Active Continual Learning with Metaplastic Binary Bayesian Neural Networks

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cottart, Kellian, Ballet, Théo, Bonnet, Djohan, Querlioz, Damien
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913170749128704
author Cottart, Kellian
Ballet, Théo
Bonnet, Djohan
Querlioz, Damien
author_facet Cottart, Kellian
Ballet, Théo
Bonnet, Djohan
Querlioz, Damien
contents Always-on edge systems must keep learning as conditions change under tight compute budgets and must detect unreliable predictions. Bayesian binary neural networks are attractive in this setting, but mean-field Bernoulli posteriors can saturate on long non-stationary streams, wiping out epistemic uncertainty and freezing plasticity. We propose BiMU, derived from a bounded-memory variational objective that balances stability, plasticity, and forgetting. BiMU combines a data term with controlled relaxation toward the prior and an uncertainty-dependent step size that prevents saturation and sustains informative uncertainty. This non-degenerate posterior enables fully online, buffer-free active querying via Monte Carlo disagreement, reducing label queries and backpropagation updates under imbalance. BiMU sustains learning and strong OOD detection on 1000-tasks Permuted-MNIST, and on OpenLORIS-Object achieves up to 32$\times$ label/update savings at matched accuracy under class imbalance and feature compression.
format Preprint
id arxiv_https___arxiv_org_abs_2605_30198
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Active Continual Learning with Metaplastic Binary Bayesian Neural Networks
Cottart, Kellian
Ballet, Théo
Bonnet, Djohan
Querlioz, Damien
Machine Learning
Always-on edge systems must keep learning as conditions change under tight compute budgets and must detect unreliable predictions. Bayesian binary neural networks are attractive in this setting, but mean-field Bernoulli posteriors can saturate on long non-stationary streams, wiping out epistemic uncertainty and freezing plasticity. We propose BiMU, derived from a bounded-memory variational objective that balances stability, plasticity, and forgetting. BiMU combines a data term with controlled relaxation toward the prior and an uncertainty-dependent step size that prevents saturation and sustains informative uncertainty. This non-degenerate posterior enables fully online, buffer-free active querying via Monte Carlo disagreement, reducing label queries and backpropagation updates under imbalance. BiMU sustains learning and strong OOD detection on 1000-tasks Permuted-MNIST, and on OpenLORIS-Object achieves up to 32$\times$ label/update savings at matched accuracy under class imbalance and feature compression.
title Active Continual Learning with Metaplastic Binary Bayesian Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2605.30198