iiinova — where your digital self keeps evolving

Théo Gnassounou @tgnassou.bsky.social · 17/06/2026

💡Interested in domain adaptation? If you're working on domain adaptation or simply curious about the field, don't hesitate to reach out and get involved with skada. Contributions, ideas, and feedback are always welcome!

010

Théo Gnassounou @tgnassou.bsky.social · 17/06/2026

*Compatibility and bug fixes: Improved compatibility with the upcoming scikit-learn 1.8 release and fixed test failures and addressed API compatibility issues. 🤓 Try it out: pip install -U skada

110

Théo Gnassounou @tgnassou.bsky.social · 17/06/2026

What's new? * Gradual Domain Adaptation: Progressively adapt models across a sequence of domains with the new gradual domain adaptation capabilities. * Test-Time Adaptation API: A new API for test-time adaptation with shallow methods makes it easier to adapt models at inference time.

110

Théo Gnassounou @tgnassou.bsky.social · 17/06/2026

🚀 Excited to announce the release of skada v0.6.0! This new release brings important additions to the library and continued work to keep the ecosystem compatible with Sklearn!

142

Théo Gnassounou @tgnassou.bsky.social · 17/06/2026

I'm thrilled to have been awarded the thesis prize by the SSFAM 🥳 Thank you to the jury for the recognition you've given me 🙏 A big thanks to @rflamary.bsky.social and Alex to supporting me in this PhD! I'm looking forward to present my work at CAp 2026 in Montpellier, see you there :)

2122

Reposted by Théo Gnassounou

Rémi Flamary @rflamary.bsky.social · 30/09/2025

Figure 1. Happy ML researcher and open source developer presenting his toolbox SKADA at PyData Paris. Congrats @tgnassou.bsky.social the presentation was awesome!

091

Théo Gnassounou @tgnassou.bsky.social · 20/05/2025

🎯 Goal of the Skada Coding Sprint - Improve Skada: add new methods, improve documentation, fix bugs ... - Contribute to open source in a welcoming environment - Collaborate with a community of ML researchers and developers - Implement and test your own Domain Adaptation methods - Have a lot of fun!

110

Théo Gnassounou @tgnassou.bsky.social · 20/05/2025

💡 To make it easier for everyone to apply these techniques, we built Skada: a simple, Python-based library for Domain Adaptation. Skada team organizes a coding sprint :(@rflamary.bsky.social , @antoinecollas.bsky.social , @ambroiseodt.bsky.social) 📍 When: June 24–25 📍 Where: Inria Saclay

121

Théo Gnassounou @tgnassou.bsky.social · 20/05/2025

Skada Sprint Alert: Contribute to Domain Adaptation in Python 📖 Machine learning models often fail when the data distribution changes between training and testing. That’s where Domain Adaptation comes in — helping models stay reliable across domains.

1126

Théo Gnassounou @tgnassou.bsky.social · 12/02/2025

SKADA-Bench is built on SKADA: github.com/scikit-adapt... This work results from a collaboration with Yanis Lalou, @antoinecollas.bsky.social , Antoine de Mathelin, Oleksii Kachaiev, @ambroiseodt.bsky.social , Alexandre Gramfort, Thomas Moreau and @rflamary.bsky.social !

lnkd.in

This link will take you to a page that’s not on LinkedIn

110

Théo Gnassounou @tgnassou.bsky.social · 12/02/2025

The benchmark shows deep DA methods struggle beyond computer vision, highlighting their limits on other modalities!

110

Théo Gnassounou @tgnassou.bsky.social · 12/02/2025

The results show the benefit of DA in some cases but parameter-sensitive shallow methods struggle to adapt to new domains. Better to use low-parameter methods like LinOT & Coral!

110

Théo Gnassounou @tgnassou.bsky.social · 12/02/2025

This benchmark is done using a realistic scenario comprising the validation of hyperparameters using nested loop and DA scorers!

110

Théo Gnassounou @tgnassou.bsky.social · 12/02/2025

🔬 What’s inside? • Multi-Modality Benchmark: 4 simulated + 8 real datasets • 20 Shallow DA Methods: Reweighting, mapping, subspace alignment & others • 7 Deep DA Methods: CAN, MCC, MDD, SPA & more • 7 Unsupervised Validation Scorers

110

Théo Gnassounou @tgnassou.bsky.social · 12/02/2025

DA adapts machine learning models to distribution shifts between training and test sets. We propose SKADA-Bench, the first comprehensive, reproducible benchmark that evaluates DA methods across multiple modalities: computer vision, natural language processing, tabular, and biomedical data.

120

Théo Gnassounou @tgnassou.bsky.social · 12/02/2025

🚀 I’m pleased to announce a new preprint! "SKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation On Diverse Modalities" 📢 Check it out & contribute! 📜 Paper: arxiv.org/abs/2407.11676 💻 Code: github.com/scikit-adapt...

1135

Théo Gnassounou @tgnassou.bsky.social · 06/12/2024

This library is a team effort: @antoinecollas.bsky.social, Oleksii Kachaiev, @rflamary.bsky.social , Yanis Lalou, Antoine de Mathelin, Ruben Bueno, Apolline Mellot, @ambroiseodt.bsky.social , Alexandre Gramfort and myself!

030

Théo Gnassounou @tgnassou.bsky.social · 06/12/2024

🔀 Improved Subsampling Tools - Added StratifiedDomainSubsampler and DomainSubsampler to handle large datasets effortlessly. 🤖 Deep Model Enhancements - Smarter batch handling. - Many bug fixes. 📖 Documentation Upgrades - Contributor Guide: Join the development of Skada! - New Logo!!

100

Théo Gnassounou @tgnassou.bsky.social · 06/12/2024

📊 Advanced Scorers - New MixValScorer for mixup validation. - Enhanced scorer compatibility with deep models.

100

Théo Gnassounou @tgnassou.bsky.social · 06/12/2024

💡New Deep Domain Adaptation Methods: CAN, SPA, MCC, and MDD.These methods combine the cross entropy loss on the source domain with domain aware losses (graph based, adversarial, class confusion, …).

100

Théo Gnassounou @tgnassou.bsky.social · 06/12/2024

💡New Shallow Domain Adaptation Methods: MongeAlignment and JCPOT for linear multi-source domain adaptation with optimal transport.

100

Théo Gnassounou @tgnassou.bsky.social · 06/12/2024

🚀 Skada v0.4.0 is out! Skada is an open-source Python library built for domain adaptation (DA), helping machine learning models to adapt to distribution shifts. Github: github.com/scikit-adapt... Doc: scikit-adaptation.github.io DOI: doi.org/10.5281/zeno... Installation: `pip install skada`

1106