English
Related papers

Related papers: Adaptive Message Passing: A General Framework to M…

200 papers

Graph neural networks have shown significant success in the field of graph representation learning. Graph convolutions perform neighborhood aggregation and represent one of the most important graph operations. Nevertheless, one layer of…

Machine Learning · Computer Science 2020-07-21 Meng Liu , Hongyang Gao , Shuiwang Ji

In this paper, we study the factors that contribute to the effect of oversmoothing in deep Graph Neural Networks (GNNs). Specifically, our analysis is based on a new metric (Mean Average Squared Distance - $MASED$) to quantify the extent of…

Machine Learning · Computer Science 2025-10-08 Dimitrios Kelesis , Dimitris Fotakis , Georgios Paliouras

Graph Neural Networks (GNNs) have become a popular approach for various applications, ranging from social network analysis to modeling chemical properties of molecules. While GNNs often show remarkable performance on public datasets, they…

Machine Learning · Computer Science 2022-02-03 Krzysztof Sadowski , Michał Szarmach , Eddie Mattia

In recent years, Graph Neural Networks (GNNs) have been popular in the graph classification task. Currently, shallow GNNs are more common due to the well-known over-smoothing problem facing deeper GNNs. However, they are sub-optimal without…

Machine Learning · Computer Science 2023-02-20 Lanning Wei , Zhiqiang He , Huan Zhao , Quanming Yao

The message-passing paradigm of Graph Neural Networks often struggles with exchanging information across distant nodes typically due to structural bottlenecks in certain graph regions, a limitation known as \textit{over-squashing}. To…

Machine Learning · Computer Science 2025-06-23 Langzhang Liang , Fanchen Bu , Zixing Song , Zenglin Xu , Shirui Pan , Kijung Shin

Graph neural networks (GNNs) have emerged as powerful tools for processing relational data in applications. However, GNNs suffer from the problem of oversmoothing, the property that the features of all nodes exponentially converge to the…

Machine Learning · Statistics 2025-05-22 Bastian Epping , Alexandre René , Moritz Helias , Michael T. Schaub

Graph Neural Networks learn on graph-structured data by iteratively aggregating local neighborhood information. While this local message passing paradigm imparts a powerful inductive bias and exploits graph sparsity, it also yields three…

Machine Learning · Computer Science 2025-11-07 Ryien Hosseini , Filippo Simini , Venkatram Vishwanath , Rebecca Willett , Henry Hoffmann

Graph-based environments pose unique challenges to multi-agent reinforcement learning. In decentralized approaches, agents operate within a given graph and make decisions based on partial or outdated observations. The size of the observed…

Multiagent Systems · Computer Science 2024-06-05 Jannis Weil , Zhenghua Bao , Osama Abboud , Tobias Meuser

Hypergraph networks are closer to real life because they can reflect higher-order interactions, so researchers have begun using them to build models for real-world networks. The mean-field approach is the current tool for studying the…

Physics and Society · Physics 2023-03-01 Hao Peng , Cheng Qian , Dandan Zhao , Ming Zhong , Jianmin Han , Runchao Li , Wei Wang

Strategies to improve the predicting performance of Message-Passing Neural-Networks for molecular property predictions can be achieved by simplifying how the message is passed and by using descriptors that capture multiple aspects of…

Machine Learning · Computer Science 2025-10-22 Alma C. Castaneda-Leautaud , Rommie E. Amaro

The ability to scale out training workloads has been one of the key performance enablers of deep learning. The main scaling approach is data-parallel GPU-based training, which has been boosted by hardware and software support for highly…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-01-02 Ilia Markov , Hamidreza Ramezanikebrya , Dan Alistarh

New ideas and technologies adopted by a small number of individuals occasionally spread globally through a complex web of social ties. Here, we present a simple and general approximation method, namely, a message-passing approach, that…

Physics and Society · Physics 2022-09-01 Teruyoshi Kobayashi , Tomokatsu Onaga

Graph neural networks have been a powerful tool for mesh-based physical simulation. To efficiently model large-scale systems, existing methods mainly employ hierarchical graph structures to capture multi-scale node relations. However, these…

Machine Learning · Computer Science 2025-05-22 Huayu Deng , Xiangming Zhu , Yunbo Wang , Xiaokang Yang

Node features of graph neural networks (GNNs) tend to become more similar with the increase of the network depth. This effect is known as over-smoothing, which we axiomatically define as the exponential convergence of suitable similarity…

Machine Learning · Computer Science 2023-03-21 T. Konstantin Rusch , Michael M. Bronstein , Siddhartha Mishra

We propose a unified framework for adaptive connection sampling in graph neural networks (GNNs) that generalizes existing stochastic regularization methods for training GNNs. The proposed framework not only alleviates over-smoothing and…

The quality of signal propagation in message-passing graph neural networks (GNNs) strongly influences their expressivity as has been observed in recent works. In particular, for prediction tasks relying on long-range interactions, recursive…

Machine Learning · Computer Science 2022-08-09 Pradeep Kr. Banerjee , Kedar Karhadkar , Yu Guang Wang , Uri Alon , Guido Montúfar

Comparing networks is essential for a number of downstream tasks, from clustering to anomaly detection. Despite higher-order interactions being critical for understanding the dynamics of complex systems, traditional approaches for network…

Physics and Society · Physics 2025-11-03 Helcio Felippe , Alec Kirkley , Federico Battiston

Message passing has become the dominant framework in graph representation learning. The essential idea of the message-passing framework is to update node embeddings based on the information aggregated from local neighbours. However, most…

Machine Learning · Computer Science 2024-04-16 Haimin Zhang , Min Xu

Graph neural networks excel at graph representation learning but struggle with heterophilous data and long-range dependencies. And graph transformers address these issues through self-attention, yet face scalability and noise challenges on…

Machine Learning · Computer Science 2025-02-13 Xuanze Chen , Jiajun Zhou , Shanqing Yu , Qi Xuan

\emph{Over-fitting} and \emph{over-smoothing} are two main obstacles of developing deep Graph Convolutional Networks (GCNs) for node classification. In particular, over-fitting weakens the generalization ability on small dataset, while…

Machine Learning · Computer Science 2020-03-13 Yu Rong , Wenbing Huang , Tingyang Xu , Junzhou Huang
‹ Prev 1 3 4 5 6 7 10 Next ›