English
Related papers

Related papers: Enhancing the Inductive Biases of Graph Neural ODE…

200 papers

We introduce an approach for imposing physically motivated inductive biases on graph networks to learn interpretable representations and improved zero-shot generalization. Our experiments show that our graph network models, which implement…

Machine Learning · Computer Science 2019-11-04 Miles D. Cranmer , Rui Xu , Peter Battaglia , Shirley Ho

Scientific computing using deep learning has seen significant advancements in recent years. There has been growing interest in models that learn the operator from the parameters of a partial differential equation (PDE) to the corresponding…

Machine Learning · Computer Science 2024-02-14 Sung Woong Cho , Jae Yong Lee , Hyung Ju Hwang

In the trend of hybrid Artificial Intelligence techniques, Physical-Informed Machine Learning has seen a growing interest. It operates mainly by imposing data, learning, or architecture bias with simulation data, Partial Differential…

Machine Learning · Computer Science 2024-08-05 Alexis-Raja Brachet , Pierre-Yves Richard , Céline Hudelot

Graph Neural Networks (GNNs) with equivariant properties have emerged as powerful tools for modeling complex dynamics of multi-object physical systems. However, their generalization ability is limited by the inadequate consideration of…

Machine Learning · Computer Science 2024-03-13 Yang Liu , Jiashun Cheng , Haihong Zhao , Tingyang Xu , Peilin Zhao , Fugee Tsung , Jia Li , Yu Rong

Graph neural networks (GNNs) are widely applied in graph data modeling. However, existing GNNs are often trained in a task-driven manner that fails to fully capture the intrinsic nature of the graph structure, resulting in sub-optimal node…

Machine Learning · Computer Science 2024-07-17 Zhenhua Huang , Kunhao Li , Shaojie Wang , Zhaohong Jia , Wentao Zhu , Sharad Mehrotra

Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by additionally making use of graph structure based on the relational inductive bias (edge bias), rather than treating the nodes as collections of independent and identically…

Machine Learning · Computer Science 2023-11-07 Sitao Luan , Chenqing Hua , Qincheng Lu , Jiaqi Zhu , Xiao-Wen Chang , Doina Precup

The progress in hyperbolic neural networks (HNNs) research is hindered by their absence of inductive bias mechanisms, which are essential for generalizing to new tasks and facilitating scalable learning over large datasets. In this paper,…

Machine Learning · Computer Science 2023-10-31 Nurendra Choudhary , Nikhil Rao , Chandan K. Reddy

A vast majority of spiking neural networks (SNNs) are trained based on inductive biases that are not necessarily a good fit for several critical tasks that require low-latency and power efficiency. Inferring brain behavior based on the…

Neural and Evolutionary Computing · Computer Science 2023-04-20 Xi Chen , Siwei Mai , Konstantinos Michmizos

Graph neural networks (GNNs) have been widely used in deep learning on graphs. They can learn effective node representations that achieve superior performances in graph analysis tasks such as node classification and node clustering.…

Machine Learning · Computer Science 2021-04-19 Jianxin Li , Hao Peng , Yuwei Cao , Yingtong Dou , Hekai Zhang , Philip S. Yu , Lifang He

Graph Neural Networks (GNNs) have shown success in learning from graph structured data containing node/edge feature information, with application to social networks, recommendation, fraud detection and knowledge graph reasoning. In this…

Machine Learning · Computer Science 2021-11-24 Xiang Song , Runjie Ma , Jiahang Li , Muhan Zhang , David Paul Wipf

Classical neural ODEs trained with explicit methods are intrinsically limited by stability, crippling their efficiency and robustness for stiff learning problems that are common in graph learning and scientific machine learning. We present…

Machine Learning · Computer Science 2024-12-17 Hong Zhang , Ying Liu , Romit Maulik

We present a novel model Graph Neural Stochastic Differential Equations (Graph Neural SDEs). This technique enhances the Graph Neural Ordinary Differential Equations (Graph Neural ODEs) by embedding randomness into data representation using…

Machine Learning · Computer Science 2023-08-25 Richard Bergna , Felix Opolka , Pietro Liò , Jose Miguel Hernandez-Lobato

Estimating the structure of directed acyclic graphs (DAGs) of features (variables) plays a vital role in revealing the latent data generation process and providing causal insights in various applications. Although there have been many…

Machine Learning · Computer Science 2024-03-06 Shaohua Fan , Shuyang Zhang , Xiao Wang , Chuan Shi

The incorporation of appropriate inductive bias plays a critical role in learning dynamics from data. A growing body of work has been exploring ways to enforce energy conservation in the learned dynamics by encoding Lagrangian or…

Robotics · Computer Science 2021-11-15 Yaofeng Desmond Zhong , Biswadip Dey , Amit Chakraborty

Graph neural networks have shown remarkable success in exploiting the spatial and temporal patterns on dynamic graphs. However, existing GNNs exhibit poor generalization ability under distribution shifts, which is inevitable in dynamic…

Machine Learning · Computer Science 2025-11-25 Qingyun Sun , Jiayi Luo , Haonan Yuan , Xingcheng Fu , Hao Peng , Jianxin Li , Philip S. Yu

Graph neural networks (GNNs) have been proven to be effective in various network-related tasks. Most existing GNNs usually exploit the low-frequency signals of node features, which gives rise to one fundamental question: is the…

Machine Learning · Computer Science 2021-01-05 Deyu Bo , Xiao Wang , Chuan Shi , Huawei Shen

Learning representations for graphs plays a critical role in a wide spectrum of downstream applications. In this paper, we summarize the limitations of the prior works in three folds: representation space, modeling dynamics and modeling…

Machine Learning · Computer Science 2021-04-07 Li Sun , Zhongbao Zhang , Jiawei Zhang , Feiyang Wang , Hao Peng , Sen Su , Philip S. Yu

Temporal Graph Networks (TGNs) have shown remarkable performance in learning representation for continuous-time dynamic graphs. However, real-world dynamic graphs typically contain diverse and intricate noise. Noise can significantly…

Machine Learning · Computer Science 2023-09-06 Siwei Zhang , Yun Xiong , Yao Zhang , Yiheng Sun , Xi Chen , Yizhu Jiao , Yangyong Zhu

Learning representations of sets of nodes in a graph is crucial for applications ranging from node-role discovery to link prediction and molecule classification. Graph Neural Networks (GNNs) have achieved great success in graph…

Machine Learning · Computer Science 2020-10-30 Pan Li , Yanbang Wang , Hongwei Wang , Jure Leskovec

Heterophilic Graph Neural Networks (HGNNs) have shown promising results for semi-supervised learning tasks on graphs. Notably, most real-world heterophilic graphs are composed of a mixture of nodes with different neighbor patterns,…

Machine Learning · Computer Science 2025-02-26 Jinluan Yang , Zhengyu Chen , Teng Xiao , Wenqiao Zhang , Yong Lin , Kun Kuang
‹ Prev 1 3 4 5 6 7 10 Next ›