SELF: Surrogate-light Feature Selection with Large Language Models in Deep Recommender Systems

TL;DR

SELF introduces a novel feature selection method for deep recommender systems that combines semantic insights from Large Language Models with surrogate model refinement, enhancing efficiency and predictive accuracy.

Contribution

The paper presents SELF, a new feature selection approach that leverages LLMs and surrogate models to improve feature importance estimation in recommender systems.

Findings

SELF outperforms traditional methods on real-world datasets.

Semantic reasoning from LLMs enhances feature importance ranking.

Refinement by surrogate models improves predictive performance.

Abstract

Feature selection is crucial in recommender systems for improving model efficiency and predictive performance. Conventional approaches typically employ surrogate models-such as decision trees or neural networks-to estimate feature importance. However, their effectiveness is inherently constrained, as these models may struggle under suboptimal training conditions, including feature collinearity, high-dimensional sparsity, and insufficient data. In this paper, we propose SELF, an SurrogatE-Light Feature selection method for deep recommender systems. SELF integrates semantic reasoning from Large Language Models (LLMs) with task-specific learning from surrogate models. Specifically, LLMs first produce a semantically informed ranking of feature importance, which is subsequently refined by a surrogate model, effectively integrating general world knowledge with task-specific learning. Comprehensive experiments on three public datasets from real-world recommender platforms validate the effectiveness of SELF.