paper-with-me

홈 › Papers

PC-Conv: Unifying Homophily and Heterophily with Two-fold Filtering

2023-12-22 · Bingheng Li, Erlin Pan, Zhao Kang

Recently, many carefully crafted graph representation learning methods have achieved impressive performance on either strong heterophilic or homophilic graphs, but not both. Therefore, they are incapable of generalizing well across real-world graphs with different levels of homophily. This is attributed to their neglect of homophily in heterophilic graphs, and vice versa. In this paper, we propose a two-fold filtering mechanism to extract homophily in heterophilic graphs and vice versa. In particular, we extend the graph heat equation to perform heterophilic aggregation of global information from a long distance. The resultant filter can be exactly approximated by the Possion-Charlier (PC) polynomials. To further exploit information at multiple orders, we introduce a powerful graph convolution PC-Conv and its instantiation PCNet for the node classification task. Compared with state-of-the-art GNNs, PCNet shows competitive performance on well-known homophilic and heterophilic graphs. Our implementation is available at https://github.com/uestclbh/PC-Conv.

📄 PDF Abstract BibTeX arXiv:2312.14438

Code (1)

uestclbh/pc-conv 공식 구현 pytorch

Tasks

Graph Representation LearningNode ClassificationRepresentation Learning

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Finding the Missing-half: Graph Complementary Learning for Homophily-prone and Heterophily-prone Graphs

2023-06-13 · Yizhen Zheng, He Zhang, Vincent CS Lee, Yu Zheng 외

Real-world graphs generally have only one kind of tendency in their connections. These connections are either homophily-prone or heterophily-prone. While graphs with homophily-prone edges tend to connect nodes with the s…

Powerful Graph Convolutioal Networks with Adaptive Propagation Mechanism for Homophily and Heterophily

2021-12-27 · Tao Wang, Rui Wang, Di Jin, Dongxiao He 외

Graph Convolutional Networks (GCNs) have been widely applied in various fields due to their significant power on processing graph-structured data. Typical GCN and its variants work under a homophily assumption (i.e., nod…

Attribute

RAW-GNN: RAndom Walk Aggregation based Graph Neural Network

2022-06-28 · Di Jin, Rui Wang, Meng Ge, Dongxiao He 외

Graph-Convolution-based methods have been successfully applied to representation learning on homophily graphs where nodes with the same label or similar attributes tend to connect with one another. Due to the homophily a…

Graph Neural NetworkRepresentation Learning

Unifying Homophily and Heterophily Network Transformation via Motifs

2020-12-21 · Yan Ge, Jun Ma, Li Zhang, Haiping Lu

Higher-order proximity (HOP) is fundamental for most network embedding methods due to its significant effects on the quality of node embedding and performance on downstream network analysis tasks. Most existing HOP defin…

Computational EfficiencyNetwork EmbeddingNode ClassificationPrediction

H$^3$GNNs: Harmonizing Heterophily and Homophily in GNNs via Joint Structural Node Encoding and Self-Supervised Learning

2025-04-16 · Rui Xue, Tianfu Wu

Graph Neural Networks (GNNs) struggle to balance heterophily and homophily in representation learning, a challenge further amplified in self-supervised settings. We propose H$^3$GNNs, an end-to-end self-supervised learni…

Representation LearningSelf-Supervised Learning