Disentangled Causal Embedding With Contrastive Learning For Recommender System

TL;DR

This paper introduces DCCL, a contrastive learning framework that disentangles user interest and conformity in recommender systems, improving robustness and performance especially in out-of-distribution scenarios.

Contribution

The paper proposes a novel, model-agnostic contrastive learning approach to disentangle interest and conformity, addressing data sparsity and long-tail issues in recommender systems.

Findings

DCCL outperforms state-of-the-art baselines on real-world datasets.

DCCL improves recommendation robustness in out-of-distribution environments.

Online A/B testing shows significant performance gains in a billion-user system.

Abstract

Recommender systems usually rely on observed user interaction data to build personalized recommendation models, assuming that the observed data reflect user interest. However, user interacting with an item may also due to conformity, the need to follow popular items. Most previous studies neglect user's conformity and entangle interest with it, which may cause the recommender systems fail to provide satisfying results. Therefore, from the cause-effect view, disentangling these interaction causes is a crucial issue. It also contributes to OOD problems, where training and test data are out-of-distribution. Nevertheless, it is quite challenging as we lack the signal to differentiate interest and conformity. The data sparsity of pure cause and the items' long-tail problem hinder disentangled causal embedding. In this paper, we propose DCCL, a framework that adopts contrastive learning to disentangle these two causes by sample augmentation for interest and conformity respectively. Futhermore, DCCL is model-agnostic, which can be easily deployed in any industrial online system. Extensive experiments are conducted over two real-world datasets and DCCL outperforms state-of-the-art baselines on top of various backbone models in various OOD environments. We also demonstrate the performance improvements by online A/B testing on Kuaishou, a billion-user scale short-video recommender system.