CausalLP: Learning causal relations with weighted knowledge graph link prediction

TL;DR

CausalLP introduces a novel method for completing incomplete causal networks by framing the problem as knowledge graph link prediction, integrating external knowledge and causal weights to improve accuracy.

Contribution

It formulates causal network completion as a knowledge graph link prediction task, incorporating causal weights and proposing a new dataset splitting method for evaluation.

Findings

Weighted causal relations enhance link prediction accuracy.

CausalLP outperforms baseline methods in experiments.

Markov-based data split provides a more realistic evaluation.

Abstract

Causal networks are useful in a wide variety of applications, from medical diagnosis to root-cause analysis in manufacturing. In practice, however, causal networks are often incomplete with missing causal relations. This paper presents a novel approach, called CausalLP, that formulates the issue of incomplete causal networks as a knowledge graph completion problem. More specifically, the task of finding new causal relations in an incomplete causal network is mapped to the task of knowledge graph link prediction. The use of knowledge graphs to represent causal relations enables the integration of external domain knowledge; and as an added complexity, the causal relations have weights representing the strength of the causal association between entities in the knowledge graph. Two primary tasks are supported by CausalLP: causal explanation and causal prediction. An evaluation of this approach uses a benchmark dataset of simulated videos for causal reasoning, CLEVRER-Humans, and compares the performance of multiple knowledge graph embedding algorithms. Two distinct dataset splitting approaches are used for evaluation: (1) random-based split, which is the method typically employed to evaluate link prediction algorithms, and (2) Markov-based split, a novel data split technique that utilizes the Markovian property of causal relations. Results show that using weighted causal relations improves causal link prediction over the baseline without weighted relations.