Propagation is All You Need: A New Framework for Representation Learning and Classifier Training on Graphs

Jiaming Zhuo, Can Cui, Kun Fu, Bingxin Niu, Dongxiao He, Yuanfang Guo, Zhen Wang, Chuan Wang, Xiaochun Cao, Liang Yang

科研成果: 书/报告/会议事项章节会议稿件同行评审

4 引用 (Scopus)

摘要

Graph Neural Networks (GNNs) have been the standard toolkit for processing non-euclidean spatial data since their powerful capability in graph representation learning. Unfortunately, their training strategy for network parameters is inefficient since it is directly inherited from classic Neural Networks (NNs), ignoring the characteristic of GNNs. To alleviate this issue, experimental analyses are performed to investigate the knowledge captured in classifier parameters during network training. We conclude that the parameter features, i.e., the column vectors of the classifier parameter matrix, are cluster representations with high discriminability. And after a theoretical analysis, we conclude that the discriminability of these features is obtained from the feature propagation from nodes to parameters. Furthermore, an experiment verifies that compared with cluster centroids, the parameter features are more potential for augmenting the feature propagation between nodes. Accordingly, a novel GNN-specific training framework is proposed by simultaneously updating node representations and classifier parameters via a unified feature propagation scheme. Moreover, two augmentation schemes are implemented for the framework, named Full Propagation Augmentation (FPA) and Simplified Full Propagation Augmentation (SFPA). Specifically, FPA augmentates the feature propagation of each node with the updated classifier parameters. SFPA only augments nodes with the classifier parameters corresponding to their clusters. Theoretically, FPA is equivalent to optimizing a novel graph learning objective, which demonstrates the universality of the proposed framework to existing GNNs. Extensive experiments demonstrate the superior performance and the universality of the proposed framework.

源语言英语
主期刊名MM 2023 - Proceedings of the 31st ACM International Conference on Multimedia
出版商Association for Computing Machinery, Inc
481-489
页数9
ISBN(电子版)9798400701085
DOI
出版状态已出版 - 26 10月 2023
活动31st ACM International Conference on Multimedia, MM 2023 - Ottawa, 加拿大
期限: 29 10月 20233 11月 2023

出版系列

姓名MM 2023 - Proceedings of the 31st ACM International Conference on Multimedia

会议

会议31st ACM International Conference on Multimedia, MM 2023
国家/地区加拿大
Ottawa
时期29/10/233/11/23

指纹

探究 'Propagation is All You Need: A New Framework for Representation Learning and Classifier Training on Graphs' 的科研主题。它们共同构成独一无二的指纹。

引用此