dgl._ffi.base.DGLError: There are 0-in-degree nodes in the graph, output
for those nodes will be invalid. This is harmful for some applications,
causing silent performance regression. Adding self-loop on the input
graph by calling ±g = dgl.add_self_loop(g)± will resolve the issue.
Setting ±±allow_zero_in_degree±± to be ±True± when constructing this
module will suppress the check and let the code run.
Added add_self_loop parameter to embedding constructor to overcome this problem.
Fix for graphs with isolated nodes:
dgl._ffi.base.DGLError: There are 0-in-degree nodes in the graph, output for those nodes will be invalid. This is harmful for some applications, causing silent performance regression. Adding self-loop on the input graph by calling ±g = dgl.add_self_loop(g)± will resolve the issue. Setting ±±allow_zero_in_degree±± to be ±True± when constructing this module will suppress the check and let the code run.
Added add_self_loop parameter to embedding constructor to overcome this problem.
Added more GCN tests (for all datasets)