# Continual Machine Reading Comprehension via Uncertainty-aware Fixed Memory and Adversarial Domain Adaptation

arXiv: https://arxiv.org/abs/2208.05217 · HTML: https://mlsanity.com/paper/2208.05217/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 29 references that are in the map.
- First posted on arXiv 10 Aug 2022.

## Builds on (most cited first, 24 of 24)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018)
- [Progress & Compress: A scalable framework for continual learning](https://mlsanity.com/paper/1805.06370/) (2018)
- [NewsQA: A Machine Comprehension Dataset](https://mlsanity.com/paper/1611.09830/) (2016)
- [Bidirectional Attention Flow for Machine Comprehension](https://mlsanity.com/paper/1611.01603/) (2016)
- [Episodic Memory in Lifelong Language Learning](https://mlsanity.com/paper/1906.01076/) (2019)
- [Reinforced Continual Learning](https://mlsanity.com/paper/1805.12369/) (2018)
- [MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension](https://mlsanity.com/paper/1910.09753/) (2019)
- [Retrospective Reader for Machine Reading Comprehension](https://mlsanity.com/paper/2001.09694/) (2020)
- [Continual Learning in Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2012.15504/) (2020)
- [Domain-agnostic Question-Answering with Adversarial Training](https://mlsanity.com/paper/1910.09342/) (2019)
- [Adversarial Domain Adaptation for Machine Reading Comprehension](https://mlsanity.com/paper/1908.09209/) (2019)
- [Unsupervised Domain Adaptation on Reading Comprehension](https://mlsanity.com/paper/1911.06137/) (2019)
- [Context-Aware Answer Extraction in Question Answering](https://mlsanity.com/paper/2011.02687/) (2020)
- [Continual Domain Adaptation for Machine Reading Comprehension](https://mlsanity.com/paper/2008.10874/) (2020)

## Built on by (most cited first, 2 of 2)

- [Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives](https://mlsanity.com/paper/2307.16851/) (2023)
- [Source-Free Domain Adaptation for Question Answering with Masked Self-training](https://mlsanity.com/paper/2212.09563/) (2022)

## Abstract (arXiv)

Continual Machine Reading Comprehension aims to incrementally learn from a continuous data stream across time without access the previous seen data, which is crucial for the development of real-world MRC systems. However, it is a great challenge to learn a new domain incrementally without catastrophically forgetting previous knowledge. In this paper, MA-MRC, a continual MRC model with uncertainty-aware fixed Memory and Adversarial domain adaptation, is proposed. In MA-MRC, a fixed size memory stores a small number of samples in previous domain data along with an uncertainty-aware updating strategy when new domain data arrives. For incremental learning, MA-MRC not only keeps a stable understanding by learning both memory and new domain data, but also makes full use of the domain adaptation relationship between them by adversarial learning strategy. The experimental results show that MA-MRC is superior to strong baselines and has a substantial incremental learning ability without catastrophically forgetting under two different continual MRC settings.