Results 31 to 40 of about 124,133 (290)
Adaptive Parameter-Efficient Federated Fine-Tuning on Heterogeneous Devices
IEEE Transactions on Mobile ComputingFederated fine-tuning (FedFT) has been proposed to fine-tune the pre-trained language models in a distributed manner. However, there are two critical challenges for efficient FedFT in practical applications, i.e., resource constraints and system heterogeneity.
Jianchun Liu, Yunming Liao, Hongli Xu
exaly +3 more sources
AdapterGNN: Parameter-Efficient Fine-Tuning Improves Generalization in GNNs
Proceedings of the AAAI Conference on Artificial Intelligence, 2023 Fine-tuning pre-trained models has recently yielded remarkable performance gains in graph neural networks (GNNs). In addition to pre-training techniques, inspired by the latest work in the natural language fields, more recent work has shifted towards applying effective fine-tuning approaches, such as parameter-efficient fine-tuning (PEFT).
Shengrui Li, Xueting Han, Jing Bai 0010
core +4 more sources
Multimodal Assessment of Schizophrenia Symptom Severity From Linguistic, Acoustic and Visual Cues
IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023 Assessing the condition of every schizophrenia patient correctly normally requires lengthy and frequent interviews with professionally trained doctors.
Chih-Yuan Chuang +7 more
doaj +1 more source
On the Effectiveness of Parameter-Efficient Fine-Tuning
Proceedings of the AAAI Conference on Artificial Intelligence, 2023 Fine-tuning pre-trained models has been ubiquitously proven to be effective in a wide range of NLP tasks. However, fine-tuning the whole model is parameter inefficient as it always yields an entirely new model for each task. Currently, many research works propose to only fine-tune a small portion of the parameters while keeping most of the parameters ...
Zihao Fu +5 more
openaire +2 more sources
Parameter-Efficient Fine-Tuning Design Spaces
CoRR, 2023 Code is available at https://github.com/amazon-science/peft-design ...
Jiaao Chen +5 more
openaire +3 more sources
Deepfake Detection Method Integrating Multiple Parameter-Efficient Fine-Tuning Techniques [PDF]
Jisuanji kexue yu tansuoIn recent years, as deepfake technology matures, face-swapping software and synthesized videos have become widespread. While these techniques offer entertainment, they also provide opportunities for misuse by malicious actors.
ZHANG Yiwen, CAI Manchun, CHEN Yonghao, ZHU Yi, YAO Lifeng
doaj +1 more source
CE-Prompt: enhance prompt expression stability by multiple understanding [PDF]
PeerJ Computer ScienceIn this article, we propose CE-Prompt, an enhanced version of Prompt-Tuning designed to address issues such as the instability of random initialization and inefficiencies caused by long text in pre-trained large language models (LLMs).
Wujian Yang +3 more
doaj +2 more sources
Exploring The Principles and Prospects for Efficient Fine-Tuning of Transformer-Based Pre-Trained Large Language Models [PDF]
ITM Web of ConferencesIn recent years, large language models (LLMs) have made breakthroughs in natural language processing and multimodal tasks. However, the growing model size and the high cost of full parameter fine-tuning pose challenges to their efficient adaptation. This
He Ruiqi
doaj +1 more source
Gradient-based Parameter Selection for Efficient Fine-Tuning [PDF]
With the growing size of pre-trained models, full fine-tuning and storing all the parameters for various down-stream tasks is costly and infeasible.
Zhang, S. +6 more
core +2 more sources
Parameter-Efficient Fine-Tuning With Adapters
CoRRIn the arena of language model fine-tuning, the traditional approaches, such as Domain-Adaptive Pretraining (DAPT) and Task-Adaptive Pretraining (TAPT), although effective, but computational intensive. This research introduces a novel adaptation method utilizing the UniPELT framework as a base and added a PromptTuning Layer, which significantly reduces
Keyu Chen, Yuan Pang, Zi Yang
openaire +2 more sources