Frozenmad
3e9fd78448
Merge branch 'dev' into doc
4 years ago
Frozenmad
6413c6aa6f
debug gin + lp decoder
4 years ago
Frozenmad
f1d67ce9de
add sumpoolmlp; loose the graph clf last dim.
4 years ago
Frozenmad
b93f2831a0
add trainer document
4 years ago
Frozenmad
22e1959d79
fix style for test performance
4 years ago
Frozenmad
8cb9ad099b
fix bugs for pyg trainer
4 years ago
Frozenmad
acdaff71a4
decouple framework design
4 years ago
Frozenmad
bebccfa19e
fix bugs of pyg backend
4 years ago
lihy96
c47ce10d66
fix bugs
4 years ago
lihy96
153e4df651
fix bugs
4 years ago
lihy96
6d7c3d8ca2
Update graph_classification_full.py
4 years ago
lihy96
7e8f274b1d
Update graph_classification_full.py
4 years ago
lihy96
ad22adfe81
Update graph_classification_full.py
4 years ago
lihy96
6823aa6347
dgl dataloader should set shuffle False for val loader
4 years ago
lihy96
0d35503024
trainner dgl
4 years ago
lihy96
bedd87aca4
merge dgl into trainer
4 years ago
Frozenmad
be3c462b2a
black format
4 years ago
null
136bddfdc1
merge dev and revert some mutations for LeaderBoard
5 years ago
null
194cd502c0
Implement layer-wise prediction for LADIES, improve the LeaderBoard
Speed up the prediction procedure by caching the immutable edges conducted by deterministic neighbors for specific batch of target nodes in the layer-wise prediction procedure.
5 years ago
Frozenmad
3e9a11fa36
change the default num_workers to 0
5 years ago
Frozenmad
07d2329476
black style
5 years ago
null
3d8e9d1847
Implement partial GraphSAINT Methodolgy and refactor BaseModel
Reproduce partial implementation of GraphSAINT, a representative Subgraph-wise sampling method.
Add experimental BaseModel for future major version.
TODO: Migrate the base class for all the concrete models to ClassificationModel (ClassificationApproach)
5 years ago
null
ba81889c90
Refactor module.train and fix a bug in example for graph cls
5 years ago
Frozenmad
de9c1ce59e
Merge branch 'dev' into multiprocess
5 years ago
Frozenmad
38ab2b06b9
rebase trainer
5 years ago