User-specific Adaptive Fine-tuning for Cross-domain Recommendations
- 14 October 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. PP (10414347) , 1
Abstract
Making accurate recommendations for cold-start users has been a long-standing and critical challenge for recommender systems (RS). Cross-domain recommendations (CDR) offer a solution to tackle such a cold-start problem when there is no sufficient data for the users who have rarely used the system. An effective approach in CDR is to leverage the knowledge (e.g., user representations) learned from a related but different domain and transfer it to the target domain. Fine-tuning works as an effective transfer learning technique for this objective, which adapts the parameters of a pre-trained model from the source domain to the target domain. However, current methods are mainly based on the global fine-tuning strategy: the decision of which layers of the pre-trained model to freeze or fine-tune is taken for all users in the target domain. In this paper, we argue that users in RS are personalized and should have their own fine-tuning policies for better preference transfer learning. As such, we propose a novel User-specific Adaptive Fine-tuning method (UAF), selecting which layers of the pre-trained network to fine-tune, on a per-user basis. Extensive experiments show that the proposed UAF exhibits significantly better and more robust performance for user cold-start recommendation.Keywords
Funding Information
- Youth Innovation Promotion Association of CAS China (2020357)
- Shenzhen Basic Research Foundation (JCYJ20200109113441941)
- Shenzhen Science and Technology Innovation Program (KQTD20190929172835662)
- National Natural Science Foundation of China (61906185)
This publication has 36 references indexed in Scilit:
- Contextual Hybrid Session-Based News Recommendation With Recurrent Neural NetworksIEEE Access, 2019
- SpotTune: Transfer Learning Through Adaptive Fine-Tuning2019
- Cross-Domain Recommendation via Deep Domain Adaptation2019
- BlockDrop: Dynamic Inference Paths in Residual Networks2018
- Efficient Parametrization of Multi-domain Deep Neural Networks2018
- Self-Critical Sequence Training for Image Captioning2017
- Cross-Stitch Networks for Multi-task Learning2016
- Deep Learning of Representations: Looking Forward2013
- Multitask LearningMachine Learning, 1997
- Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement LearningMachine Learning, 1992