English
Related papers

Related papers: Graph Attention Inference of Network Topology in M…

200 papers

We introduce Attention Graphs, a new tool for mechanistic interpretability of Graph Neural Networks (GNNs) and Graph Transformers based on the mathematical equivalence between message passing in GNNs and the self-attention mechanism in…

Machine Learning · Computer Science 2025-02-26 Batu El , Deepro Choudhury , Pietro Liò , Chaitanya K. Joshi

This paper presents a comprehensive study on stock price prediction, leveragingadvanced machine learning (ML) and deep learning (DL) techniques to improve financial forecasting accuracy. The research evaluates the performance of various…

Statistical Finance · Quantitative Finance 2025-02-25 Daksh Dave , Gauransh Sawhney , Vikhyat Chauhan

Modelling long-range dependencies is critical for scene understanding tasks in computer vision. Although convolution neural networks (CNNs) have excelled in many vision tasks, they are still limited in capturing long-range structured…

Computer Vision and Pattern Recognition · Computer Science 2022-09-21 Li Zhang , Mohan Chen , Anurag Arnab , Xiangyang Xue , Philip H. S. Torr

Autonomous mobility-on-demand (AMoD) systems represent a rapidly developing mode of transportation wherein travel requests are dynamically handled by a coordinated fleet of robotic, self-driving vehicles. Given a graph representation of the…

Systems and Control · Electrical Eng. & Systems 2021-08-17 Daniele Gammelli , Kaidi Yang , James Harrison , Filipe Rodrigues , Francisco C. Pereira , Marco Pavone

Autonomous vehicles navigate in dynamically changing environments under a wide variety of conditions, being continuously influenced by surrounding objects. Modelling interactions among agents is essential for accurately forecasting other…

Machine Learning · Computer Science 2021-06-01 Sandra Carrasco , David Fernández Llorca , Miguel Ángel Sotelo

We examine two fundamental tasks associated with graph representation learning: link prediction and node classification. We present a new autoencoder architecture capable of learning a joint representation of local graph structure and…

Machine Learning · Computer Science 2018-11-08 Phi Vu Tran

Link prediction is an important learning task for graph-structured data. In this paper, we propose a novel topological approach to characterize interactions between two nodes. Our topological feature, based on the extended persistent…

Machine Learning · Computer Science 2021-06-15 Zuoyu Yan , Tengfei Ma , Liangcai Gao , Zhi Tang , Chao Chen

We address the problem of learning the legitimacy of other agents in a multiagent network when an unknown subset is comprised of malicious actors. We specifically derive results for the case of directed graphs and where stochastic side…

Multiagent Systems · Computer Science 2024-08-06 Orhan Eren Akgün , Arif Kerem Dayı , Stephanie Gil , Angelia Nedić

Safe and efficient navigation in dynamic environments shared with humans remains an open and challenging task for mobile robots. Previous works have shown the efficacy of using reinforcement learning frameworks to train policies for…

Robotics · Computer Science 2024-01-15 Yanying Zhou , Jochen Garcke

This paper studies consensus problems for multi-agent systems defined on directed graphs where the consensus dynamics involves nonlinear and discontinuous functions. Sufficient conditions, involving the nonlinear functions and the topology…

Optimization and Control · Mathematics 2017-05-16 J. Wei , A. R. F. Everts , M. K. Camlibel , A. J. van der Schaft

From pedestrians to Kuramoto oscillators, interactions between agents govern how dynamical systems evolve in space and time. Discovering how these agents relate to each other has the potential to improve our understanding of the often…

Machine Learning · Computer Science 2025-03-12 Yulong Yang , Bowen Feng , Keqin Wang , Naomi Ehrich Leonard , Adji Bousso Dieng , Christine Allen-Blanchette

Deep reinforcement learning in continuous domains focuses on learning control policies that map states to distributions over actions that ideally concentrate on the optimal choices in each step. In multi-agent navigation problems, the…

Robotics · Computer Science 2022-10-20 Chenning Yu , Hongzhan Yu , Sicun Gao

This paper proposes a novel problem: vision-based perception to learn and predict the collective dynamics of multi-agent systems, specifically focusing on interaction strength and convergence time. Multi-agent systems are defined as…

Multiagent Systems · Computer Science 2024-11-12 Minah Lee , Uday Kamal , Saibal Mukhopadhyay

Many potential applications of reinforcement learning in the real world involve interacting with other agents whose numbers vary over time. We propose new neural policy architectures for these multi-agent problems. In contrast to other…

Machine Learning · Computer Science 2019-06-03 Matthew A. Wright , Roberto Horowitz

Network topology inference is a prominent problem in Network Science. Most graph signal processing (GSP) efforts to date assume that the underlying network is known, and then analyze how the graph's algebraic and spectral characteristics…

Signal Processing · Electrical Eng. & Systems 2019-05-22 Gonzalo Mateos , Santiago Segarra , Antonio G. Marques , Alejandro Ribeiro

Networks in nature have complex interactions among agents. One significant phenomenon induced by interactions is synchronization of coupled agents, and the interactive network topology can be tuned to optimize synchronization. The previous…

Physics and Society · Physics 2021-08-26 Ying Tang , Dinghua Shi , Linyuan Lü

In this work, we aim to predict the future motion of vehicles in a traffic scene by explicitly modeling their pairwise interactions. Specifically, we propose a graph neural network that jointly predicts the discrete interaction modes and…

Machine Learning · Statistics 2019-12-18 Donsuk Lee , Yiming Gu , Jerrick Hoang , Micol Marchetti-Bowick

Memory emerges as the core module in the Large Language Model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game playing, scientific discovery), where memory can enable knowledge accumulation, iterative…

Deep neural networks can be powerful tools, but require careful application-specific design to ensure that the most informative relationships in the data are learnable. In this paper, we apply deep neural networks to the nonlinear…

Machine Learning · Computer Science 2019-12-04 Matthew A. Wright , Simon F. G. Ehlers , Roberto Horowitz

This paper addresses the problem of positive consensus of directed multi-agent systems with observer-type output-feedback protocols. More specifically, directed graph is used to model the communication topology of the multi-agent system and…

Optimization and Control · Mathematics 2020-09-02 Nachuan Yang , Yonghua Yin , Jinrong Liu