Model-based Subsampling for Knowledge Graph Completion
This addresses overfitting in knowledge graph completion for AI researchers, but it is incremental as it builds on existing subsampling methods.
The paper tackled the problem of overfitting in Knowledge Graph Embedding (KGE) due to dataset sparsity by proposing Model-based Subsampling (MBS) and Mixed Subsampling (MIX) to better estimate appearance probabilities of infrequent queries. The result was improved KG completion performance on datasets FB15k-237, WN18RR, and YAGO3-10 for models like RotatE and TransE, though no concrete numbers were provided.
Subsampling is effective in Knowledge Graph Embedding (KGE) for reducing overfitting caused by the sparsity in Knowledge Graph (KG) datasets. However, current subsampling approaches consider only frequencies of queries that consist of entities and their relations. Thus, the existing subsampling potentially underestimates the appearance probabilities of infrequent queries even if the frequencies of their entities or relations are high. To address this problem, we propose Model-based Subsampling (MBS) and Mixed Subsampling (MIX) to estimate their appearance probabilities through predictions of KGE models. Evaluation results on datasets FB15k-237, WN18RR, and YAGO3-10 showed that our proposed subsampling methods actually improved the KG completion performances for popular KGE models, RotatE, TransE, HAKE, ComplEx, and DistMult.