2 Classes you need to self define when you implement Graph Neural Network(GNN):
MyNet(pytorch.nn.Moduel) MyGraphModel(torch_geometric.nn.MessagePassing) MyNet(pytorch.nn.Moduel) In your overall model structure, you should implement:
(in __init__): call a MessagePassing child class to build massage-passing model (in forward): make sure the data follows the requirement of MessagePassing child class do the “iterative massage passing"(K-times) in forward, the final output will be the node embedding you need.
Zhang, Yunhao, and Junchi Yan. 2021. “Neural Relation Inference for Multi-Dimensional Temporal Point Processes via Message Passing Graph.” In , 3:3406–12. https://doi.org/10.24963/ijcai.2021/469.
A multidimentional(D nodes) marked(M types of possible events) TPP($N_m$ length of sequence) modeling
modeling continuous timing in temporal graph learning
A basic framework of continous temporal dynamic graph modeling. Benchmarked in 2020
Clarification: This Note is based on the presentation of Rex Ying in Youtube. Some related resources:
Slides Code Short Intro in SNAP A node classification problem that suitable for
Published in ICLR 2019. Openreview
Problem Formulation Model: DyRep In general Modeling two-time sclae graph dynamics Inductive representation network Localized Embedding Propagation Aggregator (analogue to Attention mechanism(S) + update A) Training Parameters: Method: MLE Likelihood function batch training Evaluation Link prediction Event time prediction Appendix Summary of Overall Embedding Update Process Attention Mechanism Node Attributes and Edge Types Support New nodes Monte Carlo Estimation for survival term in Likelihood Some random thinking Problem Formulation Graph:
Generally, NEVER use pip install something !!! This may lead to fatal result on your environment.
You have to specify which verison of something you intend to install.
From 0 to 100 Here is a stable version of Graph Research Environment provided by Dr.
Genral PyG GraphGym, a design space for GNN Emmerging stars in GNN research, Jiaxuan You and Rex Ying Jure Leskovec related GNN resources Some Content on this web is a little old.
This Note was my personal review of GraphGym Intro in Stanford Computer Forum - Graph Learning Workshop: Sept 16, 2021 presented by Jiaxuan You.
Some new feature may be added after this post