Search

Your search keyword '"WANG Shangguang"' showing total 117 results
Start Over Author "WANG Shangguang" Publication Type Conference Materials
117 results on '"WANG Shangguang"'

1. Mobile Foundation Model as Firmware

Author

Yuan, Jinliang, primary, Yang, Chen, additional, Cai, Dongqi, additional, Wang, Shihe, additional, Yuan, Xin, additional, Zhang, Zeling, additional, Li, Xiang, additional, Zhang, Dingge, additional, Mei, Hanzi, additional, Jia, Xianqing, additional, Wang, Shangguang, additional, and Xu, Mengwei, additional

Published
2024
Full Text
View/download PDF

12. Deciphering the Enigma of Satellite Computing with COTS Devices: Measurement and Analysis.

Author

Xing, Ruolin, Xu, Mengwei, Zhou, Ao, Li, Qing, Zhang, Yiran, Qian, Feng, and Wang, Shangguang

Subjects
COMPUTING platforms, ORBITS (Astronomy), EARTH (Planet), CURIOSITIES & wonders, TEMPERATURE
Abstract

In the wake of the rapid deployment of large-scale low-Earth orbit satellite constellations, exploiting the full computing potential of Commercial Off-The-Shelf (COTS) devices in these environments has become a pressing issue. However, understanding this problem is far from straightforward due to the inherent differences between the terrestrial infrastructure and the satellite platform in space. In this paper, we take an important step towards closing this knowledge gap by presenting the first measurement study on the thermal control, power management, and performance of COTS computing devices on satellites. Our measurements reveal that the satellite platform and COTS computing devices significantly interplay in terms of the temperature and energy, forming the main constraints on satellite computing. Further, we analyze the critical factors that shape the characteristics of onboard COTS computing devices. We provide guidelines for future research on optimizing the use of such devices for computing purposes. Finally, we have released the datasets to facilitate further study in satellite computing. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

13. Mobile Foundation Model as Firmware.

Author

Yuan, Jinliang, Yang, Chen, Cai, Dongqi, Wang, Shihe, Yuan, Xin, Zhang, Zeling, Li, Xiang, Zhang, Dingge, Mei, Hanzi, Jia, Xianqing, Wang, Shangguang, and Xu, Mengwei

Subjects
ARTIFICIAL neural networks, MOBILE operating systems, MOBILE computing, ARTIFICIAL intelligence, SCALABILITY
Abstract

In the current AI era, mobile devices such as smartphones are tasked with executing a myriad of deep neural networks (DNNs) locally. It presents a complex landscape, as these models are highly fragmented in terms of architecture, operators, and implementations. Such fragmentation poses significant challenges to the co-optimization of hardware, systems, and algorithms for efficient and scalable mobile AI. Inspired by the recent groundbreaking progress in large foundation models, this work introduces a novel paradigm for mobile AI, where mobile OS and hardware jointly manage a foundation model that is capable of serving a wide array of mobile AI tasks. This foundation model functions akin to firmware, unmodifiable by apps or the OS, exposed as a system service to Apps. They can invoke this foundation model through a small, offline fine-tuned "adapter" for various downstream tasks. We propose a tangible design of this vision called M4, and prototype it from publicly available pre-trained models. To assess its capability, we also build a comprehensive benchmark consisting of 38 mobile AI tasks and 50 datasets, spanning 5 multimodal inputs. Extensive experiments demonstrate M4's remarkable results: it achieves comparable accuracy in 85% of tasks, offers enhanced scalability regarding storage and memory, and has much simpler operations. In broader terms, this work paves a new way towards efficient and scalable mobile AI in the post-LLM era. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

31. Mandheling

Author

Xu, Daliang, primary, Xu, Mengwei, additional, Wang, Qipeng, additional, Wang, Shangguang, additional, Ma, Yun, additional, Huang, Kang, additional, Huang, Gang, additional, Jin, Xin, additional, and Liu, Xuanzhe, additional

Published
2022
Full Text
View/download PDF

33. Federated Few-Shot Learning for Mobile NLP.

Author

Cai, Dongqi, Wang, Shangguang, Wu, Yaozong, Lin, Felix Xiaozhu, and Xu, Mengwei

Subjects
COMPUTER network traffic, TRAIN delays & cancellations, MOBILE apps, RETROFITTING, PARTICIPATORY design
Abstract

Natural language processing (NLP) sees rich mobile applications. To support various language understanding tasks, a foundation NLP model is often fine-tuned in a federated, privacy-preserving setting (FL). This process currently relies on at least hundreds of thousands of labeled training samples from mobile clients; yet mobile users often lack willingness or knowledge to label their data. Such an inadequacy of data labels is known as a few-shot scenario; it becomes the key blocker for mobile NLP applications. For the first time, this work investigates federated NLP in the few-shot scenario (FedFSL). By retrofitting algorithmic advances of pseudo labeling and prompt learning, we first establish a training pipeline that delivers competitive accuracy when only 0.05% (fewer than 100) of the training data is labeled and the remaining is unlabeled. To instantiate the workflow, we further present a system FeS1, addressing the high execution cost with novel designs: (1) Curriculum pacing, which injects pseudo labels to the training workflow at a rate commensurate to the learning progress; (2) Representational diversity, a mechanism for selecting the most learnable data, only for which pseudo labels will be generated; (3) Co-planning of a model's training depth and layer capacity. Together, these designs reduce the training delay, client energy, and network traffic by up to 46.0×, 41.2× and 3000.0×, respectively. Through algorithm/system co-design, FeS demonstrates that FL can apply to challenging settings where most training samples are unlabeled. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

34. Efficient Federated Learning for Modern NLP.

Author

Cai, Dongqi, Wu, Yaozong, Wang, Shangguang, Lin, Felix Xiaozhu, and Xu, Mengwei

Subjects
FEDERATED learning, TRANSFORMER models, DEEP learning, VANILLA
Abstract

Transformer-based pre-trained models have revolutionized NLP for superior performance and generality. Fine-tuning pre-trained models for downstream tasks often requires private data, for which federated learning is the de-facto approach (i.e., FedNLP). However, our measurements show that FedNLP is prohibitively slow due to the large model sizes and the resultant high network/computation cost. Towards practical FedNLP, we identify as the key building blocks adapters, small bottleneck modules inserted at a variety of model layers. A key challenge is to properly configure the depth and width of adapters, to which the training speed and efficiency is highly sensitive. No silver-bullet configuration exists: the optimal choice varies across downstream NLP tasks, desired model accuracy, and mobile resources. To automate adapter configuration, we propose AdaFL1, a framework that enhances the existing FedNLP with two novel designs. First, AdaFL progressively upgrades the adapter configuration throughout a training session; the principle is to quickly learn shallow knowledge by only training fewer and smaller adapters at the model's top layers, and incrementally learn deep knowledge by incorporating deeper and larger adapters. Second, AdaFL continuously profiles future adapter configurations by allocating participant devices to trial groups. Extensive experiments show that AdaFL can reduce FedNLP's model convergence delay to no more than several hours, which is up to 155.5× faster compared to vanilla FedNLP and 48× faster compared to strong baselines. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

39. From cloud to edge

Author

Xu, Mengwei, primary, Fu, Zhe, additional, Ma, Xiao, additional, Zhang, Li, additional, Li, Yanan, additional, Qian, Feng, additional, Wang, Shangguang, additional, Li, Ke, additional, Yang, Jingyu, additional, and Liu, Xuanzhe, additional

Published
2021
Full Text
View/download PDF

45. Towards Ubiquitous Learning

Author

Cai, Dongqi, primary, Wang, Qipeng, additional, Liu, Yuanqiang, additional, Liu, Yunxin, additional, Wang, Shangguang, additional, and Xu, Mengwei, additional

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results