Matrix Completion with Hierarchical Graph Side Information

01/02/2022
by   Adel Elmahdy, et al.
4

We consider a matrix completion problem that exploits social or item similarity graphs as side information. We develop a universal, parameter-free, and computationally efficient algorithm that starts with hierarchical graph clustering and then iteratively refines estimates both on graph clustering and matrix ratings. Under a hierarchical stochastic block model that well respects practically-relevant social graphs and a low-rank rating matrix model (to be detailed), we demonstrate that our algorithm achieves the information-theoretic limit on the number of observed matrix entries (i.e., optimal sample complexity) that is derived by maximum likelihood estimation together with a lower-bound impossibility result. One consequence of this result is that exploiting the hierarchical structure of social graphs yields a substantial gain in sample complexity relative to the one that simply identifies different groups without resorting to the relational structure across them. We conduct extensive experiments both on synthetic and real-world datasets to corroborate our theoretical results as well as to demonstrate significant performance improvements over other matrix completion algorithms that leverage graph side information.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/12/2021

On the Fundamental Limits of Matrix Completion: Leveraging Hierarchical Similarity Graphs

We study the matrix completion problem that leverages hierarchical simil...
research
06/08/2020

MC2G: An Efficient Algorithm for Matrix Completion with Social and Item Similarity Graphs

We consider a discrete-valued matrix completion problem for recommender ...
research
03/16/2020

Discrete-valued Preference Estimation with Graph Side Information

Incorporating graph side information into recommender systems has been w...
research
12/06/2019

Community Detection and Matrix Completion with Two-Sided Graph Side-Information

We consider the problem of recovering communities of users and communiti...
research
02/16/2018

Learning Latent Features with Pairwise Penalties in Matrix Completion

Low-rank matrix completion (MC) has achieved great success in many real-...
research
03/03/2018

Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow

We revisit the inductive matrix completion problem that aims to recover ...
research
02/10/2020

Robust Mean Estimation under Coordinate-level Corruption

Data corruption, systematic or adversarial, may skew statistical estimat...

Please sign up or login with your details

Forgot password? Click here to reset