Disentangled Representation for Diversified Recommendations

TL;DR

This paper introduces a disentangled representation framework that improves recommendation diversity and accuracy by modeling user preferences over item categories separately from item quality.

Contribution

It proposes a novel, category-disentangled user representation approach that enhances both diversity and accuracy in recommendations without relying on specific algorithms.

Findings

Improved diversity and accuracy demonstrated on benchmark datasets.

Effective disentanglement of user preferences over categories.

Enhanced user preference modeling leads to better ranking within categories.

Abstract

Accuracy and diversity have long been considered to be two conflicting goals for recommendations. We point out, however, that as the diversity is typically measured by certain pre-selected item attributes, e.g., category as the most popularly employed one, improved diversity can be achieved without sacrificing recommendation accuracy, as long as the diversification respects the user's preference about the pre-selected attributes. This calls for a fine-grained understanding of a user's preferences over items, where one needs to recognize the user's choice is driven by the quality of the item itself, or the pre-selected attributes of the item. In this work, we focus on diversity defined on item categories. We propose a general diversification framework agnostic to the choice of recommendation algorithms. Our solution disentangles the learnt user representation in the recommendation module into category-independent and category-dependent components to differentiate a user's preference over items from two orthogonal perspectives. Experimental results on three benchmark datasets and online A/B test demonstrate the effectiveness of our solution in improving both recommendation accuracy and diversity. In-depth analysis suggests that the improvement is due to our improved modeling of users' categorical preferences and refined ranking within item categories.