paper-with-me

홈 › Papers

Faster Verified Explanations for Neural Networks

2025-11-28 · Alessandro De Palma, Greta Dolcetti, Caterina Urban arxiv

Verified explanations are a principled way to explain the decisions taken by neural networks, which are otherwise black-box in nature. However, these techniques face significant scalability challenges, as they require multiple calls to neural network verifiers, each of them with an exponential worst-case complexity. We present FaVeX, a novel algorithm to compute verified explanations. FaVeX accelerates the computation by dynamically combining batch and sequential processing of input features, and by reusing information from previous queries, both when proving invariances with respect to certain input features, and when searching for feature assignments altering the prediction. Furthermore, we present a novel and hierarchical definition of verified explanations, termed verifieroptimal robust explanations, that explicitly factors the incompleteness of network verifiers within the explanation. Our comprehensive experimental evaluation demonstrates the superior scalability of both FaVeX, and of verifier-optimal robust explanations, which together can produce meaningful formal explanation on networks with hundreds of thousands of non-linear activations.

📄 PDF Abstract BibTeX arXiv:2512.00164

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Better Verified Explanations with Applications to Incorrectness and Out-of-Distribution Detection

2024-09-04 · Min Wu, Xiaofu Li, Haoze Wu, Clark Barrett

Building on VeriX (Verified eXplainability, arXiv:2212.01051), a system for producing optimal verified explanations for machine learning model outputs, we present VeriX+, which significantly improves both the size and th…

Out-of-Distribution Detection

VeriX: Towards Verified Explainability of Deep Neural Networks

2022-12-02 · NeurIPS 2023 11

We present VeriX (Verified eXplainability), a system for producing optimal robust explanations and generating counterfactuals along decision boundaries of machine learning models. We build such explanations and counterfa…

Sensitivity

Towards a unified and verified understanding of group-operation networks

2024-10-09 · Wilson Wu, Louis Jaburi, Jacob Drori, Jason Gross

A recent line of work in mechanistic interpretability has focused on reverse-engineering the computation performed by neural networks trained on the binary operation of finite groups. We investigate the internals of one-…

EXPLAIN, AGREE, LEARN: Scaling Learning for Neural Probabilistic Logic

2024-08-15 · Victor Verreet, Lennert De Smet, Luc De Raedt, Emanuele Sansone

Neural probabilistic logic systems follow the neuro-symbolic (NeSy) paradigm by combining the perceptive and learning capabilities of neural networks with the robustness of probabilistic logic. Learning corresponds to li…

Diversity

FASTER-CE: Fast, Sparse, Transparent, and Robust Counterfactual Explanations

2022-10-12 · Shubham Sharma, Alan H. Gee, Jette Henderson, Joydeep Ghosh

Counterfactual explanations have substantially increased in popularity in the past few years as a useful human-centric way of understanding individual black-box model predictions. While several properties desired of high…

counterfactualExplanation Generation