Formal explainability guarantees the rigor of computed explanations, and so it is paramount in domains where rigor is critical, including those deemed high-risk. Unfortunately, since its inception formal explainability has been hampered by poor scalability. At present, this limitation still holds true for some families of classifiers, the most significant being deep neural networks. This paper addresses the poor scalability of formal explainability and proposes novel efficient algorithms for computing formal explanations. The novel algorithm computes explanations by answering instead a number of robustness queries, and such that the number of such queries is at most linear on the number of features. Consequently, the proposed algorithm establishes a direct relationship between the practical complexity of formal explainability and that of robustness. To achieve the proposed goals, the paper generalizes the definition of formal explanations, thereby allowing the use of robustness tools that are based on different distance norms, and also by reasoning in terms of some target degree of robustness. Preliminary experiments validate the practical efficiency of the proposed approach.
fEDM+: A Risk-Based Fuzzy Ethical Decision Making Framework with Principle-Level Explainability and Pluralistic Validation
Dept. of Informatics, University of Bari ``Aldo Moro'', Bari, Italy(信息学院,巴里阿尔多·莫罗大学);Centro Interdipartimentale di Logica e Applicazioni (CILA), University of Bari ``Aldo Moro'', Bari, Italy(逻辑与应用跨部门中心(CILA),巴里阿尔多·莫罗大学)
Back to the Baseline: Examining Baseline Effects on Explainability Metrics
IRT Saint-Exupéry(圣埃克苏佩里技术研究院);Artificial and Natural Intelligence Toulouse Institute, Université de Toulouse(图卢兹大学人工与自然智能图卢兹研究所);Carney Institute for Brain Science, Brown University(布朗大学卡尼脑科学研究所);Sorbonne Université(索邦大学);CNRS(法国国家科学研究中心);Harvard University(哈佛大学)
Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods
Technical University of Munich(慕尼黑技术大学);School of Computation, Information and Technology(计算、信息与技术学院);Department of Computer Science(计算机科学系);Technische Universität Berlin(柏林技术大学);BIFOLD – Berlin Institute for the Foundations of Learning and Data(柏林学习与数据基础研究所);German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心)
Saliency strikes back: How filtering out high frequencies improves white-box explanations
Carney Institute for Brain Science, Brown University(布朗大学卡尼脑科学研究所);CerCo, CNRS(法国国家科学研究中心CerCo研究所);SNCF(法国国家铁路公司);Institute of Mathematics of Toulouse, University Paul Sabatier(保罗萨巴蒂埃大学图卢兹数学研究所)
SAGE: Semantic Explainability of Attention-Based Survival Models in Computational Pathology
Massachusetts Institute of Technology(麻省理工学院);Dana-Farber Cancer Institute(达纳-法伯癌症研究所);Brigham and Women’s Hospital(布莱根妇女医院);Harvard Medical School(哈佛医学院)
From Pixels to Explanations: Interpretable Diabetic Retinopathy Grading with CNN-Transformer Ensembles, Visual Explainability and Vision-Language Models
Department of Informatics, University of Salerno(萨勒诺大学信息学院);Department of Information Security and Communication Technology (IIK), Norwegian University of Science and Technology(挪威科技大学信息安全部)
EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use case
ENSTA, Institut Polytechnique Paris(巴黎综合理工学院ENSTA);Inria(法国国家信息与自动化研究所);DaSCI Andalusian Institute in Data Science and Computational Intelligence, University of Granada(格拉纳达大学DaSCI安达卢西亚数据科学与计算智能研究所);University of Granada(格拉纳达大学);Free University of Bozen-Bolzano(波尔扎诺自由大学)