Community Detection and Matrix Completion with Social and Item Similarity Graphs

TL;DR

This paper investigates how social and item similarity graphs, modeled by stochastic block models, can improve the recovery of binary rating matrices and clustering, providing bounds and revealing synergistic effects.

Contribution

It introduces theoretical bounds on sample complexity for matrix completion using side-information graphs and demonstrates the combined benefit of social and item graphs.

Findings

Matching lower and upper bounds on sample complexity.

Social and item graphs provide a synergistic reduction in sample requirements.

Side-information graphs enhance matrix recovery performance.

Abstract

We consider the problem of recovering a binary rating matrix as well as clusters of users and items based on a partially observed matrix together with side-information in the form of social and item similarity graphs. These two graphs are both generated according to the celebrated stochastic block model (SBM). We develop lower and upper bounds on sample complexity that match for various scenarios. Our information-theoretic results quantify the benefits of the availability of the social and item similarity graphs. Further analysis reveals that under certain scenarios, the social and item similarity graphs produce an interesting synergistic effect. This means that observing two graphs is strictly better than observing just one in terms of reducing the sample complexity.