Faster Parameter-Efficient Tuning with Token Redundancy Reduction
Parameter-efficient tuning (PET) aims to transfer pre-trained foundation models to downstream tasks by learning a small number of parameters. Compared to traditional fine-tuning, which updates the entire model, PET significantly reduces storage and transfer costs for each task regardless of exponentially increasing pre-trained model capacity. However, most PET methods inherit the inference latency of their large backbone models and often introduce additional computational overhead due to additional modules (e.g. adapters), limiting their practicality for compute-intensive applications. In this paper, we propose Faster Parameter-Efficient Tuning (FPET), a novel approach that enhances inference speed and training efficiency while maintaining high storage efficiency. Specifically, we introduce a plug-and-play token redundancy reduction module delicately designed for PET. This module refines tokens from the self-attention layer using an adapter to learn the accurate similarity between tokens and cuts off the tokens through a fully-differentiable token merging strategy, which uses a straight-through estimator for optimal token reduction. Experimental results prove that our FPET achieves faster inference and higher memory efficiency than the pre-trained backbone while keeping competitive performance on par with state-of-the-art PET methods.
Code (1)
Tasks
Token ReductionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Making Large Language Models Efficient Dense Retrievers
Recent work has shown that directly fine-tuning large language models (LLMs) for dense retrieval yields strong performance, but their substantial parameter counts make them computationally inefficient. While prior studie…
TS-PEFT: Unveiling Token-Level Redundancy in Parameter-Efficient Fine-Tuning
Current Parameter-Efficient Fine-Tuning (PEFT) methods typically operate under an implicit assumption: Once a target module is selected, every token passing through it contributes equally to the downstream task and requi…
parameter-efficient fine-tuningTraining-Free Acceleration of ViTs with Delayed Spatial Merging
Token merging has emerged as a new paradigm that can accelerate the inference of Vision Transformers (ViTs) without any retraining or fine-tuning. To push the frontier of training-free acceleration in ViTs, we improve to…
Transfer LearningQTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMs
Large language models (LLMs) demand substantial computational and memory resources, posing challenges for efficient deployment. Two complementary approaches have emerged to address these issues: token-adaptive layer exec…
Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference
Parameter-efficient fine-tuning (PEFT) has emerged as a popular solution for adapting pre-trained Vision Transformer (ViT) models to downstream applications. While current PEFT methods have achieved parameter efficiency,…
GPUparameter-efficient fine-tuning