-
Notifications
You must be signed in to change notification settings - Fork 3k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'master' into async_gpu_sampling
- Loading branch information
Showing
44 changed files
with
1,775 additions
and
142 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,24 @@ | ||
| Graph Attention Networks (GAT) | ||
| ============ | ||
|
|
||
| - Paper link: [https://arxiv.org/abs/1710.10903](https://arxiv.org/abs/1710.10903) | ||
| - Author's code repo (tensorflow implementation): | ||
| [https://github.com/PetarV-/GAT](https://github.com/PetarV-/GAT). | ||
| - Popular pytorch implementation: | ||
| [https://github.com/Diego999/pyGAT](https://github.com/Diego999/pyGAT). | ||
|
|
||
| How to run | ||
| ------- | ||
|
|
||
| Run with the following for multiclass node classification (available datasets: "cora", "citeseer", "pubmed") | ||
| ```bash | ||
| python3 train.py --dataset cora | ||
| ``` | ||
|
|
||
| > **_NOTE:_** Users may occasionally run into low accuracy issue (e.g., test accuracy < 0.8) due to overfitting. This can be resolved by adding Early Stopping or reducing maximum number of training epochs. | ||
| Summary | ||
| ------- | ||
| * cora: ~0.821 | ||
| * citeseer: ~0.710 | ||
| * pubmed: ~0.780 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,140 @@ | ||
| import argparse | ||
| import time | ||
|
|
||
| import dgl.nn as dglnn | ||
|
|
||
| import torch | ||
| import torch.nn as nn | ||
| import torch.nn.functional as F | ||
| from dgl import AddSelfLoop | ||
| from dgl.data import CiteseerGraphDataset, CoraGraphDataset, PubmedGraphDataset | ||
|
|
||
|
|
||
| class GAT(nn.Module): | ||
| def __init__(self, in_size, hid_size, out_size, heads): | ||
| super().__init__() | ||
| self.gat_layers = nn.ModuleList() | ||
| # two-layer GAT | ||
| self.gat_layers.append( | ||
| dglnn.GATConv( | ||
| in_size, | ||
| hid_size, | ||
| heads[0], | ||
| feat_drop=0.6, | ||
| attn_drop=0.6, | ||
| activation=F.elu, | ||
| ) | ||
| ) | ||
| self.gat_layers.append( | ||
| dglnn.GATConv( | ||
| hid_size * heads[0], | ||
| out_size, | ||
| heads[1], | ||
| feat_drop=0.6, | ||
| attn_drop=0.6, | ||
| activation=None, | ||
| ) | ||
| ) | ||
|
|
||
| def forward(self, g, inputs): | ||
| h = inputs | ||
| for i, layer in enumerate(self.gat_layers): | ||
| h = layer(g, h) | ||
| if i == len(self.gat_layers) - 1: # last layer | ||
| h = h.mean(1) | ||
| else: # other layer(s) | ||
| h = h.flatten(1) | ||
| return h | ||
|
|
||
|
|
||
| def evaluate(g, features, labels, mask, model): | ||
| model.eval() | ||
| with torch.no_grad(): | ||
| logits = model(g, features) | ||
| logits = logits[mask] | ||
| labels = labels[mask] | ||
| _, indices = torch.max(logits, dim=1) | ||
| correct = torch.sum(indices == labels) | ||
| return correct.item() * 1.0 / len(labels) | ||
|
|
||
|
|
||
| def train(g, features, labels, masks, model, num_epochs): | ||
| # Define train/val samples, loss function and optimizer | ||
| train_mask = masks[0] | ||
| val_mask = masks[1] | ||
| loss_fcn = nn.CrossEntropyLoss() | ||
| optimizer = torch.optim.Adam(model.parameters(), lr=5e-3, weight_decay=5e-4) | ||
|
|
||
| for epoch in range(num_epochs): | ||
| t0 = time.time() | ||
| model.train() | ||
| logits = model(g, features) | ||
| loss = loss_fcn(logits[train_mask], labels[train_mask]) | ||
| optimizer.zero_grad() | ||
| loss.backward() | ||
| optimizer.step() | ||
| acc = evaluate(g, features, labels, val_mask, model) | ||
| t1 = time.time() | ||
| print( | ||
| "Epoch {:05d} | Loss {:.4f} | Accuracy {:.4f} | Time {:.4f}".format( | ||
| epoch, loss.item(), acc, t1 - t0 | ||
| ) | ||
| ) | ||
|
|
||
|
|
||
| if __name__ == "__main__": | ||
| parser = argparse.ArgumentParser() | ||
| parser.add_argument( | ||
| "--dataset", | ||
| type=str, | ||
| default="cora", | ||
| help="Dataset name ('cora', 'citeseer', 'pubmed').", | ||
| ) | ||
| parser.add_argument( | ||
| "--num_epochs", | ||
| type=int, | ||
| default=200, | ||
| help="Number of epochs for train.", | ||
| ) | ||
| parser.add_argument( | ||
| "--num_gpus", | ||
| type=int, | ||
| default=0, | ||
| help="Number of GPUs used for train and evaluation.", | ||
| ) | ||
| args = parser.parse_args() | ||
| print(f"Training with DGL built-in GATConv module.") | ||
|
|
||
| # Load and preprocess dataset | ||
| transform = ( | ||
| AddSelfLoop() | ||
| ) # by default, it will first remove self-loops to prevent duplication | ||
| if args.dataset == "cora": | ||
| data = CoraGraphDataset(transform=transform) | ||
| elif args.dataset == "citeseer": | ||
| data = CiteseerGraphDataset(transform=transform) | ||
| elif args.dataset == "pubmed": | ||
| data = PubmedGraphDataset(transform=transform) | ||
| else: | ||
| raise ValueError("Unknown dataset: {}".format(args.dataset)) | ||
| g = data[0] | ||
| if args.num_gpus > 0 and torch.cuda.is_available(): | ||
| device = torch.device("cuda") | ||
| else: | ||
| device = torch.device("cpu") | ||
| g = g.int().to(device) | ||
| features = g.ndata["feat"] | ||
| labels = g.ndata["label"] | ||
| masks = g.ndata["train_mask"], g.ndata["val_mask"], g.ndata["test_mask"] | ||
|
|
||
| # Create GAT model | ||
| in_size = features.shape[1] | ||
| out_size = data.num_classes | ||
| model = GAT(in_size, 8, out_size, heads=[8, 1]).to(device) | ||
|
|
||
| print("Training...") | ||
| train(g, features, labels, masks, model, args.num_epochs) | ||
|
|
||
| print("Testing...") | ||
| acc = evaluate(g, features, labels, masks[2], model) | ||
| print("Test accuracy {:.4f}".format(acc)) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,23 @@ | ||
| Gated Graph ConvNet (GatedGCN) | ||
| ============================== | ||
|
|
||
| * paper link: [https://arxiv.org/abs/2003.00982.pdf](https://arxiv.org/abs/2003.00982.pdf) | ||
|
|
||
| ## Dataset | ||
|
|
||
| Task: Graph Property Prediction | ||
|
|
||
| | Dataset | #Graphs | #Node Feats | #Edge Feats | Metric | | ||
| | :---------: | :-----: | :---------: | :---------: | :-----: | | ||
| | ogbg-molhiv | 41,127 | 9 | 3 | ROC-AUC | | ||
|
|
||
| How to run | ||
| ---------- | ||
|
|
||
| ```bash | ||
| python train.py | ||
| ``` | ||
|
|
||
| ## Summary | ||
|
|
||
| * ogbg-molhiv: ~0.781 |
Oops, something went wrong.