CL4KGE: A Curriculum Learning Method for Knowledge Graph Embedding
This work addresses the challenge of optimizing training for knowledge graph embeddings, which is incremental as it builds on existing KGE methods with a novel training strategy.
The paper tackled the problem of improving knowledge graph embedding (KGE) training by introducing a curriculum learning method called CL4KGE, which uses a new metric Z-counts to measure triple difficulty and a scheduler to enhance training efficiency, resulting in state-of-the-art performance improvements on popular KGE models.
Knowledge graph embedding (KGE) constitutes a foundational task, directed towards learning representations for entities and relations within knowledge graphs (KGs), with the objective of crafting representations comprehensive enough to approximate the logical and symbolic interconnections among entities. In this paper, we define a metric Z-counts to measure the difficulty of training each triple ($<$head entity, relation, tail entity$>$) in KGs with theoretical analysis. Based on this metric, we propose \textbf{CL4KGE}, an efficient \textbf{C}urriculum \textbf{L}earning based training strategy for \textbf{KGE}. This method includes a difficulty measurer and a training scheduler that aids in the training of KGE models. Our approach possesses the flexibility to act as a plugin within a wide range of KGE models, with the added advantage of adaptability to the majority of KGs in existence. The proposed method has been evaluated on popular KGE models, and the results demonstrate that it enhances the state-of-the-art methods. The use of Z-counts as a metric has enabled the identification of challenging triples in KGs, which helps in devising effective training strategies.