CausE: Towards Causal Knowledge Graph Embedding
This addresses the issue of noisy data in knowledge graphs for researchers and practitioners in AI, representing an incremental improvement with a novel causal approach.
The paper tackles the problem of knowledge graph embedding (KGE) being misled by trivial patterns and noisy links in real-world knowledge graphs, proposing a causality-enhanced framework (CausE) that outperforms baseline models and achieves state-of-the-art performance in knowledge graph completion.
Knowledge graph embedding (KGE) focuses on representing the entities and relations of a knowledge graph (KG) into the continuous vector spaces, which can be employed to predict the missing triples to achieve knowledge graph completion (KGC). However, KGE models often only briefly learn structural correlations of triple data and embeddings would be misled by the trivial patterns and noisy links in real-world KGs. To address this issue, we build the new paradigm of KGE in the context of causality and embedding disentanglement. We further propose a Causality-enhanced knowledge graph Embedding (CausE) framework. CausE employs causal intervention to estimate the causal effect of the confounder embeddings and design new training objectives to make stable predictions. Experimental results demonstrate that CausE could outperform the baseline models and achieve state-of-the-art KGC performance. We release our code in https://github.com/zjukg/CausE.