Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning

2024-10-22

arXiv.org

AI Summary

Inductive knowledge graph completion (KGC) faces significant challenges in predicting relations for unseen entities due to the absence of structural and semantic priors during inference. Method: This paper proposes a dual-module framework integrating type-aware modeling and subgraph reasoning. It is the first to deeply fuse large language models’ semantic understanding with implicit type constraints and neighborhood facts—bypassing reliance on handcrafted relational paths. A prompt-guided supervised fine-tuning mechanism jointly models entity latent types and relevant local subgraph structures, including contextual paths and neighboring triples. Contribution/Results: Evaluated across 18 settings—including inductive, transductive, and few-shot scenarios—on three benchmark datasets, the method achieves state-of-the-art performance on 16 out of 18 MRR metrics, with an average absolute improvement of 7.2%. These results substantiate the effectiveness and generalizability of context-aware semantic inference for inductive KGC.

Technology Category

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

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

Inductive knowledge graph completion (KGC) aims to predict missing triples with unseen entities. Recent works focus on modeling reasoning paths between the head and tail entity as direct supporting evidence. However, these methods depend heavily on the existence and quality of reasoning paths, which limits their general applicability in different scenarios. In addition, we observe that latent type constraints and neighboring facts inherent in KGs are also vital in inferring missing triples. To effectively utilize all useful information in KGs, we introduce CATS, a novel context-aware inductive KGC solution. With sufficient guidance from proper prompts and supervised fine-tuning, CATS activates the strong semantic understanding and reasoning capabilities of large language models to assess the existence of query triples, which consist of two modules. First, the type-aware reasoning module evaluates whether the candidate entity matches the latent entity type as required by the query relation. Then, the subgraph reasoning module selects relevant reasoning paths and neighboring facts, and evaluates their correlation to the query triple. Experiment results on three widely used datasets demonstrate that CATS significantly outperforms state-of-the-art methods in 16 out of 18 transductive, inductive, and few-shot settings with an average absolute MRR improvement of 7.2%.

Problem

• Knowledge Graph Completion
• Type Rules
• Path Information

Innovation

• CATS
• Knowledge Graph Completion
• Large Language Model Inference