dgl.lap_pe
cannot scale to large graphs due to materialization of dense adjacency matrix
#5854
Labels
dgl.lap_pe
cannot scale to large graphs due to materialization of dense adjacency matrix
#5854
🐛 Bug
dgl.lap_pe
cannot scale to large graphs due to materialization of dense adjacency matrixTo Reproduce
@vijaydwivedi75 told me that he would like to scale
dgl.lap_pe
to larger graphs like OGB products, but current implementation throws a memory error:Expected behavior
We could make it work on graphs like OGB products (see fix below)
Environment
conda
,pip
, source):Additional context
@vijaydwivedi75 also suggested a fix. Instead of materializing the dense adjacency matrix in
dgl/python/dgl/transforms/functional.py
Line 3675 in df97f2e
We could as well use scipy's implementation which can work on sparse matrices:
The text was updated successfully, but these errors were encountered: