LLM-Empowered Representation Learning for Emerging Item Recommendation

TL;DR

This paper introduces EmerFlow, a novel framework that leverages large language models and meta-learning to improve recommendation accuracy for emerging items with limited interaction data.

Contribution

EmerFlow is the first LLM-empowered framework that generates distinctive embeddings for emerging items, effectively integrating reasoning and meta-learning for dynamic recommendation tasks.

Findings

EmerFlow outperforms existing methods across multiple domains.

It effectively learns embeddings from limited interactions.

The approach demonstrates robustness in diverse recommendation scenarios.

Abstract

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.