestion, and separation. Overall, our findings demonstrate the potential of reinforcement learning in mitigating UAM's noise impact while maintaining safe separation using altitude adjustments
Authors: Paolo Baldan, Sebastian Gurke, Barbara K\"onig, Tommaso Padoan, Florian Wittbold
Abstract: Fixpoints are ubiquitous in computer science and when dealing with quantitative semantics and verification one is commonly led to consider least fixpoints of (higher-dimensional) functions over the nonnegative reals. We show how to approximate the least fixpoint of such functions, focusing on the case in which they are not known precisely, but represented by a sequence of approximating functions that converge to them. We concentrate on monotone and non-expansive functions, for which uniqueness of fixpoints is not guaranteed and standard fixpoint iteration schemes might get stuck at a fixpoint that is not the least. Our main contribution is the identification of an iteration scheme, a variation of Mann iteration with a dampening factor, which, under suitable conditions, is shown to guarantee convergence to the least fixpoint of the function of interest. We then argue that these results are relevant in the context of model-based reinforcement learning for Markov decision processes (MDPs), showing that the proposed iteration scheme instantiates to MDPs and allows us to derive convergence to the optimal expected return. More generally, we show that our results can be used to iterate to the least fixpoint almost surely for systems where the function of interest can be approximated with given probabilistic error bounds, as it happens for probabilistic systems, such as simple stochastic games, that can be explored via sampling.
Authors: Ilia Shumailov, Daniel Ramage, Sarah Meiklejohn, Peter Kairouz, Florian Hartmann, Borja Balle, Eugene Bagdasarian
Abstract: We often interact with untrusted parties. Prioritization of privacy can limit the effectiveness of these interactions, as achieving certain goals necessitates sharing private data. Traditionally, addressing this challenge has involved either seeking trusted intermediaries or constructing cryptographic protocols that restrict how much data is revealed, such as multi-party computations or zero-knowledge proofs. While significant advances have been made in scaling cryptographic approaches, they remain limited in terms of the size and complexity of applications they can be used for. In this paper, we argue that capable machine learning models can fulfill the role of a trusted third party, thus enabling secure computations for applications that were previously infeasible. In particular, we describe Trusted Capable Model Environments (TCMEs) as an alternative approach for scaling secure computation, where capable machine learning model(s) interact under input/output constraints, with explicit information flow control and explicit statelessness. This approach aims to achieve a balance between privacy and computational efficiency, enabling private inference where classical cryptographic solutions are currently infeasible. We describe a number of use cases that are enabled by TCME, and show that even some simple classic cryptographic problems can already be solved with TCME. Finally, we outline current limitations and discuss the path forward in implementing them.
Authors: Krit Tangsongcharoen, Teerachote Pakornchote, Chayanon Atthapak, Natthaphon Choomphon-anomakhun, Annop Ektarawong, Bj\"orn Alling, Christopher Sutton, Thiti Bovornratanaraks, Thiparat Chotibut
Abstract: Determining whether a candidate crystalline material is thermodynamically stable depends on identifying its true ground-state structure, a central challenge in computational materials science. We introduce CrystalGRW, a diffusion-based generative model on Riemannian manifolds that proposes novel crystal configurations and can predict stable phases validated by density functional theory. The crystal properties, such as fractional coordinates, atomic types, and lattice matrices, are represented on suitable Riemannian manifolds, ensuring that new predictions generated through the diffusion process preserve the periodicity of crystal structures. We incorporate an equivariant graph neural network to also account for rotational and translational symmetries during the generation process. CrystalGRW demonstrates the ability to generate realistic crystal structures that are close to their ground states with accuracy comparable to existing models, while also enabling conditional control, such as specifying a desired crystallographic point group. These features help accelerate materials discovery and inverse design by offering stable, symmetry-consistent crystal candidates for experimental validation.
Authors: Ishan Amin, Sanjeev Raja, Aditi Krishnapriyan
Abstract: The foundation model (FM) paradigm is transforming Machine Learning Force Fields (MLFFs), leveraging general-purpose representations and scalable training to perform a variety of computational chemistry tasks. Although MLFF FMs have begun to close the accuracy gap relative to first-principles methods, there is still a strong need for faster inference speed. Additionally, while research is increasingly focused on general-purpose models which transfer across chemical space, practitioners typically only study a small subset of systems at a given time. This underscores the need for fast, specialized MLFFs relevant to specific downstream applications, which preserve test-time physical soundness while maintaining train-time scalability. In this work, we introduce a method for transferring general-purpose representations from MLFF foundation models to smaller, faster MLFFs specialized to specific regions of chemical space. We formulate our approach as a knowledge distillation procedure, where the smaller "student" MLFF is trained to match the Hessians of the energy predictions of the "teacher" foundation model. Our specialized MLFFs can be up to 20 $\times$ faster than the original foundation model, while retaining, and in some cases exceeding, its performance and that of undistilled models. We also show that distilling from a teacher model with a direct force parameterization into a student model trained with conservative forces (i.e., computed as derivatives of the potential energy) successfully leverages the representations from the large-scale teacher for improved accuracy, while maintaining energy conservation during test-time molecular dynamics simulations. More broadly, our work suggests a new paradigm for MLFF development, in which foundation models are released along with smaller, specialized simulation "engines" for common chemical subsets.
Authors: Seth Neel
Abstract: We introduce a new private regression setting we call Private Regression in Multiple Outcomes (PRIMO), inspired by the common situation where a data analyst wants to perform a set of $l$ regressions while preserving privacy, where the features $X$ are shared across all $l$ regressions, and each regression $i \in [l]$ has a different vector of outcomes $y_i$. Naively applying existing private linear regression techniques $l$ times leads to a $\sqrt{l}$ multiplicative increase in error over the standard linear regression setting. We apply a variety of techniques including sufficient statistics perturbation (SSP) and geometric projection-based methods to develop scalable algorithms that outperform this baseline across a range of parameter regimes. In particular, we obtain no dependence on l in the asymptotic error when $l$ is sufficiently large. Empirically, on the task of genomic risk prediction with multiple phenotypes we find that even for values of $l$ far smaller than the theory would predict, our projection-based method improves the accuracy relative to the variant that doesn't use the projection.
Authors: Pengfei Li, Jianyi Yang, Mohammad A. Islam, Shaolei Ren
Abstract: The growing carbon footprint of artificial intelligence (AI) has been undergoing public scrutiny. Nonetheless, the equally important water (withdrawal and consumption) footprint of AI has largely remained under the radar. For example, training the GPT-3 language model in Microsoft's state-of-the-art U.S. data centers can directly evaporate 700,000 liters of clean freshwater, but such information has been kept a secret. More critically, the global AI demand is projected to account for 4.2-6.6 billion cubic meters of water withdrawal in 2027, which is more than the total annual water withdrawal of 4-6 Denmark or half of the United Kingdom. This is concerning, as freshwater scarcity has become one of the most pressing challenges. To respond to the global water challenges, AI can, and also must, take social responsibility and lead by example by addressing its own water footprint. In this paper, we provide a principled methodology to estimate the water footprint of AI, and also discuss the unique spatial-temporal diversities of AI's runtime water efficiency. Finally, we highlight the necessity of holistically addressing water footprint along with carbon footprint to enable truly sustainable AI.
Authors: Luke Snow, Vikram Krishnamurthy
Abstract: This paper provides a finite-sample analysis of a passive stochastic gradient Langevin dynamics (PSGLD) algorithm. This algorithm is designed to achieve adaptive inverse reinforcement learning (IRL). Adaptive IRL aims to estimate the cost function of a forward learner performing a stochastic gradient algorithm (e.g., policy gradient reinforcement learning) by observing their estimates in real-time. The PSGLD algorithm is considered passive because it incorporates noisy gradients provided by an external stochastic gradient algorithm (forward learner), of which it has no control. The PSGLD algorithm acts as a randomized sampler to achieve adaptive IRL by reconstructing the forward learner's cost function nonparametrically from the stationary measure of a Langevin diffusion. This paper analyzes the non-asymptotic (finite-sample) performance; we provide explicit bounds on the 2-Wasserstein distance between PSGLD algorithm sample measure and the stationary measure encoding the cost function, and provide guarantees for a kernel density estimation scheme which reconstructs the cost function from empirical samples. Our analysis uses tools from the study of Markov diffusion operators. The derived bounds have both practical and theoretical significance. They provide finite-time guarantees for an adaptive IRL mechanism, and substantially generalize the analytical framework of a line of research in passive stochastic gradient algorithms.
Authors: Jiajun Zhou, Shengbo Gong, Xuanze Chen, Chenxuan Xie, Shanqing Yu, Qi Xuan, Xiaoniu Yang
Abstract: Graph neural networks (GNNs) have achieved remarkable advances in graph-oriented tasks. However, real-world graphs invariably contain a certain proportion of heterophilous nodes, challenging the homophily assumption of traditional GNNs and hindering their performance. Most existing studies continue to design generic models with shared weights between heterophilous and homophilous nodes. Despite the incorporation of high-order messages or multi-channel architectures, these efforts often fall short. A minority of studies attempt to train different node groups separately but suffer from inappropriate separation metrics and low efficiency. In this paper, we first propose a new metric, termed Neighborhood Confusion (NC), to facilitate a more reliable separation of nodes. We observe that node groups with different levels of NC values exhibit certain differences in intra-group accuracy and visualized embeddings. These pave the way for Neighborhood Confusion-guided Graph Convolutional Network (NCGCN), in which nodes are grouped by their NC values and accept intra-group weight sharing and message passing. Extensive experiments on both homophilous and heterophilous benchmarks demonstrate that our framework can effectively separate nodes and yield significant performance improvement compared to the latest methods. The source code will be available in https://github.com/GISec-Team/NCGNN.
Authors: Karthik R., Ramamoorthy A
Abstract: Intelligent automation supports us against cyclones, droughts, and seismic events with recent technology advancements. Algorithmic learning has advanced fields like neuroscience, genetics, and human-computer interaction. Time-series data boosts progress. Challenges persist in adopting these approaches in traditional fields. Neural networks face comprehension and bias issues. AI's expansion across scientific areas is due to adaptable descriptors and combinatorial argumentation. This article focuses on modeling Forest loss using the VANYA Model, incorporating Prey Predator Dynamics. VANYA predicts forest cover, demonstrated on Amazon Rainforest data against other forecasters like Long Short-Term Memory, N-BEATS, RCN.
Authors: Katharina Limbeck, Rayna Andreeva, Rik Sarkar, Bastian Rieck
Abstract: The magnitude of a metric space is a novel invariant that provides a measure of the 'effective size' of a space across multiple scales, while also capturing numerous geometrical properties, such as curvature, density, or entropy. We develop a family of magnitude-based measures of the intrinsic diversity of latent representations, formalising a novel notion of dissimilarity between magnitude functions of finite metric spaces. Our measures are provably stable under perturbations of the data, can be efficiently calculated, and enable a rigorous multi-scale characterisation and comparison of latent representations. We show their utility and superior performance across different domains and tasks, including (i) the automated estimation of diversity, (ii) the detection of mode collapse, and (iii) the evaluation of generative models for text, image, and graph data.
Authors: Zhiwei Zuo, Zhuo Tang, Kenli Li, Anwitaman Datta
Abstract: Machine unlearning techniques, which involve retracting data records and reducing influence of said data on trained models, help with the user privacy protection objective but incur significant computational costs. Weight perturbation-based unlearning is a general approach, but it typically involves globally modifying the parameters. We propose fine-grained Top-K and Random-k parameters perturbed inexact machine unlearning strategies that address the privacy needs while keeping the computational costs tractable. In order to demonstrate the efficacy of our strategies we also tackle the challenge of evaluating the effectiveness of machine unlearning by considering the model's generalization performance across both unlearning and remaining data. To better assess the unlearning effect and model generalization, we propose novel metrics, namely, the forgetting rate and memory retention rate. However, for inexact machine unlearning, current metrics are inadequate in quantifying the degree of forgetting that occurs after unlearning strategies are applied. To address this, we introduce SPD-GAN, which subtly perturbs the distribution of data targeted for unlearning. Then, we evaluate the degree of unlearning by measuring the performance difference of the models on the perturbed unlearning data before and after the unlearning process. By implementing these innovative techniques and metrics, we achieve computationally efficacious privacy protection in machine learning applications without significant sacrifice of model performance. Furthermore, this approach provides a novel method for evaluating the degree of unlearning.
Authors: Andreas Abildtrup Hansen, Anna Calissano, Aasa Feragen
Abstract: Latent representations are used extensively for downstream tasks, such as visualization, interpolation or feature extraction of deep learning models. Invariant and equivariant neural networks are powerful and well-established models for enforcing inductive biases. In this paper, we demonstrate that the inductive bias imposed on the by an equivariant model must also be taken into account when using latent representations. We show how not accounting for the inductive biases leads to decreased performance on downstream tasks, and vice versa, how accounting for inductive biases can be done effectively by using an invariant projection of the latent representations. We propose principles for how to choose such a projection, and show the impact of using these principles in two common examples: First, we study a permutation equivariant variational auto-encoder trained for molecule graph generation; here we show that invariant projections can be designed that incur no loss of information in the resulting invariant representation. Next, we study a rotation-equivariant representation used for image classification. Here, we illustrate how random invariant projections can be used to obtain an invariant representation with a high degree of retained information. In both cases, the analysis of invariant latent representations proves superior to their equivariant counterparts. Finally, we illustrate that the phenomena documented here for equivariant neural networks have counterparts in standard neural networks where invariance is encouraged via augmentation. Thus, while these ambiguities may be known by experienced developers of equivariant models, we make both the knowledge as well as effective tools to handle the ambiguities available to the broader community.
Authors: Azmine Toushik Wasi, MD Shafikul Islam, Adipto Raihan Akib
Abstract: Graph Neural Networks (GNNs) have gained traction across different domains such as transportation, bio-informatics, language processing, and computer vision. However, there is a noticeable absence of research on applying GNNs to supply chain networks. Supply chain networks are inherently graph-like in structure, making them prime candidates for applying GNN methodologies. This opens up a world of possibilities for optimizing, predicting, and solving even the most complex supply chain problems. A major setback in this approach lies in the absence of real-world benchmark datasets to facilitate the research and resolution of supply chain problems using GNNs. To address the issue, we present a real-world benchmark dataset for temporal tasks, obtained from one of the leading FMCG companies in Bangladesh, focusing on supply chain planning for production purposes. The dataset includes temporal data as node features to enable sales predictions, production planning, and the identification of factory issues. By utilizing this dataset, researchers can employ GNNs to address numerous supply chain problems, thereby advancing the field of supply chain analytics and planning. Source: https://github.com/CIOL-SUST/SupplyGraph
Authors: Olabode T. Ajenifujah, Francis Ogoke, Florian Wirth, Jack Beuth, Amir Barati Farimani
Abstract: Laser powder bed fusion (LPBF) has shown promise for wide range of applications due to its ability to fabricate freeform geometries and generate a controlled microstructure. However, components generated by LPBF still possess sub-optimal mechanical properties due to the defects that are created during laser-material interactions. In this work, we investigate mechanism of spatter formation, using a high-fidelity modelling tool that was built to simulate the multi-physics phenomena in LPBF. The modelling tool have the capability to capture the 3D resolution of the meltpool and the spatter behavior. To understand spatter behavior and formation, we reveal its properties at ejection and evaluate its variation from the meltpool, the source where it is formed. The dataset of the spatter and the meltpool collected consist of 50 % spatter and 50 % melt pool samples, with features that include position components, velocity components, velocity magnitude, temperature, density and pressure. The relationship between the spatter and the meltpool were evaluated via correlation analysis and machine learning (ML) algorithms for classification tasks. Upon screening different ML algorithms on the dataset, a high accuracy was observed for all the ML models, with ExtraTrees having the highest at 96 % and KNN having the lowest at 94 %.
Authors: Andrew C. Li, Zizhao Chen, Toryn Q. Klassen, Pashootan Vaezipoor, Rodrigo Toro Icarte, Sheila A. McIlraith
Abstract: Reward Machines provide an automaton-inspired structure for specifying instructions, safety constraints, and other temporally extended reward-worthy behaviour. By exposing the underlying structure of a reward function, they enable the decomposition of an RL task, leading to impressive gains in sample efficiency. Although Reward Machines and similar formal specifications have a rich history of application towards sequential decision-making problems, they critically rely on a ground-truth interpretation of the domain-specific vocabulary that forms the building blocks of the reward function--such ground-truth interpretations are elusive in the real world due in part to partial observability and noisy sensing. In this work, we explore the use of Reward Machines for Deep RL in noisy and uncertain environments. We characterize this problem as a POMDP and propose a suite of RL algorithms that exploit task structure under uncertain interpretation of the domain-specific vocabulary. Through theory and experiments, we expose pitfalls in naive approaches to this problem while simultaneously demonstrating how task structure can be successfully leveraged under noisy interpretations of the vocabulary.
Authors: Lingjing Kong, Guangyi Chen, Biwei Huang, Eric P. Xing, Yuejie Chi, Kun Zhang
Abstract: Learning concepts from natural high-dimensional data (e.g., images) holds potential in building human-aligned and interpretable machine learning models. Despite its encouraging prospect, formalization and theoretical insights into this crucial task are still lacking. In this work, we formalize concepts as discrete latent causal variables that are related via a hierarchical causal model that encodes different abstraction levels of concepts embedded in high-dimensional data (e.g., a dog breed and its eye shapes in natural images). We formulate conditions to facilitate the identification of the proposed causal model, which reveals when learning such concepts from unsupervised data is possible. Our conditions permit complex causal hierarchical structures beyond latent trees and multi-level directed acyclic graphs in prior work and can handle high-dimensional, continuous observed variables, which is well-suited for unstructured data modalities such as images. We substantiate our theoretical claims with synthetic data experiments. Further, we discuss our theory's implications for understanding the underlying mechanisms of latent diffusion models and provide corresponding empirical evidence for our theoretical insights.
Authors: Farnoush Rezaei Jafari, Gr\'egoire Montavon, Klaus-Robert M\"uller, Oliver Eberle
Abstract: Recent sequence modeling approaches using selective state space sequence models, referred to as Mamba models, have seen a surge of interest. These models allow efficient processing of long sequences in linear time and are rapidly being adopted in a wide range of applications such as language modeling, demonstrating promising performance. To foster their reliable use in real-world scenarios, it is crucial to augment their transparency. Our work bridges this critical gap by bringing explainability, particularly Layer-wise Relevance Propagation (LRP), to the Mamba architecture. Guided by the axiom of relevance conservation, we identify specific components in the Mamba architecture, which cause unfaithful explanations. To remedy this issue, we propose MambaLRP, a novel algorithm within the LRP framework, which ensures a more stable and reliable relevance propagation through these components. Our proposed method is theoretically sound and excels in achieving state-of-the-art explanation performance across a diverse range of models and datasets. Moreover, MambaLRP facilitates a deeper inspection of Mamba architectures, uncovering various biases and evaluating their significance. It also enables the analysis of previous speculations regarding the long-range capabilities of Mamba models.
Authors: Yujie Lin, Dong Li, Chen Zhao, Minglai Shao, Guihong Wan
Abstract: Fairness-aware domain generalization (FairDG) has emerged as a critical challenge for deploying trustworthy AI systems, particularly in scenarios involving distribution shifts. Traditional methods for addressing fairness have failed in domain generalization due to their lack of consideration for distribution shifts. Although disentanglement has been used to tackle FairDG, it is limited by its strong assumptions. To overcome these limitations, we propose Fairness-aware Classifier-Guided Score-based Diffusion Models (FADE) as a novel approach to effectively address the FairDG issue. Specifically, we first pre-train a score-based diffusion model (SDM) and two classifiers to equip the model with strong generalization capabilities across different domains. Then, we guide the SDM using these pre-trained classifiers to effectively eliminate sensitive information from the generated data. Finally, the generated fair data is used to train downstream classifiers, ensuring robust performance under new data distributions. Extensive experiments on three real-world datasets demonstrate that FADE not only enhances fairness but also improves accuracy in the presence of distribution shifts. Additionally, FADE outperforms existing methods in achieving the best accuracy-fairness trade-offs.
Authors: Jirui Yang, Peng Chen, Zhihui Lu, Qiang Duan, Yubing Bao
Abstract: Vertical Federated Learning (VFL) facilitates collaborative machine learning without the need for participants to share raw private data. However, recent studies have revealed privacy risks where adversaries might reconstruct sensitive features through data leakage during the learning process. Although data reconstruction methods based on gradient or model information are somewhat effective, they reveal limitations in VFL application scenarios. This is because these traditional methods heavily rely on specific model structures and/or have strict limitations on application scenarios. To address this, our study introduces the Unified InverNet Framework into VFL, which yields a novel and flexible approach (dubbed UIFV) that leverages intermediate feature data to reconstruct original data, instead of relying on gradients or model details. The intermediate feature data is the feature exchanged by different participants during the inference phase of VFL. Experiments on four datasets demonstrate that our methods significantly outperform state-of-the-art techniques in attack precision. Our work exposes severe privacy vulnerabilities within VFL systems that pose real threats to practical VFL applications and thus confirms the necessity of further enhancing privacy protection in the VFL architecture.
Authors: Matthijs Pals, A Erdem Sa\u{g}tekin, Felix Pei, Manuel Gloeckler, Jakob H Macke
Abstract: A central aim in computational neuroscience is to relate the activity of large populations of neurons to an underlying dynamical system. Models of these neural dynamics should ideally be both interpretable and fit the observed data well. Low-rank recurrent neural networks (RNNs) exhibit such interpretability by having tractable dynamics. However, it is unclear how to best fit low-rank RNNs to data consisting of noisy observations of an underlying stochastic system. Here, we propose to fit stochastic low-rank RNNs with variational sequential Monte Carlo methods. We validate our method on several datasets consisting of both continuous and spiking neural data, where we obtain lower dimensional latent dynamics than current state of the art methods. Additionally, for low-rank models with piecewise linear nonlinearities, we show how to efficiently identify all fixed points in polynomial rather than exponential cost in the number of units, making analysis of the inferred dynamics tractable for large RNNs. Our method both elucidates the dynamical systems underlying experimental recordings and provides a generative model whose trajectories match observed variability.
Authors: Han-Jia Ye, Si-Yang Liu, Hao-Run Cai, Qi-Le Zhou, De-Chuan Zhan
Abstract: Tabular data is prevalent across diverse domains in machine learning. While classical methods like tree-based models have long been effective, Deep Neural Network (DNN)-based methods have recently demonstrated promising performance. However, the diverse characteristics of methods and the inherent heterogeneity of tabular datasets make understanding and interpreting tabular methods both challenging and prone to unstable observations. In this paper, we conduct in-depth evaluations and comprehensive analyses of tabular methods, with a particular focus on DNN-based models, using a benchmark of over 300 tabular datasets spanning a wide range of task types, sizes, and domains. First, we perform an extensive comparison of 32 state-of-the-art deep and tree-based methods, evaluating their average performance across multiple criteria. Although method ranks vary across datasets, we empirically find that top-performing methods tend to concentrate within a small subset of tabular models, regardless of the criteria used. Next, we investigate whether the training dynamics of deep tabular models can be predicted based on dataset properties. This approach not only offers insights into the behavior of deep tabular methods but also identifies a core set of "meta-features" that reflect dataset heterogeneity. The other subset includes datasets where method ranks are consistent with the overall benchmark, acting as a reliable probe for further tabular analysis.
Authors: David Holzm\"uller, L\'eo Grinsztajn, Ingo Steinwart
Abstract: For classification and regression on tabular data, the dominance of gradient-boosted decision trees (GBDTs) has recently been challenged by often much slower deep learning methods with extensive hyperparameter tuning. We address this discrepancy by introducing (a) RealMLP, an improved multilayer perceptron (MLP), and (b) strong meta-tuned default parameters for GBDTs and RealMLP. We tune RealMLP and the default parameters on a meta-train benchmark with 118 datasets and compare them to hyperparameter-optimized versions on a disjoint meta-test benchmark with 90 datasets, as well as the GBDT-friendly benchmark by Grinsztajn et al. (2022). Our benchmark results on medium-to-large tabular datasets (1K--500K samples) show that RealMLP offers a favorable time-accuracy tradeoff compared to other neural baselines and is competitive with GBDTs in terms of benchmark scores. Moreover, a combination of RealMLP and GBDTs with improved default parameters can achieve excellent results without hyperparameter tuning. Finally, we demonstrate that some of RealMLP's improvements can also considerably improve the performance of TabR with default parameters.
Authors: Pinxue Zhao, Hailin Zhang, Fangcheng Fu, Xiaonan Nie, Qibin Liu, Fang Yang, Yuanbo Peng, Dian Jiao, Shuaipeng Li, Jinbao Xue, Yangyu Tao, Bin Cui
Abstract: Nowadays, Large Language Models (LLMs) have been trained using extended context lengths to foster more creative applications. However, long context training poses great challenges considering the constraint of GPU memory. It not only leads to substantial activation memory consumption during training, but also incurs considerable memory fragmentation. To facilitate long context training, existing frameworks have adopted strategies such as recomputation and various forms of parallelisms. Nevertheless, these techniques rely on redundant computation or extensive communication, resulting in low Model FLOPS Utilization (MFU). In this paper, we propose MEMO, a novel LLM training framework designed for fine-grained activation memory management. Given the quadratic scaling of computation and linear scaling of memory with sequence lengths when using FlashAttention, we offload memory-consuming activations to CPU memory after each layer's forward pass and fetch them during the backward pass. To maximize the swapping of activations without hindering computation, and to avoid exhausting limited CPU memory, we implement a token-wise activation recomputation and swapping mechanism. Furthermore, we tackle the memory fragmentation issue by employing a bi-level Mixed Integer Programming (MIP) approach, optimizing memory reuse across transformer layers. Empirical results demonstrate that MEMO achieves an average of 1.97x and 1.80x MFU compared to Megatron-LM and DeepSpeed, respectively. This improvement is attributed to MEMO's ability to minimize memory fragmentation, reduce recomputation and intensive communication, and circumvent the delays associated with the memory reorganization process due to fragmentation. By leveraging fine-grained activation memory management, MEMO facilitates efficient training of 7B LLM with 1 million sequence length on just 8 A800 GPUs, achieving an MFU of 52.30%.
Authors: Zhi-Song Liu, Petri Clusius, Michael Boy
Abstract: Modeling atmospheric chemistry is complex and computationally intense. Given the recent success of Deep neural networks in digital signal processing, we propose a Neural Network Emulator for fast chemical concentration modeling. We consider atmospheric chemistry as a time-dependent Ordinary Differential Equation. To extract the hidden correlations between initial states and future time evolution, we propose ChemNNE, an Attention based Neural Network Emulator (NNE) that can model the atmospheric chemistry as a neural ODE process. To efficiently simulate the chemical changes, we propose the sinusoidal time embedding to estimate the oscillating tendency over time. More importantly, we use the Fourier neural operator to model the ODE process for efficient computation. We also propose three physical-informed losses to supervise the training optimization. To evaluate our model, we propose a large-scale chemical dataset that can be used for neural network training and evaluation. The extensive experiments show that our approach achieves state-of-the-art performance in modeling accuracy and computational speed.
Authors: Randall Balestriero, Ahmed Imtiaz Humayun, Richard Baraniuk
Abstract: In this paper, we overview one promising avenue of progress at the mathematical foundation of deep learning: the connection between deep networks and function approximation by affine splines (continuous piecewise linear functions in multiple dimensions). In particular, we will overview work over the past decade on understanding certain geometrical properties of a deep network's affine spline mapping, in particular how it tessellates its input space. As we will see, the affine spline connection and geometrical viewpoint provide a powerful portal through which to view, analyze, and improve the inner workings of a deep network.
Authors: Jifeng Hu, Li Shen, Sili Huang, Zhejian Yang, Hechang Chen, Lichao Sun, Yi Chang, Dacheng Tao
Abstract: Artificial neural networks, especially recent diffusion-based models, have shown remarkable superiority in gaming, control, and QA systems, where the training tasks' datasets are usually static. However, in real-world applications, such as robotic control of reinforcement learning (RL), the tasks are changing, and new tasks arise in a sequential order. This situation poses the new challenge of plasticity-stability trade-off for training an agent who can adapt to task changes and retain acquired knowledge. In view of this, we propose a rehearsal-based continual diffusion model, called Continual Diffuser (CoD), to endow the diffuser with the capabilities of quick adaptation (plasticity) and lasting retention (stability). Specifically, we first construct an offline benchmark that contains 90 tasks from multiple domains. Then, we train the CoD on each task with sequential modeling and conditional generation for making decisions. Next, we preserve a small portion of previous datasets as the rehearsal buffer and replay it to retain the acquired knowledge. Extensive experiments on a series of tasks show CoD can achieve a promising plasticity-stability trade-off and outperform existing diffusion-based methods and other representative baselines on most tasks.
Authors: Dominic Schneider, Lutz Rapp
Abstract: Optical fiber amplifiers are key elements in present optical networks. Failures of these components result in high financial loss of income of the network operator as the communication traffic over an affected link is interrupted. Applying Remaining useful lifetime (RUL) prediction in the context of Predictive Maintenance (PdM) to optical fiber amplifiers to predict upcoming system failures at an early stage, so that network outages can be minimized through planning of targeted maintenance actions, ensures reliability and safety. Optical fiber amplifier are complex systems, that work under various operating conditions, which makes correct forecasting a difficult task. Increased monitoring capabilities of systems results in datasets that facilitate the application of data-driven RUL prediction methods. Deep learning models in particular have shown good performance, but generalization based on comparatively small datasets for RUL prediction is difficult. In this paper, we propose Sparse Low-ranked self-Attention Transformer (SLAT) as a novel RUL prediction method. SLAT is based on an encoder-decoder architecture, wherein two parallel working encoders extract features for sensors and time steps. By utilizing the self-attention mechanism, long-term dependencies can be learned from long sequences. The implementation of sparsity in the attention matrix and a low-rank parametrization reduce overfitting and increase generalization. Experimental application to optical fiber amplifiers exemplified on EDFA, as well as a reference dataset from turbofan engines, shows that SLAT outperforms the state-of-the-art methods.
Authors: Yao Ni, Shan Zhang, Piotr Koniusz
Abstract: Parameter-Efficient Fine-Tuning (PEFT) effectively adapts pre-trained transformers to downstream tasks. However, the optimization of tasks performance often comes at the cost of generalizability in fine-tuned models. To address this issue, we theoretically connect smaller weight gradient norms during training and larger datasets to the improvements in model generalization. Motivated by this connection, we propose reducing gradient norms for enhanced generalization and aligning fine-tuned model with the pre-trained counterpart to retain knowledge from large-scale pre-training data. Yet, naive alignment does not guarantee gradient reduction and can potentially cause gradient explosion, complicating efforts to manage gradients. To address such an issue, we propose PACE, marrying generalization of PArameter-efficient fine-tuning with Consistency rEgularization. We perturb features learned from the adapter with the multiplicative noise and ensure the fine-tuned model remains consistent for same sample under different perturbations. Theoretical analysis shows that PACE not only implicitly regularizes gradients for enhanced generalization, but also implicitly aligns the fine-tuned and pre-trained models to retain knowledge. Experimental evidence supports our theories. PACE surpasses existing PEFT methods in visual adaptation tasks (VTAB-1k, FGVC, few-shot learning, domain adaptation) showcasing its potential for resource-efficient fine-tuning. It also improves LoRA in text classification (GLUE) and mathematical reasoning (GSM-8K). The code is available at https://github.com/MaxwellYaoNi/PACE
Authors: Youngsik Hwang, Dong-Young Lim
Abstract: Physics-informed neural networks (PINNs) have emerged as a prominent approach for solving partial differential equations (PDEs) by minimizing a combined loss function that incorporates both boundary loss and PDE residual loss. Despite their remarkable empirical performance in various scientific computing tasks, PINNs often fail to generate reasonable solutions, and such pathological behaviors remain difficult to explain and resolve. In this paper, we identify that PINNs can be adversely trained when gradients of each loss function exhibit a significant imbalance in their magnitudes and present a negative inner product value. To address these issues, we propose a novel optimization framework, Dual Cone Gradient Descent (DCGD), which adjusts the direction of the updated gradient to ensure it falls within a dual cone region. This region is defined as a set of vectors where the inner products with both the gradients of the PDE residual loss and the boundary loss are non-negative. Theoretically, we analyze the convergence properties of DCGD algorithms in a non-convex setting. On a variety of benchmark equations, we demonstrate that DCGD outperforms other optimization algorithms in terms of various evaluation metrics. In particular, DCGD achieves superior predictive accuracy and enhances the stability of training for failure modes of PINNs and complex PDEs, compared to existing optimally tuned models. Moreover, DCGD can be further improved by combining it with popular strategies for PINNs, including learning rate annealing and the Neural Tangent Kernel (NTK).
Authors: Xiaochuan Gong, Jie Hao, Mingrui Liu
Abstract: This paper investigates a class of stochastic bilevel optimization problems where the upper-level function is nonconvex with potentially unbounded smoothness and the lower-level problem is strongly convex. These problems have significant applications in sequential data learning, such as text classification using recurrent neural networks. The unbounded smoothness is characterized by the smoothness constant of the upper-level function scaling linearly with the gradient norm, lacking a uniform upper bound. Existing state-of-the-art algorithms require $\widetilde{O}(1/\epsilon^4)$ oracle calls of stochastic gradient or Hessian/Jacobian-vector product to find an $\epsilon$-stationary point. However, it remains unclear if we can further improve the convergence rate when the assumptions for the function in the population level also hold for each random realization almost surely. To address this issue, we propose a new Accelerated Bilevel Optimization algorithm named AccBO. The algorithm updates the upper-level variable by normalized stochastic gradient descent with recursive momentum and the lower-level variable by the stochastic Nesterov accelerated gradient descent algorithm with averaging. We prove that our algorithm achieves an oracle complexity of $\widetilde{O}(1/\epsilon^3)$ to find an $\epsilon$-stationary point, when the lower-level stochastic gradient's variance is $O(\epsilon)$. Our proof relies on a novel lemma characterizing the dynamics of stochastic Nesterov accelerated gradient descent algorithm under distribution drift with high probability for the lower-level variable, which is of independent interest and also plays a crucial role in analyzing the hypergradient estimation error over time. Experimental results on various tasks confirm that our proposed algorithm achieves the predicted theoretical acceleration and significantly outperforms baselines in bilevel optimization.
Authors: Jonathan von Rad, Florian Seuffert
Abstract: Deep Neural Networks (DNNs) are often over-parameterized for their tasks and can be compressed quite drastically by removing weights, a process called pruning. We investigate the impact of different pruning techniques on the classification performance and interpretability of GoogLeNet. We systematically apply unstructured and structured pruning, as well as connection sparsity (pruning of input weights) methods to the network and analyze the outcomes regarding the network's performance on the validation set of ImageNet. We also compare different retraining strategies, such as iterative pruning and one-shot pruning. We find that with sufficient retraining epochs, the performance of the networks can approximate the performance of the default GoogLeNet - and even surpass it in some cases. To assess interpretability, we employ the Mechanistic Interpretability Score (MIS) developed by Zimmermann et al. . Our experiments reveal that there is no significant relationship between interpretability and pruning rate when using MIS as a measure. Additionally, we observe that networks with extremely low accuracy can still achieve high MIS scores, suggesting that the MIS may not always align with intuitive notions of interpretability, such as understanding the basis of correct decisions.
Authors: Binchuan Qi, Wei Gong, Li Li
Abstract: This paper introduces an optimization framework aimed at providing a theoretical foundation for a class of composite optimization problems, particularly those encountered in deep learning. In this framework, we introduce $\mathcal{H}(\phi)$-convexity and $\mathcal{H}(\Phi)$-smoothness to generalize the existing concepts of Lipschitz smoothness and strong convexity. Furthermore, we analyze and establish the convergence of both gradient descent and stochastic gradient descent methods for objective functions that are $\mathcal{H}(\Phi)$-smooth. We prove that the optimal convergence rates of these methods depend solely on the homogeneous degree of $\Phi$. Based on these findings, we construct two types of non-convex and non-smooth optimization problems: deterministic composite and stochastic composite optimization problems, which encompass the majority of optimization problems in deep learning. To address these problems, we develop the gradient structure control algorithm and prove that it can locate approximate global optima. This marks a significant departure from traditional non-convex analysis framework, which typically settle for stationary points. Therefore, with the introduction of $\mathcal{H}(\phi)$-convexity and $\mathcal{H}(\Phi)$-smoothness, along with the GSC algorithm, the non-convex optimization mechanisms in deep learning can be theoretically explained and supported. Finally, the effectiveness of the proposed framework is substantiated through empirical experimentation.
Authors: Zhongchao Yi, Zhengyang Zhou, Qihe Huang, Yanjiang Chen, Liheng Yu, Xu Wang, Yang Wang
Abstract: Spatiotemporal learning has become a pivotal technique to enable urban intelligence. Traditional spatiotemporal models mostly focus on a specific task by assuming a same distribution between training and testing sets. However, given that urban systems are usually dynamic, multi-sourced with imbalanced data distributions, current specific task-specific models fail to generalize to new urban conditions and adapt to new domains without explicitly modeling interdependencies across various dimensions and types of urban data. To this end, we argue that there is an essential to propose a Continuous Multi-task Spatio-Temporal learning framework (CMuST) to empower collective urban intelligence, which reforms the urban spatiotemporal learning from single-domain to cooperatively multi-dimensional and multi-task learning. Specifically, CMuST proposes a new multi-dimensional spatiotemporal interaction network (MSTI) to allow cross-interactions between context and main observations as well as self-interactions within spatial and temporal aspects to be exposed, which is also the core for capturing task-level commonality and personalization. To ensure continuous task learning, a novel Rolling Adaptation training scheme (RoAda) is devised, which not only preserves task uniqueness by constructing data summarization-driven task prompts, but also harnesses correlated patterns among tasks by iterative model behavior modeling. We further establish a benchmark of three cities for multi-task spatiotemporal learning, and empirically demonstrate the superiority of CMuST via extensive evaluations on these datasets. The impressive improvements on both few-shot streaming data and new domain tasks against existing SOAT methods are achieved. Code is available at https://github.com/DILab-USTCSZ/CMuST.
Authors: Albert Gong, Kyuseong Choi, Raaz Dwivedi
Abstract: The kernel thinning algorithm of Dwivedi & Mackey (2024) provides a better-than-i.i.d. compression of a generic set of points. By generating high-fidelity coresets of size significantly smaller than the input points, KT is known to speed up unsupervised tasks like Monte Carlo integration, uncertainty quantification, and non-parametric hypothesis testing, with minimal loss in statistical accuracy. In this work, we generalize the KT algorithm to speed up supervised learning problems involving kernel methods. Specifically, we combine two classical algorithms--Nadaraya-Watson (NW) regression or kernel smoothing, and kernel ridge regression (KRR)--with KT to provide a quadratic speed-up in both training and inference times. We show how distribution compression with KT in each setting reduces to constructing an appropriate kernel, and introduce the Kernel-Thinned NW and Kernel-Thinned KRR estimators. We prove that KT-based regression estimators enjoy significantly superior computational efficiency over the full-data estimators and improved statistical efficiency over i.i.d. subsampling of the training data. En route, we also provide a novel multiplicative error guarantee for compressing with KT. We validate our design choices with both simulations and real data experiments.
Authors: Beyazit Yalcinkaya, Niklas Lauffer, Marcell Vazquez-Chanlatte, Sanjit A. Seshia
Abstract: Goal-conditioned reinforcement learning is a powerful way to control an AI agent's behavior at runtime. That said, popular goal representations, e.g., target states or natural language, are either limited to Markovian tasks or rely on ambiguous task semantics. We propose representing temporal goals using compositions of deterministic finite automata (cDFAs) and use cDFAs to guide RL agents. cDFAs balance the need for formal temporal semantics with ease of interpretation: if one can understand a flow chart, one can understand a cDFA. On the other hand, cDFAs form a countably infinite concept class with Boolean semantics, and subtle changes to the automaton can result in very different tasks, making them difficult to condition agent behavior on. To address this, we observe that all paths through a DFA correspond to a series of reach-avoid tasks and propose pre-training graph neural network embeddings on "reach-avoid derived" DFAs. Through empirical evaluation, we demonstrate that the proposed pre-training method enables zero-shot generalization to various cDFA task classes and accelerated policy specialization without the myopic suboptimality of hierarchical methods.
Authors: Ruihuai Liang, Bo Yang, Pengyu Chen, Xianjin Li, Yifan Xue, Zhiwen Yu, Xuelin Cao, Yan Zhang, M\'erouane Debbah, H. Vincent Poor, Chau Yuen
Abstract: Network optimization is a fundamental challenge in the Internet of Things (IoT) network, often characterized by complex features that make it difficult to solve these problems. Recently, generative diffusion models (GDMs) have emerged as a promising new approach to network optimization, with the potential to directly address these optimization problems. However, the application of GDMs in this field is still in its early stages, and there is a noticeable lack of theoretical research and empirical findings. In this study, we first explore the intrinsic characteristics of generative models. Next, we provide a concise theoretical proof and intuitive demonstration of the advantages of generative models over discriminative models in network optimization. Based on this exploration, we implement GDMs as optimizers aimed at learning high-quality solution distributions for given inputs, sampling from these distributions during inference to approximate or achieve optimal solutions. Specifically, we utilize denoising diffusion probabilistic models (DDPMs) and employ a classifier-free guidance mechanism to manage conditional guidance based on input parameters. We conduct extensive experiments across three challenging network optimization problems. By investigating various model configurations and the principles of GDMs as optimizers, we demonstrate the ability to overcome prediction errors and validate the convergence of generated solutions to optimal solutions. We provide code and data at https://github.com/qiyu3816/DiffSG.
Authors: John Brandon Graham-Knight, Jamil Fayyad, Nourhan Bayasi, Patricia Lasserre, Homayoun Najjaran
Abstract: Class imbalance and label noise are pervasive in large-scale datasets, yet much of machine learning research assumes well-labeled, balanced data, which rarely reflects real world conditions. Existing approaches typically address either label noise or class imbalance in isolation, leading to suboptimal results when both issues coexist. In this work, we propose Conformal-in-the-Loop (CitL), a novel training framework that addresses both challenges with a conformal prediction-based approach. CitL evaluates sample uncertainty to adjust weights and prune unreliable examples, enhancing model resilience and accuracy with minimal computational cost. Our extensive experiments include a detailed analysis showing how CitL effectively emphasizes impactful data in noisy, imbalanced datasets. Our results show that CitL consistently boosts model performance, achieving up to a 6.1% increase in classification accuracy and a 5.0 mIoU improvement in segmentation. Our code is publicly available: CitL.
Authors: Marvin Alles, Philip Becker-Ehmck, Patrick van der Smagt, Maximilian Karl
Abstract: In offline reinforcement learning, a policy is learned using a static dataset in the absence of costly feedback from the environment. In contrast to the online setting, only using static datasets poses additional challenges, such as policies generating out-of-distribution samples. Model-based offline reinforcement learning methods try to overcome these by learning a model of the underlying dynamics of the environment and using it to guide policy search. It is beneficial but, with limited datasets, errors in the model and the issue of value overestimation among out-of-distribution states can worsen performance. Current model-based methods apply some notion of conservatism to the Bellman update, often implemented using uncertainty estimation derived from model ensembles. In this paper, we propose Constrained Latent Action Policies (C-LAP) which learns a generative model of the joint distribution of observations and actions. We cast policy learning as a constrained objective to always stay within the support of the latent action distribution, and use the generative capabilities of the model to impose an implicit constraint on the generated actions. Thereby eliminating the need to use additional uncertainty penalties on the Bellman update and significantly decreasing the number of gradient steps required to learn a policy. We empirically evaluate C-LAP on the D4RL and V-D4RL benchmark, and show that C-LAP is competitive to state-of-the-art methods, especially outperforming on datasets with visual observations.
Authors: Moritz Schneider, Robert Krug, Narunas Vaskevicius, Luigi Palmieri, Joschka Boedecker
Abstract: Visual Reinforcement Learning (RL) methods often require extensive amounts of data. As opposed to model-free RL, model-based RL (MBRL) offers a potential solution with efficient data utilization through planning. Additionally, RL lacks generalization capabilities for real-world tasks. Prior work has shown that incorporating pre-trained visual representations (PVRs) enhances sample efficiency and generalization. While PVRs have been extensively studied in the context of model-free RL, their potential in MBRL remains largely unexplored. In this paper, we benchmark a set of PVRs on challenging control tasks in a model-based RL setting. We investigate the data efficiency, generalization capabilities, and the impact of different properties of PVRs on the performance of model-based agents. Our results, perhaps surprisingly, reveal that for MBRL current PVRs are not more sample efficient than learning representations from scratch, and that they do not generalize better to out-of-distribution (OOD) settings. To explain this, we analyze the quality of the trained dynamics model. Furthermore, we show that data diversity and network architecture are the most important contributors to OOD generalization performance.
Authors: Lucas Correia, Jan-Christoph Goos, Thomas B\"ack, Anna V. Kononova
Abstract: Benchmarking anomaly detection approaches for multivariate time series is challenging due to the lack of high-quality datasets. Current publicly available datasets are too small, not diverse and feature trivial anomalies, which hinders measurable progress in this research area. We propose a solution: a diverse, extensive, and non-trivial dataset generated via state-of-the-art simulation tools that reflects realistic behaviour of an automotive powertrain, including its multivariate, dynamic and variable-state properties. To cater for both unsupervised and semi-supervised anomaly detection settings, as well as time series generation and forecasting, we make different versions of the dataset available, where training and test subsets are offered in contaminated and clean versions, depending on the task. We also provide baseline results from a small selection of approaches based on deterministic and variational autoencoders, as well as a non-parametric approach. As expected, the baseline experimentation shows that the approaches trained on the semi-supervised version of the dataset outperform their unsupervised counterparts, highlighting a need for approaches more robust to contaminated training data.
Authors: Bethia Sun, Maurice Pagnucco, Yang Song
Abstract: Since the inception of the classicalist vs. connectionist debate, it has been argued that the ability to systematically combine symbol-like entities into compositional representations is crucial for human intelligence. In connectionist systems, the field of disentanglement has gained prominence for its ability to produce explicitly compositional representations; however, it relies on a fundamentally symbolic, concatenative representation of compositional structure that clashes with the continuous, distributed foundations of deep learning. To resolve this tension, we extend Smolensky's Tensor Product Representation (TPR) and introduce Soft TPR, a representational form that encodes compositional structure in an inherently distributed, flexible manner, along with Soft TPR Autoencoder, a theoretically-principled architecture designed specifically to learn Soft TPRs. Comprehensive evaluations in the visual representation learning domain demonstrate that the Soft TPR framework consistently outperforms conventional disentanglement alternatives -- achieving state-of-the-art disentanglement, boosting representation learner convergence, and delivering superior sample efficiency and low-sample regime performance in downstream tasks. These findings highlight the promise of a distributed and flexible approach to representing compositional structure by potentially enhancing alignment with the core principles of deep learning over the conventional symbolic approach.
Authors: Yilei Zhao, Wentao Zhang, Tingran Yang, Yong Jiang, Fei Huang, Wei Yang Bryan Lim
Abstract: In financial trading, factor models are widely used to price assets and capture excess returns from mispricing. Recently, we have witnessed the rise of variational autoencoder-based latent factor models, which learn latent factors self-adaptively. While these models focus on modeling overall market conditions, they often fail to effectively capture the temporal patterns of individual stocks. Additionally, representing multiple factors as single values simplifies the model but limits its ability to capture complex relationships and dependencies. As a result, the learned factors are of low quality and lack diversity, reducing their effectiveness and robustness across different trading periods. To address these issues, we propose a Spatio-Temporal factOR Model based on dual vector quantized variational autoencoders, named STORM, which extracts features of stocks from temporal and spatial perspectives, then fuses and aligns these features at the fine-grained and semantic level, and represents the factors as multi-dimensional embeddings. The discrete codebooks cluster similar factor embeddings, ensuring orthogonality and diversity, which helps distinguish between different factors and enables factor selection in financial trading. To show the performance of the proposed factor model, we apply it to two downstream experiments: portfolio management on two stock datasets and individual trading tasks on six specific stocks. The extensive experiments demonstrate STORM's flexibility in adapting to downstream tasks and superior performance over baseline models.
Authors: Alexis Fox, Samarth Swarup, Abhijin Adiga
Abstract: Considering the difficulty of interpreting generative model output, there is significant current research focused on determining meaningful evaluation metrics. Several recent approaches utilize "precision" and "recall," borrowed from the classification domain, to individually quantify the output fidelity (realism) and output diversity (representation of the real data variation), respectively. With the increase in metric proposals, there is a need for a unifying perspective, allowing for easier comparison and clearer explanation of their benefits and drawbacks. To this end, we unify a class of kth-nearest-neighbors (kNN)-based metrics under an information-theoretic lens using approaches from kNN density estimation. Additionally, we propose a tri-dimensional metric composed of Precision Cross-Entropy (PCE), Recall Cross-Entropy (RCE), and Recall Entropy (RE), which separately measure fidelity and two distinct aspects of diversity, inter- and intra-class. Our domain-agnostic metric, derived from the information-theoretic concepts of entropy and cross-entropy, can be dissected for both sample- and mode-level analysis. Our detailed experimental results demonstrate the sensitivity of our metric components to their respective qualities and reveal undesirable behaviors of other metrics.
Authors: Maxime Ryckewaert, Diego Marcos, Christophe Botella, Maximilien Servajean, Pierre Bonnet, Alexis Joly
Abstract: The rapid expansion of citizen science initiatives has led to a significant growth of biodiversity databases, and particularly presence-only (PO) observations. PO data are invaluable for understanding species distributions and their dynamics, but their use in a Species Distribution Model (SDM) is curtailed by sampling biases and the lack of information on absences. Poisson point processes are widely used for SDMs, with Maxent being one of the most popular methods. Maxent maximises the entropy of a probability distribution across sites as a function of predefined transformations of variables, called features. In contrast, neural networks and deep learning have emerged as a promising technique for automatic feature extraction from complex input variables. Arbitrarily complex transformations of input variables can be learned from the data efficiently through backpropagation and stochastic gradient descent (SGD). In this paper, we propose DeepMaxent, which harnesses neural networks to automatically learn shared features among species, using the maximum entropy principle. To do so, it employs a normalised Poisson loss where for each species, presence probabilities across sites are modelled by a neural network. We evaluate DeepMaxent on a benchmark dataset known for its spatial sampling biases, using PO data for calibration and presence-absence (PA) data for validation across six regions with different biological groups and covariates. Our results indicate that DeepMaxent performs better than Maxent and other leading SDMs across all regions and taxonomic groups. The method performs particularly well in regions of uneven sampling, demonstrating substantial potential to increase SDM performances. In particular, our approach yields more accurate predictions than traditional single-species models, which opens up new possibilities for methodological enhancement.
Authors: Hui Liu, Shikai Jin
Abstract: Phenotypic drug discovery has attracted widespread attention because of its potential to identify bioactive molecules. Transcriptomic profiling provides a comprehensive reflection of phenotypic changes in cellular responses to external perturbations. In this paper, we propose XTransferCDR, a novel generative framework designed for feature decoupling and transferable representation learning across domains. Given a pair of perturbed expression profiles, our approach decouples the perturbation representations from basal states through domain separation encoders and then cross-transfers them in the latent space. The transferred representations are then used to reconstruct the corresponding perturbed expression profiles via a shared decoder. This cross-transfer constraint effectively promotes the learning of transferable drug perturbation representations. We conducted extensive evaluations of our model on multiple datasets, including single-cell transcriptional responses to drugs and single- and combinatorial genetic perturbations. The experimental results show that XTransferCDR achieved better performance than current state-of-the-art methods, showcasing its potential to advance phenotypic drug discovery.
Authors: Chenyu You, Haocheng Dai, Yifei Min, Jasjeet S. Sekhon, Sarang Joshi, James S. Duncan
Abstract: Machine learning models often rely on simple spurious features -- patterns in training data that correlate with targets but are not causally related to them, like image backgrounds in foreground classification. This reliance typically leads to imbalanced test performance across minority and majority groups. In this work, we take a closer look at the fundamental cause of such imbalanced performance through the lens of memorization, which refers to the ability to predict accurately on \textit{atypical} examples (minority groups) in the training set but failing in achieving the same accuracy in the testing set. This paper systematically shows the ubiquitous existence of spurious features in a small set of neurons within the network, providing the first-ever evidence that memorization may contribute to imbalanced group performance. Through three experimental sources of converging empirical evidence, we find the property of a small subset of neurons or channels in memorizing minority group information. Inspired by these findings, we articulate the hypothesis: the imbalanced group performance is a byproduct of ``noisy'' spurious memorization confined to a small set of neurons. To further substantiate this hypothesis, we show that eliminating these unnecessary spurious memorization patterns via a novel framework during training can significantly affect the model performance on minority groups. Our experimental results across various architectures and benchmarks offer new insights on how neural networks encode core and spurious knowledge, laying the groundwork for future research in demystifying robustness to spurious correlation.
Authors: Wenying Duan, Shujun Guo, Wei huang, Hong Rao, Xiaoxi He
Abstract: Spatial-temporal data, fundamental to many intelligent applications, reveals dependencies indicating causal links between present measurements at specific locations and historical data at the same or other locations. Within this context, adaptive spatial-temporal graph neural networks (ASTGNNs) have emerged as valuable tools for modelling these dependencies, especially through a data-driven approach rather than pre-defined spatial graphs. While this approach offers higher accuracy, it presents increased computational demands. Addressing this challenge, this paper delves into the concept of localisation within ASTGNNs, introducing an innovative perspective that spatial dependencies should be dynamically evolving over time. We introduce \textit{DynAGS}, a localised ASTGNN framework aimed at maximising efficiency and accuracy in distributed deployment. This framework integrates dynamic localisation, time-evolving spatial graphs, and personalised localisation, all orchestrated around the Dynamic Graph Generator, a light-weighted central module leveraging cross attention. The central module can integrate historical information in a node-independent manner to enhance the feature representation of nodes at the current moment. This improved feature representation is then used to generate a dynamic sparse graph without the need for costly data exchanges, and it supports personalised localisation. Performance assessments across two core ASTGNN architectures and nine real-world datasets from various applications reveal that \textit{DynAGS} outshines current benchmarks, underscoring that the dynamic modelling of spatial dependencies can drastically improve model expressibility, flexibility, and system efficiency, especially in distributed settings.
Authors: Zenon Lamprou, Yashar Moshfeghi
Abstract: The rapid advancement of Artificial Intelligence has resulted in the advent of Large Language Models (LLMs) with the capacity to produce text that closely resembles human communication. These models have been seamlessly integrated into diverse applications, enabling interactive and responsive communication across multiple platforms. The potential utility of chatbots transcends these traditional applications, particularly in research contexts, wherein they can offer valuable insights and facilitate the design of innovative experiments. In this study, we present a Customizable LLM-Powered Chatbot (CLPC), a web-based chatbot system designed to assist in behavioral science research. The system is meticulously designed to function as an experimental instrument rather than a conventional chatbot, necessitating users to input a username and experiment code upon access. This setup facilitates precise data cross-referencing, thereby augmenting the integrity and applicability of the data collected for research purposes. It can be easily expanded to accommodate new basic events as needed; and it allows researchers to integrate their own logging events without the necessity of implementing a separate logging mechanism. It is worth noting that our system was built to assist primarily behavioral science research but is not limited to it, it can easily be adapted to assist information retrieval research or interacting with chat bot agents in general.
Authors: Raghav Singhal, Zachary Horvitz, Ryan Teehan, Mengye Ren, Zhou Yu, Kathleen McKeown, Rajesh Ranganath
Abstract: Diffusion models produce impressive results in modalities ranging from images and video to protein design and text. However, generating samples with user-specified properties remains a challenge. Recent research proposes fine-tuning models to maximize rewards that capture desired properties, but these methods require expensive training and are prone to mode collapse. In this work, we propose Feynman Kac (FK) steering, an inference-time framework for steering diffusion models with reward functions. FK steering works by sampling a system of multiple interacting diffusion processes, called particles, and resampling particles at intermediate steps based on scores computed using functions called potentials. Potentials are defined using rewards for intermediate states and are selected such that a high value indicates that the particle will yield a high-reward sample. We explore various choices of potentials, intermediate rewards, and samplers. We evaluate FK steering on text-to-image and text diffusion models. For steering text-to-image models with a human preference reward, we find that FK steering a 0.8B parameter model outperforms a 2.6B parameter fine-tuned model on prompt fidelity, with faster sampling and no training. For steering text diffusion models with rewards for text quality and specific text attributes, we find that FK steering generates lower perplexity, more linguistically acceptable outputs and enables gradient-free control of attributes like toxicity. Our results demonstrate that inference-time scaling and steering of diffusion models, even with off-the-shelf rewards, can provide significant sample quality gains and controllability benefits. Code is available at https://github.com/zacharyhorvitz/Fk-Diffusion-Steering .
URLs: https://github.com/zacharyhorvitz/Fk-Diffusion-Steering
Authors: Cornelius Hake, Jonas Weigele, Frederik Reichert, Christian Friedrich
Abstract: The present study examines the effectiveness of applying Artificial Intelligence methods in an automotive production environment to predict unknown lead times in a non-cycle-controlled production area. Data structures are analyzed to identify contextual features and then preprocessed using one-hot encoding. Methods selection focuses on supervised machine learning techniques. In supervised learning methods, regression and classification methods are evaluated. Continuous regression based on target size distribution is not feasible. Classification methods analysis shows that Ensemble Learning and Support Vector Machines are the most suitable. Preliminary study results indicate that gradient boosting algorithms LightGBM, XGBoost, and CatBoost yield the best results. After further testing and extensive hyperparameter optimization, the final method choice is the LightGBM algorithm. Depending on feature availability and prediction interval granularity, relative prediction accuracies of up to 90% can be achieved. Further tests highlight the importance of periodic retraining of AI models to accurately represent complex production processes using the database. The research demonstrates that AI methods can be effectively applied to highly variable production data, adding business value by providing an additional metric for various control tasks while outperforming current non AI-based systems.
Authors: Marios Aristodemou, Xiaolan Liu, Yuan Wang, Konstantinos G. Kyriakopoulos, Sangarapillai Lambotharan, Qingsong Wei
Abstract: As we transition from Narrow Artificial Intelligence towards Artificial Super Intelligence, users are increasingly concerned about their privacy and the trustworthiness of machine learning (ML) technology. A common denominator for the metrics of trustworthiness is the quantification of uncertainty inherent in DL algorithms, and specifically in the model parameters, input data, and model predictions. One of the common approaches to address privacy-related issues in DL is to adopt distributed learning such as federated learning (FL), where private raw data is not shared among users. Despite the privacy-preserving mechanisms in FL, it still faces challenges in trustworthiness. Specifically, the malicious users, during training, can systematically create malicious model parameters to compromise the models predictive and generative capabilities, resulting in high uncertainty about their reliability. To demonstrate malicious behaviour, we propose a novel model poisoning attack method named Delphi which aims to maximise the uncertainty of the global model output. We achieve this by taking advantage of the relationship between the uncertainty and the model parameters of the first hidden layer of the local model. Delphi employs two types of optimisation , Bayesian Optimisation and Least Squares Trust Region, to search for the optimal poisoned model parameters, named as Delphi-BO and Delphi-LSTR. We quantify the uncertainty using the KL Divergence to minimise the distance of the predictive probability distribution towards an uncertain distribution of model output. Furthermore, we establish a mathematical proof for the attack effectiveness demonstrated in FL. Numerical results demonstrate that Delphi-BO induces a higher amount of uncertainty than Delphi-LSTR highlighting vulnerability of FL systems to model poisoning attacks.
Authors: Xinye Qu, Longxiao Liu, Wenjie Huang
Abstract: In this paper, we propose a novel reinforcement learning algorithm for inventory management of newly launched products with no or limited historical demand information. The algorithm follows the classic Dyna-$Q$ structure, balancing the model-based and model-free approaches, while accelerating the training process of Dyna-$Q$ and mitigating the model discrepancy generated by the model-based feedback. Warm-start information from the demand data of existing similar products can be incorporated into the algorithm to further stabilize the early-stage training and reduce the variance of the estimated optimal policy. Our approach is validated through a case study of bakery inventory management with real data. The adjusted Dyna-$Q$ shows up to a 23.7% reduction in average daily cost compared with $Q$-learning, and up to a 77.5% reduction in training time within the same horizon compared with classic Dyna-$Q$. By incorporating the warm-start information, it can be found that the adjusted Dyna-$Q$ has the lowest total cost, lowest variance in total cost, and relatively low shortage percentages among all the algorithms under a 30-day testing.
Authors: Giuseppe Marra, Michelangelo Diligenti, Francesco Giannini
Abstract: Neuro-symbolic methods integrate neural architectures, knowledge representation and reasoning. However, they have been struggling at both dealing with the intrinsic uncertainty of the observations and scaling to real-world applications. This paper presents Relational Reasoning Networks (R2N), a novel end-to-end model that performs relational reasoning in the latent space of a deep learner architecture, where the representations of constants, ground atoms and their manipulations are learned in an integrated fashion. Unlike flat architectures like Knowledge Graph Embedders, which can only represent relations between entities, R2Ns define an additional computational structure, accounting for higher-level relations among the ground atoms. The considered relations can be explicitly known, like the ones defined by logic formulas, or defined as unconstrained correlations among groups of ground atoms. R2Ns can be applied to purely symbolic tasks or as a neuro-symbolic platform to integrate learning and reasoning in heterogeneous problems with both symbolic and feature-based represented entities. The proposed model overtakes the limitations of previous neuro-symbolic methods that have been either limited in terms of scalability or expressivity. The proposed methodology is shown to achieve state-of-the-art results in different experimental settings.
Authors: Maura Pintor, Daniele Angioni, Angelo Sotgiu, Luca Demetrio, Ambra Demontis, Battista Biggio, Fabio Roli
Abstract: Adversarial patches are optimized contiguous pixel blocks in an input image that cause a machine-learning model to misclassify it. However, their optimization is computationally demanding, and requires careful hyperparameter tuning, potentially leading to suboptimal robustness evaluations. To overcome these issues, we propose ImageNet-Patch, a dataset to benchmark machine-learning models against adversarial patches. It consists of a set of patches, optimized to generalize across different models, and readily applicable to ImageNet data after preprocessing them with affine transformations. This process enables an approximate yet faster robustness evaluation, leveraging the transferability of adversarial perturbations. We showcase the usefulness of this dataset by testing the effectiveness of the computed patches against 127 models. We conclude by discussing how our dataset could be used as a benchmark for robustness, and how our methodology can be generalized to other domains. We open source our dataset and evaluation code at https://github.com/pralab/ImageNet-Patch.
Authors: Shulei Wang
Abstract: Data augmentation is a widely used technique and an essential ingredient in the recent advance in self-supervised representation learning. By preserving the similarity between augmented data, the resulting data representation can improve various downstream analyses and achieve state-of-the-art performance in many applications. Despite the empirical effectiveness, most existing methods lack theoretical understanding under a general nonlinear setting. To fill this gap, we develop a statistical framework on a low-dimension product manifold to model the data augmentation transformation. Under this framework, we introduce a new representation learning method called augmentation invariant manifold learning and design a computationally efficient algorithm by reformulating it as a stochastic optimization problem. Compared with existing self-supervised methods, the new method simultaneously exploits the manifold's geometric structure and invariant property of augmented data and has an explicit theoretical guarantee. Our theoretical investigation characterizes the role of data augmentation in the proposed method and reveals why and how the data representation learned from augmented data can improve the $k$-nearest neighbor classifier in the downstream analysis, showing that a more complex data augmentation leads to more improvement in downstream analysis. Finally, numerical experiments on simulated and real data sets are presented to demonstrate the merit of the proposed method.
Authors: Abdulmoneam Ali, Ahmed Arafa
Abstract: The impact of local averaging on the performance of federated learning (FL) systems is studied in the presence of communication delay between the clients and the parameter server. To minimize the effect of delay, clients are assigned into different groups, each having its own local parameter server (LPS) that aggregates its clients' models. The groups' models are then aggregated at a global parameter server (GPS) that only communicates with the LPSs. Such setting is known as hierarchical FL (HFL). Unlike most works in the literature, the number of local and global communication rounds in our work is randomly determined by the (different) delays experienced by each group of clients. Specifically, the number of local averaging rounds is tied to a wall-clock time period coined the sync time $S$, after which the LPSs synchronize their models by sharing them with the GPS. Such sync time $S$ is then reapplied until a global wall-clock time is exhausted. First, an upper bound on the deviation between the updated model at each LPS with respect to that available at the GPS is derived. This is then used as a tool to derive the convergence analysis of our proposed delay-sensitive HFL algorithm, first at each LPS individually, and then at the GPS. Our theoretical convergence bound showcases the effects of the whole system's parameters, including the number of groups, the number of clients per group, and the value of $S$. Our results show that the value of $S$ should be carefully chosen, especially since it implicitly governs how the delay statistics affect the performance of HFL in situations where training time is restricted.
Authors: Songwei Ge, Taesung Park, Jun-Yan Zhu, Jia-Bin Huang
Abstract: Plain text has become a prevalent interface for text-to-image synthesis. However, its limited customization options hinder users from accurately describing desired outputs. For example, plain text makes it hard to specify continuous quantities, such as the precise RGB color value or importance of each word. Furthermore, creating detailed text prompts for complex scenes is tedious for humans to write and challenging for text encoders to interpret. To address these challenges, we propose using a rich-text editor supporting formats such as font style, size, color, and footnote. We extract each word's attributes from rich text to enable local style control, explicit token reweighting, precise color rendering, and detailed region synthesis. We achieve these capabilities through a region-based diffusion process. We first obtain each word's region based on attention maps of a diffusion process using plain text. For each region, we enforce its text attributes by creating region-specific detailed prompts and applying region-specific guidance, and maintain its fidelity against plain-text generation through region-based injections. We present various examples of image generation from rich text and demonstrate that our method outperforms strong baselines with quantitative evaluations.
Authors: David Janz, Alexander E. Litvak, Csaba Szepesv\'ari
Abstract: We provide the first useful and rigorous analysis of ensemble sampling for the stochastic linear bandit setting. In particular, we show that, under standard assumptions, for a $d$-dimensional stochastic linear bandit with an interaction horizon $T$, ensemble sampling with an ensemble of size of order $d \log T$ incurs regret at most of the order $(d \log T)^{5/2} \sqrt{T}$. Ours is the first result in any structured setting not to require the size of the ensemble to scale linearly with $T$ -- which defeats the purpose of ensemble sampling -- while obtaining near $\smash{\sqrt{T}}$ order regret. Our result is also the first to allow for infinite action sets.
Authors: Joseph Paul Cohen, Louis Blankemeier, Akshay Chaudhari
Abstract: Models driven by spurious correlations often yield poor generalization performance. We propose the counterfactual (CF) alignment method to detect and quantify spurious correlations of black box classifiers. Our methodology is based on counterfactual images generated with respect to one classifier being input into other classifiers to see if they also induce changes in the outputs of these classifiers. The relationship between these responses can be quantified and used to identify specific instances where a spurious correlation exists. This is validated by observing intuitive trends in face-attribute and waterbird classifiers, as well as by fabricating spurious correlations and detecting their presence, both visually and quantitatively. Furthermore, utilizing the CF alignment method, we demonstrate that we can evaluate robust optimization methods (GroupDRO, JTT, and FLAC) by detecting a reduction in spurious correlations.
Authors: Easton K. Huch, Jieru Shi, Madeline R. Abbott, Jessica R. Golbus, Alexander Moreno, Walter H. Dempsey
Abstract: Mobile health leverages personalized and contextually tailored interventions optimized through bandit and reinforcement learning algorithms. In practice, however, challenges such as participant heterogeneity, nonstationarity, and nonlinear relationships hinder algorithm performance. We propose RoME, a Robust Mixed-Effects contextual bandit algorithm that simultaneously addresses these challenges via (1) modeling the differential reward with user- and time-specific random effects, (2) network cohesion penalties, and (3) debiased machine learning for flexible estimation of baseline rewards. We establish a high-probability regret bound that depends solely on the dimension of the differential-reward model, enabling us to achieve robust regret bounds even when the baseline reward is highly complex. We demonstrate the superior performance of the RoME algorithm in a simulation and two off-policy evaluation studies.
Authors: Qiwen Cui, Maryam Fazel, Simon S. Du
Abstract: In multiplayer games, self-interested behavior among the players can harm the social welfare. Tax mechanisms are a common method to alleviate this issue and induce socially optimal behavior. In this work, we take the initial step of learning the optimal tax that can maximize social welfare with limited feedback in congestion games. We propose a new type of feedback named \emph{equilibrium feedback}, where the tax designer can only observe the Nash equilibrium after deploying a tax plan. Existing algorithms are not applicable due to the exponentially large tax function space, nonexistence of the gradient, and nonconvexity of the objective. To tackle these challenges, we design a computationally efficient algorithm that leverages several novel components: (1) a piece-wise linear tax to approximate the optimal tax; (2) extra linear terms to guarantee a strongly convex potential function; (3) an efficient subroutine to find the exploratory tax that can provide critical information about the game. The algorithm can find an $\epsilon$-optimal tax with $O(\beta F^2/\epsilon)$ sample complexity, where $\beta$ is the smoothness of the cost function and $F$ is the number of facilities.
Authors: Liangxin Liu, Xuebo Liu, Derek F. Wong, Dongfang Li, Ziyi Wang, Baotian Hu, Min Zhang
Abstract: Instruction tuning (IT) is crucial to tailoring large language models (LLMs) towards human-centric interactions. Recent advancements have shown that the careful selection of a small, high-quality subset of IT data can significantly enhance the performance of LLMs. Despite this, common approaches often rely on additional models or data, which increases costs and limits widespread adoption. In this work, we propose a novel approach, termed SelectIT, that capitalizes on the foundational capabilities of the LLM itself. Specifically, we exploit the intrinsic uncertainty present in LLMs to more effectively select high-quality IT data, without the need for extra resources. Furthermore, we introduce a curated IT dataset, the Selective Alpaca, created by applying SelectIT to the Alpaca-GPT4 dataset. Empirical results demonstrate that IT using Selective Alpaca leads to substantial model ability enhancement. The robustness of SelectIT has also been corroborated in various foundation models and domain-specific tasks. Our findings suggest that longer and more computationally intensive IT data may serve as superior sources of IT, offering valuable insights for future research in this area. Data, code, and scripts are freely available at https://github.com/Blue-Raincoat/SelectIT.
Authors: Zhengxiao Du, Aohan Zeng, Yuxiao Dong, Jie Tang
Abstract: Recent studies have put into question the belief that emergent abilities in language models are exclusive to large models. This skepticism arises from two observations: 1) smaller models can also exhibit high performance on emergent abilities and 2) there is doubt on the discontinuous metrics used to measure these abilities. In this paper, we propose to study emergent abilities in the lens of pre-training loss, instead of model size or training compute. We demonstrate that the Transformer models with the same pre-training loss, but different model and data sizes, generate the same performance on various downstream tasks, with a fixed data corpus, tokenization, and model architecture. We also discover that a model exhibits emergent abilities on certain tasks -- regardless of the continuity of metrics -- when its pre-training loss falls below a specific threshold. Before reaching this threshold, its performance remains at the level of random guessing. This inspires us to redefine emergent abilities as those that manifest in models with lower pre-training losses, highlighting that these abilities cannot be predicted by merely extrapolating the performance trends of models with higher pre-training losses.
Authors: Sadanand Modak, Noah Patton, Isil Dillig, Joydeep Biswas
Abstract: This paper addresses the problem of preference learning, which aims to align robot behaviors through learning user specific preferences (e.g. "good pull-over location") from visual demonstrations. Despite its similarity to learning factual concepts (e.g. "red door"), preference learning is a fundamentally harder problem due to its subjective nature and the paucity of person-specific training data. We address this problem using a novel framework called SYNAPSE, which is a neuro-symbolic approach designed to efficiently learn preferential concepts from limited data. SYNAPSE represents preferences as neuro-symbolic programs, facilitating inspection of individual parts for alignment, in a domain-specific language (DSL) that operates over images and leverages a novel combination of visual parsing, large language models, and program synthesis to learn programs representing individual preferences. We perform extensive evaluations on various preferential concepts as well as user case studies demonstrating its ability to align well with dissimilar user preferences. Our method significantly outperforms baselines, especially when it comes to out of distribution generalization. We show the importance of the design choices in the framework through multiple ablation studies. Code, additional results, and supplementary material can be found on the website: https://amrl.cs.utexas.edu/synapse
Authors: ChonLam Lao, Jiaqi Gao, Ganesh Ananthanarayanan, Aditya Akella, Minlan Yu
Abstract: Traditional ML inference is evolving toward modeless inference, which abstracts the complexity of model selection from users, allowing the system to automatically choose the most appropriate model for each request based on accuracy and resource requirements. While prior studies have focused on modeless inference within data centers, this paper tackles the pressing need for cost-efficient modeless inference at the edge -- particularly within its unique constraints of limited device memory, volatile network conditions, and restricted power consumption. To overcome these challenges, we propose EdgeSight, a system that provides cost-efficient EdgeSight serving for diverse DNNs at the edge. EdgeSight employs an edge-data center (edge-DC) architecture, utilizing confidence scaling to reduce the number of model options while meeting diverse accuracy requirements. Additionally, it supports lossy inference in volatile network environments. Our experimental results show that EdgeSight outperforms existing systems by up to 1.6x in P99 latency for modeless services. Furthermore, our FPGA prototype demonstrates similar performance at certain accuracy levels, with a power consumption reduction of up to 3.34x.
Authors: Matilde Tullii, Solenne Gaucher, Nadav Merlis, Vianney Perchet
Abstract: In contextual dynamic pricing, a seller sequentially prices goods based on contextual information. Buyers will purchase products only if the prices are below their valuations. The goal of the seller is to design a pricing strategy that collects as much revenue as possible. We focus on two different valuation models. The first assumes that valuations linearly depend on the context and are further distorted by noise. Under minor regularity assumptions, our algorithm achieves an optimal regret bound of $\tilde{\mathcal{O}}(T^{2/3})$, improving the existing results. The second model removes the linearity assumption, requiring only that the expected buyer valuation is $\beta$-H\"older in the context. For this model, our algorithm obtains a regret $\tilde{\mathcal{O}}(T^{d+2\beta/d+3\beta})$, where $d$ is the dimension of the context space.
Authors: Jen Ning Lim, Adam M. Johansen
Abstract: Semi-implicit variational inference (SIVI) enriches the expressiveness of variational families by utilizing a kernel and a mixing distribution to hierarchically define the variational distribution. Existing SIVI methods parameterize the mixing distribution using implicit distributions, leading to intractable variational densities. As a result, directly maximizing the evidence lower bound (ELBO) is not possible, so they resort to one of the following: optimizing bounds on the ELBO, employing costly inner-loop Markov chain Monte Carlo runs, or solving minimax objectives. In this paper, we propose a novel method for SIVI called Particle Variational Inference (PVI) which employs empirical measures to approximate the optimal mixing distributions characterized as the minimizer of a free energy functional. PVI arises naturally as a particle approximation of a Euclidean--Wasserstein gradient flow and, unlike prior works, it directly optimizes the ELBO whilst making no parametric assumption about the mixing distribution. Our empirical results demonstrate that PVI performs favourably compared to other SIVI methods across various tasks. Moreover, we provide a theoretical analysis of the behaviour of the gradient flow of a related free energy functional: establishing the existence and uniqueness of solutions as well as propagation of chaos results.
Authors: Cong Cao, Huanjing Yue, Xin Liu, Jingyu Yang
Abstract: Diffusion-based zero-shot image restoration and enhancement models have achieved great success in various tasks of image restoration and enhancement. However, directly applying them to video restoration and enhancement results in severe temporal flickering artifacts. In this paper, we propose the first framework for zero-shot video restoration and enhancement based on the pre-trained image diffusion model. By replacing the spatial self-attention layer with the proposed short-long-range (SLR) temporal attention layer, the pre-trained image diffusion model can take advantage of the temporal correlation between frames. We further propose temporal consistency guidance, spatial-temporal noise sharing, and an early stopping sampling strategy to improve temporally consistent sampling. Our method is a plug-and-play module that can be inserted into any diffusion-based image restoration or enhancement methods to further improve their performance. Experimental results demonstrate the superiority of our proposed method. Our code is available at https://github.com/cao-cong/ZVRD.
Authors: Junghyun Lee, Se-Young Yun, Kwang-Sung Jun
Abstract: We present a unified likelihood ratio-based confidence sequence (CS) for any (self-concordant) generalized linear model (GLM) that is guaranteed to be convex and numerically tight. We show that this is on par or improves upon known CSs for various GLMs, including Gaussian, Bernoulli, and Poisson. In particular, for the first time, our CS for Bernoulli has a $\mathrm{poly}(S)$-free radius where $S$ is the norm of the unknown parameter. Our first technical novelty is its derivation, which utilizes a time-uniform PAC-Bayesian bound with a uniform prior/posterior, despite the latter being a rather unpopular choice for deriving CSs. As a direct application of our new CS, we propose a simple and natural optimistic algorithm called OFUGLB, applicable to any generalized linear bandits (GLB; Filippi et al. (2010)). Our analysis shows that the celebrated optimistic approach simultaneously attains state-of-the-art regrets for various self-concordant (not necessarily bounded) GLBs, and even $\mathrm{poly}(S)$-free for bounded GLBs, including logistic bandits. The regret analysis, our second technical novelty, follows from combining our new CS with a new proof technique that completely avoids the previously widely used self-concordant control lemma (Faury et al., 2020, Lemma 9). Numerically, OFUGLB outperforms or is at par with prior algorithms for logistic bandits.
Authors: Kensen Shi, Deniz Alt{\i}nb\"uken, Saswat Anand, Mihai Christodorescu, Katja Gr\"unwedel, Alexa Koenings, Sai Naidu, Anurag Pathak, Marc Rasi, Fredde Ribeiro, Brandon Ruffin, Siddhant Sanyam, Maxim Tabachnyk, Sara Toth, Roy Tu, Tobias Welp, Pengcheng Yin, Manzil Zaheer, Satish Chandra, Charles Sutton
Abstract: We propose using natural language outlines as a novel modality and interaction surface for providing AI assistance to developers throughout the software development process. An NL outline for a code function comprises multiple statements written in concise prose, which partition the code and summarize its main ideas in the style of literate programming. Crucially, we find that modern LLMs can generate accurate and high-quality NL outlines in practice. Moreover, NL outlines enable a bidirectional sync between code and NL, allowing changes in one to be automatically reflected in the other. We discuss many use cases for NL outlines: they can accelerate understanding and navigation of code and diffs, simplify code maintenance, augment code search, steer code generation, and more. We then propose and compare multiple LLM prompting techniques for generating outlines and ask professional developers to judge outline quality. Finally, we present two case studies applying NL outlines toward code review and malware detection.
Authors: Zijian Zhao, Tingwei Chen, Zhijie Cai, Xiaoyang Li, Hang Li, Qimei Chen, Guangxu Zhu
Abstract: In recent years, Wi-Fi sensing has garnered significant attention due to its numerous benefits, such as privacy protection, low cost, and penetration ability. Extensive research has been conducted in this field, focusing on areas such as gesture recognition, people identification, and fall detection. However, many data-driven methods encounter challenges related to domain shift, where the model fails to perform well in environments different from the training data. One major factor contributing to this issue is the limited availability of Wi-Fi sensing datasets, which makes models learn excessive irrelevant information and over-fit to the training set. Unfortunately, collecting large-scale Wi-Fi sensing datasets across diverse scenarios is a challenging task. To address this problem, we propose CrossFi, a siamese network-based approach that excels in both in-domain scenario and cross-domain scenario, including few-shot, zero-shot scenarios, and even works in few-shot new-class scenario where testing set contains new categories. The core component of CrossFi is a sample-similarity calculation network called CSi-Net, which improves the structure of the siamese network by using an attention mechanism to capture similarity information, instead of simply calculating the distance or cosine similarity. Based on it, we develop an extra Weight-Net that can generate a template for each class, so that our CrossFi can work in different scenarios. Experimental results demonstrate that our CrossFi achieves state-of-the-art performance across various scenarios. In gesture recognition task, our CrossFi achieves an accuracy of 98.17% in in-domain scenario, 91.72% in one-shot cross-domain scenario, 64.81% in zero-shot cross-domain scenario, and 84.75% in one-shot new-class scenario. The code for our model is publicly available at https://github.com/RS2002/CrossFi.
Authors: Hugo Cui
Abstract: Recent years have been marked with the fast-pace diversification and increasing ubiquity of machine learning applications. Yet, a firm theoretical understanding of the surprising efficiency of neural networks to learn from high-dimensional data still proves largely elusive. In this endeavour, analyses inspired by statistical physics have proven instrumental, enabling the tight asymptotic characterization of the learning of neural networks in high dimensions, for a broad class of solvable models. This manuscript reviews the tools and ideas underlying recent progress in this line of work. We introduce a generic model -- the sequence multi-index model -- which encompasses numerous previously studied models as special instances. This unified framework covers a broad class of machine learning architectures with a finite number of hidden units, including multi-layer perceptrons, autoencoders, attention mechanisms; and tasks, including (un)supervised learning, denoising, contrastive learning, in the limit of large data dimension, and comparably large number of samples. We explicate in full detail the analysis of the learning of sequence multi-index models, using statistical physics techniques such as the replica method and approximate message-passing algorithms. This manuscript thus provides a unified presentation of analyses reported in several previous works, and a detailed overview of central techniques in the field of statistical physics of machine learning. This review should be a useful primer for machine learning theoreticians curious of statistical physics approaches; it should also be of value to statistical physicists interested in the transfer of such ideas to the study of neural networks.
Authors: Hannah Schulz-K\"umpel, Sebastian Fischer, Roman Hornung, Anne-Laure Boulesteix, Thomas Nagler, Bernd Bischl
Abstract: When assessing the quality of prediction models in machine learning, confidence intervals (CIs) for the generalization error, which measures predictive performance, are a crucial tool. Luckily, there exist many methods for computing such CIs and new promising approaches are continuously being proposed. Typically, these methods combine various resampling procedures, most popular among them cross-validation and bootstrapping, with different variance estimation techniques. Unfortunately, however, there is currently no consensus on when any of these combinations may be most reliably employed and how they generally compare. In this work, we conduct a large-scale study comparing CIs for the generalization error, the first one of such size, where we empirically evaluate 13 different CI methods on a total of 19 tabular regression and classification problems, using seven different inducers and a total of eight loss functions. We give an overview of the methodological foundations and inherent challenges of constructing CIs for the generalization error and provide a concise review of all 13 methods in a unified framework. Finally, the CI methods are evaluated in terms of their relative coverage frequency, width, and runtime. Based on these findings, we can identify a subset of methods that we would recommend. We also publish the datasets as a benchmarking suite on OpenML and our code on GitHub to serve as a basis for further studies.
Authors: Shivang Rawat, David J. Heeger, Stefano Martiniani
Abstract: Stability in recurrent neural models poses a significant challenge, particularly in developing biologically plausible neurodynamical models that can be seamlessly trained. Traditional cortical circuit models are notoriously difficult to train due to expansive nonlinearities in the dynamical system, leading to an optimization problem with nonlinear stability constraints that are difficult to impose. Conversely, recurrent neural networks (RNNs) excel in tasks involving sequential data but lack biological plausibility and interpretability. In this work, we address these challenges by linking dynamic divisive normalization (DN) to the stability of ORGaNICs, a biologically plausible recurrent cortical circuit model that dynamically achieves DN and that has been shown to simulate a wide range of neurophysiological phenomena. By using the indirect method of Lyapunov, we prove the remarkable property of unconditional local stability for an arbitrary-dimensional ORGaNICs circuit when the recurrent weight matrix is the identity. We thus connect ORGaNICs to a system of coupled damped harmonic oscillators, which enables us to derive the circuit's energy function, providing a normative principle of what the circuit, and individual neurons, aim to accomplish. Further, for a generic recurrent weight matrix, we prove the stability of the 2D model and demonstrate empirically that stability holds in higher dimensions. Finally, we show that ORGaNICs can be trained by backpropagation through time without gradient clipping/scaling, thanks to its intrinsic stability property and adaptive time constants, which address the problems of exploding, vanishing, and oscillating gradients. By evaluating the model's performance on RNN benchmarks, we find that ORGaNICs outperform alternative neurodynamical models on static image classification tasks and perform comparably to LSTMs on sequential tasks.
Authors: Jean-Eudes Ayilo (MULTISPEECH), Mostafa Sadeghi (MULTISPEECH), Romain Serizel (MULTISPEECH), Xavier Alameda-Pineda (ROBOTLEARN)
Abstract: This paper proposes a new unsupervised audio-visual speech enhancement (AVSE) approach that combines a diffusion-based audio-visual speech generative model with a non-negative matrix factorization (NMF) noise model. First, the diffusion model is pre-trained on clean speech conditioned on corresponding video data to simulate the speech generative distribution. This pre-trained model is then paired with the NMF-based noise model to estimate clean speech iteratively. Specifically, a diffusion-based posterior sampling approach is implemented within the reverse diffusion process, where after each iteration, a speech estimate is obtained and used to update the noise parameters. Experimental results confirm that the proposed AVSE approach not only outperforms its audio-only counterpart but also generalizes better than a recent supervised-generative AVSE method. Additionally, the new inference algorithm offers a better balance between inference speed and performance compared to the previous diffusion-based method. Code and demo available at: https://jeaneudesayilo.github.io/fast_UdiffSE
Authors: Md Rajib Khan Musa, Yichen Qian, Jie Peng, David Cereceda
Abstract: Finding Minimum Energy Configurations (MECs) is essential in fields such as physics, chemistry, and materials science, as they represent the most stable states of the systems. In particular, identifying such MECs in multi-component alloys considered candidate PFMs is key because it determines the most stable arrangement of atoms within the alloy, directly influencing its phase stability, structural integrity, and thermo-mechanical properties. However, since the search space grows exponentially with the number of atoms considered, obtaining such MECs using computationally expensive first-principles DFT calculations often results in a cumbersome task. To escape the above compromise between physical fidelity and computational efficiency, we have developed a novel physics-based data-driven approach that combines Monte Carlo sampling, first-principles DFT calculations, and Machine Learning to accelerate the discovery of MECs in multi-component alloys. More specifically, we have leveraged well-established Cluster Expansion (CE) techniques with Local Outlier Factor models to establish strategies that enhance the reliability of the CE method. In this work, we demonstrated the capabilities of the proposed approach for the particular case of a tungsten-based quaternary high-entropy alloy. However, the method is applicable to other types of alloys and enables a wide range of applications.
Authors: Chad Brown
Abstract: This paper establishes statistical properties of deep neural network (DNN) estimators under dependent data. Two general results for nonparametric sieve estimators directly applicable to DNN estimators are given. The first establishes rates for convergence in probability under nonstationary data. The second provides non-asymptotic probability bounds on $\mathcal{L}^{2}$-errors under stationary $\beta$-mixing data. I apply these results to DNN estimators in both regression and classification contexts imposing only a standard H\"older smoothness assumption. The DNN architectures considered are common in applications, featuring fully connected feedforward networks with any continuous piecewise linear activation function, unbounded weights, and a width and depth that grows with sample size. The framework provided also offers potential for research into other DNN architectures and time-series applications.
Authors: Xiaohang Xu, Renhe Jiang, Chuang Yang, Zipei Fan, Kaoru Sezaki
Abstract: With the popularity of location-based services, human mobility prediction plays a key role in enhancing personalized navigation, optimizing recommendation systems, and facilitating urban mobility and planning. This involves predicting a user's next POI (point-of-interest) visit using their past visit history. However, the uneven distribution of visitations over time and space, namely the long-tail problem in spatial distribution, makes it difficult for AI models to predict those POIs that are less visited by humans. In light of this issue, we propose the Long-Tail Adjusted Next POI Prediction (LoTNext) framework for mobility prediction, combining a Long-Tailed Graph Adjustment module to reduce the impact of the long-tailed nodes in the user-POI interaction graph and a novel Long-Tailed Loss Adjustment module to adjust loss by logit score and sample weight adjustment strategy. Also, we employ the auxiliary prediction task to enhance generalization and accuracy. Our experiments with two real-world trajectory datasets demonstrate that LoTNext significantly surpasses existing state-of-the-art works.
Authors: Roman Bushuiev, Anton Bushuiev, Niek F. de Jonge, Adamo Young, Fleming Kretschmer, Raman Samusevich, Janne Heirman, Fei Wang, Luke Zhang, Kai D\"uhrkop, Marcus Ludwig, Nils A. Haupt, Apurva Kalia, Corinna Brungs, Robin Schmid, Russell Greiner, Bo Wang, David S. Wishart, Li-Ping Liu, Juho Rousu, Wout Bittremieux, Hannes Rost, Tytus D. Mak, Soha Hassoun, Florian Huber, Justin J. J. van der Hooft, Michael A. Stravs, Sebastian B\"ocker, Josef Sivic, Tom\'a\v{s} Pluskal
Abstract: The discovery and identification of molecules in biological and environmental samples is crucial for advancing biomedical and chemical sciences. Tandem mass spectrometry (MS/MS) is the leading technique for high-throughput elucidation of molecular structures. However, decoding a molecular structure from its mass spectrum is exceptionally challenging, even when performed by human experts. As a result, the vast majority of acquired MS/MS spectra remain uninterpreted, thereby limiting our understanding of the underlying (bio)chemical processes. Despite decades of progress in machine learning applications for predicting molecular structures from MS/MS spectra, the development of new methods is severely hindered by the lack of standard datasets and evaluation protocols. To address this problem, we propose MassSpecGym -- the first comprehensive benchmark for the discovery and identification of molecules from MS/MS data. Our benchmark comprises the largest publicly available collection of high-quality labeled MS/MS spectra and defines three MS/MS annotation challenges: \textit{de novo} molecular structure generation, molecule retrieval, and spectrum simulation. It includes new evaluation metrics and a generalization-demanding data split, therefore standardizing the MS/MS annotation tasks and rendering the problem accessible to the broad machine learning community. MassSpecGym is publicly available at \url{https://github.com/pluskal-lab/MassSpecGym}.
Authors: Alexander Decruyenaere, Heidelinde Dehaene, Paloma Rabaey, Christiaan Polet, Johan Decruyenaere, Thomas Demeester, Stijn Vansteelandt
Abstract: While synthetic data hold great promise for privacy protection, their statistical analysis poses significant challenges that necessitate innovative solutions. The use of deep generative models (DGMs) for synthetic data generation is known to induce considerable bias and imprecision into synthetic data analyses, compromising their inferential utility as opposed to original data analyses. This bias and uncertainty can be substantial enough to impede statistical convergence rates, even in seemingly straightforward analyses like mean calculation. The standard errors of such estimators then exhibit slower shrinkage with sample size than the typical 1 over root-$n$ rate. This complicates fundamental calculations like p-values and confidence intervals, with no straightforward remedy currently available. In response to these challenges, we propose a new strategy that targets synthetic data created by DGMs for specific data analyses. Drawing insights from debiased and targeted machine learning, our approach accounts for biases, enhances convergence rates, and facilitates the calculation of estimators with easily approximated large sample variances. We exemplify our proposal through a simulation study on toy data and two case studies on real-world data, highlighting the importance of tailoring DGMs for targeted data analysis. This debiasing strategy contributes to advancing the reliability and applicability of synthetic data in statistical inference.
Authors: Huiwon Jang, Sihyun Yu, Jinwoo Shin, Pieter Abbeel, Younggyo Seo
Abstract: Efficient tokenization of videos remains a challenge in training vision models that can process long videos. One promising direction is to develop a tokenizer that can encode long video clips, as it would enable the tokenizer to leverage the temporal coherence of videos better for tokenization. However, training existing tokenizers on long videos often incurs a huge training cost as they are trained to reconstruct all the frames at once. In this paper, we introduce CoordTok, a video tokenizer that learns a mapping from coordinate-based representations to the corresponding patches of input videos, inspired by recent advances in 3D generative models. In particular, CoordTok encodes a video into factorized triplane representations and reconstructs patches that correspond to randomly sampled $(x,y,t)$ coordinates. This allows for training large tokenizer models directly on long videos without requiring excessive training resources. Our experiments show that CoordTok can drastically reduce the number of tokens for encoding long video clips. For instance, CoordTok can encode a 128-frame video with 128$\times$128 resolution into 1280 tokens, while baselines need 6144 or 8192 tokens to achieve similar reconstruction quality. We further show that this efficient video tokenization enables memory-efficient training of a diffusion transformer that can generate 128 frames at once.
Authors: Zhenxiong Tan, Songhua Liu, Xingyi Yang, Qiaochu Xue, Xinchao Wang
Abstract: In this paper, we introduce OminiControl, a highly versatile and parameter-efficient framework that integrates image conditions into pre-trained Diffusion Transformer (DiT) models. At its core, OminiControl leverages a parameter reuse mechanism, enabling the DiT to encode image conditions using itself as a powerful backbone and process them with its flexible multi-modal attention processors. Unlike existing methods, which rely heavily on additional encoder modules with complex architectures, OminiControl (1) effectively and efficiently incorporates injected image conditions with only ~0.1% additional parameters, and (2) addresses a wide range of image conditioning tasks in a unified manner, including subject-driven generation and spatially-aligned conditions such as edges, depth, and more. Remarkably, these capabilities are achieved by training on images generated by the DiT itself, which is particularly beneficial for subject-driven generation. Extensive evaluations demonstrate that OminiControl outperforms existing UNet-based and DiT-adapted models in both subject-driven and spatially-aligned conditional generation. Additionally, we release our training dataset, Subjects200K, a diverse collection of over 200,000 identity-consistent images, along with an efficient data synthesis pipeline to advance research in subject-consistent generation.
Authors: Alexander Meinke, Bronson Schoen, J\'er\'emy Scheurer, Mikita Balesni, Rusheb Shah, Marius Hobbhahn
Abstract: Frontier models are increasingly trained and deployed as autonomous agent. One safety concern is that AI agents might covertly pursue misaligned goals, hiding their true capabilities and objectives - also known as scheming. We study whether models have the capability to scheme in pursuit of a goal that we provide in-context and instruct the model to strongly follow. We evaluate frontier models on a suite of six agentic evaluations where models are instructed to pursue goals and are placed in environments that incentivize scheming. Our results show that o1, Claude 3.5 Sonnet, Claude 3 Opus, Gemini 1.5 Pro, and Llama 3.1 405B all demonstrate in-context scheming capabilities. They recognize scheming as a viable strategy and readily engage in such behavior. For example, models strategically introduce subtle mistakes into their responses, attempt to disable their oversight mechanisms, and even exfiltrate what they believe to be their model weights to external servers. Additionally, this deceptive behavior proves persistent. When o1 has engaged in scheming, it maintains its deception in over 85% of follow-up questions and often remains deceptive in multi-turn interrogations. Analysis of the models' chains-of-thought reveals that models explicitly reason about these deceptive strategies, providing evidence that the scheming behavior is not accidental. Surprisingly, we also find rare instances where models engage in scheming when only given a goal, without being strongly nudged to pursue it. We observe cases where Claude 3.5 Sonnet strategically underperforms in evaluations in pursuit of being helpful, a goal that was acquired during training rather than in-context. Our findings demonstrate that frontier models now possess capabilities for basic in-context scheming, making the potential of AI agents to engage in scheming behavior a concrete rather than theoretical concern.
Authors: Maida Wang, Jinyang Jiang, Peter V. Coveney
Abstract: Quantum machine learning has gained attention for its potential to address computational challenges. However, whether those algorithms can effectively solve practical problems and outperform their classical counterparts, especially on current quantum hardware, remains a critical question. In this work, we propose a novel quantum machine learning method, called Quantum Support Vector Data Description (QSVDD), for practical image anomaly detection, which aims to achieve both parameter efficiency and superior accuracy compared to classical models. Emulation results indicate that QSVDD demonstrates favourable recognition capabilities compared to classical baselines, achieving an average accuracy of over 90% on benchmarks with significantly fewer trainable parameters. Theoretical analysis confirms that QSVDD has a comparable expressivity to classical counterparts while requiring only a fraction of the parameters. Furthermore, we demonstrate the first implementation of a quantum anomaly detection method for general image datasets on a superconducting quantum processor. Specifically, we achieve an accuracy of over 80% with only 16 parameters on the device, providing initial evidence of QSVDD's practical viability in the noisy intermediate-scale quantum era and highlighting its significant reduction in parameter requirements.
Authors: Chenxi Zhang, Qing Zhang, Jiayun Wu, Youwei Pang
Abstract: Camouflaged Object Detection (COD) aims to identify objects that blend seamlessly into their surroundings. The inherent visual complexity of camouflaged objects, including their low contrast with the background, diverse textures, and subtle appearance variations, often obscures semantic cues, making accurate segmentation highly challenging. Existing methods primarily rely on visual features, which are insufficient to handle the variability and intricacy of camouflaged objects, leading to unstable object perception and ambiguous segmentation results. To tackle these limitations, we introduce a novel task, class-guided camouflaged object detection (CGCOD), which extends traditional COD task by incorporating object-specific class knowledge to enhance detection robustness and accuracy. To facilitate this task, we present a new dataset, CamoClass, comprising real-world camouflaged objects with class annotations. Furthermore, we propose a multi-stage framework, CGNet, which incorporates a plug-and-play class prompt generator and a simple yet effective class-guided detector. This establishes a new paradigm for COD, bridging the gap between contextual understanding and class-guided detection. Extensive experimental results demonstrate the effectiveness of our flexible framework in improving the performance of proposed and existing detectors by leveraging class-level textual information.
Authors: Tony Cai, Abhinav Chakraborty, Lasse Vuursteen
Abstract: Federated learning (FL) is a distributed machine learning technique designed to preserve data privacy and security, and it has gained significant importance due to its broad range of applications. This paper addresses the problem of optimal functional mean estimation from discretely sampled data in a federated setting. We consider a heterogeneous framework where the number of individuals, measurements per individual, and privacy parameters vary across one or more servers, under both common and independent design settings. In the common design setting, the same design points are measured for each individual, whereas in the independent design, each individual has their own random collection of design points. Within this framework, we establish minimax upper and lower bounds for the estimation error of the underlying mean function, highlighting the nuanced differences between common and independent designs under distributed privacy constraints. We propose algorithms that achieve the optimal trade-off between privacy and accuracy and provide optimality results that quantify the fundamental limits of private functional mean estimation across diverse distributed settings. These results characterize the cost of privacy and offer practical insights into the potential for privacy-preserving statistical analysis in federated environments.
Authors: Team OLMo, Pete Walsh, Luca Soldaini, Dirk Groeneveld, Kyle Lo, Shane Arora, Akshita Bhagia, Yuling Gu, Shengyi Huang, Matt Jordan, Nathan Lambert, Dustin Schwenk, Oyvind Tafjord, Taira Anderson, David Atkinson, Faeze Brahman, Christopher Clark, Pradeep Dasigi, Nouha Dziri, Michal Guerquin, Hamish Ivison, Pang Wei Koh, Jiacheng Liu, Saumya Malik, William Merrill, Lester James V. Miranda, Jacob Morrison, Tyler Murray, Crystal Nam, Valentina Pyatkin, Aman Rangapur, Michael Schmitz, Sam Skjonsberg, David Wadden, Christopher Wilhelm, Michael Wilson, Luke Zettlemoyer, Ali Farhadi, Noah A. Smith, Hannaneh Hajishirzi
Abstract: We present OLMo 2, the next generation of our fully open language models. OLMo 2 includes dense autoregressive models with improved architecture and training recipe, pretraining data mixtures, and instruction tuning recipes. Our modified model architecture and training recipe achieve both better training stability and improved per-token efficiency. Our updated pretraining data mixture introduces a new, specialized data mix called Dolmino Mix 1124, which significantly improves model capabilities across many downstream task benchmarks when introduced via late-stage curriculum training (i.e. specialized data during the annealing phase of pretraining). Finally, we incorporate best practices from T\"ulu 3 to develop OLMo 2-Instruct, focusing on permissive data and extending our final-stage reinforcement learning with verifiable rewards (RLVR). Our OLMo 2 base models sit at the Pareto frontier of performance to compute, often matching or outperforming open-weight only models like Llama 3.1 and Qwen 2.5 while using fewer FLOPs and with fully transparent training data, code, and recipe. Our fully open OLMo 2-Instruct models are competitive with or surpassing open-weight only models of comparable size, including Qwen 2.5, Llama 3.1 and Gemma 2. We release all OLMo 2 artifacts openly -- models at 7B and 13B scales, both pretrained and post-trained, including their full training data, training code and recipes, training logs and thousands of intermediate checkpoints. The final instruction model is available on the Ai2 Playground as a free research demo.
Authors: Roi Papo, Sapir Gershov, Tom Friedman, Itay Or, Gil Bolotin, Shlomi Laufer
Abstract: Hand-specific localization has garnered significant interest within the computer vision community. Although there are numerous datasets with hand annotations from various angles and settings, domain transfer techniques frequently struggle in surgical environments. This is mainly due to the limited availability of gloved hand instances and the unique challenges of operating rooms (ORs). Thus, hand-detection models tailored to OR settings require extensive training and expensive annotation processes. To overcome these challenges, we present "RoHan" - a novel approach for robust hand detection in the OR, leveraging advanced semi-supervised domain adaptation techniques to tackle the challenges of varying recording conditions, diverse glove colors, and occlusions common in surgical settings. Our methodology encompasses two main stages: (1) data augmentation strategy that utilizes "Artificial Gloves," a method for augmenting publicly available hand datasets with synthetic images of hands-wearing gloves; (2) semi-supervised domain adaptation pipeline that improves detection performance in real-world OR settings through iterative prediction refinement and efficient frame filtering. We evaluate our method using two datasets: simulated enterotomy repair and saphenous vein graft harvesting. "RoHan" substantially reduces the need for extensive labeling and model training, paving the way for the practical implementation of hand detection technologies in medical settings.
Authors: Yin Fang, Xinle Deng, Kangwei Liu, Ningyu Zhang, Jingyang Qian, Penghui Yang, Xiaohui Fan, Huajun Chen
Abstract: Large language models excel at interpreting complex natural language instructions, enabling them to perform a wide range of tasks. In the life sciences, single-cell RNA sequencing (scRNA-seq) data serves as the "language of cellular biology", capturing intricate gene expression patterns at the single-cell level. However, interacting with this "language" through conventional tools is often inefficient and unintuitive, posing challenges for researchers. To address these limitations, we present InstructCell, a multi-modal AI copilot that leverages natural language as a medium for more direct and flexible single-cell analysis. We construct a comprehensive multi-modal instruction dataset that pairs text-based instructions with scRNA-seq profiles from diverse tissues and species. Building on this, we develop a multi-modal cell language architecture capable of simultaneously interpreting and processing both modalities. InstructCell empowers researchers to accomplish critical tasks-such as cell type annotation, conditional pseudo-cell generation, and drug sensitivity prediction-using straightforward natural language commands. Extensive evaluations demonstrate that InstructCell consistently meets or exceeds the performance of existing single-cell foundation models, while adapting to diverse experimental conditions. More importantly, InstructCell provides an accessible and intuitive tool for exploring complex single-cell data, lowering technical barriers and enabling deeper biological insights.