Search · four archives
Search · four archives
26 papers · ranked by Valyu relevance
Authors not listed
Machine olfaction—the artificial replication of the sense of smell—faces significant challenges due to the absence of large, standardized training datasets. Unlike vision, language, and audio models, which benefit from extensive corpora such as ImageNet, GLUE, and AudioSet, olfaction lacks scaled equivalents and…
S. Dai, G. B. Sun, F. Li, X. Tang + 2 more
—Spectral clustering has emerged as one of the most effective clustering algorithms due to its superior performance. However, most existing models are designed for centralized settings, rendering them inapplicable in modern decentralized environments. Moreover, current federated learning approaches often suffer from…
Eloi Campagne, Yvenn Amara-Ouali, Yannig Goude, Mathilde Mougeot + 1 more
Many-Task Learning refers to the setting where a large number of related tasks need to be learned, the exact relationships between tasks are not known. We introduce the Cascaded Transfer Learning, a novel many-task transfer learning paradigm where information (e.g. model parameters) cascades hierarchically through…
Pengchao Han, Xi Huang, Yi Fang, Guojun Han
—Collaborative learning has emerged as a key paradigm in large-scale intelligent systems, enabling distributed agents to cooperatively train their models while addressing their privacy concerns. Central to this paradigm is knowledge distillation (KD), a technique that facilitates efficient knowledge transfer among…
Zhuojun Tian, Chaouki Ben Issaid, Mehdi Bennis
In large-scale distributed scenarios, increasingly complex tasks demand more intelligent collaboration across networks, requiring the joint extraction of structural representations from data samples. However, conventional task-specific approaches often result in nonstructural embeddings, leading to collapsed…
Shahil Shaik, Jonathon M. Smereka, Yue Wang
Centralized training with decentralized execution (CTDE) has been the dominant paradigm in multi-agent reinforcement learning (MARL), but its reliance on global state information during training introduces scalability, robustness, and generalization bottlenecks. Moreover, in practical scenarios such as adding/dropping…
Zhuojun Tian, Mehdi Bennis
—In this letter, we formulate a compositional distributed learning framework for multi-view perception by leveraging the maximal coding rate reduction principle combined with subspace basis fusion. In the proposed algorithm, each agent conducts a periodic singular value decomposition on its learned subspaces and…
Authors not listed
Equivariant graph neural networks have shown remarkable success in molecular property prediction, but their performance on novel molecular geometries remains limited without extensive training data. We present a computationally efficient approach to cross-geometry pretraining for molecular systems that improves…
Owen Marschall, David G. Clark, Ashok Litwin-Kumar
Neural activity during the performance of a stereotyped behavioral task is often described as low-dimensional, occupying only a limited region in the space of all firing-rate patterns. This region has been referred to as the “neural manifold” associated with a task. More recently, recordings of neural activity in…
Hongyu Xiong, Ming Dai
Existing multimodal federated learning methods typically assume complete modality availability and struggle with heterogeneity between training and testing data distributions, making them unsuitable for handling missing modalities and distribution drift in distributed learning scenarios such as the Internet of Things…
Shengtian Zhang, Haolin Yang, Hyeonseok Kim, Incheol Shin + 2 more
Edge computing (EC) in the Internet of Ships (IoS) reduces the latency and energy burdens of cloud-centric architectures, but fully realizing its benefits requires effective computation offloading strategies. Designing such strategies in dynamic maritime environments remains challenging due to the high-dimensional…
Bin Du, Chang Liu, Dingqi Zhu, Lintao Ye + 1 more
We study distributed online submodular maximization under partition matroid constraints, in which multiple agents select a limited number of actions from their own subsets sequentially to maximize the cumulative value of a sequence of objective functions. We develop a unified algorithmic framework that accommodates…
Fei Liu, ZhiLi Liu, XiaoHong Liu, Hua Zhou
Fog computing offers a decentralized paradigm to address the low-latency and energy-efficiency requirements of emerging IoT applications. However, the heterogeneity of edge nodes, the dynamic nature of workloads, and the dual need for both real-time and non-real-time scheduling introduce significant challenges in task…
Authors not listed
Recent advances in machine learning force fields (MLFF) have significantly extended the reach of atomistic simulations. Continuous progress in this field requires reliable reference datasets, accurate MLFF architectures, and efficient active learning strategies to enable robust modeling of complex molecular and…
Rong Cheng, Zhiwei Sun, Kun Qi, Wangyu Wu + 2 more
As multi-view datasets expand across diverse practical fields, feature selection (FS) has become an indispensable preparatory stage for machine learning models. Nevertheless, real-world multi-view data is often unlabeled and distributed among isolated clients, posing significant challenges to traditional centralized…
Patrick Q. Zhang, Michael J. Jutras, Adam J.O. Dede, Edgar Y. Walker + 2 more
Adaptive behavior requires maintaining and updating probabilistic beliefs about the world, yet how distributed brain circuits implement such computations remains unknown. We recorded from over 1,400 neurons across six brain regions in monkeys performing a multi-dimensional inference task requiring them to infer hidden…
Mingcong Wu, Alessandro Giuliani
This paper investigates robust high-dimensional convoluted rank regression in distributed environments. We propose an estimation method suitable for sparse regimes, which remains effective under heavy-tailed errors and outliers, as it does not impose moment assumptions on the noise distribution. To facilitate scalable…
Xizhao Li, Ning Xu, Qingjia Chi, Hu Chen
To address the challenge of cooperative roundup of maneuvering targets under limited perception, this paper proposes TransMARL, a transformer-based multi-agent reinforcement learning framework for observation-constrained coordination. The roundup task is formulated as a decentralized partially observable Markov…
Li Wan, Bin Zhang, Lin Xu
The rapid evolution of social networks has positioned multimodal content, including text, images, and audio, as a pivotal medium for self-expression and public sentiment analysis. However, existing multimodal fusion methods are often limited by privacy risks, parameter redundancy, and insufficient exploitation of…
Chao Li, Yanfei Liu, Jieling Wang, Zhong Wang + 2 more
Multi-agent reinforcement learning (MARL) relies on trial-and-error interactions to update policies. However, trial-and-error learning typically requires extensive interactions to achieve satisfactory performance, resulting in low sample efficiency, which limits its application in the real world. To reduce the…
Authors not listed
This comprehensive review examines the evolution of autonomous materials synthesis laboratories that integrate artificial intelligence with advanced robotics to accelerate discovery. Traditional materials development pipelines typically require 10-20 years, but self-driving laboratories (SDLs) and Materials…
Authors not listed
Next Generation Risk Assessment (NGRA) promotes animal-free, exposure-informed, and hypothesis-driven approaches to chemical safety assessment. In silico tools, such as quantitative structure-activity relationship (QSAR) models, are valuable new approach methodologies (NAMs) for use in NGRA. However, the practical…
Pranav Mahajan, Ben Seymour
The seminal reward prediction error account of dopamine has been highly successful, but faces several key challenges. Most notable are the difficulty of learning multiple rewards simultaneously, inefficient on-policy learning, and accounting for the heterogeneous striatal responses observed across and within striatal…
Pranav Mahajan, Ben Seymour
The seminal reward prediction error theory of dopamine function faces several key challenges. Most notable is the difficulty learning multiple rewards simultaneously, inefficient on-policy learning, and accounting for heterogeneous striatal responses in the tail of the striatum. We propose a normative framework, based…
David G. Clark, Blake Bordelon, Jacob A. Zavatone-Veth, Cengiz Pehlevan
Across many brain areas, neurons produce heterogeneous, seemingly disordered responses. Yet the circuits these neurons comprise cannot be purely random; they must possess some structure to generate representations and computations underlying behavior. How much structure is present in recurrent connectivity relative to…
Jie Zhu, Tianxu Lv, Xiang Pan
Drug target interaction (DTl) prediction is a fundamental task in computational drug discovery. However, most existing DTI models assume a static learning environment, whereas real-world biomedical data are dynamic, characterized by the continuous emergence of new protein families and interaction patterns. This poses…