Distributed Matrix Factorization Via ADMM

Matrix factorization(MF) has become one of the most popular techniques for recommender systems due to its promising performance. With the advent of the Internet era, online information increases tremendously, which makes personal recommender systems widely used. On the other side, machine learning algorithms have to transfer to distributed version to handle large-scale datasets. Recently, Distributed(parallel)MF models have received much attention from researchers of big data community. In this paper, we propose a novel model, called distributed stochastic alternating direction methods of multipliers(DS-ADMM), for large-scale MF problems. In particular, we first devise a new data split strategy to make the distributed MF problem fit for the ADMM framework. Then, a stochastic ADMM scheme is designed for learning. Finally, we implement DS-ADMM based on MPI(Message Passing Interface), which can run on clusters with multiple machines(nodes). Experiments on several data sets from recommendation applications show that our DS-ADMM model can outperform other state-of-the-art distributed MF models in terms of both efficiency and accuracy.