Knowledge Graph Completion with Counterfactual Augmentation

Chang, Heng; Cai, Jie; Li, Jia

doi:10.1145/3543507.3583401

Cited by 7 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the context of GNNs, removing a small fraction of nodes of the input graph identified by explanations can significantly change the predictions made by the GNNs. Counterfactual evidence is often concise and understandable [6,47] since they are matched with human intuitions of described causal situations [45]. To make explanations more robust and trustworthy, the counterfactual evidence should be diverse.…”

Section: Introductionmentioning

confidence: 99%

Rumor Detection with Diverse Counterfactual Evidence

Zhang

Shi

et al. 2023

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

The growth in social media has exacerbated the threat of fake news to individuals and communities. This draws increasing attention to developing efficient and timely rumor detection methods. The prevailing approaches resort to graph neural networks (GNNs) to exploit the post-propagation patterns of the rumor-spreading process. However, these methods lack inherent interpretation of rumor detection due to the black-box nature of GNNs. Moreover, these methods suffer from less robust results as they employ all the propagation patterns for rumor detection. In this paper, we address the above issues with the proposed Diverse Counterfactual Evidence framework for Rumor Detection (DCE-RD). Our intuition is to exploit the diverse counterfactual evidence of an event graph to serve as multi-view interpretations, which are further aggregated for robust rumor detection results. Specifically, our method first designs a subgraph generation strategy to efficiently generate different subgraphs of the event graph. We constrain the removal of these subgraphs to cause the change in rumor detection results. Thus, these subgraphs naturally serve as counterfactual evidence for rumor detection. To achieve multi-view interpretation, we design a diversity loss inspired by Determinantal Point Processes (DPP) to encourage diversity among the counterfactual evidence. A GNN-based rumor detection model further aggregates the diverse counterfactual evidence discovered by the proposed DCE-RD to achieve interpretable and robust rumor detection results. Extensive experiments on two real-world datasets show the superior performance of our method.

show abstract

Section: Introductionmentioning

confidence: 99%