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
- What is a firewall? Explanation of basic knowledge of firewall
- 一题多解,ASP.NET Core应用启动初始化的N种方案[上篇]
- [beauty of algebra] singular value decomposition (SVD) and its application to linear least squares solution ax=b
- L'information et l'entropie, tout ce que vous voulez savoir est ici.
- 基于STM32单片机的测温仪(带人脸检测)
- C # image difference comparison: image subtraction (pointer method, high speed)
- Ministry of transport and Ministry of Education: widely carry out water traffic safety publicity and drowning prevention safety reminders
- 12. Dynamic link library, DLL
- 阿里云发送短信验证码
- nodejs_ 01_ fs. readFile
猜你喜欢
Rebuild my 3D world [open source] [serialization-1]
The combination of deep learning model and wet experiment is expected to be used for metabolic flux analysis
[code practice] [stereo matching series] Classic ad census: (4) cross domain cost aggregation
Editor use of VI and VIM
Hi Fun Summer, play SQL planner with starrocks!
Confusion matrix
Understanding rotation matrix R from the perspective of base transformation
嗨 FUN 一夏,与 StarRocks 一起玩转 SQL Planner!
C form click event did not respond
C [essential skills] use of configurationmanager class (use of file app.config)
随机推荐
Using request headers to develop multi terminal applications
C # draw Bezier curve with control points for lattice images and vector graphics
Alibaba cloud sends SMS verification code
nodejs_ fs. writeFile
Composition of applet code
22-07-04 西安 尚好房-项目经验总结(01)
Uni app implements global variables
Codeforces Round #648 (Div. 2) E.Maximum Subsequence Value
Meta tag details
OpenGL - Coordinate Systems
The location search property gets the login user name
Array, date, string object method
Luo Gu p3177 tree coloring [deeply understand the cycle sequence of knapsack on tree]
C # image difference comparison: image subtraction (pointer method, high speed)
Confusing basic concepts member variables local variables global variables
Causes and appropriate analysis of possible errors in seq2seq code of "hands on learning in depth"
Creation and reference of applet
STM32简易多级菜单(数组查表法)
File server migration scheme of a company
信息與熵,你想知道的都在這裏了