EMNLP Findings2024
Efficient Active Learning with Adapters
Daria Galimzianova, Leonid Sanochkin
Abstract
One of the main obstacles for deploying Active Learning (AL) in practical NLP tasks is high computational cost of modern deep learning models. This issue can be partially mitigated by applying lightweight models as an acquisition model, but it can lead to the acquisitionsuccessor mismatch (ASM) problem. Previous works show that the ASM problem can be partially alleviated by using distilled versions of a successor models as acquisition ones. However, distilled versions of pretrained models are not always available. Also, the exact pipeline of model distillation that does not lead to the ASM problem is not clear. To address these issues, we propose to use adapters as an alternative to full fine-tuning for acquisition model training. Since adapters are lightweight, this approach reduces the training cost of the model. We provide empirical evidence that it does not cause the ASM problem and can help to deploy active learning in practical NLP tasks.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Uncertainty Estimation of Transformer Predictions for Misclassification Detection cites ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
- Parameter-Efficient Language Model Tuning with Active Learning in Low-Resource Settings cites Active Learning for BERT: An Empirical Study
Builds on4
- ELECTRA: Pre-training Text Encoders as Discriminators Rather Than GeneratorsKevin Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. ManningICLR 2020 · 541 citations
- Active Learning for BERT: An Empirical StudyLiat Ein-Dor, Alon Halfon, Ariel Gera, Eyal Shnarch et al.EMNLP 2020 · 144 citations
- Uncertainty Estimation of Transformer Predictions for Misclassification DetectionArtem Vazhentsev, Gleb Kuzmin, Artem Shelmanov, Akim Tsvigun et al.ACL 2022 · 59 citations
- Parameter-Efficient Language Model Tuning with Active Learning in Low-Resource SettingsJosip Jukic, Jan SnajderEMNLP 2023 · 4 citations
Related papers
- On the Effectiveness of Adapter-based Tuning for Pretrained Language Model AdaptationRuidan He, Linlin Liu, Hai Ye, Qingyu Tan et al.ACL 2021
- SADA: Bridging In-Context Learning and Fine-Tuning via State-Aligned Distillation AdaptersWenhao Gao, Tianlong Wang, Wei Jia, Linhao Zhang et al.ACL 2026
- On Dataset Transferability in Active Learning for TransformersFran Jelenic, Josip Jukic, Nina Drobac, Jan SnajderACL Findings 2023 · 4 citations
- Efficient Federated Learning for Modern NLPDongqi Cai, Yaozong Wu, Shangguang Wang, Felix Xiaozhu Lin et al.MobiCom 2023 · 63 citations
- Cold-start Active Learning through Self-supervised Language ModelingMichelle Yuan, Hsuan-Tien Lin, Jordan L. Boyd-GraberEMNLP 2020 · 128 citations
