ScaleGNN: Towards Scalable Graph Neural Networks via Adaptive High-order Neighboring Feature Fusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Xiang, Qi, Jianpeng, Liu, Haobing, Cao, Yuan, Chao, Guoqing, Zhao, Zhongying, Dong, Junyu, Liu, Xinwang, Yu, Yanwei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914378961387520
author Li, Xiang
Qi, Jianpeng
Liu, Haobing
Cao, Yuan
Chao, Guoqing
Zhao, Zhongying
Dong, Junyu
Liu, Xinwang
Yu, Yanwei
author_facet Li, Xiang
Qi, Jianpeng
Liu, Haobing
Cao, Yuan
Chao, Guoqing
Zhao, Zhongying
Dong, Junyu
Liu, Xinwang
Yu, Yanwei
contents Graph Neural Networks (GNNs) have demonstrated impressive performance across diverse graph-based tasks by leveraging message passing to capture complex node relationships. However, on large-scale real-world graphs, GNNs face two major challenges: (1) GNNs struggle to ensure scalability and efficiency as repeated aggregation of large neighborhoods incurs significant computational overhead; (2) GNNs suffer from over-smoothing, where excessive propagation makes node representations indistinguishable, hindering model expressiveness. To tackle these, we propose ScaleGNN, which adaptively fuses multi-hop node features for scalable and effective graph learning. We first compute per-hop pure-neighbor matrices to isolate exclusive structural signals, then apply lightweight fusion to balance low- and high-order information, preserving both local detail and global correlations. To curb redundancy and over-smoothing, we introduce Local Contribution Score (LCS)-based masking to prune low-relevance high-order neighbors, and impose learnable sparsity to selectively integrate valuable multi-hop features. Extensive experiments on real-world datasets show that ScaleGNN consistently outperforms state-of-the-art GNNs in both predictive accuracy and computational efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2504_15920
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ScaleGNN: Towards Scalable Graph Neural Networks via Adaptive High-order Neighboring Feature Fusion
Li, Xiang
Qi, Jianpeng
Liu, Haobing
Cao, Yuan
Chao, Guoqing
Zhao, Zhongying
Dong, Junyu
Liu, Xinwang
Yu, Yanwei
Machine Learning
Graph Neural Networks (GNNs) have demonstrated impressive performance across diverse graph-based tasks by leveraging message passing to capture complex node relationships. However, on large-scale real-world graphs, GNNs face two major challenges: (1) GNNs struggle to ensure scalability and efficiency as repeated aggregation of large neighborhoods incurs significant computational overhead; (2) GNNs suffer from over-smoothing, where excessive propagation makes node representations indistinguishable, hindering model expressiveness. To tackle these, we propose ScaleGNN, which adaptively fuses multi-hop node features for scalable and effective graph learning. We first compute per-hop pure-neighbor matrices to isolate exclusive structural signals, then apply lightweight fusion to balance low- and high-order information, preserving both local detail and global correlations. To curb redundancy and over-smoothing, we introduce Local Contribution Score (LCS)-based masking to prune low-relevance high-order neighbors, and impose learnable sparsity to selectively integrate valuable multi-hop features. Extensive experiments on real-world datasets show that ScaleGNN consistently outperforms state-of-the-art GNNs in both predictive accuracy and computational efficiency.
title ScaleGNN: Towards Scalable Graph Neural Networks via Adaptive High-order Neighboring Feature Fusion
topic Machine Learning
url https://arxiv.org/abs/2504.15920