paper-with-me

홈 › Papers

Evaluating Explainability in Machine Learning Predictions through Explainer-Agnostic Metrics

2023-02-23 · Cristian Munoz, Kleyton da Costa, Bernardo Modenesi, Adriano Koshiyama

The rapid integration of artificial intelligence (AI) into various industries has introduced new challenges in governance and regulation, particularly regarding the understanding of complex AI systems. A critical demand from decision-makers is the ability to explain the results of machine learning models, which is essential for fostering trust and ensuring ethical AI practices. In this paper, we develop six distinct model-agnostic metrics designed to quantify the extent to which model predictions can be explained. These metrics measure different aspects of model explainability, ranging from local importance, global importance, and surrogate predictions, allowing for a comprehensive evaluation of how models generate their outputs. Furthermore, by computing our metrics, we can rank models in terms of explainability criteria such as importance concentration and consistency, prediction fluctuation, and surrogate fidelity and stability, offering a valuable tool for selecting models based not only on accuracy but also on transparency. We demonstrate the practical utility of these metrics on classification and regression tasks, and integrate these metrics into an existing Python package for public use.

📄 PDF Abstract BibTeX arXiv:2302.12094

Code (1)

holistic-ai/holisticai-research 공식 구현

Tasks

Feature Importance

Similar Papers 제목 키워드 기반

The Explanation Game: Towards Prediction Explainability through Sparse Communication

2020-04-28 · EMNLP (BlackboxNLP) 2020 11 · Marcos V. Treviso, André F. T. Martins

Explainability is a topic of growing importance in NLP. In this work, we provide a unified perspective of explainability as a communication problem between an explainer and a layperson about a classifier's decision. We u…

feature selectionMachine TranslationPredictiontext-classification+2

Measuring What Matters: A Unified Evaluation Framework for GNN Explainability

2026-07-06 · Francesco Paolo Nerini, Mirko Zaffaroni, Paolo Baracco, Gabriele Ciravegna 외 arxiv

Graph eXplainable AI (G-XAI) is increasingly important for making Graph Neural Networks interpretable and accountable. While a growing number of explainers are available, choosing the right method and assessing the trust…

bLIMEy: Surrogate Prediction Explanations Beyond LIME

2019-10-29 · Kacper Sokol, Alexander Hepburn, Raul Santos-Rodriguez, Peter Flach

Surrogate explainers of black-box machine learning predictions are of paramount importance in the field of eXplainable Artificial Intelligence since they can be applied to any type of data (images, text and tabular), are…

Explainable artificial intelligencePrediction

Evaluating the Explainers: Black-Box Explainable Machine Learning for Student Success Prediction in MOOCs

2022-07-01 · Vinitra Swamy, Bahar Radmehr, Natasa Krco, Mirko Marras 외

Neural networks are ubiquitous in applied machine learning for education. Their pervasive success in predictive performance comes alongside a severe weakness, the lack of explainability of their decisions, especially rel…

BIG-bench Machine LearningFeature Importance

InteractiveGNNExplainer: A Visual Analytics Framework for Multi-Faceted Understanding and Probing of Graph Neural Network Predictions

2025-11-17 · TC Singh, Sougata Mukherjea arxiv

Graph Neural Networks (GNNs) excel in graph-based learning tasks, but their complex, non-linear operations often render them as opaque "black boxes". This opacity hinders user trust, complicates debugging, bias detection…

Graph Neural NetworkNode ClassificationBias Detection