Loading [MathJax]/jax/element/mml/optable/GeneralPunctuation.js

Feature homophily metric

[1] Chen Y., Luo Y., Tang J., Yang L., Qiu S., Wang C. and Cao X. LSGNN: Towards general graph neural network in node classification by local similarity. 2023.

[2] Jin D., Wang R., Ge M., He D., Li X., Lin W. and Zhang W. RAW-GNN: Random walk aggregation based graph neural network. 2022.

[3] Lee S. Y., Kim S., Bu F., Yoo J., Tang J. and Shin K. Feature distribution on graph topology mediates the effect of graph convolution: Homophily perspective. ICML, 2023.

[4] Yang L., Li M., Liu L., Niu B., Wang C., Cao X. and Guo Y. Diverse message passing for attribute with heterophily. NeurIPS, 2021.

Zheng Y., Luan S. and Chen L. What is missing in homophily? Disentangling graph homophily for graph neural networks. 2024.

收集了一些基于 feature 而不是 label 的 homophily 的指标.

符号说明

  • G=(V,E), 图;
  • XR|V|×M, node features;
  • Nu,, 节点 u 的一阶邻居;

Homophily on Feature Aspect

  • Generalized edge homophily [2]:

    hGE(G,X)=1|E|euvEsim(xu,xv),

    其中 sim(,) 可以是 cosine 相似度, 欧式距离等.

  • Local Similarity [1]:

    hLScos(G,X)=1|V|uV1duvNusim(xu,xv).

  • Attribute homophily:

    hattr,m(G,X:,m)=1uVXu,muV(Xu,mvNuXv,mdu),hattr(G,X)=Mm=1hattr,m(G,X:,m).

  • Class-controlled feature homophily [3]:

    hCF(G,X,Y)=1|V|vV1duvNu(d(v,V{u}),d(v,{u})),d(u,V)=1|V|vV

posted @   馒头and花卷  阅读(16)  评论(0编辑  收藏  举报
相关博文:
阅读排行:
· [翻译] 为什么 Tracebit 用 C# 开发
· 腾讯ima接入deepseek-r1,借用别人脑子用用成真了~
· Deepseek官网太卡,教你白嫖阿里云的Deepseek-R1满血版
· DeepSeek崛起:程序员“饭碗”被抢,还是职业进化新起点?
· RFID实践——.NET IoT程序读取高频RFID卡/标签
历史上的今天:
2021-06-30 Sharpness-Aware Minimization for Efficiently Improving Generalization
点击右上角即可分享
微信分享提示