Litcius/Paper detail

Exploring Adapter-based Transfer Learning for Recommender Systems: Empirical Studies and Practical Insights

Junchen Fu, Fajie Yuan, Yu Song, Zheng Yuan, Mingyue Cheng, Shenghui Cheng, Jiaqi Zhang, Jie Wang, Yunzhu Pan

202435 citationsDOIOpen Access PDF

Abstract

Adapters, a plug-in neural network module with some tunable parameters, have emerged as a parameter-efficient transfer learning technique for adapting pre-trained models to downstream tasks, especially for natural language processing (NLP) and computer vision (CV) fields. Meanwhile, learning recommendation models directly from raw item modality features --- e.g., texts of NLP and images of CV --- can enable effective and transferable recommender systems (called TransRec). In view of this, a natural question arises:can adapter-based learning techniques achieve parameter-efficient TransRec with good performance?

Topics & Concepts

Adapter (computing)Computer scienceRecommender systemArtificial intelligenceTransfer of learningMachine learningArtificial neural networkNatural language processingComputer hardwareRecommender Systems and TechniquesMultimodal Machine Learning ApplicationsTopic Modeling
Exploring Adapter-based Transfer Learning for Recommender Systems: Empirical Studies and Practical Insights | Litcius