论文解读(SCAGC)《Self-supervised Contrastive Attributed Graph Clustering》
2022-05-20 21:46
791 查看
论文信息
论文标题:Self-supervised Contrastive Attributed Graph Clustering
论文作者:Wei Xia, Quanxue Gao, Ming Yang, Xinbo Gao
论文来源:2021, arXiv
论文地址:download
论文代码:download
1 Introduction
基于对比学习的图聚类算法存在的问题:
- [li]无法从不精确的聚类标签中获益;
- 需要进行后处理操作才能获得聚类标签;
- 不能解决 out-of-sample(OOS)问题;
本文比较简单,不做过多赘述。
2 Method
总体框架如下:
组件:
- [li]Shared Graph Convolutional Encoder
- Self-Supervised GCRL Module
- Contrastive Clustering Module
算法
3 Experiment
数据集
聚类结果
相关文章推荐
- 论文解读(Survey)《Self-supervised Learning on Graphs: Contrastive, Generative,or Predictive》第一部分:问题阐述
- 论文解读(S^3-CL)《Structural and Semantic Contrastive Learning for Self-supervised Node Representation Learning》
- 论文解读(Survey)《Self-supervised Learning on Graphs: Contrastive, Generative,or Predictive》第二部分:对比学习
- 论文解读(MCGC)《Multi-view Contrastive Graph Clustering》
- 论文解读(SCGC)《Simple Contrastive Graph Clustering》
- 论文解读(CGC)《CGC: Contrastive Graph Clustering for Community Detection and Tracking》
- 论文解读(SupCosine)《Supervised Contrastive Learning with Structure Inference for Graph Classification》
- 论文解读(DGB)《Self-supervised Graph Representation Learning via Bootstrapping》
- 论文解读(MLGCL)《Multi-Level Graph Contrastive Learning》
- 论文解读(IGSD)《Iterative Graph Self-Distillation》
- 论文解读(GraphCL)《Graph Contrastive Learning with Augmentations》
- 《Knowledge Transfer from Multiple Self-supervised Learning Tasks via Graph Distillation 对于视频分类》论文笔记
- 论文解读(SAGPool)《Self-Attention Graph Pooling》
- 论文解读(CSSL)《Contrastive Self-supervised Learning for Graph Classification》
- 论文解读(SimGRACE)《SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation》
- NRL论文解读:《Deep Network Embedding for Graph Representation Learning in Signed Networks》
- 论文解读(MCNS)《Understanding Negative Sampling in Graph RepresentationLearning》
- CVPR 2016 Structural-RNN: Deep Learning on Spatio-Temporal Graphs 论文解读
- 3.《SEMI-SUPERVISED CLASSIFICATION WITH GRAPH CONVOLUTIONAL NETWORKS》论文理解
- 论文解读SDCN《Structural Deep Clustering Network》