User-specific Adaptive Fine-tuning for Cross-domain Recommendations
arXiv:2106.07864
Abstract
Making accurate recommendations for cold-start users has been a longstanding 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. Specifically, we devise a policy network with three alternative strategies to automatically decide which layers to be fine-tuned and which layers to have their parameters frozen for each user. Extensive experiments show that the proposed UAF exhibits significantly better and more robust performance for user cold-start recommendation.
References in corpus (11)
- BPR: Bayesian Personalized Ranking from Implicit Feedback
- How transferable are features in deep neural networks?
- Categorical Reparameterization with Gumbel-Softmax
- Language Models are Few-Shot Learners
- Recurrent Neural Networks with Top-k Gains for Session-based Recommendations
- Domain Separation Networks
- Neural Machine Translation in Linear Time
- Contextual Hybrid Session-based News Recommendation with Recurrent Neural Networks
- StackRec: Efficient Training of Very Deep Sequential Recommender Models by Iterative Stacking
- One Person, One Model, One World: Learning Continual User Representation without Forgetting
- A Generic Network Compression Framework for Sequential Recommender Systems