# Meta-Learning with Sparse Experience Replay for Lifelong Language Learning

arXiv: https://arxiv.org/abs/2009.04891 · HTML: https://mlsanity.com/paper/2009.04891/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2020.

## Built on by (most cited first, 12 of 12)

- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [Continual Learning for Text Classification with Information Disentanglement Based Regularization](https://mlsanity.com/paper/2104.05489/) (2021)
- [Lifelong Language Pretraining with Distribution-Specialized Experts](https://mlsanity.com/paper/2305.12281/) (2023)
- [Recent Advances of Foundation Language Models-based Continual Learning: A Survey](https://mlsanity.com/paper/2405.18653/) (2024)
- [Continual Sequence Generation with Adaptive Compositional Modules](https://mlsanity.com/paper/2203.10652/) (2022)
- [Prototype-Guided Memory Replay for Continual Learning](https://mlsanity.com/paper/2108.12641/) (2021)
- [How Relevant is Selective Memory Population in Lifelong Language Learning?](https://mlsanity.com/paper/2210.00940/) (2022)
- [MoE-CT: A Novel Approach For Large Language Models Training With Resistance To Catastrophic Forgetting](https://mlsanity.com/paper/2407.00875/) (2024)
- [Learning to Learn for Few-shot Continual Active Learning](https://mlsanity.com/paper/2311.03732/) (2023)
- [DRILL: Dynamic Representations for Imbalanced Lifelong Learning](https://mlsanity.com/paper/2105.08445/) (2021)
- [Meta-Learning with Variational Semantic Memory for Word Sense Disambiguation](https://mlsanity.com/paper/2106.02960/) (2021)
- [MetaCLBench: Meta Continual Learning Benchmark on Resource-Constrained Edge Devices](https://mlsanity.com/paper/2504.00174/) (2025)

## Abstract (arXiv)

Lifelong learning requires models that can continuously learn from sequential streams of data without suffering catastrophic forgetting due to shifts in data distributions. Deep learning models have thrived in the non-sequential learning paradigm; however, when used to learn a sequence of tasks, they fail to retain past knowledge and learn incrementally. We propose a novel approach to lifelong learning of language tasks based on meta-learning with sparse experience replay that directly optimizes to prevent forgetting. We show that under the realistic setting of performing a single pass on a stream of tasks and without any task identifiers, our method obtains state-of-the-art results on lifelong text classification and relation extraction. We analyze the effectiveness of our approach and further demonstrate its low computational and space complexity.