Transfer Learning for Efficient Domain Adaptation in Sequential Recommendation Systems
Authors:
- Vinay VenkateshVVVinay Venkatesh
- Sankaranainar ParmsivanSPSankaranainar Parmsivan
- Kathiresan JayabalanKJKathiresan Jayabalan
- 29 October 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 0258-0264
Abstract
The effectiveness of sequential modeling in personalized recommendation systems is often hindered by the challenge of providing high-precision recommendations to "power users" with concentrated, niche interests. Generic, single-model architectures tend to dilute these specific signals within a vast sea of general user behavior. While our previous research introduced domain-specific models and weighted loss functions as solutions, these approaches either lack scalability or may still struggle with sparse domains. This paper proposes a novel and more efficient framework based on transfer learning to combine the benefits of both. We introduce a methodology that fine-tunes a single, pre-trained PinnerFormer-based foundation model on smaller, domain-specific datasets. This approach bypasses the need to train a new, large model from scratch for each domain, significantly reducing computational costs while achieving superior performance. Our empirical validation on the MovieLens 25M Dataset shows that our fine-tuned model achieves substantial lifts in key metrics like Recall@10 and NDCG@10 for both "Horror" and "Action" movie domains, demonstrating its generalizability and efficiency.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Domain Focused Sequence Model Architecture for Predicting Long Term User Interests2025
- AI-Augmented DevSecOps Pipelines for Secure and Scalable Service-Oriented Architectures in Cloud-Native Systems2025
- Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation2023
- BERT4Rec2019
- Sampling-bias-corrected neural modeling for large corpus item recommendations2019
- Self-Attentive Sequential Recommendation2018
- Recurrent Neural Networks with Top-k Gains for Session-based Recommendations2018
- Nonlinear latent factorization by embedding multiple user interests2013
- Factorization Machines2010
- A Survey on Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 2009