PANDA-CDR: Perturbation-Aware and Neural Dual-Channel Alignment for Cross-Domain Recommendation

Ruohan Wang, Gaode Chen, Miaobo Hu, Ji Xiang, Ruixin Song, Cong Xue, Lei Wang, Haoyuan Teng

Abstract: Recommender systems have been widely adopted in real-world applications, yet they still face challenges in addressing the cold-start problem. Cross-domain recommendation (CDR) offers a promising solution to the cold-start problem by transferring user preferences across domains. However, existing methods often rely on overlapping users or biased embeddings, limiting their generalization and fairness. We propose PANDA-CDR, a unified CDR framework that integrates perturbation-guided contrastive bottleneck and dual-channel disentanglement to learn robust transferable semantics. To enhance fairness, especially under long-tail distributions, we further introduce adversarial domain alignment and exposure-aware reweighting to mitigate popularity bias. Extensive experiments on real-world benchmarks show that PANDA-CDR achieves state-of-the-art performance while improving cold-start and long-tail recommendation fairness in sparse, low-overlap scenarios.

External IDs:dblp:conf/trustcom/WangCHXSXWT25