Latent Collaborative Retrieval

TL;DR

This paper introduces a factorized model for joint collaborative retrieval and recommendation, effectively handling query, user, and item data, and demonstrating superior performance over baselines.

Contribution

The paper proposes a novel factorized model for collaborative retrieval that incorporates queries, user profiles, and optional content features, advancing beyond traditional methods.

Findings

Outperforms several baseline methods in empirical tests.

Effectively models query, user, and item interactions.

Handles cases with and without content features.

Abstract

Retrieval tasks typically require a ranking of items given a query. Collaborative filtering tasks, on the other hand, learn to model user's preferences over items. In this paper we study the joint problem of recommending items to a user with respect to a given query, which is a surprisingly common task. This setup differs from the standard collaborative filtering one in that we are given a query x user x item tensor for training instead of the more traditional user x item matrix. Compared to document retrieval we do have a query, but we may or may not have content features (we will consider both cases) and we can also take account of the user's profile. We introduce a factorized model for this new task that optimizes the top-ranked items returned for the given query and user. We report empirical results where it outperforms several baselines.