Semi-Disentangled Representation Learning in Recommendation System

TL;DR

This paper introduces SDRL, a semi-disentangled autoencoder-based method for recommendation systems that enhances interpretability and generalization by separating explainable and unexplainable features in user/item embeddings.

Contribution

The paper proposes a novel semi-disentangled representation learning approach that divides embeddings into explainable and unexplainable parts, improving interpretability and performance in recommendation systems.

Findings

SDRL effectively captures user and item features.

It improves explainability over existing methods.

It enhances generalization in recommendation tasks.

Abstract

Disentangled representation has been widely explored in many fields due to its maximal compactness, interpretability and versatility. Recommendation system also needs disentanglement to make representation more explainable and general for downstream tasks. However, some challenges slow its broader application -- the lack of fine-grained labels and the complexity of user-item interactions. To alleviate these problems, we propose a Semi-Disentangled Representation Learning method (SDRL) based on autoencoders. SDRL divides each user/item embedding into two parts: the explainable and the unexplainable, so as to improve proper disentanglement while preserving complex information in representation. The explainable part consists of $internal\ block$ for individual-based features and $external\ block$ for interaction-based features. The unexplainable part is composed by $other\ block$ for other remaining information. Experimental results on three real-world datasets demonstrate that the proposed SDRL could not only effectively express user and item features but also improve the explainability and generality compared with existing representation methods.