Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion

2024-11-12

arXiv.org

AI Summary

Knowledge graph completion (KGC) faces dual challenges: embedding-based methods are sensitive to noisy relations and long-tail entities, while text-based approaches suffer from semantic gaps between structured triples and natural language. Method: This paper proposes a retrieval–reasoning–reranking framework that jointly leverages structured triples and rich entity contexts—including labels, descriptions, and aliases—for the first time in KGC end-to-end pipelines. It introduces an LLM-driven dual-path candidate generation mechanism and a differentiable, context-aware reranking module, enabling synergistic structural and semantic reasoning. The framework integrates graph-based retrieval augmentation, LLM-based inference, and fine-tuned reranking, and is compatible with conventional embedding models (e.g., RotatE) for initial candidate generation. Contribution/Results: On FB15k237 and WN18RR, the method achieves absolute Hits@1 improvements of 12.3% and 5.6%, respectively, significantly outperforming state-of-the-art approaches.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Knowledge Representation and Reasoning: Knowledge Acquisition
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The Knowledge Graph Completion~(KGC) task aims to infer the missing entity from an incomplete triple. Existing embedding-based methods rely solely on triples in the KG, which is vulnerable to specious relation patterns and long-tail entities. On the other hand, text-based methods struggle with the semantic gap between KG triples and natural language. Apart from triples, entity contexts (e.g., labels, descriptions, aliases) also play a significant role in augmenting KGs. To address these limitations, we propose KGR3, a context-enriched framework for KGC. KGR3 is composed of three modules. Firstly, the Retrieval module gathers supporting triples from the KG, collects plausible candidate answers from a base embedding model, and retrieves context for each related entity. Then, the Reasoning module employs a large language model to generate potential answers for each query triple. Finally, the Re-ranking module combines candidate answers from the two modules mentioned above, and fine-tunes an LLM to provide the best answer. Extensive experiments on widely used datasets demonstrate that KGR3 consistently improves various KGC methods. Specifically, the best variant of KGR3 achieves absolute Hits@1 improvements of 12.3% and 5.6% on the FB15k237 and WN18RR datasets.

Problem

• Infer missing entities in incomplete knowledge graph triples
• Address limitations of embedding-based and text-based KGC methods
• Enhance KGC using entity contexts and multi-module reasoning

Innovation

• Retrieval module gathers triples and entity contexts
• Reasoning module uses LLM to generate potential answers
• Re-ranking module combines and fine-tunes LLM outputs