# Disentangled Causal Embedding With Contrastive Learning For Recommender System

arXiv: https://arxiv.org/abs/2302.03248 · HTML: https://mlsanity.com/paper/2302.03248/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2023.

## Built on by (most cited first, 10 of 10)

- [Towards Cross-Table Masked Pretraining for Web Data Mining](https://mlsanity.com/paper/2307.04308/) (2023)
- [Multi-task Heterogeneous Graph Learning on Electronic Health Records](https://mlsanity.com/paper/2408.07569/) (2024)
- [Democratizing Large Language Model-Based Graph Data Augmentation via Latent Knowledge Graphs](https://mlsanity.com/paper/2502.13555/) (2025)
- [Causal Representation Learning for Generalisable Recommendation](https://mlsanity.com/paper/2605.27043/) (2026)
- [Debiased Contrastive Representation Learning for Mitigating Dual Biases in Recommender Systems](https://mlsanity.com/paper/2408.09646/) (2024)
- [Interaction-Data-guided Conditional Instrumental Variables for Debiasing Recommender Systems](https://mlsanity.com/paper/2408.09651/) (2024)
- [Rethinking Popularity Bias in Collaborative Filtering via Analytical Vector Decomposition](https://mlsanity.com/paper/2512.10688/) (2025)
- [MCLMR: A Model-Agnostic Causal Learning Framework for Multi-Behavior Recommendation](https://mlsanity.com/paper/2603.25126/) (2026)
- [Generate the browsing process for short-video recommendation](https://mlsanity.com/paper/2504.08771/) (2025)
- [Breaker: Removing Shortcut Cues with User Clustering for Single-slot Recommendation System](https://mlsanity.com/paper/2506.00828/) (2025)

## Abstract (arXiv)

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.