# Cross-Domain Recommendation to Cold-Start Users via Variational Information Bottleneck

arXiv: https://arxiv.org/abs/2203.16863 · HTML: https://mlsanity.com/paper/2203.16863/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2022.

## Built on by (most cited first, 21 of 21)

- [Cross-domain recommendation via user interest alignment](https://mlsanity.com/paper/2301.11467/) (2023)
- [Enhancing Multimodal Entity and Relation Extraction with Variational Information Bottleneck](https://mlsanity.com/paper/2304.02328/) (2023)
- [Federated Graph Learning for Cross-Domain Recommendation](https://mlsanity.com/paper/2410.08249/) (2024)
- [Multi-domain Recommendation with Embedding Disentangling and Domain Alignment](https://mlsanity.com/paper/2308.05508/) (2023)
- [FedDCSR: Federated Cross-domain Sequential Recommendation via Disentangled Representation Learning](https://mlsanity.com/paper/2309.08420/) (2023)
- [A Comprehensive Survey on Self-Supervised Learning for Recommendation](https://mlsanity.com/paper/2404.03354/) (2024)
- [Towards Open-world Cross-Domain Sequential Recommendation: A Model-Agnostic Contrastive Denoising Approach](https://mlsanity.com/paper/2311.04760/) (2023)
- [Pre-trained Neural Recommenders: A Transferable Zero-Shot Framework for Recommendation Systems](https://mlsanity.com/paper/2309.01188/) (2023)
- [Diffusion Cross-domain Recommendation](https://mlsanity.com/paper/2402.02182/) (2024)
- [FedHCDR: Federated Cross-Domain Recommendation with Hypergraph Signal Decoupling](https://mlsanity.com/paper/2403.02630/) (2024)
- [All-in-One: Heterogeneous Interaction Modeling for Cold-Start Rating Prediction](https://mlsanity.com/paper/2403.17740/) (2024)
- [DisCo: Graph-Based Disentangled Contrastive Learning for Cold-Start Cross-Domain Recommendation](https://mlsanity.com/paper/2412.15005/) (2024)
- [DADIN: Domain Adversarial Deep Interest Network for Cross Domain Recommender Systems](https://mlsanity.com/paper/2305.12058/) (2023)
- [Cross-domain Transfer of Valence Preferences via a Meta-optimization Approach](https://mlsanity.com/paper/2406.16494/) (2024)
- [Stable Heterogeneous Treatment Effect Estimation across Out-of-Distribution Populations](https://mlsanity.com/paper/2407.03082/) (2024)
- [MDAP: A Multi-view Disentangled and Adaptive Preference Learning Framework for Cross-Domain Recommendation](https://mlsanity.com/paper/2410.05877/) (2024)
- [DIIT: A Domain-Invariant Information Transfer Method for Industrial Cross-Domain Recommendation](https://mlsanity.com/paper/2410.10835/) (2024)
- [LightFusionRec: Lightweight Transformers-Based Cross-Domain Recommendation Model](https://mlsanity.com/paper/2410.15656/) (2024)
- [Detecting and explaining postpartum depression in real-time with generative artificial intelligence](https://mlsanity.com/paper/2508.10025/) (2025)
- [Multimodal Representation-disentangled Information Bottleneck for Multimodal Recommendation](https://mlsanity.com/paper/2509.20225/) (2025)
- [TRWH: A Text-Driven Random Walk Heterogeneous GNN for Semantic-Aware Sparse Recommendation](https://mlsanity.com/paper/2607.25471/) (2026)

## Abstract (arXiv)

Recommender systems have been widely deployed in many real-world applications, but usually suffer from the long-standing user cold-start problem. As a promising way, Cross-Domain Recommendation (CDR) has attracted a surge of interest, which aims to transfer the user preferences observed in the source domain to make recommendations in the target domain. Previous CDR approaches mostly achieve the goal by following the Embedding and Mapping (EMCDR) idea which attempts to learn a mapping function to transfer the pre-trained user representations (embeddings) from the source domain into the target domain. However, they pre-train the user/item representations independently for each domain, ignoring to consider both domain interactions simultaneously. Therefore, the biased pre-trained representations inevitably involve the domain-specific information which may lead to negative impact to transfer information across domains. In this work, we consider a key point of the CDR task: what information needs to be shared across domains? To achieve the above idea, this paper utilizes the information bottleneck (IB) principle, and proposes a novel approach termed as CDRIB to enforce the representations encoding the domain-shared information. To derive the unbiased representations, we devise two IB regularizers to model the cross-domain/in-domain user-item interactions simultaneously and thereby CDRIB could consider both domain interactions jointly for de-biasing.