English

Great Models Think Alike: Improving Model Reliability via Inter-Model Latent Agreement

Machine Learning 2023-05-03 v1 Artificial Intelligence Computer Vision and Pattern Recognition

Abstract

Reliable application of machine learning is of primary importance to the practical deployment of deep learning methods. A fundamental challenge is that models are often unreliable due to overconfidence. In this paper, we estimate a model's reliability by measuring \emph{the agreement between its latent space, and the latent space of a foundation model}. However, it is challenging to measure the agreement between two different latent spaces due to their incoherence, \eg, arbitrary rotations and different dimensionality. To overcome this incoherence issue, we design a \emph{neighborhood agreement measure} between latent spaces and find that this agreement is surprisingly well-correlated with the reliability of a model's predictions. Further, we show that fusing neighborhood agreement into a model's predictive confidence in a post-hoc way significantly improves its reliability. Theoretical analysis and extensive experiments on failure detection across various datasets verify the effectiveness of our method on both in-distribution and out-of-distribution settings.

Keywords

Cite

@article{arxiv.2305.01481,
  title  = {Great Models Think Alike: Improving Model Reliability via Inter-Model Latent Agreement},
  author = {Ailin Deng and Miao Xiong and Bryan Hooi},
  journal= {arXiv preprint arXiv:2305.01481},
  year   = {2023}
}

Comments

ICML 2023

R2 v1 2026-06-28T10:23:32.109Z