Papers › Meta-Adapters: Parameter Efficient Few-shot Fine-tuning through Meta-Learning

Meta-Adapters: Parameter Efficient Few-shot Fine-tuning through Meta-Learning

19 Sep 2022Proceedings of the First International Conference on Automated Machine Learning 2022 9archive 2025-07-28

Trapit Bansal, Salaheddin Alzubi, Tong Wang, Jay-Yoon Lee, Andrew McCallum

Consistent improvements in the representational capacity of large pre-trained transformers has made it increasingly viable to serve these models as shared priors that can be fine-tuned on a large number of downstream tasks. However, fine-tuning the entire model for every task of interest makes a copy of all the model parameters, rendering such scenarios highly impractical. Recently introduced Adapter methods propose a promising alternative, one where only a small number of additional parameters are introduced per task specifically for fine-tuning. However, Adapters often require large amounts of task-specific data for good performance and don’t work well in data-scarce few-shot scenarios. In this paper, we approach parameter-efficient fine-tuning in few-shot settings from a meta-learning perspective. We introduce Meta-Adapters, which are small blocks of meta-learned adapter layers inserted in a pre-trained model that re-purpose a frozen pre-trained model into a parameter-efficient few-shot learner. Meta-Adapters perform competitively with state-of-the-art few-shot learning methods that require full fine-tuning, while only fine-tuning 0.6% of the parameters. We evaluate Meta-Adapters along with multiple transfer learning baselines on an evaluation suite of 17 classification tasks and find that they improve few-shot accuracy by a large margin over competitive parameter-efficient methods, while requiring significantly lesser parameters for fine-tuning. Moreover, when comparing few-shot prompting of GPT-3 against few-shot fine-tuning with Meta-Adapters, we find that Meta-Adapters perform competitively while working with pre-trained transformers that are many orders of magnitude (1590{\texttimes}) smaller in size than GPT-3.

PaperPDFCode

Code

theTB/meta_adapters mentioned in papertf 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.

Tasks

Few-Shot LearningMeta-LearningTransfer Learningparameter-efficient fine-tuning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAdapterAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDropoutGPT-3Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight Decay

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