Adapters Strike Back

• URL: http://arxiv.org/abs/2406.06820v1
• Date: Mon, 10 Jun 2024 22:07:57 GMT
• Title: Adapters Strike Back
• Authors: Jan-Martin O. Steitz, Stefan Roth,
• Abstract summary: We provide an in-depth study of adapters, their internal structure, as well as various implementation choices. We suggest a concrete, improved adapter architecture, called Adapter+, that not only outperforms previous adapter implementations but surpasses a number of other, more complex adaptation mechanisms in several challenging settings.
• Score: 10.490880056507198
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Adapters provide an efficient and lightweight mechanism for adapting trained transformer models to a variety of different tasks. However, they have often been found to be outperformed by other adaptation mechanisms, including low-rank adaptation. In this paper, we provide an in-depth study of adapters, their internal structure, as well as various implementation choices. We uncover pitfalls for using adapters and suggest a concrete, improved adapter architecture, called Adapter+, that not only outperforms previous adapter implementations but surpasses a number of other, more complex adaptation mechanisms in several challenging settings. Despite this, our suggested adapter is highly robust and, unlike previous work, requires little to no manual intervention when addressing a novel scenario. Adapter+ reaches state-of-the-art average accuracy on the VTAB benchmark, even without a per-task hyperparameter optimization.

Related papers

• Towards Optimal Adapter Placement for Efficient Transfer Learning [73.1149084352343]
  PETL aims to adapt pre-trained models to new downstream tasks while minimizing the number of fine-tuned parameters. adapters, a popular approach in PETL, inject additional capacity into existing networks by incorporating low-rank projections. This paper investigates the relationship between the placement of an adapter and its performance.
  arXiv  Detail & Related papers  (2024-10-21T10:37:17Z)
• Hierarchical Recurrent Adapters for Efficient Multi-Task Adaptation of Large Speech Models [12.230087530720652]
  We introduce an adapter module that has a better efficiency in large scale multi-task adaptation scenario. The adapter consists of a single shared controller network and multiple task-level adapter heads.
  arXiv  Detail & Related papers  (2024-03-25T17:21:56Z)
• MoSA: Mixture of Sparse Adapters for Visual Efficient Tuning [20.68925288222065]
  Mixture of Sparse Adapters, or MoSA, is a novel Adapter Tuning method. MoSA can achieve significantly better performance than standard without any additional computational storage overhead. MoSA consistently outperforms other Adapter Tuning methods as well as other baselines by a large margin.
  arXiv  Detail & Related papers  (2023-12-05T17:50:55Z)
• Selective Feature Adapter for Dense Vision Transformers [30.409313135985528]
  selective feature adapter (SFA) achieves comparable or better performance than fully fine-tuned models across various dense tasks. SFA consists of external adapters and internal adapters which are sequentially operated over a transformer model. Experiments show that the dual adapter module, a.k.a SFA, is essential to achieve the best trade-off on dense vision tasks.
  arXiv  Detail & Related papers  (2023-10-03T07:17:58Z)
• MerA: Merging Pretrained Adapters For Few-Shot Learning [71.44422347502409]
  We propose textbftextttMerging Pretrained Adapters (MerA) that efficiently incorporates pretrained adapters to a single model through model fusion. Experiments on two PLMs demonstrate that MerA substantial improvements compared to both single adapters and AdapterFusion.
  arXiv  Detail & Related papers  (2023-08-30T12:10:17Z)
• AdaMix: Mixture-of-Adapter for Parameter-efficient Tuning of Large Language Models [119.7093605087114]
  Fine-tuning large-scale pre-trained language models to downstream tasks require updating hundreds of millions of parameters. This not only increases the serving cost to store a large copy of the model weights for every task, but also exhibits instability during few-shot task adaptation. We introduce a new mechanism to improve adapter capacity without increasing parameters or computational cost by two key techniques.
  arXiv  Detail & Related papers  (2022-05-24T23:41:22Z)
• Adaptable Adapters [74.65986170056945]
  State-of-the-art pretrained NLP models contain a hundred million to trillion parameters. Adaptable adapters contain different activation functions for different layers and different input data. We show that adaptable adapters achieve on-par performances with the standard adapter architecture.
  arXiv  Detail & Related papers  (2022-05-03T14:59:27Z)
• AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP Tasks [55.705355299065474]
  Transformer-based pre-trained models with millions of parameters require large storage. Recent approaches tackle this shortcoming by training adapters, but these approaches still require a relatively large number of parameters. In this study, AdapterBias, a surprisingly simple yet effective adapter architecture, is proposed.
  arXiv  Detail & Related papers  (2022-04-30T16:49:41Z)
• AdapterDrop: On the Efficiency of Adapters in Transformers [53.845909603631945]
  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.
  arXiv  Detail & Related papers  (2020-10-22T17:49:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.