International Peer-Reviewed JournalOpen AccessISSN 2456-8880
irejournals@gmail.com+91-7433024337

Home / Current Issue / Paper 1719292

1719292PublishedVol 9 · Issue 12

Meta-Learning for Domain Generalization Under Distribution Shift: Methods, Benchmarks, and Open Challenges

Aryanil Roy Mainak Ghatak Sananda Chatterjee Kaushik Banerjee

Subject area: Science,Engineering and Technology  ·  Area of research: Artificial Intelligence / Machine Learning

DOI: https://doi.org/10.64388/IREV9I12-1719292

Abstract

Domain generalization (DG) explores how a model trained on a fixed set of source domains can perform reliably on unseen tar-get domains. Meta-learning addresses this by training models to explic-itly learn to generalize, yet curated benchmarks have repeatedly shown that well-tuned evidence-based risk minimization (ERM) is a formidable baseline. This survey examines that tension with a focus on what ac-tually generalizes and why. We contribute three things. First, a bivari-ate taxonomy that cross references shift type (covariate, conditional, in-variant covariate, category, compound) against meta intervention level (data/augmentation, representation/gradient, optimization/parameter, prompt/foundation). Second, a structured comparison of benchmark fam-ilies: DomainBed, WILDS, single source, and open set settings that shows how benchmark choice, and not just method design, drives published conclusions. Third, a critical analysis of conditions under which meta-learning gains over ERM are real versus aphemeral, updated for the 2023-2026 period when foundation models, causal approaches, and meta prompting have substantially changed the landscape. We conclude with actionable open challenges and directions where meta-learning retains a genuine edge.

Keywords

Domain Generalization, Meta-Learning, Distribution Shift, Domainbed, WILDS, Benchmark Comparison, Transfer Learning

How to cite this paper

Aryanil Roy, Mainak Ghatak, Sananda Chatterjee, Kaushik Banerjee "Meta-Learning for Domain Generalization Under Distribution Shift: Methods, Benchmarks, and Open Challenges" Iconic Research And Engineering Journals Volume 9 Issue 12 2026 Page 3230-3238 https://doi.org/10.64388/IREV9I12-1719292
Aryanil Roy, Mainak Ghatak, Sananda Chatterjee, Kaushik Banerjee "Meta-Learning for Domain Generalization Under Distribution Shift: Methods, Benchmarks, and Open Challenges" Iconic Research And Engineering Journals, vol. 9, no. 12, Jun. 2026, doi: https://doi.org/10.64388/IREV9I12-1719292
Aryanil Roy, Mainak Ghatak, Sananda Chatterjee, Kaushik Banerjee (2026). Meta-Learning for Domain Generalization Under Distribution Shift: Methods, Benchmarks, and Open Challenges. Iconic Research And Engineering Journals, 9(12). doi: https://doi.org/10.64388/IREV9I12-1719292
Aryanil Roy, Mainak Ghatak, Sananda Chatterjee, Kaushik Banerjee "Meta-Learning for Domain Generalization Under Distribution Shift: Methods, Benchmarks, and Open Challenges" Iconic Research And Engineering Journals, vol. 9, no. 12, Jun. 2026. Crossref, https://doi.org/10.64388/IREV9I12-1719292
@article{1719292,
      author = {Aryanil Roy, Mainak Ghatak, Sananda Chatterjee, Kaushik Banerjee},
      title = {Meta-Learning for Domain Generalization Under Distribution Shift: Methods, Benchmarks, and Open Challenges},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {9},
      number = {12},
      pages = {3230-3238},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1719292.pdf},
      abstract = {Domain generalization (DG) explores how a model trained on a fixed set of source domains can perform reliably on unseen tar-get domains. Meta-learning addresses this by training models to explic-itly learn to generalize, yet curated benchmarks have repeatedly shown that well-tuned evidence-based risk minimization (ERM) is a formidable baseline. This survey examines that tension with a focus on what ac-tually generalizes and why. We contribute three things. First, a bivari-ate taxonomy that cross references shift type (covariate, conditional, in-variant covariate, category, compound) against meta intervention level (data/augmentation, representation/gradient, optimization/parameter, prompt/foundation). Second, a structured comparison of benchmark fam-ilies: DomainBed, WILDS, single source, and open set settings that shows how benchmark choice, and not just method design, drives published conclusions. Third, a critical analysis of conditions under which meta-learning gains over ERM are real versus aphemeral, updated for the 2023-2026 period when foundation models, causal approaches, and meta prompting have substantially changed the landscape. We conclude with actionable open challenges and directions where meta-learning retains a genuine edge.},
      keywords = {Domain Generalization, Meta-Learning, Distribution Shift, Domainbed, WILDS, Benchmark Comparison, Transfer Learning},
      month = {June},
      doi = {https://doi.org/10.64388/IREV9I12-1719292}
  }