# DisCo: Graph-Based Disentangled Contrastive Learning for Cold-Start Cross-Domain Recommendation

arXiv: https://arxiv.org/abs/2412.15005 · HTML: https://mlsanity.com/paper/2412.15005/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 38 references that are in the map.
- First posted on arXiv 19 Dec 2024.

## Builds on (most cited first, 16 of 16)

- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [Neural Graph Collaborative Filtering](https://mlsanity.com/paper/1905.08108/) (2019)
- [Disentangled Graph Collaborative Filtering](https://mlsanity.com/paper/2007.01764/) (2020)
- [Learning Disentangled Representations for Recommendation](https://mlsanity.com/paper/1910.14238/) (2019)
- [CoNet: Collaborative Cross Networks for Cross-Domain Recommendation](https://mlsanity.com/paper/1804.06769/) (2018)
- [DDTCDR: Deep Dual Transfer Cross Domain Recommendation](https://mlsanity.com/paper/1910.05189/) (2019)
- [A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challenges](https://mlsanity.com/paper/2403.04468/) (2024)
- [Improving Disentangled Text Representation Learning with Information-Theoretic Guidance](https://mlsanity.com/paper/2006.00693/) (2020)
- [DisenHAN: Disentangled Heterogeneous Graph Attention Network for Recommendation](https://mlsanity.com/paper/2106.10879/) (2021)
- [Towards Graph Contrastive Learning: A Survey and Beyond](https://mlsanity.com/paper/2405.11868/) (2024)
- [Transfer-Meta Framework for Cross-domain Recommendation to Cold-Start Users](https://mlsanity.com/paper/2105.04785/) (2021)
- [Decoupled Contrastive Multi-View Clustering with High-Order Random Walks](https://mlsanity.com/paper/2308.11164/) (2023)
- [Cross-Domain Recommendation to Cold-Start Users via Variational Information Bottleneck](https://mlsanity.com/paper/2203.16863/) (2022)
- [A Survey of Data-Efficient Graph Learning](https://mlsanity.com/paper/2402.00447/) (2024)
- [CDRNP: Cross-Domain Recommendation to Cold-Start Users via Neural Process](https://mlsanity.com/paper/2401.12732/) (2024)
- [DisenSemi: Semi-supervised Graph Classification via Disentangled Representation Learning](https://mlsanity.com/paper/2407.14081/) (2024)

## Built on by (most cited first, 2 of 2)

- [DG-STMTL: A Novel Graph Convolutional Network for Multi-Task Spatio-Temporal Traffic Forecasting](https://mlsanity.com/paper/2504.07822/) (2025)
- [Inductive Transfer Learning for Graph-Based Recommenders](https://mlsanity.com/paper/2510.22799/) (2025)

## Abstract (arXiv)

Recommender systems are widely used in various real-world applications, but they often encounter the persistent challenge of the user cold-start problem. Cross-domain recommendation (CDR), which leverages user interactions from one domain to improve prediction performance in another, has emerged as a promising solution. However, users with similar preferences in the source domain may exhibit different interests in the target domain. Therefore, directly transferring embeddings may introduce irrelevant source-domain collaborative information. In this paper, we propose a novel graph-based disentangled contrastive learning framework to capture fine-grained user intent and filter out irrelevant collaborative information, thereby avoiding negative transfer. Specifically, for each domain, we use a multi-channel graph encoder to capture diverse user intents. We then construct the affinity graph in the embedding space and perform multi-step random walks to capture high-order user similarity relationships. Treating one domain as the target, we propose a disentangled intent-wise contrastive learning approach, guided by user similarity, to refine the bridging of user intents across domains. Extensive experiments on four benchmark CDR datasets demonstrate that DisCo consistently outperforms existing state-of-the-art baselines, thereby validating the effectiveness of both DisCo and its components.