Rule-Assisted Attribute Embedding

2025-06-10

AI Summary

Existing recommendation methods on attributed graphs often neglect deep attribute semantics, limiting their representational capacity. To address this, we propose a rule-guided attributed graph neural recommendation framework. First, high-confidence semantic rules are automatically mined from the attributed graph. Second, a rule-driven random walk strategy is designed to generate enhanced attribute paths. Finally, rule-aware attribute embeddings are integrated into a graph convolutional network (GCN) for joint optimization. Our approach establishes the first end-to-end coupling of semantic rule mining and attribute representation learning, significantly improving robustness under sparse or missing attribute conditions. Extensive experiments on BlogCatalog and Flickr demonstrate consistent gains: Recall@20 and NDCG@20 improve by an average of 10.6% over state-of-the-art methods.

Technology Category

• Data Mining & Knowledge Management: Rule Mining & Pattern Mining
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Reasoning with Beliefs

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Recommendation systems often overlook the rich attribute information embedded in property graphs, limiting their effectiveness. Existing graph convolutional network (GCN) models either ignore attributes or rely on simplistictriples, failing to capture deeper semantic structures. We propose RAE (Rule- Assisted Approach for Attribute Embedding), a novel method that improves recommendations by mining semantic rules from property graphs to guide attribute embedding. RAE performs rule-based random walks to generate enriched attribute representations, which are integrated into GCNs. Experiments on real-world datasets (BlogCatalog, Flickr) show that RAE outperforms state-of-the-art baselines by 10.6% on average in Recall@20 and NDCG@20. RAE also demonstrates greater robustness to sparse data and missing attributes, highlighting the value of leveraging structured attribute information in recommendation tasks.

Problem

• Enhancing recommendation systems with rich attribute information
• Improving attribute embedding using semantic rule mining
• Addressing data sparsity and missing attributes in recommendations

Innovation

• Mines semantic rules from property graphs
• Integrates rule-based random walks with GCNs
• Enhances attribute embedding for better recommendations