Regression-based latent factor models

TLDR

The study proposes a latent factor model to predict responses in large‑scale dyadic data using feature information. The model estimates row and column latent factors through separate regressions on features, combines them multiplicatively to predict dyadic responses, and is fitted with scalable Iterated Conditional Mode and Monte Carlo EM, supporting both cold/warm starts and online updates. The model induces a stochastic process with a polynomial feature kernel, demonstrates superior performance on benchmark and Yahoo recommendation datasets, and outperforms several standard methods. Front Page.

Abstract

We propose a novel latent factor model to accurately predict response for large scale dyadic data in the presence of features. Our approach is based on a model that predicts response as a multiplicative function of row and column latent factors that are estimated through separate regressions on known row and column features. In fact, our model provides a single unified framework to address both cold and warm start scenarios that are commonplace in practical applications like recommender systems, online advertising, web search, etc. We provide scalable and accurate model fitting methods based on Iterated Conditional Mode and Monte Carlo EM algorithms. We show our model induces a stochastic process on the dyadic space with kernel (covariance) given by a polynomial function of features. Methods that generalize our procedure to estimate factors in an online fashion for dynamic applications are also considered. Our method is illustrated on benchmark datasets and a novel content recommendation application that arises in the context of Yahoo! Front Page. We report significant improvements over several commonly used methods on all datasets.