mlsanityData to 14 Oct 2026

CoRCi: Cross-Reconstruction of Coherent Interests Modeling in Cross-Domain Sequential Recommendation

arXiv 2608.09580 ↗First posted 10 Aug 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Cross-Domain Sequential Recommendation (CDSR) aims to alleviate data sparsity by transferring dynamic user interests across related domains. A key challenge lies in effectively bridging these domains. In single-domain modeling, models cannot distinguish between domain-specific and domain-invariant interests. Recent methods merge domain-specific sequences chronologically into a mixed-domain sequence to capture domain-invariant knowledge. However, they typically deploy separate encoders for the mixed-domain sequence and train them with per-domain loss aggregation. This workflow magnifies inter-domain discrepancies and disrupts domain-invariant interest coherence, especially when query target pairs in Seq2Seq originate from different domains. In this paper, we present CoRCi (Cross-Reconstruction for Coherent Interest), a dual-target CDSR framework that tackles these drawbacks. Specifically, CoRCi proposes a Cross-Reconstruction approach that generates mixed-domain representations directly from pre-encoded specific-domain representations via cross-attention. The generated representations are then trained using a single, sequence-level, domain-agnostic loss to preserve the coherence of domain-invariant interests. To further suppress domain discrepancies in mixed-domain modeling, CoRCi introduces FocalNCE, which embeds Focal Loss into the preceding mixed-domain InfoNCE objective. The new loss assigns higher penalties to negatives drawn from the same domain as the query, thereby strengthening domain-invariant alignment. Extensive experiments on four real-world datasets demonstrate that CoRCi consistently outperforms state-of-the-art CDSR counterparts, achieving statistically significant gains across all metrics.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 37 of its 65 references that are in the map. First posted on arXiv 10 Aug 2026.

Builds on

37 of 65 references.

References · 37

  1. 2017Attention Is All You Needcited by 60,361
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  5. 2023Qwen Technical Reportcited by 3,344
  6. 2018Self-Attentive Sequential Recommendationcited by 1,184
  7. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 964
  8. 2015Image-based Recommendations on Styles and Substitutescited by 706
  9. 2015Session-based Recommendations with Recurrent Neural Networkscited by 695
  10. 2016Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filteringcited by 520
  11. 2018Personalized Top-N Sequential Recommendation via Convolutional Sequence Embeddingcited by 476
  12. 2016Fusing Similarity Models with Markov Chains for Sparse Sequential Recommendationcited by 152
25 more
  1. 2021Sequential Recommendation with Graph Neural Networkscited by 89
  2. 2017Joint Deep Modeling of Users and Items Using Reviews for Recommendationcited by 84
  3. 2018CoNet: Collaborative Cross Networks for Cross-Domain Recommendationcited by 81
  4. 2021Global Context Enhanced Graph Neural Networks for Session-based Recommendationcited by 81
  5. 2023Leveraging Large Language Models for Sequential Recommendationcited by 78
  6. 2024Harnessing Large Language Models for Text-Rich Sequential Recommendationcited by 38
  7. 2019CosRec: 2D Convolutional Neural Networks for Sequential Recommendationcited by 37
  8. 2021DA-GCN: A Domain-aware Attentive Graph Convolution Network for Shared-account Cross-domain Sequential Recommendationcited by 34
  9. 2023Contrastive Cross-Domain Sequential Recommendationcited by 31
  10. 2021Transfer-Meta Framework for Cross-domain Recommendation to Cold-Start Userscited by 24
  11. 2021SAR-Net: A Scenario-Aware Ranking Network for Personalized Fair Recommendation in Hundreds of Travel Scenarioscited by 23
  12. 2020Mixed Information Flow for Cross-domain Sequential Recommendationscited by 22
  13. 2019Parallel Split-Join Networks for Shared-account Cross-domain Sequential Recommendationscited by 21
  14. 2022Adaptive Domain Interest Network for Multi-domain Recommendationcited by 20
  15. 2023Rethinking Cross-Domain Sequential Recommendation under Open-World Assumptionscited by 20
  16. 2024Exploring User Retrieval Integration towards Large Language Models for Cross-Domain Sequential Recommendationcited by 19
  17. 2021Dual Attentive Sequential Learning for Cross-Domain Click-Through Rate Predictioncited by 17
  18. 2023Mixed Attention Network for Cross-domain Sequential Recommendationcited by 15
  19. 2025Bridge the Domains: Large Language Models Enhanced Cross-domain Sequential Recommendationcited by 15
  20. 2024Pacer and Runner: Cooperative Learning Framework between Single- and Cross-Domain Sequential Recommendationcited by 13
  21. 2022DDGHM: Dual Dynamic Graph with Hybrid Metric Training for Cross-Domain Sequential Recommendationcited by 11
  22. 2017SPMC: Socially-Aware Personalized Markov Chains for Sparse Sequential Recommendationcited by 8
  23. 2023Cracking the Code of Negative Transfer: A Cooperative Game Theoretic Approach for Cross-Domain Sequential Recommendationcited by 7
  24. 2025ABXI: Invariant Interest Adaptation for Task-Guided Cross-Domain Sequential Recommendationcited by 7
  25. 2023FedDCSR: Federated Cross-domain Sequential Recommendation via Disentangled Representation Learningcited by 6

Built on by

Not cited yet.