Regression with GCN. Run with `--many-graphs` to train it one graph at a time, default is one batched graph, many epoch.

gcn_many_graphs.py

#%%
"""GCN using DGL nn package
References:
- Semi-Supervised Classification with Graph Convolutional Networks
- Paper: https://arxiv.org/abs/1609.02907
- Code: https://github.com/tkipf/gcn
"""
from random import randint
import torch
import torch.nn as nn
from dgl.nn.pytorch import GraphConv


class GCN(nn.Module):
    def __init__(self, g, in_feats, n_hidden, n_classes, n_layers, activation, dropout):
        super(GCN, self).__init__()
        # self.g = g
        self.layers = nn.ModuleList()
        # input layer
        self.layers.append(GraphConv(in_feats, n_hidden, activation=activation))
        # hidden layers
        for i in range(n_layers - 1):
            self.layers.append(GraphConv(n_hidden, n_hidden, activation=activation))
        # output layer
        self.layers.append(GraphConv(n_hidden, n_classes))
        self.dropout = nn.Dropout(p=dropout)

    def forward(self, g, features):
        # self.g = g
        h = features
        for i, layer in enumerate(self.layers):
            if i != 0:
                h = self.dropout(h)
            # h = layer(self.g, h)
            h = layer(g, h)
        return h


def train_test_val_mask(N, train_size, test_size, val_size):
    """returns 3 masks as binary np arrays"""
    train_mask = torch.zeros(N)
    train_mask[:train_size] = True
    test_mask = torch.zeros(N)
    test_mask[train_size : train_size + test_size] = True
    val_mask = torch.zeros(N)
    val_mask[train_size + test_size : train_size + test_size + val_size] = True
    return train_mask.bool(), test_mask.bool(), val_mask.bool()


def gen_random_graph(n_nodes, n_edges):
    """
    generate a random dgl graph with n_nodes nodes and n_edges edges, with the following ndata properties:
    strat: either 0 or 1
    degree: the node's degree
    label: degree * label
    """
    g = dgl.rand_graph(n_nodes, n_edges)
    dgl.add_self_loop(g)
    g.ndata["strat"] = torch.tensor([randint(0, 1) for _ in range(n_nodes)]).float()
    g.ndata["degree"] = torch.tensor([g.in_degrees(i) for i in range(n_nodes)]).float()
    g.ndata["feat"] = torch.stack((g.ndata["degree"], g.ndata["strat"]), axis=1).float()
    g.ndata["label"] = g.ndata["degree"] * g.ndata["strat"]
    # g.ndata["label"] = (g.ndata["degree"] * g.ndata["strat"] > 7).long()  # classif
    N = n_nodes
    (
        g.ndata["train_mask"],
        g.ndata["val_mask"],
        g.ndata["test_mask"],
    ) = train_test_val_mask(N, int(N * 0.8), int(N * 0.1), int(N * 0.1))
    return g


import argparse
import time
import numpy as np
import torch
import torch.nn.functional as F
import dgl
from dgl.data import CoraGraphDataset, CiteseerGraphDataset, PubmedGraphDataset


# from gcn_mp import GCN
# from gcn_spmv import GCN


def evaluate(model, g, features, labels, mask):
    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 main(args):
    # load and preprocess dataset
    num_graphs = 10
    batch_size = 50
    gs = [
        dgl.batch([gen_random_graph(10, 70) for _ in range(num_graphs)])
        for _ in range(batch_size)
    ]
    g = dgl.batch(gs)
    if args.gpu < 0:
        cuda = False
    else:
        cuda = True
        g = g.int().to(args.gpu)

    features = g.ndata["feat"]
    labels = g.ndata["label"]
    train_mask = g.ndata["train_mask"]
    val_mask = g.ndata["val_mask"]
    test_mask = g.ndata["test_mask"]
    in_feats = features.shape[1]
    # n_classes = data.num_labels
    n_classes = 1
    n_edges = g.num_edges()
    print(
        """----Data statistics------'
      #Edges %d
      #Classes %d
      #Train samples %d
      #Val samples %d
      #Test samples %d"""
        % (
            n_edges,
            n_classes,
            train_mask.int().sum().item(),
            val_mask.int().sum().item(),
            test_mask.int().sum().item(),
        )
    )

    # add self loop
    if args.self_loop:
        g = dgl.remove_self_loop(g)
        g = dgl.add_self_loop(g)
    n_edges = g.number_of_edges()

    # normalization
    # degs = g.in_degrees().float()
    # norm = torch.pow(degs, -0.5)
    # norm[torch.isinf(norm)] = 0
    # if cuda:
    #     norm = norm.cuda()
    # g.ndata["norm"] = norm.unsqueeze(1)

    # create GCN model
    model = GCN(
        g, in_feats, args.n_hidden, n_classes, args.n_layers, F.relu, args.dropout
    )

    if cuda:
        model.cuda()
    loss_fcn = torch.nn.MSELoss()
    # loss_fcn = torch.nn.CrossEntropyLoss()

    # use optimizer
    optimizer = torch.optim.Adam(
        model.parameters(), lr=args.lr, weight_decay=args.weight_decay
    )

    # initialize graph
    dur = []
    for epoch in range(args.n_epochs):
        model.train()
        if epoch >= 3:
            t0 = time.time()
        losses = []
        # forward
        if args.many_graphs:
            for g in gs:
                features = g.ndata["feat"]
                labels = g.ndata["label"]
                train_mask = g.ndata["train_mask"]
                val_mask = g.ndata["val_mask"]
                test_mask = g.ndata["test_mask"]
                in_feats = features.shape[1]
                # n_classes = data.num_labels
                n_classes = n_classes
                n_edges = g.num_edges()

                logits = model(g, features)
                loss = loss_fcn(logits[train_mask], labels[train_mask])
                losses.append(loss.item())
                optimizer.zero_grad()
                loss.backward()
                optimizer.step()
        else:
            logits = model(g, features)
            loss = loss_fcn(logits[train_mask], labels[train_mask])
            losses.append(loss.item())
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()

        if epoch >= 3:
            dur.append(time.time() - t0)

        acc = evaluate(model, g, features, labels, val_mask)
        print(
            "Epoch {:05d} | Time(s) {:.4f} | Loss {:.4f} | "
            "ETputs(KTEPS) {:.2f}".format(
                epoch, np.mean(dur), np.mean(losses), n_edges / np.mean(dur) / 1000
            )
        )

    print()
    acc = evaluate(model, g, features, labels, test_mask)
    print("Test accuracy {:.2%}".format(acc))


#%%
if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="GCN")
    parser.add_argument(
        "--dataset",
        type=str,
        default="cora",
        help="Dataset name ('cora', 'citeseer', 'pubmed').",
    )
    parser.add_argument(
        "--dropout", type=float, default=0.5, help="dropout probability"
    )
    parser.add_argument("--gpu", type=int, default=-1, help="gpu")
    parser.add_argument("--lr", type=float, default=1e-2, help="learning rate")
    parser.add_argument(
        "--n-epochs", type=int, default=200, help="number of training epochs"
    )
    parser.add_argument(
        "--n-hidden", type=int, default=16, help="number of hidden gcn units"
    )
    parser.add_argument(
        "--n-layers", type=int, default=1, help="number of hidden gcn layers"
    )
    parser.add_argument(
        "--weight-decay", type=float, default=5e-4, help="Weight for L2 loss"
    )
    parser.add_argument(
        "--self-loop", action="store_true", help="graph self-loop (default=False)"
    )
    parser.add_argument(
        "--many-graphs", action="store_true", help="graph many-graphs (default=False)"
    )
    parser.set_defaults(self_loop=False)
    parser.set_defaults(many_graphs=False)
    args = parser.parse_args()
    print(args)

    main(args)