# Task Agnostic Continual Learning via Meta Learning

arXiv: https://arxiv.org/abs/1906.05201 · HTML: https://mlsanity.com/paper/1906.05201/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2019.

## Built on by (most cited first, 30 of 53)

- [New Insights on Reducing Abrupt Representation Change in Online Continual Learning](https://mlsanity.com/paper/2104.05025/) (2021)
- [Probing Representation Forgetting in Supervised and Unsupervised Continual Learning](https://mlsanity.com/paper/2203.13381/) (2022)
- [Continual Learning via Local Module Composition](https://mlsanity.com/paper/2111.07736/) (2021)
- [Posterior Meta-Replay for Continual Learning](https://mlsanity.com/paper/2103.01133/) (2021)
- [Towards mental time travel: a hierarchical memory for reinforcement learning agents](https://mlsanity.com/paper/2105.14039/) (2021)
- [DualNet: Continual Learning, Fast and Slow](https://mlsanity.com/paper/2110.00175/) (2021)
- [Understanding Continual Learning Settings with Data Distribution Drift Analysis](https://mlsanity.com/paper/2104.01678/) (2021)
- [On the Soft-Subnetwork for Few-shot Class Incremental Learning](https://mlsanity.com/paper/2209.07529/) (2022)
- [Non-IID data and Continual Learning processes in Federated Learning: A long road ahead](https://mlsanity.com/paper/2111.13394/) (2021)
- [Continual Learning for Recurrent Neural Networks: an Empirical Evaluation](https://mlsanity.com/paper/2103.07492/) (2021)
- [Learning where to learn: Gradient sparsity in meta and continual learning](https://mlsanity.com/paper/2110.14402/) (2021)
- [Improving Task-free Continual Learning by Distributionally Robust Memory Evolution](https://mlsanity.com/paper/2207.07256/) (2022)
- [Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffer](https://mlsanity.com/paper/2101.09536/) (2021)
- [Learning to Modulate pre-trained Models in RL](https://mlsanity.com/paper/2306.14884/) (2023)
- [Online-LoRA: Task-free Online Continual Learning via Low Rank Adaptation](https://mlsanity.com/paper/2411.05663/) (2024)
- [Optimizing Reusable Knowledge for Continual Learning via Metalearning](https://mlsanity.com/paper/2106.05390/) (2021)
- [Continual Semi-Supervised Learning through Contrastive Interpolation Consistency](https://mlsanity.com/paper/2108.06552/) (2021)
- [Drift-Resilient TabPFN: In-Context Learning Temporal Distribution Shifts on Tabular Data](https://mlsanity.com/paper/2411.10634/) (2024)
- [Modality-Agnostic Variational Compression of Implicit Neural Representations](https://mlsanity.com/paper/2301.09479/) (2023)
- [DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend Forecasting](https://mlsanity.com/paper/2306.09862/) (2023)
- [Sequoia: A Software Framework to Unify Continual Learning Research](https://mlsanity.com/paper/2108.01005/) (2021)
- [Discrete Key-Value Bottleneck](https://mlsanity.com/paper/2207.11240/) (2022)
- [Encoders and Ensembles for Task-Free Continual Learning](https://mlsanity.com/paper/2105.13327/) (2021)
- [Task-agnostic Continual Learning with Hybrid Probabilistic Models](https://mlsanity.com/paper/2106.12772/) (2021)
- [CoMPS: Continual Meta Policy Search](https://mlsanity.com/paper/2112.04467/) (2021)
- [When Meta-Learning Meets Online and Continual Learning: A Survey](https://mlsanity.com/paper/2311.05241/) (2023)
- [Continual Learning on Graphs: A Survey](https://mlsanity.com/paper/2402.06330/) (2024)
- [Towards a theory of out-of-distribution learning](https://mlsanity.com/paper/2109.14501/) (2021)
- [Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges](https://mlsanity.com/paper/2205.14495/) (2022)
- [Beyond Supervised Continual Learning: a Review](https://mlsanity.com/paper/2208.14307/) (2022)

## Abstract (arXiv)

While neural networks are powerful function approximators, they suffer from catastrophic forgetting when the data distribution is not stationary. One particular formalism that studies learning under non-stationary distribution is provided by continual learning, where the non-stationarity is imposed by a sequence of distinct tasks. Most methods in this space assume, however, the knowledge of task boundaries, and focus on alleviating catastrophic forgetting. In this work, we depart from this view and move the focus towards faster remembering -- i.e measuring how quickly the network recovers performance rather than measuring the network's performance without any adaptation. We argue that in many settings this can be more effective and that it opens the door to combining meta-learning and continual learning techniques, leveraging their complementary advantages. We propose a framework specific for the scenario where no information about task boundaries or task identity is given. It relies on a separation of concerns into what task is being solved and how the task should be solved. This framework is implemented by differentiating task specific parameters from task agnostic parameters, where the latter are optimized in a continual meta learning fashion, without access to multiple tasks at the same time. We showcase this framework in a supervised learning scenario and discuss the implication of the proposed formalism.