def test_gin_conv(aggregator_type):
g = dgl.DGLGraph(sp.sparse.random(100, 100, density=0.1), readonly=True)
gin = nn.GINConv(tf.keras.layers.Dense(12), aggregator_type)
feat = F.randn((100, 5))
gin = gin
h = gin(g, feat)
assert h.shape == (100, 12)
g = dgl.bipartite(sp.sparse.random(100, 200, density=0.1))
gin = nn.GINConv(tf.keras.layers.Dense(12), aggregator_type)
feat = (F.randn((100, 5)), F.randn((200, 5)))
h = gin(g, feat)
assert h.shape == (200, 12)
def test_gin_conv_bi(g, idtype, aggregator_type):
g = g.astype(idtype).to(F.ctx())
gin = nn.GINConv(tf.keras.layers.Dense(12), aggregator_type)
feat = (F.randn(
(g.number_of_src_nodes(), 5)), F.randn((g.number_of_dst_nodes(), 5)))
h = gin(g, feat)
assert h.shape == (g.number_of_dst_nodes(), 12)
def test_gin_conv():
for aggregator_type in ['mean', 'max', 'sum']:
g = dgl.DGLGraph(sp.sparse.random(100, 100, density=0.1),
readonly=True)
gin = nn.GINConv(tf.keras.layers.Dense(12), aggregator_type)
feat = F.randn((100, 5))
gin = gin
h = gin(g, feat)
assert h.shape[-1] == 12
def test_gin_conv(aggregator_type):
g = dgl.DGLGraph(sp.sparse.random(100, 100, density=0.1), readonly=True)
gin = nn.GINConv(tf.keras.layers.Dense(12), aggregator_type)
feat = F.randn((100, 5))
gin = gin
h = gin(g, feat)
assert h.shape == (100, 12)
g = dgl.bipartite(sp.sparse.random(100, 200, density=0.1))
gin = nn.GINConv(tf.keras.layers.Dense(12), aggregator_type)
feat = (F.randn((100, 5)), F.randn((200, 5)))
h = gin(g, feat)
assert h.shape == (200, 12)
g = dgl.graph(sp.sparse.random(100, 100, density=0.001))
seed_nodes = np.unique(g.edges()[1].numpy())
block = dgl.to_block(g, seed_nodes)
gin = nn.GINConv(tf.keras.layers.Dense(12), aggregator_type)
feat = F.randn((block.number_of_src_nodes(), 5))
h = gin(block, feat)
assert h.shape == (block.number_of_dst_nodes(), 12)
