Scalable Bayesian Modelling of Paired Symbols

TL;DR

This paper introduces a scalable Bayesian method for modeling paired symbols, combining popularity and preference factors, with efficient inference suitable for large datasets, demonstrated on movie viewing data.

Contribution

It proposes a novel variational inference approach with site-independent bounds for scalable Bayesian modeling of paired data.

Findings

Achieved state-of-the-art results on movie viewing datasets.

Developed a scalable inference algorithm for large-scale paired symbol data.

Validated the model's effectiveness on real-world data.

Abstract

We present a novel, scalable and Bayesian approach to modelling the occurrence of pairs of symbols (i,j) drawn from a large vocabulary. Observed pairs are assumed to be generated by a simple popularity based selection process followed by censoring using a preference function. By basing inference on the well-founded principle of variational bounding, and using new site-independent bounds, we show how a scalable inference procedure can be obtained for large data sets. State of the art results are presented on real-world movie viewing data.