Combining Graph Convolutional Neural Networks and Label Propagation

Author:

Wang Hongwei1ORCID,Leskovec Jure1

Affiliation:

1. Stanford University, CA, United States

Abstract

Label Propagation Algorithm (LPA) and Graph Convolutional Neural Networks (GCN) are both message passing algorithms on graphs. Both solve the task of node classification, but LPA propagates node label information across the edges of the graph, while GCN propagates and transforms node feature information. However, while conceptually similar, theoretical relationship between LPA and GCN has not yet been systematically investigated. Moreover, it is unclear how LPA and GCN can be combined under a unified framework to improve the performance. Here we study the relationship between LPA and GCN in terms of feature/label influence , in which we characterize how much the initial feature/label of one node influences the final feature/label of another node in GCN/LPA. Based on our theoretical analysis, we propose an end-to-end model that combines GCN and LPA. In our unified model, edge weights are learnable, and the LPA serves as regularization to assist the GCN in learning proper edge weights that lead to improved performance. Our model can also be seen as learning the weights of edges based on node labels, which is more direct and efficient than existing feature-based attention models or topology-based diffusion models. In a number of experiments for semi-supervised node classification and knowledge-graph-aware recommendation, our model shows superiority over state-of-the-art baselines.

Funder

DARPA

ARO

NSF

NIH

Stanford Data Science Initiative

Wu Tsai Neurosciences Institute

Chan Zuckerberg Biohub

Amazon

JPMorgan Chase

Docomo

Hitachi

Intel

JD.com

KDDI

NVIDIA

Dell

Toshiba

Visa

UnitedHealth Group

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Science Applications,General Business, Management and Accounting,Information Systems

Reference49 articles.

1. On the Equivalence of Decoupled Graph Convolution Network and Label Propagation

2. Label propagation via teaching-to-learn and learning-to-teach;Gong Chen;IEEE Trans. Neural Netw. Learn. Syst.,2016

Cited by 26 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Unified structure-aware feature learning for Graph Convolutional Network;Expert Systems with Applications;2024-11

2. Adversarially deep interative-fused embedding clustering via joint self-supervised networks;Neurocomputing;2024-10

3. Revisiting Attack-Caused Structural Distribution Shift in Graph Anomaly Detection;IEEE Transactions on Knowledge and Data Engineering;2024-09

4. Solving Interactive Video Object Segmentation with Label-Propagating Neural Networks;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

5. A Structure-Aware Graph Representation Learning Optimization;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3