Methods › General › Fine-Tuning › Virtual Data Augmentation
Virtual Data Augmentation
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.
In Syntology repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: official). This answer is about arXiv:2109.05793, the paper the archive credits with this method.
Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.
- Data-IQ · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Data-IQ') - Data-SUITE · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Data-SUITE') - Local Augmentation · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Local Augmentation') - reward-augmented data · shares_name_tokens (shares name tokens with this name; a different method) · level V2 · retrieve with
get_reference_implementation(name='reward-augmented data') - Spectral Augmentation · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Spectral Augmentation') - Learning Antidote Data · shares_name_tokens (shares name tokens with this name; a different method) · level V2 · retrieve with
get_reference_implementation(name='Learning Antidote Data')
Origin paper of this answer, arXiv:2109.05793 (its page on this site · its page on Syntology).
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 4 · with a code link: 4 · where Syntology ran a sample: 0 (0 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran: none of the 4 tagged papers has a Syntology run on record
Page 1 of 1: papers 1 to 4 of 4, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
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.
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