English
Related papers

Related papers: Exploring Heterophily in Graph-level Tasks

200 papers

Much data with graph structures satisfy the principle of homophily, meaning that connected nodes tend to be similar with respect to a specific attribute. As such, ubiquitous datasets for graph machine learning tasks have generally been…

Machine Learning · Computer Science 2021-07-07 Derek Lim , Xiuyu Li , Felix Hohne , Ser-Nam Lim

Homophily is a graph property describing the tendency of edges to connect similar nodes; the opposite is called heterophily. It is often believed that heterophilous graphs are challenging for standard message-passing graph neural networks…

Social and Information Networks · Computer Science 2024-04-17 Oleg Platonov , Denis Kuznedelev , Artem Babenko , Liudmila Prokhorenkova

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

Machine Learning · Computer Science 2021-09-14 Sitao Luan , Chenqing Hua , Qincheng Lu , Jiaqi Zhu , Mingde Zhao , Shuyuan Zhang , Xiao-Wen Chang , Doina Precup

Graph Neural Networks (GNNs) have achieved significant success in addressing node classification tasks. However, the effectiveness of traditional GNNs degrades on heterophilic graphs, where connected nodes often belong to different labels…

Machine Learning · Computer Science 2025-11-11 Asela Hevapathige , Asiri Wijesinghe , Ahad N. Zehmakan

We propose a novel graph-driven generative model, that unifies multiple heterogeneous learning tasks into the same framework. The proposed model is based on the fact that heterogeneous learning tasks, which correspond to different…

Machine Learning · Computer Science 2019-11-21 Wenlin Wang , Hongteng Xu , Zhe Gan , Bai Li , Guoyin Wang , Liqun Chen , Qian Yang , Wenqi Wang , Lawrence Carin

Graph Convolutional Networks (GCNs) are predominantly tailored for graphs displaying homophily, where similar nodes connect, but often fail on heterophilic graphs. The strategy of adopting distinct approaches to learn from homophilic and…

Machine Learning · Computer Science 2025-04-09 Han Lei , Jiaxing Xu , Xia Dong , Yiping Ke

Homophily, as a measure, has been critical to increasing our understanding of graph neural networks (GNNs). However, to date this measure has only been analyzed in the context of static graphs. In our work, we explore homophily in dynamic…

Machine Learning · Computer Science 2025-04-30 Michael Ito , Danai Koutra , Jenna Wiens

Existing multiplex graph models often assume homophily, where connected nodes tend to belong to the same class or share similar attributes. Consequently, these models may struggle with graphs exhibiting heterophily, where connected nodes…

Machine Learning · Computer Science 2026-05-14 Kamel Abdous , Nairouz Mrabah , Mohamed Bouguessa

Graph neural networks (GNNs) have shown great prowess in learning representations suitable for numerous graph-based machine learning tasks. When applied to semi-supervised node classification, GNNs are widely believed to work well due to…

Machine Learning · Computer Science 2023-07-24 Yao Ma , Xiaorui Liu , Neil Shah , Jiliang Tang

Graph neural networks (GNNs) have been extensively studied for prediction tasks on graphs. As pointed out by recent studies, most GNNs assume local homophily, i.e., strong similarities in local neighborhoods. This assumption however limits…

Machine Learning · Computer Science 2021-10-04 Sean Li , Dongwoo Kim , Qing Wang

Graph Neural Networks (GNNs) excel at analyzing graph-structured data but struggle on heterophilic graphs, where connected nodes often belong to different classes. While this challenge is commonly addressed with specialized GNN…

Machine Learning · Computer Science 2025-05-20 Harel Mendelman , Haggai Maron , Ronen Talmon

Graph neural networks (GNN) have achieved remarkable success in a wide range of tasks by encoding features combined with topology to create effective representations. However, the fundamental problem of understanding and analyzing how graph…

Machine Learning · Computer Science 2024-04-12 Kailong Wu , Yule Xie , Jiaxin Ding , Yuxiang Ren , Luoyi Fu , Xinbing Wang , Chenghu Zhou

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

Graphs with heterophily have been regarded as challenging scenarios for Graph Neural Networks (GNNs), where nodes are connected with dissimilar neighbors through various patterns. In this paper, we present theoretical understandings of the…

Machine Learning · Computer Science 2024-06-05 Junfu Wang , Yuanfang Guo , Liang Yang , Yunhong Wang

We consider feature representation learning problem of molecular graphs. Graph Neural Networks have been widely used in feature representation learning of molecular graphs. However, most existing methods deal with molecular graphs…

Machine Learning · Computer Science 2022-06-08 Zhaoning Yu , Hongyang Gao

Graph Neural Networks (GNNs) have been predominant for graph learning tasks; however, recent studies showed that a well-known graph algorithm, Label Propagation (LP), combined with a shallow neural network can achieve comparable performance…

Machine Learning · Computer Science 2022-12-01 Zhiqiang Zhong , Sergey Ivanov , Jun Pang

Graph neural networks (GNNs) have emerged as a powerful tool for modeling graph-structured data. However, existing GNNs often struggle with heterophilic graphs, where connected nodes tend to have dissimilar features or labels. While…

Machine Learning · Computer Science 2025-09-17 Ruizhong Qiu , Ting-Wei Li , Gaotang Li , Hanghang Tong

Spectral Graph Neural Networks (GNNs) are gaining attention for their ability to surpass the limitations of message-passing GNNs. They rely on supervision from downstream tasks to learn spectral filters that capture the graph signal's…

Machine Learning · Computer Science 2024-05-24 Junjie Xu , Enyan Dai , Dongsheng Luo , Xiang Zhang , Suhang Wang

Graph convolution networks (GCNs) have been enormously successful in learning representations over several graph-based machine learning tasks. Specific to learning rich node representations, most of the methods have solely relied on the…

Machine Learning · Computer Science 2022-11-03 Ashish Tiwari , Sresth Tosniwal , Shanmuganathan Raman

Graph Neural Networks (GNNs) have emerged as a promising tool to handle data exhibiting an irregular structure. However, most GNN architectures perform well on homophilic datasets, where the labels of neighboring nodes are likely to be the…

Machine Learning · Computer Science 2024-12-03 Victor M. Tenorio , Madeline Navarro , Samuel Rey , Santiago Segarra , Antonio G. Marques