AdapterDrop: On the Efficiency of Adapters in Transformers
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Transformer models are expensive to fine-tune, slow for inference, and have large storage requirements.Recent approaches tackle these shortcomings by training smaller models, dynamically reducing the model size, and by training light-weight adapters.In this paper, we propose AdapterDrop, removing adapters from lower transformer layers during training and inference, which incorporates concepts from all three directions.We show that Adap-terDrop can dynamically reduce the computational overhead when performing inference over multiple tasks simultaneously, with minimal decrease in task performances.We further prune adapters from AdapterFusion, which improves the inference efficiency while maintaining the task performances entirely.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2019) · arXiv · doi:10.48550/arxiv.1910.01108 · Cited by 4,653
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., & Soricut, R. (2019) · arXiv · doi:10.48550/arxiv.1909.11942 · Cited by 4,308 · cited 2×
“This is similar to weight sharing in ALBERT (Lan et al., 2019), but specialized on adapters and can therefore be applied to a wide range of pre-trained models.”
BackgroundGLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. (2018) · Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w18-5446 · Cited by 4,222
Universal Language Model Fine-tuning for Text Classification
Howard, J., & Ruder, S. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1031 · Cited by 4,100 · cited 1×
“While transfer learning has become the go-to method for solving NLP tasks (Pan and Yang, 2010; Torrey and Shavlik, 2010; Ruder, 2019; Howard and Ruder, 2018; Peters et al., 2018), transformer-based models are notoriously deep requiring millions or even billions of parameters (Radford et al., 2018;…”
Energy and Policy Considerations for Deep Learning in NLP
Strubell, E., Ganesh, A., & McCallum, A. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1355 · Cited by 3,684 · cited 1×
“We have established that adapters are more efficient in terms of training time, however, there is a perpetuate need for sustainable and efficient models (Strubell et al., 2019).”
BackgroundParameter-efficient transfer learning for NLP
Houlsby, N., Giurgiu, A., Jastrzebski, S., Morrone, B., de Laroussilhe, Q., Gesmundo, A., Attariyan, M., & Gelly, S. (2019) · arXiv · doi:10.48550/arxiv.1902.00751 · Cited by 2,270
MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices
Sun, Z., Yu, H., Song, X., Liu, R., Yang, Y., & Zhou, D. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.195 · Cited by 757
Cited by
Parameter-efficient fine-tuning of large-scale pre-trained language models
Ding, N., Qin, Y., Yang, G., Wei, F., Yang, Z., Su, Y., Hu, S., Chen, Y., Chan, C.-M., Chen, W., et al. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00626-4 · Cited by 1,191
“In addition, the computational cost could be further reduced dynamically by removing adapters from lower transformer layers 32 .”
BackgroundParameter-efficient fine-tuning in large language models: a survey of methodologies
Wang, L., Chen, S., Jiang, L., Pan, S., Cai, R., Yang, S., & Yang, F. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11236-4 · Cited by 186
“AdapterDrop [142] dynamically removes adapters from the lower layers of a transformer during training and inference, which significantly enhances inference speed in multi-task settings with minimal impact on task performance.”
Differentially Private Fine-tuning of Language Models
Yu, D., Naik, S., Backurs, A., Gopi, S., Inan, H. A., Kamath, G., Kulkarni, J., Lee, Y. T., Manoel, A., Wutschitz, L., et al. (2021) · arXiv · doi:10.48550/arxiv.2110.06500 · Cited by 101
“Some of these include random subspace projection (exploiting intrinsic dimensionality (Li et al., 2018; Aghajanyan et al., 2020)), prefix and prompt tuning (Li & Liang, 2021; Lester et al., 2021), tuning only biases (Cai et al., 2020; Ben Zaken et al., 2021), and other architecture variants including Adapters (Pfeiffer…”
BackgroundBLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting
Yong, Z. X., Schoelkopf, H., Muennighoff, N., Aji, A. F., Adelani, D. I., Almubarak, K., Bari, M. S., Sutawika, L., Kasai, J., Baruwa, A., et al. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.653 · Cited by 30
How to protect copyright data in optimization of large language models?
Chu, T., Song, Z., & Yang, C. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i16.29741 · Cited by 16
Metadata
- Authors
- Rücklé, A., Geigle, G., Glockner, M., Beck, T., Pfeiffer, J., Reimers, N., & Gurevych, I.
- Venue
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Published
- 2021
- Pages
- 7930-7946
- OpenAlex
- W3094491777
- Cited by
- 181
- References
- 14
- FWCI
- 15.05
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: AdapterDrop: On the Efficiency of Adapters in Transformers. https://app.cochat.ai/papers/10.18653/v1/2021.emnlp-main.626
- The paper
- Rücklé, A., Geigle, G., Glockner, M., Beck, T., Pfeiffer, J., Reimers, N., & Gurevych, I. (2021). AdapterDrop: On the Efficiency of Adapters in Transformers. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/2021.emnlp-main.626
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.