A Probabilistic Approach to Self-Supervised Learning using Cyclical Stochastic Gradient MCMC
Javanbakhat, Masoumeh, Lippert, Christoph
–arXiv.org Artificial Intelligence
In this paper we present a practical Bayesian self-supervised learning method with Cyclical Stochastic Gradient Hamiltonian Monte Carlo (cSGHMC). Within this framework, we place a prior over the parameters of a self-supervised learning model and use cSGHMC to approximate the high dimensional and multimodal posterior distribution over the embeddings. By exploring an expressive posterior over the embeddings, Bayesian self-supervised learning produces interpretable and diverse representations. Marginalizing over these representations yields a significant gain in performance, calibration and out-of-distribution detection on a variety of downstream classification tasks. We provide experimental results on multiple classification tasks on four challenging datasets. Moreover, we demonstrate the effectiveness of the proposed method in out-of-distribution detection using the SVHN and CIFAR-10 datasets.
arXiv.org Artificial Intelligence
Aug-2-2023
- Country:
- Europe > Germany (0.04)
- North America
- United States > New York
- New York County > New York City (0.04)
- Canada > Ontario
- Toronto (0.14)
- United States > New York
- Genre:
- Research Report (1.00)
- Technology: