A Model-Agnostic Framework for Recommendation via Interest-aware Item Embeddings
This addresses a limitation in recommendation systems for domains like news, retail, and videos by enabling better capture of user interests through model-agnostic improvements.
The paper tackles the problem that existing recommendation systems lack mechanisms to directly reflect user interests in item representations, proposing an Interest-aware Capsule network (IaCN) framework that learns interest-oriented item representations as an auxiliary task. Experimental results show significant performance enhancements across diverse recommendation models.
Item representation holds significant importance in recommendation systems, which encompasses domains such as news, retail, and videos. Retrieval and ranking models utilise item representation to capture the user-item relationship based on user behaviours. While existing representation learning methods primarily focus on optimising item-based mechanisms, such as attention and sequential modelling. However, these methods lack a modelling mechanism to directly reflect user interests within the learned item representations. Consequently, these methods may be less effective in capturing user interests indirectly. To address this challenge, we propose a novel Interest-aware Capsule network (IaCN) recommendation model, a model-agnostic framework that directly learns interest-oriented item representations. IaCN serves as an auxiliary task, enabling the joint learning of both item-based and interest-based representations. This framework adopts existing recommendation models without requiring substantial redesign. We evaluate the proposed approach on benchmark datasets, exploring various scenarios involving different deep neural networks, behaviour sequence lengths, and joint learning ratios of interest-oriented item representations. Experimental results demonstrate significant performance enhancements across diverse recommendation models, validating the effectiveness of our approach.