Skip to content

Calibrate to Interpret

Trustworthy machine learning is driving a large number of ML community works in order to improve ML acceptance and adoption. The main aspect of trustworthy machine learning are the followings: fairness, uncertainty, robustness, explainability and formal guaranties. Each of these individual domains gains the ML community interest, visible by the number of related publications. However, few works tackle the interconnection between these fields. In this paper, we show a first link between uncertainty and explainability, by studying the relation between calibration and interpretation. As the calibration of a given model changes the way it scores samples, and interpretation approaches often rely on these scores, it seems safe to assume that the confidence-calibration of a model interacts with our ability to interpret such model. In this paper, we show, in the context of networks trained on image classification tasks, to what extent interpretations are sensitive to confidence-calibration. It leads us to suggest a simple practice to improve the interpretation outcomes : Calibrate to Interpret.

Gregory Scafarto, Nicolas Posocco, Antoine Bonnefoy, Calibrate to Interpret, In Proc. of The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2022), September 2022.

Click here to access the paper.

Releated Posts

Privacy Enhancing Technologies 2024: A Summary

For Large Language Models (LLMs), Azure confidential computing offers TEEs to protect data integrity throughout various stages of the LLM lifecycle, including prompts, fine-tuning, and inference. This ensures that all
Read More

IEEE Big Data 2023 – A Summary

Our CTO, Sabri Skhiri, recently travelled to Sorrento for IEEE Big Data 2023. In this article, Sabri explores for you the various keynotes and talks that took place during the
Read More