Efficient Explanations from Empirical Explainers
Amid a discussion about Green AI in which we see explainability neglected, we explore the possibility to efficiently approximate computationally expensive explainers. To this end, we propose feature attribution modelling with Empirical Explainers. Empirical Explainers learn from data to predict the attribution maps of expensive explainers. We train and test Empirical Explainers in the language domain and find that they model their expensive counterparts surprisingly well, at a fraction of the cost. They could thus mitigate the computational burden of neural explanations significantly, in applications that tolerate an approximation error.
Code (2)
Similar Papers 제목 키워드 기반
Axiomatic Explainer Globalness via Optimal Transport
Explainability methods are often challenging to evaluate and compare. With a multitude of explainers available, practitioners must often compare and select explainers based on quantitative evaluation metrics. One particu…
Diversityfeature selectionOn the Robustness of Post-hoc GNN Explainers to Label Noise
Proposed as a solution to the inherent black-box limitations of graph neural networks (GNNs), post-hoc GNN explainers aim to provide precise and insightful explanations of the behaviours exhibited by trained GNNs. Despit…
From Model Explanation to Data Misinterpretation: Uncovering the Pitfalls of Post Hoc Explainers in Business Research
Machine learning models have been increasingly used in business research. However, most state-of-the-art machine learning models, such as deep neural networks and XGBoost, are black boxes in nature. Therefore, post hoc e…
Explainers' Mental Representations of Explainees' Needs in Everyday Explanations
In explanations, explainers have mental representations of explainees' developing knowledge and shifting interests regarding the explanandum. These mental representations are dynamic in nature and develop over time, ther…
Axiomatic Characterisations of Sample-based Explainers
Explaining decisions of black-box classifiers is both important and computationally challenging. In this paper, we scrutinize explainers that generate feature-based explanations from samples or datasets. We start by pres…