paper-with-me

홈 › Papers

Global Counterfactual Explanations: Investigations, Implementations and Improvements

2022-04-14 · Dan Ley, Saumitra Mishra, Daniele Magazzeni

Counterfactual explanations have been widely studied in explainability, with a range of application dependent methods emerging in fairness, recourse and model understanding. However, the major shortcoming associated with these methods is their inability to provide explanations beyond the local or instance-level. While some works touch upon the notion of a global explanation, typically suggesting to aggregate masses of local explanations in the hope of ascertaining global properties, few provide frameworks that are either reliable or computationally tractable. Meanwhile, practitioners are requesting more efficient and interactive explainability tools. We take this opportunity to investigate existing global methods, with a focus on implementing and improving Actionable Recourse Summaries (AReS), the only known global counterfactual explanation framework for recourse.

📄 PDF Abstract BibTeX arXiv:2204.06917

Code (1)

understanding-ml/COLA pytorch

Tasks

counterfactualCounterfactual ExplanationFairness

Similar Papers 제목 키워드 기반

Counterfactual Explanations Can Be Manipulated

2021-06-04 · NeurIPS 2021 12 · Dylan Slack, Sophie Hilgard, Himabindu Lakkaraju, Sameer Singh

Counterfactual explanations are emerging as an attractive option for providing recourse to individuals adversely impacted by algorithmic decisions. As they are deployed in critical applications (e.g. law enforcement, fin…

counterfactualCounterfactual ExplanationCrime Prediction

Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learning

2024-06-19 · Danqing Wang, Antonis Antoniades, Kha-Dinh Luong, Edwin Zhang 외

Counterfactual explanations of Graph Neural Networks (GNNs) offer a powerful way to understand data that can naturally be represented by a graph structure. Furthermore, in many domains, it is highly desirable to derive d…

counterfactualCounterfactual ExplanationExplanation GenerationMolecular Property Prediction+1

CoLa-DCE -- Concept-guided Latent Diffusion Counterfactual Explanations

2024-06-03 · Franz Motzkus, Christian Hellert, Ute Schmid

Recent advancements in generative AI have introduced novel prospects and practical implementations. Especially diffusion models show their strength in generating diverse and, at the same time, realistic features, positio…

CoLAcounterfactualimage-classificationImage Classification

Global Graph Counterfactual Explanation: A Subgraph Mapping Approach

2024-10-25 · Yinhan He, Wendy Zheng, Yaochen Zhu, Jing Ma 외

Graph Neural Networks (GNNs) have been widely deployed in various real-world applications. However, most GNNs are black-box models that lack explanations. One strategy to explain GNNs is through counterfactual explanatio…

counterfactualCounterfactual Explanation

GCFX: Generative Counterfactual Explanations for Deep Graph Models at the Model Level

2026-01-26 · Jinlong Hu, Jiacheng Liu arxiv

Deep graph learning models have demonstrated remarkable capabilities in processing graph-structured data and have been widely applied across various fields. However, their complex internal architectures and lack of trans…

Graph GenerationGraph Learning