Search Results for author:
Found 2 papers, 0 papers with code
Graph Sparsification via Mixture of Graphs
Specifically, MoG incorporates multiple sparsifier experts, each characterized by unique sparsity levels and pruning criteria, and selects the appropriate experts for each node.
Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness
Specifically, GST initially constructs a topology & semantic anchor at a low training cost, followed by performing dynamic sparse training to align the sparse graph with the anchor.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
