MuCo-KGC: Multi-Context-Aware Knowledge Graph Completion
This addresses incomplete data in knowledge graphs for AI applications like recommendation systems, but it is incremental as it builds on existing textual and structural methods.
The paper tackles the problem of knowledge graph completion by predicting missing entities, proposing MuCo-KGC which uses contextual information from linked entities and relations to improve performance without needing entity descriptions or negative triplet sampling. It outperforms state-of-the-art methods on three datasets, with MRR improvements of 1.63%, 3.77%, and 20.15% on WN18RR, CoDEx-S, and CoDEx-M respectively.
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.