当前位置:网站首页>[reading notes] Figure comparative learning gnn+cl
[reading notes] Figure comparative learning gnn+cl
2022-07-05 09:16:00 【Virgo programmer's friend】
source : https://mp.weixin.qq.com/s/X7gxlcY-PaQ97MiEJmKfbg
For a given large number of unlabeled graph data , The graph contrast learning algorithm aims to train a graph encoder , At present, it generally refers to graph neural network (Graph Neural Network, GNN). By this GNN The encoded graph represents the vector , The characteristics of graph data can be well preserved .
Graph Contrastive Learning with Augmentations. NeurIPS 2020.
Algorithm steps :
1. Random sampling of a batch (batch) chart
2. Perform random data enhancement twice for each graph ( Add / delete edge / Discard nodes ) Get the new picture (view)
3. Use the to be trained GNN Yes View Encoding , Get the node representation vector (node representation) And graph represents vector (graph representations)
4. Calculate according to the above representation vector InfoNCE Loss , Among them, the same graph Enhanced view Are close to each other , By different graph Enhanced view Are far away from each other ;【 Features are enhanced 】
【 Heuristic graph data enhancement 】 As the graph data passes GNN It will produce Nodes represent and The picture shows Two levels of representation vectors Contrastive Multi-View Representation Learning on Graphs. ICML 2020. Design experiments to analyze the comparison of different levels , It is found that comparing the node representation with the graph representation will achieve better results . wuhu ~
【Learning Method graph data enhancement 】JOAO: Through confrontation training (adversarial training) The way , Iterative training selects each data enhancement method 【 semi-automatic 】 The probability matrix of , And corresponding replacement GraphCL Mapping header in (projection head). Experimental results show that , The probability matrix obtained from confrontation training is the same as before GraphCL The trend of experimental results on data enhancement selection is similar , And achieved competitive results without too much manual intervention .
【 Fully automatic 】 Automatically learn the distribution of disturbance to the graph during data enhancement .Adversarial Graph Augmentation to Improve Graph Contrastive Learning The author starts from how to preserve the information of the graph in data enhancement , Suppose the enhanced two View The greater the mutual information, the better , Because these mutual information may contain a lot of noise . The author introduces the information bottleneck (Information Bottleneck) principle , Think better View It should be on the premise of jointly preserving the characteristics of the graph itself , Mutual information between each other is minimal . That is, in training , Learn how to enhance retention graph Necessary information in , And at the same time reduce noise . Based on this principle , The author designed min-max game It's a new training mode , And train the neural network to decide whether to delete an edge in the data enhancement .【 pruning strategy ?】
————————————————
Copyright notice : This paper is about CSDN Blogger 「Amber_7422」 The original article of , follow CC 4.0 BY-SA Copyright agreement , For reprint, please attach the original source link and this statement .
Link to the original text :https://blog.csdn.net/Amber_7422/article/details/123773606
边栏推荐
- 【愚公系列】2022年7月 Go教学课程 003-IDE的安装和基本使用
- 生成对抗网络
- 2020 "Lenovo Cup" National College programming online Invitational Competition and the third Shanghai University of technology programming competition
- 一题多解,ASP.NET Core应用启动初始化的N种方案[上篇]
- Nodejs modularization
- 我的一生.
- 什么是防火墙?防火墙基础知识讲解
- Codeforces round 684 (Div. 2) e - green shopping (line segment tree)
- Applet data attribute method
- Ecmascript6 introduction and environment construction
猜你喜欢
Svgo v3.9.0+
嗨 FUN 一夏,与 StarRocks 一起玩转 SQL Planner!
Progressive JPEG pictures and related
高性能Spark_transformation性能
C [essential skills] use of configurationmanager class (use of file app.config)
Wxss template syntax
Svg optimization by svgo
Creation and reference of applet
nodejs_ 01_ fs. readFile
Codeworks round 639 (Div. 2) cute new problem solution
随机推荐
Ecmascript6 introduction and environment construction
Applet (use of NPM package)
测试老鸟浅谈unittest和pytest的区别
Codeworks round 639 (Div. 2) cute new problem solution
OpenGL - Model Loading
Transfer learning and domain adaptation
The combination of deep learning model and wet experiment is expected to be used for metabolic flux analysis
【愚公系列】2022年7月 Go教学课程 003-IDE的安装和基本使用
Applet network data request
一文详解图对比学习(GNN+CL)的一般流程和最新研究趋势
Solution to the problem of the 10th Programming Competition (synchronized competition) of Harbin University of technology "Colin Minglun Cup"
2311. Longest binary subsequence less than or equal to K
Svgo v3.9.0+
混淆矩阵(Confusion Matrix)
【PyTorch Bug】RuntimeError: Boolean value of Tensor with more than one value is ambiguous
Jenkins pipeline method (function) definition and call
Codeforces Round #648 (Div. 2) D. Solve The Maze
Hi Fun Summer, play SQL planner with starrocks!
Introduction Guide to stereo vision (6): level constraints and polar correction of fusiello method
Kotlin introductory notes (VIII) collection and traversal