ABXI: Invariant Interest Adaptation for Task-Guided Cross-Domain Sequential Recommendation

2025-01-25

AI Summary

To address the challenges of imprecise domain knowledge transfer, temporal misalignment of sequential interactions, and imbalanced modeling of domain-specific characteristics in cross-domain sequential recommendation (CDSR), this paper proposes a task-guided invariant interest adaptation framework (TIA). TIA introduces a domain-invariant interest projector to explicitly disentangle shared cross-domain interests from domain-specific representations. It further employs a dual-LoRA collaborative fine-tuning mechanism atop a shared encoder to jointly model domain-common and domain-specific patterns. Additionally, TIA proposes a target-domain-aligned sequence matching strategy to mitigate cross-domain temporal misalignment. Extensive experiments on three benchmark datasets demonstrate that TIA consistently outperforms state-of-the-art CDSR methods. The implementation code is publicly available.

Technology Category

Machine Learning: Transfer, Domain Adaptation, Multi-Task LearningApplication Domains: Humanities & Computational Social ScienceData Mining & Knowledge Management: Recommender Systems

Application Category

Search and Retrieval-Augmented AI: Vertical and domain-specific searchUser Modeling, Personalization and Recommendation: Fairness-aware retrieval and rankingGraph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Cross-Domain Sequential Recommendation (CDSR) has recently gained attention for countering data sparsity by transferring knowledge across domains. A common approach merges domain-specific sequences into cross-domain sequences, serving as bridges to connect domains. One key challenge is to correctly extract the shared knowledge among these sequences and appropriately transfer it. Most existing works directly transfer unfiltered cross-domain knowledge rather than extracting domain-invariant components and adaptively integrating them into domain-specific modelings. Another challenge lies in aligning the domain-specific and cross-domain sequences. Existing methods align these sequences based on timestamps, but this approach can cause prediction mismatches when the current tokens and their targets belong to different domains. In such cases, the domain-specific knowledge carried by the current tokens may degrade performance. To address these challenges, we propose the A-B-Cross-to-Invariant Learning Recommender (ABXI). Specifically, leveraging LoRA's effectiveness for efficient adaptation, ABXI incorporates two types of LoRAs to facilitate knowledge adaptation. First, all sequences are processed through a shared encoder that employs a domain LoRA for each sequence, thereby preserving unique domain characteristics. Next, we introduce an invariant projector that extracts domain-invariant interests from cross-domain representations, utilizing an invariant LoRA to adapt these interests into modeling each specific domain. Besides, to avoid prediction mismatches, all domain-specific sequences are aligned to match the domains of the cross-domain ground truths. Experimental results on three datasets demonstrate that our approach outperforms other CDSR counterparts by a large margin. The codes are available in url{https://github.com/DiMarzioBian/ABXI}.

Problem

• Cross-Domain Sequential Recommendation
• Time Alignment
• Data Domain Variability

Innovation

• Cross-domain Sequential Recommendation
• LoRA Technology
• Time Alignment