# Learning an evolved mixture model for task-free continual learning

arXiv: https://arxiv.org/abs/2207.05080 · HTML: https://mlsanity.com/paper/2207.05080/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 11 Jul 2022.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Task-Free Continual Learning](https://mlsanity.com/paper/1812.03596/) (2018)
- [Continual Unsupervised Representation Learning](https://mlsanity.com/paper/1910.14481/) (2019)
- [Continual Prototype Evolution: Learning Online from Non-Stationary Data Streams](https://mlsanity.com/paper/2009.00919/) (2020)
- [A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning](https://mlsanity.com/paper/2001.00689/) (2020)
- [Gradient-based Editing of Memory Examples for Online Task-free Continual Learning](https://mlsanity.com/paper/2006.15294/) (2020)
- [AdaNet: Adaptive Structural Learning of Artificial Neural Networks](https://mlsanity.com/paper/1607.01097/) (2016)
- [Learning latent representations across multiple data domains using Lifelong VAEGAN](https://mlsanity.com/paper/2007.10221/) (2020)
- [Less-forgetful Learning for Domain Expansion in Deep Neural Networks](https://mlsanity.com/paper/1711.05959/) (2017)
- [Lifelong Teacher-Student Network Learning](https://mlsanity.com/paper/2107.04689/) (2021)
- [Lifelong Mixture of Variational Autoencoders](https://mlsanity.com/paper/2107.04694/) (2021)
- [InfoVAEGAN : learning joint interpretable representations by information maximization and maximum likelihood](https://mlsanity.com/paper/2107.04705/) (2021)
- [Lifelong Infinite Mixture Model Based on Knowledge-Driven Dirichlet Process](https://mlsanity.com/paper/2108.12278/) (2021)
- [Lifelong Twin Generative Adversarial Networks](https://mlsanity.com/paper/2107.04708/) (2021)
- [Lifelong Generative Modelling Using Dynamic Expansion Graph Model](https://mlsanity.com/paper/2112.08370/) (2021)

## Built on by (most cited first, 3 of 3)

- [Task-Free Continual Learning via Online Discrepancy Distance Learning](https://mlsanity.com/paper/2210.06579/) (2022)
- [Continual Variational Autoencoder Learning via Online Cooperative Memorization](https://mlsanity.com/paper/2207.10131/) (2022)
- [Adversarially Diversified Rehearsal Memory (ADRM): Mitigating Memory Overfitting Challenge in Continual Learning](https://mlsanity.com/paper/2405.11829/) (2024)

## Abstract (arXiv)

Recently, continual learning (CL) has gained significant interest because it enables deep learning models to acquire new knowledge without forgetting previously learnt information. However, most existing works require knowing the task identities and boundaries, which is not realistic in a real context. In this paper, we address a more challenging and realistic setting in CL, namely the Task-Free Continual Learning (TFCL) in which a model is trained on non-stationary data streams with no explicit task information. To address TFCL, we introduce an evolved mixture model whose network architecture is dynamically expanded to adapt to the data distribution shift. We implement this expansion mechanism by evaluating the probability distance between the knowledge stored in each mixture model component and the current memory buffer using the Hilbert Schmidt Independence Criterion (HSIC). We further introduce two simple dropout mechanisms to selectively remove stored examples in order to avoid memory overload while preserving memory diversity. Empirical results demonstrate that the proposed approach achieves excellent performance.