# Sequential Learning for Domain Generalization

arXiv: https://arxiv.org/abs/2004.01377 · HTML: https://mlsanity.com/paper/2004.01377/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2020.

## Built on by (most cited first, 26 of 26)

- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Gradient Matching for Domain Generalization](https://mlsanity.com/paper/2104.09937/) (2021)
- [Pin the Memory: Learning to Generalize Semantic Segmentation](https://mlsanity.com/paper/2204.03609/) (2022)
- [Anomaly Detection under Distribution Shift](https://mlsanity.com/paper/2303.13845/) (2023)
- [Temporal Domain Generalization with Drift-Aware Dynamic Neural Networks](https://mlsanity.com/paper/2205.10664/) (2022)
- [Domain Generalization through Meta-Learning: A Survey](https://mlsanity.com/paper/2404.02785/) (2024)
- [Continual Learning in Medical Image Analysis: A Comprehensive Review of Recent Advancements and Future Prospects](https://mlsanity.com/paper/2312.17004/) (2023)
- [MVDG: A Unified Multi-view Framework for Domain Generalization](https://mlsanity.com/paper/2112.12329/) (2021)
- [Does Continual Learning Equally Forget All Parameters?](https://mlsanity.com/paper/2304.04158/) (2023)
- [Selective Task Group Updates for Multi-Task Optimization](https://mlsanity.com/paper/2502.11986/) (2025)
- [Continuous Temporal Domain Generalization](https://mlsanity.com/paper/2405.16075/) (2024)
- [Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challenges](https://mlsanity.com/paper/2309.07438/) (2023)
- [Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-stationary Environment](https://mlsanity.com/paper/2301.07845/) (2023)
- [Confounder Identification-free Causal Visual Feature Learning](https://mlsanity.com/paper/2111.13420/) (2021)
- [Causal Inference via Style Transfer for Out-of-distribution Generalisation](https://mlsanity.com/paper/2212.03063/) (2022)
- [Enhancing Domain Adaptation through Prompt Gradient Alignment](https://mlsanity.com/paper/2406.09353/) (2024)
- [Balanced Direction from Multifarious Choices: Arithmetic Meta-Learning for Domain Generalization](https://mlsanity.com/paper/2503.18987/) (2025)
- [Continuous Domain Generalization](https://mlsanity.com/paper/2505.13519/) (2025)
- [Explainability-aided Domain Generalization for Image Classification](https://mlsanity.com/paper/2104.01742/) (2021)
- [Fault Diagnosis across Heterogeneous Domains via Self-Adaptive Temporal-Spatial Attention and Sample Generation](https://mlsanity.com/paper/2505.11083/) (2025)
- [Unsupervised Domain Adaptation Using Compact Internal Representations](https://mlsanity.com/paper/2401.07207/) (2024)
- [FlickerFusion: Intra-trajectory Domain Generalizing Multi-Agent RL](https://mlsanity.com/paper/2410.15876/) (2024)
- [Parameter-Efficient Temporal Domain Generalization](https://mlsanity.com/paper/2602.11965/) (2026)
- [Cumulative Meta-Learning from Active Learning Queries for Robustness to Spurious Correlations](https://mlsanity.com/paper/2605.20771/) (2026)
- [Adaptive Spectral-Koopman Dynamics Modeling for Temporal Domain Generalization](https://mlsanity.com/paper/2610.02822/) (2026)

## Abstract (arXiv)

In this paper we propose a sequential learning framework for Domain Generalization (DG), the problem of training a model that is robust to domain shift by design. Various DG approaches have been proposed with different motivating intuitions, but they typically optimize for a single step of domain generalization -- training on one set of domains and generalizing to one other. Our sequential learning is inspired by the idea lifelong learning, where accumulated experience means that learning the nth thing becomes easier than the 1st thing. In DG this means encountering a sequence of domains and at each step training to maximise performance on the next domain. The performance at domain n then depends on the previous n-1 learning problems. Thus backpropagating through the sequence means optimizing performance not just for the next domain, but all following domains. Training on all such sequences of domains provides dramatically more `practice' for a base DG learner compared to existing approaches, thus improving performance on a true testing domain. This strategy can be instantiated for different base DG algorithms, but we focus on its application to the recently proposed Meta-Learning Domain generalization (MLDG). We show that for MLDG it leads to a simple to implement and fast algorithm that provides consistent performance improvement on a variety of DG benchmarks.