paper-with-me

홈 › Papers

Device Tuning for Multi-Task Large Model

2023-02-21 · Penghao Jiang, Xuanchen Hou, Yinsi Zhou

Unsupervised pre-training approaches have achieved great success in many fields such as Computer Vision (CV), Natural Language Processing (NLP) and so on. However, compared to typical deep learning models, pre-training or even fine-tuning the state-of-the-art self-attention models is extremely expensive, as they require much more computational and memory resources. It severely limits their applications and success in a variety of domains, especially for multi-task learning. To improve the efficiency, we propose Device Tuning for the efficient multi-task model, which is a massively multitask framework across the cloud and device and is designed to encourage learning of representations that generalize better to many different tasks. Specifically, we design Device Tuning architecture of a multi-task model that benefits both cloud modelling and device modelling, which reduces the communication between device and cloud by representation compression. Experimental results demonstrate the effectiveness of our proposed method.

📄 PDF Abstract BibTeX arXiv:2302.10820

Code (0)

등록된 구현이 없습니다.

Tasks

modelMulti-Task LearningUnsupervised Pre-training

Similar Papers 제목 키워드 기반

Enabling Efficient On-Device Fine-Tuning of LLMs Using Only Inference Engines

2024-09-23 · Lei Gao, Amir Ziashahabi, Yue Niu, Salman Avestimehr 외

Large Language Models (LLMs) are currently pre-trained and fine-tuned on large cloud servers. The next frontier is LLM personalization, where a foundation model can be fine-tuned with user/task-specific data. Given the s…

parameter-efficient fine-tuningText Generation

Efficient Deployment of Large Language Models on Resource-constrained Devices

2025-01-05 · Zhiwei Yao, Yang Xu, Hongli Xu, Yunming Liao 외

Deploying Large Language Models (LLMs) on resource-constrained (or weak) devices presents significant challenges due to limited resources and heterogeneous data distribution. To address the data concern, it is necessary …

Federated Learningparameter-efficient fine-tuningPrivacy Preserving

Incentivizing Multi-Tenant Split Federated Learning for Foundation Models at the Network Edge

2025-03-06 · Songyuan Li, Jia Hu, Geyong Min, Haojun Huang

Foundation models (FMs) such as GPT-4 exhibit exceptional generative capabilities across diverse downstream tasks through fine-tuning. Split Federated Learning (SFL) facilitates privacy-preserving FM fine-tuning on resou…

Federated LearningPrivacy Preserving

PocketLLM: Enabling On-Device Fine-Tuning for Personalized LLMs

2024-07-01 · Dan Peng, Zhihui Fu, Jun Wang

Recent advancements in large language models (LLMs) have indeed showcased their impressive capabilities. On mobile devices, the wealth of valuable, non-public data generated daily holds great promise for locally fine-tun…

HD-PiSSA: High-Rank Distributed Orthogonal Adaptation

2025-05-24 · Yiding Wang, Fauxu meng, Xuefeng Zhang, Fan Jiang 외

Existing parameter-efficient fine-tuning (PEFT) methods for large language models (LLMs), such as LoRA and PiSSA, constrain model updates to low-rank subspaces, limiting their expressiveness and leading to suboptimal per…

Code GenerationGPUMulti-Task Learningparameter-efficient fine-tuning