Collective Knowledge Graph Completion with Mutual Knowledge Distillation

TL;DR

This paper introduces CKGC-CKD, a novel approach for multi-knowledge graph completion that leverages relation-aware graph convolutional networks and mutual knowledge distillation to enhance predictive accuracy across multilingual datasets.

Contribution

The paper proposes a new method combining relation-aware GCNs and mutual knowledge distillation for collective knowledge graph completion across multiple languages and sources.

Findings

Outperforms state-of-the-art models on multilingual datasets.

Effectively leverages cross-graph information to improve completion accuracy.

Demonstrates the benefit of mutual knowledge distillation in multi-KG scenarios.

Abstract

Knowledge graph completion (KGC), the task of predicting missing information based on the existing relational data inside a knowledge graph (KG), has drawn significant attention in recent years. However, the predictive power of KGC methods is often limited by the completeness of the existing knowledge graphs from different sources and languages. In monolingual and multilingual settings, KGs are potentially complementary to each other. In this paper, we study the problem of multi-KG completion, where we focus on maximizing the collective knowledge from different KGs to alleviate the incompleteness of individual KGs. Specifically, we propose a novel method called CKGC-CKD that uses relation-aware graph convolutional network encoder models on both individual KGs and a large fused KG in which seed alignments between KGs are regarded as edges for message propagation. An additional mutual knowledge distillation mechanism is also employed to maximize the knowledge transfer between the models of "global" fused KG and the "local" individual KGs. Experimental results on multilingual datasets have shown that our method outperforms all state-of-the-art models in the KGC task.