English
Related papers

Related papers: Gumbel-MPNN: Graph Rewiring with Gumbel-Softmax

200 papers

Graph Neural Networks are powerful models for learning from graph-structured data, yet their effectiveness is often limited by two critical challenges: over-squashing, where information from distant nodes is excessively compressed, and…

Machine Learning · Computer Science 2026-05-05 Hugo Attali , Nathalie Pernelle , Davide Buscaldi , Fragkiskos D. Malliaros

Graph Neural Networks are powerful models for learning from graph-structured data, yet their effectiveness is often limited by two critical challenges: over-squashing, where information from distant nodes is excessively compressed, and…

Machine Learning · Computer Science 2026-05-04 Hugo Attali , Davide Buscaldi , Nathalie Pernelle , Fragkiskos D. Malliaros

Graph neural networks (GNNs) have shown promise in addressing graph-related problems, including node classification. However, conventional GNNs assume an even distribution of data across classes, which is often not the case in real-world…

Machine Learning · Computer Science 2023-10-16 Zirui Liang , Yuntao Li , Tianjin Huang , Akrati Saxena , Yulong Pei , Mykola Pechenizkiy

Maximizing the spectral gap through graph rewiring has been proposed to enhance the performance of message-passing graph neural networks (GNNs) by addressing over-squashing. However, as we show, minimizing the spectral gap can also improve…

Machine Learning · Computer Science 2025-02-10 Celia Rubio-Madrigal , Adarsh Jamadandi , Rebekka Burkholz

Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by using graph structures based on the relational inductive bias (homophily assumption). While GNNs have been commonly believed to outperform NNs in real-world tasks, recent…

Machine Learning · Computer Science 2022-10-17 Sitao Luan , Chenqing Hua , Qincheng Lu , Jiaqi Zhu , Mingde Zhao , Shuyuan Zhang , Xiao-Wen Chang , Doina Precup

Graph neural networks (GNNs) achieve strong performance on homophilic graphs but often struggle under heterophily, where adjacent nodes frequently belong to different classes. We propose an interpretable and adaptive framework for…

Machine Learning · Computer Science 2025-12-30 Soroush Vahidi

We study the task of node classification for graph neural networks (GNNs) and establish a connection between group fairness, as measured by statistical parity and equal opportunity, and local assortativity, i.e., the tendency of linked…

Social and Information Networks · Computer Science 2022-11-16 Donald Loveland , Jiong Zhu , Mark Heimann , Ben Fish , Michael T. Schaub , Danai Koutra

Graph Neural Networks (GNNs) are popular models for machine learning on graphs that typically follow the message-passing paradigm, whereby the feature of a node is updated recursively upon aggregating information over its neighbors. While…

Machine Learning · Computer Science 2024-05-07 Federico Barbero , Ameya Velingker , Amin Saberi , Michael Bronstein , Francesco Di Giovanni

Homophily principle, i.e., nodes with the same labels are more likely to be connected, has been believed to be the main reason for the performance superiority of Graph Neural Networks (GNNs) over Neural Networks on node classification…

Social and Information Networks · Computer Science 2024-01-03 Sitao Luan , Chenqing Hua , Minkai Xu , Qincheng Lu , Jiaqi Zhu , Xiao-Wen Chang , Jie Fu , Jure Leskovec , Doina Precup

Homophily principle, \ie{} nodes with the same labels or similar attributes are more likely to be connected, has been commonly believed to be the main reason for the superiority of Graph Neural Networks (GNNs) over traditional Neural…

Graph Neural Networks (GNNs) are powerful deep learning methods for Non-Euclidean data. Popular GNNs are message-passing algorithms (MPNNs) that aggregate and combine signals in a local graph neighborhood. However, shallow MPNNs tend to…

Machine Learning · Statistics 2022-11-08 Ningyuan Huang , Soledad Villar , Carey E. Priebe , Da Zheng , Chengyue Huang , Lin Yang , Vladimir Braverman

Graph Neural Networks (GNNs) have achieved great success but are often considered to be challenged by varying levels of homophily in graphs. Recent \textit{empirical} studies have surprisingly shown that homophilic GNNs can perform well…

Machine Learning · Computer Science 2025-10-27 Ming Gu , Zhuonan Zheng , Sheng Zhou , Meihan Liu , Jiawei Chen , Tanyu Qiao , Liangcheng Li , Jiajun Bu

Graph Neural Networks have become one of the indispensable tools to learn from graph-structured data, and their usefulness has been shown in wide variety of tasks. In recent years, there have been tremendous improvements in architecture…

Machine Learning · Statistics 2021-11-15 Sunil Kumar Maurya , Xin Liu , Tsuyoshi Murata

Graph rewiring has emerged as a key technique to alleviate over-squashing in Graph Neural Networks (GNNs) and Graph Transformers by modifying the graph topology to improve information flow. While effective, rewiring inherently alters the…

Machine Learning · Computer Science 2025-10-24 Alexandre Benoit , Catherine Aitken , Yu He

While Graph Neural Networks (GNNs) have achieved remarkable success, their design largely relies on empirical intuition rather than theoretical understanding. In this paper, we present a comprehensive analysis of GNN behavior through three…

Machine Learning · Computer Science 2025-02-04 Qin Jiang , Chengjia Wang , Michael Lones , Wei Pang

In computer science, there exist a large number of optimization problems defined on graphs, that is to find a best node state configuration or a network structure such that the designed objective function is optimized under some…

Machine Learning · Computer Science 2020-04-17 Yaoxin Li , Jing Liu , Guozheng Lin , Yueyuan Hou , Muyun Mou , Jiang Zhang

Graph Neural Networks (GNNs) have been highly successful for the node classification task. GNNs typically assume graphs are homophilic, i.e. neighboring nodes are likely to belong to the same class. However, a number of real-world graphs…

Machine Learning · Computer Science 2024-09-20 Yurui Lai , Taiyan Zhang , Rui Fan

Categorical variables are a natural choice for representing discrete structure in the world. However, stochastic neural networks rarely use categorical latent variables due to the inability to backpropagate through samples. In this work, we…

Machine Learning · Statistics 2017-08-08 Eric Jang , Shixiang Gu , Ben Poole

We investigate graph neural networks on graphs with heterophily. Some existing methods amplify a node's neighborhood with multi-hop neighbors to include more nodes with homophily. However, it is a significant challenge to set personalized…

Machine Learning · Computer Science 2022-05-17 Xiang Li , Renyu Zhu , Yao Cheng , Caihua Shan , Siqiang Luo , Dongsheng Li , Weining Qian

With the rapid development of the World Wide Web (WWW), heterogeneous graphs (HG) have explosive growth. Recently, heterogeneous graph neural network (HGNN) has shown great potential in learning on HG. Current studies of HGNN mainly focus…

Social and Information Networks · Computer Science 2023-02-27 Jiayan Guo , Lun Du , Wendong Bi , Qiang Fu , Xiaojun Ma , Xu Chen , Shi Han , Dongmei Zhang , Yan Zhang