DLRREC: Denoising Latent Representations via Multi-Modal Knowledge Fusion in Deep Recommender Systems

TL;DR

This paper introduces DLRREC, a novel framework that effectively denoises and fuses multi-modal features from Large Language Models in deep recommender systems, leading to improved recommendation accuracy.

Contribution

It proposes an end-to-end architecture with integrated dimensionality reduction and contrastive learning to enhance multi-modal feature utilization in recommender systems.

Findings

Outperforms existing methods on benchmark datasets.

Demonstrates significant improvement in recommendation accuracy.

Validates the effectiveness of integrated denoising and fusion techniques.

Abstract

Modern recommender systems struggle to effectively utilize the rich, yet high-dimensional and noisy, multi-modal features generated by Large Language Models (LLMs). Treating these features as static inputs decouples them from the core recommendation task. We address this limitation with a novel framework built on a key insight: deeply fusing multi-modal and collaborative knowledge for representation denoising. Our unified architecture introduces two primary technical innovations. First, we integrate dimensionality reduction directly into the recommendation model, enabling end-to-end co-training that makes the reduction process aware of the final ranking objective. Second, we introduce a contrastive learning objective that explicitly incorporates the collaborative filtering signal into the latent space. This synergistic process refines raw LLM embeddings, filtering noise while amplifying task-relevant signals. Extensive experiments confirm our method's superior discriminative power, proving that this integrated fusion and denoising strategy is critical for achieving state-of-the-art performance. Our work provides a foundational paradigm for effectively harnessing LLMs in recommender systems.