Bayesian Flow Networks in Continual Learning

Mateusz Pyla, Kamil Deja, Bartłomiej Twardowski, Tomasz Trzciński
10/18/2023
cs.LGcs.CVstat.ML

No confident code implementation found for this paper.

Abstract

Bayesian Flow Networks (BFNs) has been recently proposed as one of the most promising direction to universal generative modelling, having ability to learn any of the data type. Their power comes from the expressiveness of neural networks and Bayesian inference which make them suitable in the context of continual learning. We delve into the mechanics behind BFNs and conduct the experiments to empirically verify the generative capabilities on non-stationary data.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Bayesian Flow Networks

88% match1 repo3162023

Generative Flow Networks: Theory and Applications to Structure Learning

84% match2025

A theory of continuous generative flow networks

83% match1 repo282023

On Sequential Bayesian Inference for Continual Learning

81% match1 repo42023

General Proximal Flow Networks

81% match2026

Generative Modeling with Bayesian Sample Inference

81% match1 repo242025

Cite this paper

@article{pyla2023bayesian,
  title  = {Bayesian Flow Networks in Continual Learning},
  author = {Mateusz Pyla and Kamil Deja and Bartłomiej Twardowski and Tomasz Trzciński},
  year   = {2023},
  eprint = {2310.12001},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.12001v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.12001.svg)](https://codeofpaper.com/paper/2310.12001)

Discussion