当前位置:网站首页>Introduction to GNN
Introduction to GNN
2022-07-05 12:26:00 【Nat_ Jst】
GNN:graph neural network Figure neural network
because GNN Powerful modeling function between graph nodes , It makes a breakthrough in the research field related to graph analysis . Figure neural network (GNN) It is a kind of method based on deep learning to deal with graph information .
1. Application field
Because of its good performance and interpretability , It has been widely used in various fields . It covers the recommendation system 、 Combinatorial optimization 、 Computer vision 、 Physics / Chemistry and drug discovery .
Recommendation system : The graph structure data comes from the context of the interaction between users and products on the e-commerce platform , therefore , Many companies use GNN Make product recommendations . A standard case is to model the interaction between users and goods , Then learning nodes are embedded with some form of negative sampling loss , And use KNN The index retrieves similar products of a given user in real time .
Combinatorial optimization
Combinatorial optimization : Combinatorial optimization (combinatorial optimization, CO) The solution of the problem is finance 、 logistics 、 energy 、 The key in life science and hardware design . Most of these problems are represented by graphs . Google brain team uses GNN Optimized new hardware ( Such as Google Of TPU) Power consumption of chip block 、 Area and performance . A computer chip can be understood as a diagram composed of memory and logic components , Each diagram is represented by the coordinates and types of its components . Determine the location of each component , At the same time, comply with the restrictions of density and wiring congestion , It's a laborious process , But it is still the focus of electrical engineers . Google brain team uses GNN Models and strategies and benefits reinforcement learning (RL) A combination of functions , Generate optimized circuit chip layout , Even better than manually designed hardware layout .
Computer vision : One way to perceive an image is through a scene graph ( The paper 《Scene Graph Generation by Iterative Message Passing》), That is, the objects that appear in the image and the set of relationships between them . Scene map has been used in image retrieval 、 Understanding and reasoning 、 Subtitle generation 、 Visual question answering and image generation have been applied .
Physics / chemical : Life science benefits from representing the interaction between particles or molecules as a graph , And then use GNN Predict the properties of such systems .
Drug discovery : In biology , Graphs can be represented as interactions of different scales . At the molecular level , The edges of the graph can be the bonds between atoms in molecules or the interactions between amino acid residues in proteins . And on a larger scale , Graphs can represent more complex structures ( Like protein 、mRNA Or metabolites ) The interaction between . According to a specific level of abstraction , These graphs can be used for target recognition 、 Prediction of molecular properties 、 High throughput screening 、 New drug design 、 Protein engineering and drug reuse .
Knowledge map : The knowledge map itself is also a graph model .
Road traffic : Dynamic flow prediction
2. chart
The basic structure : Node and the edge that represents the connection between nodes .
The purpose of using graph neural network is to integrate features .
Vertex(or Node)embedding Node embedding , Expressed as a vector .
The adjacency matrix of a graph : Indicates the adjacency relationship between nodes
边栏推荐
- 【load dataset】
- abap查表程序
- MySQL multi table operation
- 语义分割实验:Unet网络/MSRC2数据集
- 【ijkplayer】when i compile file “compile-ffmpeg.sh“ ,it show error “No such file or directory“.
- JS for循环 循环次数异常
- GPS数据格式转换[通俗易懂]
- What is digital existence? Digital transformation starts with digital existence
- About cache exceptions: solutions for cache avalanche, breakdown, and penetration
- Uniapp + unicloud + Unipay realize wechat applet payment function
猜你喜欢
How to clear floating?
Multi table operation - sub query
Matlab label2idx function (convert the label matrix into a cell array with linear index)
Intern position selection and simplified career development planning in Internet companies
Two minutes will take you to quickly master the project structure, resources, dependencies and localization of flutter
Matlab superpixels function (2D super pixel over segmentation of image)
mysql拆分字符串做条件查询
mmclassification 训练自定义数据
Course design of compilation principle --- formula calculator (a simple calculator with interface developed based on QT)
Why do you always fail in automated tests?
随机推荐
Swift - enables textview to be highly adaptive
Solve the problem of cache and database double write data consistency
一类恒等式的应用(范德蒙德卷积与超几何函数)
Codeforces Round #804 (Div. 2)
MySQL data table operation DDL & data type
Hexadecimal conversion summary
Time tools
Implementing Yang Hui triangle with cyclic queue C language
MySQL index - extended data
Get all stock data of big a
Linux安装部署LAMP(Apache+MySQL+PHP)
Just a coincidence? The mysterious technology of apple ios16 is actually the same as that of Chinese enterprises five years ago!
Read and understand the rendering mechanism and principle of flutter's three trees
[HDU 2096] 小明A+B
Master the new features of fluent 2.10
Deep discussion on the decoding of sent protocol
MySQL log module of InnoDB engine
Error modulenotfounderror: no module named 'cv2 aruco‘
Redis highly available slice cluster
What is digital existence? Digital transformation starts with digital existence