Domain-Generalization to Improve Learning in Meta-Learning Algorithms
Not on the map. Why?
Abstract (arXiv)
This paper introduces Domain Generalization Sharpness-Aware Minimization Model-Agnostic Meta-Learning (DGS-MAML), a novel meta-learning algorithm designed to generalize across tasks with limited training data. DGS-MAML combines gradient matching with sharpness-aware minimization in a bi-level optimization framework to enhance model adaptability and robustness. We support our method with theoretical analysis using PAC-Bayes and convergence guarantees. Experimental results on benchmark datasets show that DGS-MAML outperforms existing approaches in terms of accuracy and generalization. The proposed method is particularly useful for scenarios requiring few-shot learning and quick adaptation, and the source code is publicly available at GitHub.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 38 of its 62 references that are in the map. First posted on arXiv 13 Aug 2025.
Builds on
38 of 62 references.
References · 38
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2017Prototypical Networks for Few-shot Learningcited by 3,015
- 2016Matching Networks for One Shot Learningcited by 2,255
- 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,417
- 2016Optimization Methods for Large-Scale Machine Learningcited by 1,150
- 2018On First-Order Meta-Learning Algorithmscited by 1,018
- 2019On the Convergence of Adam and Beyondcited by 841
- 2019Meta-Learning with Implicit Gradientscited by 525
- 2020Dataset Condensation with Gradient Matchingcited by 516
- 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
- 2021ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networkscited by 293
26 more
- 2021Gradient Matching for Domain Generalizationcited by 258
- 2018Probabilistic Model-Agnostic Meta-Learningcited by 256
- 2018Bayesian Model-Agnostic Meta-Learningcited by 194
- 2018Recasting Gradient-Based Meta-Learning as Hierarchical Bayescited by 180
- 2022Surrogate Gap Minimization Improves Sharpness-Aware Trainingcited by 172
- 2021Efficient Sharpness-aware Minimization for Improved Training of Neural Networkscited by 137
- 2019On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithmscited by 132
- 2021Open Domain Generalization with Domain-Augmented Meta-Learningcited by 115
- 2023Sharpness-Aware Gradient Matching for Domain Generalizationcited by 102
- 2022When Do Flat Minima Optimizers Work?cited by 78
- 2022Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learningcited by 58
- 2019Torchmeta: A Meta-Learning library for PyTorchcited by 52
- 2022Delving into Effective Gradient Matching for Dataset Condensationcited by 40
- 2021Generalization Bounds for Meta-Learning via PAC-Bayes and Uniform Stabilitycited by 30
- 2021On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learningcited by 29
- 2020On the Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learningcited by 19
- 2022Is Bayesian Model-Agnostic Meta Learning Better than Model-Agnostic Meta Learning, Provably?cited by 13
- 2020Yet Meta Learning Can Adapt Fast, It Can Also Break Easilycited by 10
- 2022K-SAM: Sharpness-Aware Minimization at the Speed of SGDcited by 10
- 2023mSAM: Micro-Batch-Averaged Sharpness-Aware Minimizationcited by 10
- 2021ST-MAML: A Stochastic-Task based Method for Task-Heterogeneous Meta-Learningcited by 4
- 2022Gradient-Matching Coresets for Rehearsal-Based Continual Learningcited by 4
- 2023TBAM: Towards An Agent-Based Model to Enrich Twitter Datacited by 2
- 2025Sentiment Analysis of Movie Reviews Using BERTcited by 2
- 2025Adaptive Temperature Based on Logits Correlation in Knowledge Distillationcited by 2
- 2025A Novel Approach To Implementing Knowledge Distillation In Tsetlin Machinescited by 1
Built on by
Not cited yet.