FAME: Formal Abstract Minimal Explanation for Neural Networks
We propose FAME (Formal Abstract Minimal Explanations), a new class of abductive explanations grounded in abstract interpretation. FAME is the first method to scale to large neural networks while reducing explanation size. Our main contribution is the design of dedicated perturbation domains that eliminate the need for traversal order. FAME progressively shrinks these domains and leverages LiRPA-based bounds to discard irrelevant features, ultimately converging to a formal abstract minimal explanation. To assess explanation quality, we introduce a procedure that measures the worst-case distance between an abstract minimal explanation and a true minimal explanation. This procedure combines adversarial attacks with an optional VERIX+ refinement step. We benchmark FAME against VERIX+ and demonstrate consistent gains in both explanation size and runtime on medium- to large-scale neural networks.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
FAME-MT Dataset: Formality Awareness Made Easy for Machine Translation Purposes
People use language for various purposes. Apart from sharing information, individuals may use it to express emotions or to show respect for another person. In this paper, we focus on the formality level of machine-genera…
Machine TranslationSentenceTranslationContrastive Explanations for Argumentation-Based Conclusions
In this paper we discuss contrastive explanations for formal argumentation - the question why a certain argument (the fact) can be accepted, whilst another argument (the foil) cannot be accepted under various extension-b…
A Formal Framework for the Explanation of Finite Automata Decisions
Finite automata (FA) are a fundamental computational abstraction that is widely used in practice for various tasks in computer science, linguistics, biology, electrical engineering, and artificial intelligence. Given an …
Taming Silent Failures: A Framework for Verifiable AI Reliability
The integration of Artificial Intelligence (AI) into safety-critical systems introduces a new reliability paradigm: silent failures, where AI produces confident but incorrect outputs that can be dangerous. This paper int…
Hierarchical Expertise-Level Modeling for User Specific Robot-Behavior Explanations
There is a growing interest within the AI research community to develop autonomous systems capable of explaining their behavior to users. One aspect of the explanation generation problem that has yet to receive much atte…
Explanation Generation