Counterfactual Reasoning with Knowledge Graph Embeddings

arXiv:2403.06936v1 Announce Type: new
Abstract: Knowledge graph embeddings (KGEs) were originally developed to infer true but missing facts in incomplete knowledge repositories. In this paper, we link knowledge graph completion and counterfactual reasoning via our new task CFKGR. We model the original world state as a knowledge graph, hypothetical scenarios as edges added to the graph, and plausible changes to the graph as inferences from logical rules. We create corresponding benchmark datasets, which contain diverse hypothetical scenarios with plausible changes …

abstract arxiv counterfactual cs.ai cs.cl cs.lg embeddings facts graph knowledge knowledge graph paper reasoning repositories state true type via world