Towards Optimal Adapter Placement for Efficient Transfer Learning
Nowak, Aleksandra I., Mercea, Otniel-Bogdan, Arnab, Anurag, Pfeiffer, Jonas, Dauphin, Yann, Evci, Utku
–arXiv.org Artificial Intelligence
Parameter-efficient transfer learning (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, achieving performance comparable to full fine-tuning with significantly fewer parameters. This paper investigates the relationship between the placement of an adapter and its performance. We observe that adapter location within a network significantly impacts its effectiveness, and that the optimal placement is task-dependent. To exploit this observation, we introduce an extended search space of adapter connections, including long-range and recurrent adapters. We demonstrate that even randomly selected adapter placements from this expanded space yield improved results, and that high-performing placements often correlate with high gradient rank. Our findings reveal that a small number of strategically placed adapters can match or exceed the performance of the common baseline of adding adapters in every block, opening a new avenue for research into optimal adapter placement strategies.
arXiv.org Artificial Intelligence
Oct-21-2024
- Country:
- Europe (0.14)
- Genre:
- Research Report > New Finding (1.00)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning
- Neural Networks > Deep Learning (1.00)
- Transfer Learning (0.62)
- Natural Language > Large Language Model (0.67)
- Vision (1.00)
- Machine Learning
- Information Technology > Artificial Intelligence