DiffCDSR: Diffusion-guided Contrastive Learning and Position Re-weighting for Cross-Domain Sequential Recommendation
TL;DR
DiffCDSR is a novel framework that combines diffusion-guided contrastive learning with a Position Re-weighting (PR) module, enabling fine-grained modeling of user interest drift and providing insights into hyperparameter impacts.
Abstract
Cross-Domain Sequential Recommendation (CDSR) seeks to improve next-item prediction based on the historical behaviors of users in multiple domains. However, existing methods face two critical limitations: (1) static time-decay assumptions fail to capture short-term interest shifts, and (2) negative sampling through random perturbation undermines cross-domain consistency. To overcome these limitations, we propose DiffCDSR, a novel framework that combines diffusion-guided contrastive learning with a Position Re-weighting (PR) module. The PR module dynamically adjusts position importance, enabling fine-grained modeling of user interest drift. Meanwhile, a diffusion mechanism generates semantically perturbed, yet structure-preserving negative samples, enhancing the contrastive learning process. Experiments on three CDSR benchmarks demonstrate that DiffCDSR outperforms most state-of-the-art methods in NDCG@10 and HR@10, with ablations confirming component contributions. We also provide insights into hyperparameter impacts and discuss future directions for multimodal integration and efficient diffusion design. Project website: https://github.com/ShengGit/DiffCDSR.