Graph-assisted Matrix Completion in a Multi-clustered Graph Model

Geewon Suh, Changho Suh

Abstract: We consider a matrix completion problem that exploits social graph as side information. We develop a computationally efficient algorithm that achieves the optimal sample complexity for the entire regime of graph information under the multiple cluster setting (to be detailed). The key idea is to incorporate a switching mechanism which selects the information employed in the first clustering step, between the following two types: graph & matrix ratings. Our experimental results on both synthetic and real data corroborate our theoretical result as well as demonstrate that our algorithm outperforms prior algorithms that leverage graph side information.

External IDs:dblp:conf/isit/SuhS22