mlsanityData to 14 Oct 2026

DIIT: A Domain-Invariant Information Transfer Method for Industrial Cross-Domain Recommendation

arXiv 2410.10835 ↗First posted 29 Sep 2024cs.IR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Cross-Domain Recommendation (CDR) have received widespread attention due to their ability to utilize rich information across domains. However, most existing CDR methods assume an ideal static condition that is not practical in industrial recommendation systems (RS). Therefore, simply applying existing CDR methods in the industrial RS environment may lead to low effectiveness and efficiency. To fill this gap, we propose DIIT, an end-to-end Domain-Invariant Information Transfer method for industrial cross-domain recommendation. Specifically, We first simulate the industrial RS environment that maintains respective models in multiple domains, each of them is trained in the incremental mode. Then, for improving the effectiveness, we design two extractors to fully extract domain-invariant information from the latest source domain models at the domain level and the representation level respectively. Finally, for improving the efficiency, we design a migrator to transfer the extracted information to the latest target domain model, which only need the target domain model for inference. Experiments conducted on one production dataset and two public datasets verify the effectiveness and efficiency of DIIT.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 47 references that are in the map. First posted on arXiv 29 Sep 2024.

Builds on

29 of 47 references.

References · 29

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  3. 2014FitNets: Hints for Thin Deep Netscited by 1,653
  4. 2016Wide & Deep Learning for Recommender Systemscited by 747
  5. 2017Deep & Cross Network for Ad Click Predictionscited by 393
  6. 2022Curriculum Temperature for Knowledge Distillationcited by 112
  7. 2017CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Normscited by 96
  8. 2021Cross-Domain Recommendation: Challenges, Progress, and Prospectscited by 74
  9. 2022KuaiRand: An Unbiased Sequential Recommendation Dataset with Randomly Exposed Videoscited by 72
  10. 2016Deep Learning over Multi-field Categorical Data: A Case Study on User Response Predictioncited by 67
  11. 2018Adversarial Personalized Ranking for Recommendationcited by 49
  12. 2020MiNet: Mixed Interest Network for Cross-Domain Click-Through Rate Predictioncited by 30
17 more
  1. 2021A Survey on Cross-domain Recommendation: Taxonomies, Methods, and Future Directionscited by 30
  2. 2022Differential Private Knowledge Transfer for Privacy-Preserving Cross-Domain Recommendationcited by 22
  3. 2023MADG: Margin-based Adversarial Learning for Domain Generalizationcited by 22
  4. 2022Cross-Domain Recommendation to Cold-Start Users via Variational Information Bottleneckcited by 21
  5. 2023HAMUR: Hyper Adapter for Multi-Domain Recommendationcited by 21
  6. 2021A Unified Framework for Cross-Domain and Cross-System Recommendationscited by 19
  7. 2020Ensemble Knowledge Distillation for CTR Predictioncited by 18
  8. 2020Scenario-aware and Mutual-based approach for Multi-scenario Recommendation in E-Commercecited by 12
  9. 2022KEEP: An Industrial Pre-Training Framework for Online Recommendation via Knowledge Extraction and Pluggingcited by 11
  10. 2022Unbiased Knowledge Distillation for Recommendationcited by 11
  11. 2023Enhancing Cross-domain Click-Through Rate Prediction via Explicit Feature Augmentationcited by 11
  12. 2022Exploiting Variational Domain-Invariant User Embedding for Partially Overlapped Cross Domain Recommendationcited by 9
  13. 2023A Collaborative Transfer Learning Framework for Cross-domain Recommendationcited by 7
  14. 2022Continual Transfer Learning for Cross-Domain Click-Through Rate Prediction at Taobaocited by 6
  15. 2022An Incremental Learning framework for Large-scale CTR Predictioncited by 5
  16. 2023Towards More Robust and Accurate Sequential Recommendation with Cascade-guided Adversarial Trainingcited by 2
  17. 2023PEACE: Prototype lEarning Augmented transferable framework for Cross-domain rEcommendationcited by 1

Built on by

Not cited yet.