Continuous Model Evaluation and Adaptation to Distribution Shifts: a Probabilistic Self-Supervised Approach

EasyChair Preprint no. 8303

Abstract

This paper introduces a Bayesian approach to estimating distribution shifts over the modelled variables and continuous model adaptations to mitigate the impact of such shifts. The method exploits probabilistic inference over sets of correlated variables in causal models describing data generating processes. By extending the models with latent auxiliary variables, probabilistic inference over sets of correlated variables enables estimation of the distribution shifts impacting different parts of the models. Moreover, the introduction of latent auxiliary variables makes inference more robust against distribution shifts and supports automated, self-supervised adaptation of the modelling parameters during the operation, often significantly reducing the adverse impact of the distribution shifts. The effectiveness of the method has been validated in systematic experiments using synthetic data.

Keyphrases: Bayesian networks, distribution shift, inference, machine learning, Trust

@Booklet{EasyChair:8303,
  author = {Gregor Pavlin and Pieter de Villiers and Kathryn Laskey and Franck Mignet and Lennard Jansen},
  title = {Continuous Model Evaluation and Adaptation to Distribution Shifts: a Probabilistic Self-Supervised Approach},
  howpublished = {EasyChair Preprint no. 8303},

  year = {EasyChair, 2022}}