Research

Paper

AI LLM February 24, 2026

Turning Semantics into Topology: LLM-Driven Attribute Augmentation for Collaborative Filtering

Authors

Junjie Meng, Ranxu zhang, Wei Wu, Rui Zhang, Chuan Qin, Qi Zhang, Qi Liu, Hui Xiong, Chao Wang

Abstract

Large Language Models (LLMs) have shown great potential for enhancing recommender systems through their extensive world knowledge and reasoning capabilities. However, effectively translating these semantic signals into traditional collaborative embeddings remains an open challenge. Existing approaches typically fall into two extremes: direct inference methods are computationally prohibitive for large-scale retrieval, while embedding-based methods primarily focus on unilateral feature augmentation rather than holistic collaborative signal enhancement. To bridge this gap, we propose Topology-Augmented Graph Collaborative Filtering (TAGCF), a novel framework that transforms semantic knowledge into topological connectivity. Unlike existing approaches that depend on textual features or direct interaction synthesis, TAGCF employs LLMs to infer interaction intents and underlying causal relationships from user-item pairs, representing these insights as intermediate attribute nodes within an enriched User-Attribute-Item (U-A-I) graph. Furthermore, to effectively model the heterogeneous relations in this augmented structure, we propose Adaptive Relation-weighted Graph Convolution (ARGC), which employs relation-specific prediction networks to dynamically estimate the importance of each relation type. Extensive experiments across multiple benchmark datasets and CF backbones demonstrate consistent improvements, with comprehensive evaluations including cold-start scenarios validating the effectiveness and robustness of our framework. All code will be made publicly available. For anonymous review, our code is available at the following anonymous link: https://anonymous.4open.science/r/AGCF-2441353190/.

Metadata

arXiv ID: 2602.21099
Provider: ARXIV
Primary Category: cs.IR
Published: 2026-02-24
Fetched: 2026-02-25 06:05

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.21099v1</id>\n    <title>Turning Semantics into Topology: LLM-Driven Attribute Augmentation for Collaborative Filtering</title>\n    <updated>2026-02-24T17:01:47Z</updated>\n    <link href='https://arxiv.org/abs/2602.21099v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.21099v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Large Language Models (LLMs) have shown great potential for enhancing recommender systems through their extensive world knowledge and reasoning capabilities. However, effectively translating these semantic signals into traditional collaborative embeddings remains an open challenge. Existing approaches typically fall into two extremes: direct inference methods are computationally prohibitive for large-scale retrieval, while embedding-based methods primarily focus on unilateral feature augmentation rather than holistic collaborative signal enhancement. To bridge this gap, we propose Topology-Augmented Graph Collaborative Filtering (TAGCF), a novel framework that transforms semantic knowledge into topological connectivity. Unlike existing approaches that depend on textual features or direct interaction synthesis, TAGCF employs LLMs to infer interaction intents and underlying causal relationships from user-item pairs, representing these insights as intermediate attribute nodes within an enriched User-Attribute-Item (U-A-I) graph. Furthermore, to effectively model the heterogeneous relations in this augmented structure, we propose Adaptive Relation-weighted Graph Convolution (ARGC), which employs relation-specific prediction networks to dynamically estimate the importance of each relation type. Extensive experiments across multiple benchmark datasets and CF backbones demonstrate consistent improvements, with comprehensive evaluations including cold-start scenarios validating the effectiveness and robustness of our framework. All code will be made publicly available. For anonymous review, our code is available at the following anonymous link: https://anonymous.4open.science/r/AGCF-2441353190/.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.IR'/>\n    <published>2026-02-24T17:01:47Z</published>\n    <arxiv:primary_category term='cs.IR'/>\n    <author>\n      <name>Junjie Meng</name>\n    </author>\n    <author>\n      <name>Ranxu zhang</name>\n    </author>\n    <author>\n      <name>Wei Wu</name>\n    </author>\n    <author>\n      <name>Rui Zhang</name>\n    </author>\n    <author>\n      <name>Chuan Qin</name>\n    </author>\n    <author>\n      <name>Qi Zhang</name>\n    </author>\n    <author>\n      <name>Qi Liu</name>\n    </author>\n    <author>\n      <name>Hui Xiong</name>\n    </author>\n    <author>\n      <name>Chao Wang</name>\n    </author>\n  </entry>"
}