Methods › General › Semi-Supervised Learning Methods › Gradual Self-Training
Gradual Self-Training
Introduced by Ananya Kumar et al. in Understanding Self-Training for Gradual Domain Adaptation
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Gradual self-training is a method for semi-supervised domain adaptation. The goal is to adapt an initial classifier trained on a source domain given only unlabeled data that shifts gradually in distribution towards a target domain.
This comes up for example in applications ranging from sensor networks and self-driving car perception modules to brain-machine interfaces, where machine learning systems must adapt to data distributions that evolve over time.
The gradual self-training algorithm begins with a classifier w₀ trained on labeled examples from the source domain (Figure a). For each successive domain Pₜ, the algorithm generates pseudolabels for unlabeled examples from that domain, and then trains a regularized supervised classifier on the pseudolabeled examples. The intuition, visualized in the Figure, is that after a single gradual shift, most examples are pseudolabeled correctly so self-training learns a good classifier on the shifted data, but the shift from the source to the target can be too large for self-training to correct.
Papers archive 2025-07-28
8 shown of 8, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Gradual Domain Adaptation: Theory and Algorithms 20 Oct 2023 · 2 repositories · arXiv:2310.13852Syntology ran 10 of 15 samples · 5 unverified
-
Adversarial Self-Training Improves Robustness and Generalization for Gradual Domain Adaptation 21 Sep 2023 · 1 repository
-
Gradual Domain Adaptation via Normalizing Flows 23 Jun 2022 · 1 repository · arXiv:2206.11492Syntology ran 0 of 9 samples · 9 unverified
-
Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond 18 Apr 2022 · 3 repositories · arXiv:2204.08200Syntology ran 3 of 4 samples · 1 unverified
-
Improving Word Translation via Two-Stage Contrastive Learning 15 Mar 2022 · 1 repository · arXiv:2203.08307Syntology ran 5 of 6 samples · 1 unverified · 4 pointer-only (licence)
-
Improving Word Translation via Two-Stage Contrastive Learning 16 Nov 2021 · 1 repository
-
UmBERTo-MTSA @ AcCompl-It: Improving Complexity and Acceptability Prediction with Multi-task Learning on Self-Supervised Annotations 10 Nov 2020 · 1 repository · arXiv:2011.05197
-
Understanding Self-Training for Gradual Domain Adaptation 26 Feb 2020 · 2 repositories · arXiv:2002.11361
Tasks archive 2025-07-28
16 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections