Restructuring Graph for Higher Homophily via Learnable Spectral Clustering

06/06/2022
by   Shouheng Li, et al.
0

While a growing body of literature has been studying new Graph Neural Networks (GNNs) that work on both homophilic and heterophilic graphs, little work has been done on adapting classical GNNs to less-homophilic graphs. Although lacking the ability to work with less-homophilic graphs, classical GNNs still stand out in some properties such as efficiency, simplicity and explainability. We propose a novel graph restructuring method to maximize the benefit of prevalent GNNs with the homophilic assumption. Our contribution is threefold: a) learning the weight of pseudo-eigenvectors for an adaptive spectral clustering that aligns well with known node labels, b) proposing a new homophilic metric that measures how two nodes with the same label are likely to be connected, and c) reconstructing the adjacency matrix based on the result of adaptive spectral clustering to maximize the homophilic scores. The experimental results show that our graph restructuring method can significantly boost the performance of six classical GNNs by an average of 25 less-homophilic graphs. The boosted performance is comparable to state-of-the-art methods.

READ FULL TEXT

page 13

page 16

page 17

research
03/26/2021

Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs

Graph neural networks (GNNs) have been extensively studied for predictio...
research
05/28/2021

SLGCN: Structure Learning Graph Convolutional Networks for Graphs under Heterophily

The performances of GNNs for representation learning on the graph-struct...
research
02/14/2022

Graph Neural Networks for Graphs with Heterophily: A Survey

Recent years have witnessed fast developments of graph neural networks (...
research
05/03/2023

Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering

Graph neural networks (GNNs) based methods have achieved impressive perf...
research
06/03/2020

XGNN: Towards Model-Level Explanations of Graph Neural Networks

Graphs neural networks (GNNs) learn node features by aggregating and com...
research
02/05/2023

Deep Graph-Level Clustering Using Pseudo-Label-Guided Mutual Information Maximization Network

In this work, we study the problem of partitioning a set of graphs into ...
research
06/24/2021

Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs

Graph Neural Networks (GNNs) have shown excellent performance on graphs ...

Please sign up or login with your details

Forgot password? Click here to reset