HetGCoT-Rec: Heterogeneous Graph-Enhanced Chain-of-Thought LLM Reasoning for Journal Recommendation

2025-01-02

AI Summary

This work addresses the academic journal recommendation task by proposing a novel method that jointly models heterogeneous graph structures and leverages large language models (LLMs) for interpretable reasoning. To overcome the dual bottlenecks of accuracy and interpretability in existing recommender systems, we design a structure-aware subgraph-to-natural-language context translation mechanism and develop a graph-enhanced, multi-step chain-of-thought (CoT) reasoning framework, enabling deep synergy between graph neural networks (GNNs) and LLMs. Our approach is built upon heterogeneous Graph Transformers and meta-path modeling, ensuring compatibility with diverse LLM architectures. Evaluated on the OpenAlex dataset, it achieves a Hit Rate of 96.48% and H@1 accuracy of 92.21%, significantly outperforming state-of-the-art baselines. Moreover, it generates high-quality, structurally traceable natural language explanations, bridging structural reasoning with human-understandable justifications.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Machine Learning: Graph-based Machine Learning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs 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: Large Language Models (LLM) for user modeling and recommendation

Abstract

Academic journal recommendation requires effectively combining structural understanding of scholarly networks with interpretable recommendations. While graph neural networks (GNNs) and large language models (LLMs) excel in their respective domains, current approaches often fail to achieve true integration at the reasoning level. We propose HetGCoT-Rec, a framework that deeply integrates heterogeneous graph transformer with LLMs through chain-of-thought reasoning. Our framework features two key technical innovations: (1) a structure-aware mechanism that transforms heterogeneous graph neural network learned subgraph information into natural language contexts, utilizing predefined metapaths to capture academic relationships, and (2) a multi-step reasoning strategy that systematically embeds graph-derived contexts into the LLM's stage-wise reasoning process. Experiments on a dataset collected from OpenAlex demonstrate that our approach significantly outperforms baseline methods, achieving 96.48% Hit rate and 92.21% H@1 accuracy. Furthermore, we validate the framework's adaptability across different LLM architectures, showing consistent improvements in both recommendation accuracy and explanation quality. Our work demonstrates an effective approach for combining graph-structured reasoning with language models for interpretable academic venue recommendations.

Problem

• Academic Journal Recommendation
• Graph Neural Networks
• Explainable Recommendation Methods

Innovation

• HetGCoT-Rec
• Heterogeneous Graph Neural Networks
• Large Language Model Integration