DCGL: Dual-Channel Graph Learning with Large Language Models for Knowledge-Aware Recommendation

TL;DR

DCGL introduces a dual-channel graph learning framework leveraging LLMs and KGs to improve knowledge-aware recommendations by addressing semantic modeling, fusion, and interaction frequency challenges.

Contribution

The paper proposes a novel dual-channel architecture with contrastive learning and dynamic fusion to enhance recommendation accuracy and robustness.

Findings

DCGL outperforms state-of-the-art methods on four real-world datasets.

Significant improvements in sparse data scenarios.

Maintains high precision for active users.

Abstract

Knowledge Graphs (KGs) have proven highly effective for recommendation systems by capturing latent item relationships, while recent integration of Large Language Models (LLMs) has further enhanced semantic understanding and addressed knowledge sparsity issues. Nevertheless, current KG-and-LLM-based methods still face three main limitations: 1) inadequate modeling of implicit semantic relationships beyond explicit KG links; 2) suboptimal single-channel fusion of ID and LLM embeddings, which often leads to signal interference and blurred representations; and 3) insufficient consideration of user-item interaction frequency variations in recommendation strategies. To address these challenges, we propose the Dual-Channel Graph Learning (DCGL) framework, featuring three key innovations: 1) a dual-channel architecture that structurally decouples rich semantic information from user behavioral patterns, preventing early interference; 2) a multi-level contrastive learning mechanism that enhances robustness against KG noise through intra-view contrasts and bridges semantic gaps between channels via inter-view alignment; and 3) a dynamic fusion mechanism that adaptively balances semantic generalization and behavioral specificity based on interaction frequency, resolving the cascading limitation. Extensive experiments on four real-world datasets show that DCGL consistently outperforms state-of-the-art methods, yielding substantial improvements in sparse scenarios while maintaining precision for active users. Our code is available at https://github.com/XinchiZou/DCGL.