{"url":"/method/virtual-data-augmentation","slug":"virtual-data-augmentation","name":"Virtual Data Augmentation","full_name":"Virtual Data Augmentation","full_name_withheld":false,"description_markdown":"**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.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models","paper":"/paper/virtual-data-augmentation-a-robust-and","first_author":"Kun Zhou","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/virtual-data-augmentation-a-robust-and"},"source":{"url":"https://arxiv.org/abs/2109.05793v1","title":"Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Fine-Tuning","url":"/methods/category/fine-tuning","pwc_aliases":[]}],"n_papers_tagged":4,"archive_num_papers":4,"papers_newest_first":[{"paper":"/paper/approximate-nullspace-augmented-finetuning","title":"Approximate Nullspace Augmented Finetuning for Robust Vision Transformers","date":"2024-03-15","arxiv_id":"2403.10476","n_code_links":1,"syntology":null},{"paper":"/paper/intra-extra-source-exemplar-based-style","title":"Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization","date":"2023-07-02","arxiv_id":"2307.00648","n_code_links":1,"syntology":null},{"paper":"/paper/virtual-data-augmentation-a-robust-and","title":"Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models","date":"2021-09-13","arxiv_id":"2109.05793","n_code_links":1,"syntology":null},{"paper":"/paper/ray-a-distributed-framework-for-emerging-ai","title":"Ray: A Distributed Framework for Emerging AI Applications","date":"2017-12-16","arxiv_id":"1712.05889","n_code_links":4,"syntology":null}],"papers_shown":4,"tasks":[{"task":"/task/data-augmentation","name":"Data Augmentation","papers":2},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":1},{"task":"/task/diversity","name":"Diversity","papers":1},{"task":"/task/domain-generalization","name":"Domain Generalization","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":1},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":1},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":1},{"task":"/task/style-transfer","name":"Style Transfer","papers":1},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":1}],"tasks_shown":11,"n_tasks":11,"usage_by_year":[{"year":"2017","papers":1},{"year":"2021","papers":1},{"year":"2023","papers":1},{"year":"2024","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/virtual-data-augmentation"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}