AdaKron: An Adapter-based Parameter Efficient Model Tuning with Kronecker Product

Marco Braga, Alessandro Raganato, Gabriella Pasi


Abstract
The fine-tuning paradigm has been widely adopted to train neural models tailored for specific tasks. However, the recent upsurge of Large Language Models (LLMs), characterized by billions of parameters, has introduced profound computational challenges to the fine-tuning process. This has fueled intensive research on Parameter-Efficient Fine-Tuning (PEFT) techniques, usually involving the training of a selective subset of the original model parameters. One of the most used approaches is Adapters, which add trainable lightweight layers to the existing pretrained weights. Within this context, we propose AdaKron, an Adapter-based fine-tuning with the Kronecker product. In particular, we leverage the Kronecker product to combine the output of two small networks, resulting in a final vector whose dimension is the product of the dimensions of the individual outputs, allowing us to train only 0.55% of the model’s original parameters. We evaluate AdaKron performing a series of experiments on the General Language Understanding Evaluation (GLUE) benchmark, achieving results in the same ballpark as recent state-of-the-art PEFT methods, despite training fewer parameters.
Anthology ID:
2024.lrec-main.32
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
350–357
Language:
URL:
https://aclanthology.org/2024.lrec-main.32
DOI:
Bibkey:
Cite (ACL):
Marco Braga, Alessandro Raganato, and Gabriella Pasi. 2024. AdaKron: An Adapter-based Parameter Efficient Model Tuning with Kronecker Product. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 350–357, Torino, Italia. ELRA and ICCL.
Cite (Informal):
AdaKron: An Adapter-based Parameter Efficient Model Tuning with Kronecker Product (Braga et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.32.pdf