Methods › General › Fine-Tuning › Virtual Data Augmentation

Virtual Data Augmentation

4 papers tagged archive 2025-07-28

Introduced by Kun Zhou et al. in Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models

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

Virtual Data Augmentation, or VDA, is a framework for robustly fine-tuning pre-trained language model. Based on the original token embeddings, a multinomial mixture for augmenting virtual data is constructed, where a masked language model guarantees the semantic relevance and the Gaussian noise provides the augmentation diversity. Furthermore, a regularized training strategy is proposed to balance the two aspects.

Paper Source

Papers archive 2025-07-28

4 shown of 4, 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.

Approximate Nullspace Augmented Finetuning for Robust Vision Transformers
15 Mar 2024 · 1 repository · arXiv:2403.10476
Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization
2 Jul 2023 · 1 repository · arXiv:2307.00648
Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models
13 Sep 2021 · 1 repository · arXiv:2109.05793
Ray: A Distributed Framework for Emerging AI Applications
16 Dec 2017 · 4 repositories · arXiv:1712.05889

Tasks archive 2025-07-28

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

Task	Papers
Data Augmentation	2
Autonomous Driving	1
Diversity	1
Domain Generalization	1
Language Modeling	1
Language Modelling	1
Reinforcement Learning	1
Reinforcement Learning (RL)	1
Semantic Segmentation	1
Style Transfer	1
reinforcement-learning	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (4 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

Fine-Tuning

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