Neural Network based Graph Learning: Model Evolution and Real-World Application

基于神经网络的图学习：模型演化和实际应用

• 批准号: 21K12042
• 负责人: 劉 欣
• 金额: $ 2.66万
• 依托单位: National Institute of Advanced Industrial Science and Technology
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 2021
• 资助国家: 日本
• 起止时间: 2021-04-01 至 2024-03-31
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-21K12042/
• 关键词: Graph Neural Network; Graph Embedding; Node Classification; Dynamic Graph; Imbalanced Graph; Multi-Label Graph; Geometric Learning; Graph Mining; Link Prediction; graph neural network; graph embedding; graph analysis; social network; complex

We have achieved four main outcomes. a) We introduced several key design strategies for GNNs and proposed new models. b) We proposed single-level aggregation scheme for heterogeneous graph embedding, which addresses the down-weighting issue associated with the current bi-level scheme. c) We proposed data generation strategy and new GNN models for tackling the imbalanced graph node classification problem. d) We employed graph learning approach for predicting the donations on live streaming platforms.

我们取得了四项主要成果。a）我们介绍了GNN的几个关键设计策略，并提出了新的模型。B）我们提出了一种用于异构图嵌入的单层聚合方案，该方案解决了与当前双层方案相关联的降权问题。c）提出了解决不平衡图节点分类问题的数据生成策略和新的GNN模型。d）我们采用图学习方法来预测直播平台上的捐赠。

项目成果

PGRA: Projected graph relation-feature attention network for heterogeneous information network embedding

• DOI: 10.1016/j.ins.2021.04.070
• 发表时间: 2021-06-10
• 期刊: INFORMATION SCIENCES
• 影响因子: 8.1
• 作者: Chairatanakul, Nuttapong;Liu, Xin;Murata, Tsuyoshi
• 通讯作者: Murata, Tsuyoshi

Dalian University of Technology(中国)

大连理工大学（中国）

Feature selection: Key to enhance node classification with graph neural networks

特征选择：利用图神经网络增强节点分类的关键

• DOI: 10.1049/cit2.12166
• 发表时间: 2023
• 期刊: CAAI Transactions on Intelligence Technology
• 影响因子: 5.1
• 作者: Maurya Sunil Kumar;Liu Xin;Murata Tsuyoshi
• 通讯作者: Murata Tsuyoshi

Heterogeneous graph embedding with single-level aggregation and infomax encoding

• DOI: 10.1007/s10994-022-06160-5
• 发表时间: 2022-04
• 期刊: Machine Learning
• 影响因子: 7.5
• 作者: Nuttapong Chairatanakul;Xin Liu;Nguyen Thai Hoang;T. Murata

Leaping Through Time with Gradient-based Adaptation for Recommendation

• DOI: 10.1609/aaai.v36i6.20562
• 发表时间: 2021-12
• 作者: Nuttapong Chairatanakul;Hoang NT;Xin Liu;T. Murata