LGMLJun 17, 2021

Meta-Calibration: Learning of Model Calibration Using Differentiable Expected Calibration Error

arXiv:2106.09613v335 citations
AI Analysis

This addresses the calibration issue in neural networks, which is critical for real-world applications, though it appears incremental as it builds on existing calibration strategies.

The paper tackles the problem of neural network calibration by introducing a differentiable surrogate for expected calibration error (DECE) and a meta-learning framework to optimize calibration with respect to hyper-parameters, achieving competitive performance with existing approaches.

Calibration of neural networks is a topical problem that is becoming more and more important as neural networks increasingly underpin real-world applications. The problem is especially noticeable when using modern neural networks, for which there is a significant difference between the confidence of the model and the probability of correct prediction. Various strategies have been proposed to improve calibration, yet accurate calibration remains challenging. We propose a novel framework with two contributions: introducing a new differentiable surrogate for expected calibration error (DECE) that allows calibration quality to be directly optimised, and a meta-learning framework that uses DECE to optimise for validation set calibration with respect to model hyper-parameters. The results show that we achieve competitive performance with existing calibration approaches. Our framework opens up a new avenue and toolset for tackling calibration, which we believe will inspire further work on this important challenge.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes