A Comprehensive Analysis of Adapter Efficiency

Nandini Mundra, Sumanth Doddapaneni, Raj Dabre, Anoop Kunchukuttan, Ratish Puduppully, Mitesh M Khapra

Keywords: Adapter, Parameter-efficient fine-tuning, computational efficiency, Training efficiency, Multi-task training, NLU tasks, Cross-lingual zero-shot learning, Deep Learning

Abstract:

Adapters have been positioned as a parameter-efficient fine-tuning (PEFT) approach. However, adapters have not been sufficiently analyzed to understand if PEFT translates to benefits in training/deployment efficiency and maintainability/extensibility.
Through extensive experiments on many adapters, tasks, and languages in supervised and cross-lingual zero-shot settings, we clearly show that for Natural Language Understanding (NLU) tasks, the parameter efficiency in adapters does not translate to efficiency gains compared to full fine-tuning of models. More precisely, adapters are relatively expensive to train and have slightly higher deployment latency. Furthermore, the maintainability/extensibility benefits of adapters can be achieved with simpler approaches like multi-task training via full fine-tuning, which also provide relatively faster training times. We, therefore, recommend that for moderately sized models for NLU tasks, practitioners should rely on full fine-tuning or multi-task training rather than using adapters. Our code is available at https://github.com/AI4Bharat/adapter-efficiency.

Submission Number: 55