Saved in:
Bibliographic Details
Main Authors: Zhou, Jiajun, Xie, Chenxuan, Gong, Shengbo, Qian, Jiaxu, Yu, Shanqing, Xuan, Qi, Yang, Xiaoniu
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2306.13532
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929467018969088
author Zhou, Jiajun
Xie, Chenxuan
Gong, Shengbo
Qian, Jiaxu
Yu, Shanqing
Xuan, Qi
Yang, Xiaoniu
author_facet Zhou, Jiajun
Xie, Chenxuan
Gong, Shengbo
Qian, Jiaxu
Yu, Shanqing
Xuan, Qi
Yang, Xiaoniu
contents Real-world graphs exhibit increasing heterophily, where nodes no longer tend to be connected to nodes with the same label, challenging the homophily assumption of classical graph neural networks (GNNs) and impeding their performance. Intriguingly, from the observation of heterophilous data, we notice that certain high-order information exhibits higher homophily, which motivates us to involve high-order information in node representation learning. However, common practices in GNNs to acquire high-order information mainly through increasing model depth and altering message-passing mechanisms, which, albeit effective to a certain extent, suffer from three shortcomings: 1) over-smoothing due to excessive model depth and propagation times; 2) high-order information is not fully utilized; 3) low computational efficiency. In this regard, we design a similarity-based path sampling strategy to capture smooth paths containing high-order homophily. Then we propose a lightweight model based on multi-layer perceptrons (MLP), named PathMLP, which can encode messages carried by paths via simple transformation and concatenation operations, and effectively learn node representations in heterophilous graphs through adaptive path aggregation. Extensive experiments demonstrate that our method outperforms baselines on 16 out of 20 datasets, underlining its effectiveness and superiority in alleviating the heterophily problem. In addition, our method is immune to over-smoothing and has high computational efficiency. The source code will be available in https://github.com/Graph4Sec-Team/PathMLP.
format Preprint
id arxiv_https___arxiv_org_abs_2306_13532
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle PathMLP: Smooth Path Towards High-order Homophily
Zhou, Jiajun
Xie, Chenxuan
Gong, Shengbo
Qian, Jiaxu
Yu, Shanqing
Xuan, Qi
Yang, Xiaoniu
Machine Learning
Social and Information Networks
Real-world graphs exhibit increasing heterophily, where nodes no longer tend to be connected to nodes with the same label, challenging the homophily assumption of classical graph neural networks (GNNs) and impeding their performance. Intriguingly, from the observation of heterophilous data, we notice that certain high-order information exhibits higher homophily, which motivates us to involve high-order information in node representation learning. However, common practices in GNNs to acquire high-order information mainly through increasing model depth and altering message-passing mechanisms, which, albeit effective to a certain extent, suffer from three shortcomings: 1) over-smoothing due to excessive model depth and propagation times; 2) high-order information is not fully utilized; 3) low computational efficiency. In this regard, we design a similarity-based path sampling strategy to capture smooth paths containing high-order homophily. Then we propose a lightweight model based on multi-layer perceptrons (MLP), named PathMLP, which can encode messages carried by paths via simple transformation and concatenation operations, and effectively learn node representations in heterophilous graphs through adaptive path aggregation. Extensive experiments demonstrate that our method outperforms baselines on 16 out of 20 datasets, underlining its effectiveness and superiority in alleviating the heterophily problem. In addition, our method is immune to over-smoothing and has high computational efficiency. The source code will be available in https://github.com/Graph4Sec-Team/PathMLP.
title PathMLP: Smooth Path Towards High-order Homophily
topic Machine Learning
Social and Information Networks
url https://arxiv.org/abs/2306.13532