Max-Margin Nonparametric Latent Feature Models for Link Prediction

TL;DR

This paper introduces a max-margin learning approach for nonparametric Bayesian latent feature models to improve link prediction in large-scale networks, combining discriminative power with Bayesian inference.

Contribution

It unites max-margin learning with Bayesian nonparametrics for link prediction, enabling scalable, discriminative, and hyper-parameter-free inference.

Findings

Scalable to networks with millions of entities.

Outperforms existing methods on real datasets.

Provides a full Bayesian formulation avoiding hyper-parameter tuning.

Abstract

Link prediction is a fundamental task in statistical network analysis. Recent advances have been made on learning flexible nonparametric Bayesian latent feature models for link prediction. In this paper, we present a max-margin learning method for such nonparametric latent feature relational models. Our approach attempts to unite the ideas of max-margin learning and Bayesian nonparametrics to discover discriminative latent features for link prediction. It inherits the advances of nonparametric Bayesian methods to infer the unknown latent social dimension, while for discriminative link prediction, it adopts the max-margin learning principle by minimizing a hinge-loss using the linear expectation operator, without dealing with a highly nonlinear link likelihood function. For posterior inference, we develop an efficient stochastic variational inference algorithm under a truncated mean-field assumption. Our methods can scale up to large-scale real networks with millions of entities and tens of millions of positive links. We also provide a full Bayesian formulation, which can avoid tuning regularization hyper-parameters. Experimental results on a diverse range of real datasets demonstrate the benefits inherited from max-margin learning and Bayesian nonparametric inference.