Graph-DPP: Sampling diverse neighboring nodes via determinantal point process

Yaping Zheng, Junda Wu, Xiaofeng Zhang, Xiaowen Chu

Research output: Chapter in book/report/conference proceedingConference contributionpeer-review

Abstract

Recently, various graph neural network based approaches have been proposed to learn graph feature representations. However, there exists a long-term outstanding issue, i.e., over-smoothing problem. That is, when convoluting deeper neighboring nodes, the feature difference gradually vanishes. To address this issue, this paper proposes a novel determinantal point process based sampling strategy, called Graph-DPP, to sample diverse neighboring nodes for convolution. The target of diversified sampling is to maximize the relevance between sampled nodes and target node and simultaneously minimize the similarity between any two sampled nodes. To this end, we first adapt the Hawkes process to calculate feature similarity between any two neighboring nodes. Then, their structural similarity value is calculated. Both feature and structural similarity are used to generate the positive semi-definite similarity matrix for the later sampling. To the best of our knowledge, this is among the first attempts to integrate determinantal point process technique with graph neural network model. To evaluate the model performance, the proposed Graph-DPP strategy is respectively combined with GCN, GAT and GraphSAGE, and then are performed on three datasets. Experimental results show that the proposed Graph-DPP sampling strategy could achieve the state-of-the-art model performance.

Original languageEnglish
Title of host publicationProceedings - 2020 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2020
EditorsJing He, Hemant Purohit, Guangyan Huang, Xiaoying Gao, Ke Deng
PublisherIEEE
Pages540-545
Number of pages6
ISBN (Electronic)9781665419246
ISBN (Print)9781665430173
DOIs
Publication statusPublished - Dec 2020
Event2020 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2020 - Virtual, Online, Melbourne, Australia
Duration: 14 Dec 202017 Dec 2020

Publication series

NameProceedings - IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT

Conference

Conference2020 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2020
Country/TerritoryAustralia
CityMelbourne
Period14/12/2017/12/20

Scopus Subject Areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Software

User-Defined Keywords

  • Determinantal Point Process
  • Graph Embedding
  • Graph Neural Network

Fingerprint

Dive into the research topics of 'Graph-DPP: Sampling diverse neighboring nodes via determinantal point process'. Together they form a unique fingerprint.

Cite this