Sparse graph and full graph

[immortal13]

Thanks for the innovative work! Could you please tell me how can we get a full graph？Did full graph mean the full attention map？Did sparse graph mean that we only retain the immediate neighbor nodes‘ value of full graph？

[vijaydwivedi75]

Hi @immortal13,
In sparse graph experiments, the original graph is used which means a node attends to its local neighbors only.
In full graph experiments, a new graph is created with each node connected to every other nodes which means a node attends to all other nodes in a graph.

The code that makes full graph, for example on SBM datasets, is:

graphtransformer/data/SBMs.py

Lines 123 to 142 in 011da21

	def make_full_graph(g):
	"""
	Converting the given graph to fully connected
	"""
	full_g = dgl.from_networkx(nx.complete_graph(g.number_of_nodes()))
	full_g.ndata['feat'] = g.ndata['feat']
	full_g.edata['feat'] = torch.zeros(full_g.number_of_edges())
	try:
	full_g.ndata['lap_pos_enc'] = g.ndata['lap_pos_enc']
	except:
	pass
	try:
	full_g.ndata['wl_pos_enc'] = g.ndata['wl_pos_enc']
	except:
	pass
	return full_g

[immortal13]

Thanks for you prompt reply！