COTET: Cross-view Optimal Transport for Knowledge Graph Entity Typing

TL;DR

COTET introduces a novel multi-view optimal transport approach that integrates coarse and fine-grained information for improved knowledge graph entity typing, achieving superior results over existing methods.

Contribution

The paper proposes a new multi-view framework with optimal transport and a distribution-based loss to better utilize entity and type clustering information in KGET.

Findings

COTET outperforms baseline methods in entity typing accuracy.

The multi-view approach effectively captures hierarchical entity-type relationships.

The distribution-based loss reduces false negatives during training.

Abstract

Knowledge graph entity typing (KGET) aims to infer missing entity type instances in knowledge graphs. Previous research has predominantly centered around leveraging contextual information associated with entities, which provides valuable clues for inference. However, they have long ignored the dual nature of information inherent in entities, encompassing both high-level coarse-grained cluster knowledge and fine-grained type knowledge. This paper introduces Cross-view Optimal Transport for knowledge graph Entity Typing (COTET), a method that effectively incorporates the information on how types are clustered into the representation of entities and types. COTET comprises three modules: i) Multi-view Generation and Encoder, which captures structured knowledge at different levels of granularity through entity-type, entity-cluster, and type-cluster-type perspectives; ii) Cross-view Optimal Transport, transporting view-specific embeddings to a unified space by minimizing the Wasserstein distance from a distributional alignment perspective; iii) Pooling-based Entity Typing Prediction, employing a mixture pooling mechanism to aggregate prediction scores from diverse neighbors of an entity. Additionally, we introduce a distribution-based loss function to mitigate the occurrence of false negatives during training. Extensive experiments demonstrate the effectiveness of COTET when compared to existing baselines.