Optimal and efficient text counterfactuals using Graph Neural Networks
As NLP models become increasingly integral to decision-making processes, the need for explainability and interpretability has become paramount. In this work, we propose a framework that achieves the aforementioned by generating semantically edited inputs, known as counterfactual interventions, which change the model prediction, thus providing a form of counterfactual explanations for the model. We test our framework on two NLP tasks - binary sentiment classification and topic classification - and show that the generated edits are contrastive, fluent and minimal, while the whole process remains significantly faster that other state-of-the-art counterfactual editors.
Code (1)
Tasks
counterfactualDecision MakingSentiment AnalysisSentiment ClassificationTopic ClassificationSimilar Papers 제목 키워드 기반
Graph Edits for Counterfactual Explanations: A comparative study
Counterfactuals have been established as a popular explainability technique which leverages a set of minimal edits to alter the prediction of a classifier. When considering conceptual counterfactuals on images, the edits…
counterfactualGraph Neural NetworkKnowledge GraphsMotif-Consistent Counterfactuals with Adversarial Refinement for Graph-Level Anomaly Detection
Graph-level anomaly detection is significant in diverse domains. To improve detection performance, counterfactual graphs have been exploited to benefit the generalization capacity by learning causal relations. Most exist…
Anomaly DetectioncounterfactualGenerative Adversarial NetworkA control system framework for counterfactuals: an optimization based approach
Counterfactuals are a concept inherited from the field of logic and in general attain to the existence of causal relations between sentences or events. In particular, this concept has been introduced also in the context …
Querying Counterfactuals on Tissue Graphs with Supervised Disentanglement
Tissue graph counterfactuals ask how a cell's expression would change under altered spatial neighbor contexts. Such queries are central to predicting cell behavior in tissues, but lack a unified definition, with existing…
A Few Good Counterfactuals: Generating Interpretable, Plausible and Diverse Counterfactual Explanations
Counterfactual explanations provide a potentially significant solution to the Explainable AI (XAI) problem, but good, native counterfactuals have been shown to rarely occur in most datasets. Hence, the most popular metho…
counterfactualDiversityExplainable Artificial Intelligence (XAI)valid