Papers › AdapterDrop: On the Efficiency of Adapters in Transformers

AdapterDrop: On the Efficiency of Adapters in Transformers

22 Oct 2020EMNLP 2021 11arXiv:2010.11918archive 2025-07-28

Andreas Rücklé, Gregor Geigle, Max Glockner, Tilman Beck, Jonas Pfeiffer, Nils Reimers, Iryna Gurevych

Massively pre-trained transformer models are computationally 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 AdapterDrop 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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Adapter-Hub/adapter-transformers mentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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