LLM-Empowered Representation Learning for Emerging Item Recommendation
By: Ziying Zhang, Quanming Yao, Yaqing Wang
Potential Business Impact:
Finds new things people will like.
In this work, we tackle the challenge of recommending emerging items, whose interactions gradually accumulate over time. Existing methods often overlook this dynamic process, typically assuming that emerging items have few or even no historical interactions. Such an assumption oversimplifies the problem, as a good model must preserve the uniqueness of emerging items while leveraging their shared patterns with established ones. To address this challenge, we propose EmerFlow, a novel LLM-empowered representation learning framework that generates distinctive embeddings for emerging items. It first enriches the raw features of emerging items through LLM reasoning, then aligns these representations with the embedding space of the existing recommendation model. Finally, new interactions are incorporated through meta-learning to refine the embeddings. This enables EmerFlow to learn expressive embeddings for emerging items from only limited interactions. Extensive experiments across diverse domains, including movies and pharmaceuticals, show that EmerFlow consistently outperforms existing methods.
Similar Papers
Bridging Collaborative Filtering and Large Language Models with Dynamic Alignment, Multimodal Fusion and Evidence-grounded Explanations
Information Retrieval
Shows you things you'll like, even if they change.
Learning to Make Friends: Coaching LLM Agents toward Emergent Social Ties
Artificial Intelligence
Computers learn to act like people online.
An Efficient LLM-based Evolutional Recommendation with Locate-Forget-Update Paradigm
Information Retrieval
Helps online stores recommend better by remembering what you like.