Methods › General › Self-Training Methods › STraTA

Self-Training with Task Augmentation

STraTA

1 paper tagged archive 2025-07-28

Introduced by Tu Vu et al. in STraTA: Self-Training with Task Augmentation for Better Few-shot Learning

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

STraTA, or Self-Training with Task Augmentation, is a self-training approach that builds on two key ideas for effective leverage of unlabeled data. First, STraTA uses task augmentation, a technique that synthesizes a large amount of data for auxiliary-task fine-tuning from target-task unlabeling texts. Second, STRATA performs self-training by further fine-tuning the strong base model created by task augmentation on a broad distribution of pseudo-labeled data.

In task augmentation, we train an NLI data generation model and use it to synthesize a large amount of in-domain NLI training data for each given target task, which is then used for auxiliary (intermediate) fine-tuning. The self-training algorithm iteratively learns a better model using a concatenation of labeled and pseudo-labeled examples. At each iteration, we always start with the auxiliary-task model produced by task augmentation and train on a broad distribution of pseudo-labeled data.

PaperSource

Papers archive 2025-07-28

1 shown of 1, 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.

Tasks archive 2025-07-28

3 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Few-Shot Learning1
Few-Shot NLI1
SST-21

Usage over time archive 2025-07-28

Papers per year tagged with STraTA: 2021 to 2021, peak 1 1 0 2021: 1 paper 2021
Papers per year the archive tags with this method, by the paper's archive date (1 dated). Bars are counts, not a trend claim.

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

Self-Training MethodsSemi-Supervised Learning Methods

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