MuCo-KGC: Multi-Context-Aware Knowledge Graph Completion

2025-03-05

AI Summary

Knowledge Graph Completion (KGC) faces challenges including poor generalization to unseen entities, heavy reliance on manually curated textual descriptions, high computational cost and semantic inconsistency induced by negative sampling, and—critically—the neglect of intra-graph structural context. To address these, we propose an end-to-end graph neural network method that requires neither textual entity descriptions nor negative sampling. Our approach is the first to explicitly model multi-hop adjacency structures for both entities and relations—including neighboring entities and relations—and employs a context-aware attention mechanism to learn structured semantic representations. By jointly optimizing expressiveness and efficiency, our method achieves state-of-the-art performance on FB15k-237, WN18RR, and CoDEx-S/M: it improves MRR by 1.63% on WN18RR, 3.77% on CoDEx-S, and 20.15% on CoDEx-M.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Graph-based Machine Learning
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Knowledge graph completion (KGC) seeks to predict missing entities (e.g., heads or tails) or relationships in knowledge graphs (KGs), which often contain incomplete data. Traditional embedding-based methods, such as TransE and ComplEx, have improved tail entity prediction but struggle to generalize to unseen entities during testing. Textual-based models mitigate this issue by leveraging additional semantic context; however, their reliance on negative triplet sampling introduces high computational overhead, semantic inconsistencies, and data imbalance. Recent approaches, like KG-BERT, show promise but depend heavily on entity descriptions, which are often unavailable in KGs. Critically, existing methods overlook valuable structural information in the KG related to the entities and relationships. To address these challenges, we propose Multi-Context-Aware Knowledge Graph Completion (MuCo-KGC), a novel model that utilizes contextual information from linked entities and relations within the graph to predict tail entities. MuCo-KGC eliminates the need for entity descriptions and negative triplet sampling, significantly reducing computational complexity while enhancing performance. Our experiments on standard datasets, including FB15k-237, WN18RR, CoDEx-S, and CoDEx-M, demonstrate that MuCo-KGC outperforms state-of-the-art methods on three datasets. Notably, MuCo-KGC improves MRR on WN18RR, and CoDEx-S and CoDEx-M datasets by $1.63%$, and $3.77%$ and $20.15%$ respectively, demonstrating its effectiveness for KGC tasks.

Problem

• Predicts missing entities and relationships in knowledge graphs.
• Addresses generalization issues in unseen entity prediction.
• Reduces computational complexity by eliminating negative triplet sampling.

Innovation

• Utilizes contextual information from linked entities
• Eliminates need for entity descriptions and negative sampling
• Reduces computational complexity while enhancing performance