Efficient Explanations from Empirical Explainers

Abstract

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 the task of feature attribution modelling that we address 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 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.

Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools

“…A central hub 1. would increase the comparability and replicability of explainability research, 2. would mitigate the computational burden, 3. would mitigate the implementational burden since in-depth expert knowledge of the explainers and models is required. Put differently, a central data hub containing a wide variety of feature attribution maps and offering easy access to them would (1) democratize explainability research to a certain degree, and (2) contribute to green NLP (Strubell et al, 2019) and green XAI (Schwarzenberg et al, 2021) by circumventing redundant computations.…”