Architect, Regularize and Replay (ARR): a Flexible Hybrid Approach for Continual Learning

01/06/2023
by   Vincenzo Lomonaco, et al.
University of Bologna
University of Pisa
0

In recent years we have witnessed a renewed interest in machine learning methodologies, especially for deep representation learning, that could overcome basic i.i.d. assumptions and tackle non-stationary environments subject to various distributional shifts or sample selection biases. Within this context, several computational approaches based on architectural priors, regularizers and replay policies have been proposed with different degrees of success depending on the specific scenario in which they were developed and assessed. However, designing comprehensive hybrid solutions that can flexibly and generally be applied with tunable efficiency-effectiveness trade-offs still seems a distant goal. In this paper, we propose "Architect, Regularize and Replay" (ARR), an hybrid generalization of the renowned AR1 algorithm and its variants, that can achieve state-of-the-art results in classic scenarios (e.g. class-incremental learning) but also generalize to arbitrary data streams generated from real-world datasets such as CIFAR-100, CORe50 and ImageNet-1000.

READ FULL TEXT
03/19/2022

Practical Recommendations for Replay-based Continual Learning Methods

Continual Learning requires the model to learn from a stream of dynamic,...
10/12/2020

Rethinking Experience Replay: a Bag of Tricks for Continual Learning

In Continual Learning, a Neural Network is trained on a stream of data w...
01/26/2023

Class-Incremental Learning with Repetition

Real-world data streams naturally include the repetition of previous con...
04/12/2022

Generative Negative Replay for Continual Learning

Learning continually is a key aspect of intelligence and a necessary abi...
09/08/2022

nVFNet-RDC: Replay and Non-Local Distillation Collaboration for Continual Object Detection

Continual Learning (CL) focuses on developing algorithms with the abilit...
05/23/2022

KRNet: Towards Efficient Knowledge Replay

The knowledge replay technique has been widely used in many tasks such a...

Please sign up or login with your details

Forgot password? Click here to reset