NeuroAda: Activating Each Neuron's Potential for Parameter-Efficient Fine-Tuning
By: Zhi Zhang , Yixian Shen , Congfeng Cao and more
Potential Business Impact:
Makes computer brains learn better with less memory.
Existing parameter-efficient fine-tuning (PEFT) methods primarily fall into two categories: addition-based and selective in-situ adaptation. The former, such as LoRA, introduce additional modules to adapt the model to downstream tasks, offering strong memory efficiency. However, their representational capacity is often limited, making them less suitable for fine-grained adaptation. In contrast, the latter directly fine-tunes a carefully chosen subset of the original model parameters, allowing for more precise and effective adaptation, but at the cost of significantly increased memory consumption. To reconcile this trade-off, we propose NeuroAda, a novel PEFT method that enables fine-grained model finetuning while maintaining high memory efficiency. Our approach first identifies important parameters (i.e., connections within the network) as in selective adaptation, and then introduces bypass connections for these selected parameters. During finetuning, only the bypass connections are updated, leaving the original model parameters frozen. Empirical results on 23+ tasks spanning both natural language generation and understanding demonstrate that NeuroAda achieves state-of-the-art performance with as little as $\leq \textbf{0.02}\%$ trainable parameters, while reducing CUDA memory usage by up to 60%. We release our code here: https://github.com/FightingFighting/NeuroAda.git.
Similar Papers
Parameter-Efficient Continual Fine-Tuning: A Survey
Machine Learning (CS)
AI learns new things without forgetting old ones.
HyperAdapt: Simple High-Rank Adaptation
Machine Learning (CS)
Makes smart computer programs learn faster with less effort.
A Systematic Literature Review of Parameter-Efficient Fine-Tuning for Large Code Models
Software Engineering
Makes smart computer helpers work with less power.