Class Conditional Gaussians for Continual Learning

05/30/2023
by   Thomas L. Lee, et al.
0

Dealing with representation shift is one of the main problems in online continual learning. Current methods mainly solve this by reducing representation shift, but leave the classifier on top of the representation to slowly adapt, in many update steps, to the remaining representation shift, increasing forgetting. We propose DeepCCG, an empirical Bayesian approach to solve this problem. DeepCCG works by updating the posterior of a class conditional Gaussian classifier such that the classifier adapts instantly to representation shift. The use of a class conditional Gaussian classifier also enables DeepCCG to use a log conditional marginal likelihood loss to update the representation, which can be seen as a new type of replay. To perform the update to the classifier and representation, DeepCCG maintains a fixed number of examples in memory and so a key part of DeepCCG is selecting what examples to store, choosing the subset that minimises the KL divergence between the true posterior and the posterior induced by the subset. We demonstrate the performance of DeepCCG on a range of settings, including those with overlapping tasks which thus far have been under-explored. In the experiments, DeepCCG outperforms all other methods, evidencing its potential.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/18/2021

GCR: Gradient Coreset Based Replay Buffer Selection For Continual Learning

Continual learning (CL) aims to develop techniques by which a single mod...
research
10/29/2018

Marginal Replay vs Conditional Replay for Continual Learning

We present a new replay-based method of continual classification learnin...
research
05/18/2021

ACAE-REMIND for Online Continual Learning with Compressed Feature Replay

Online continual learning aims to learn from a non-IID stream of data fr...
research
02/18/2019

A Unifying Bayesian View of Continual Learning

Some machine learning applications require continual learning - where da...
research
10/16/2022

Navigating Memory Construction by Global Pseudo-Task Simulation for Continual Learning

Continual learning faces a crucial challenge of catastrophic forgetting....

Please sign up or login with your details

Forgot password? Click here to reset