Wuyang Chen

Wuyang Chen

Auto-generated profile, based on publicly available information

Wuyang Chen

Department of Electrical and Computer Engineering The University of Texas at Austin Austin TX USA

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 November 2022
Verified
Book Chapter
Closed access
PDF file
WCWuyang Chen
Wuyang Chen
XDXianzhi Du
Xianzhi Du
FYFan Yang
Fan Yang
LBLucas Beyer
Lucas Beyer
XZXiaohua Zhai
Xiaohua Zhai
DZDenny Zhou
Denny Zhou

1 December 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Open access
WCWuyang Chen
Wuyang Chen
XGXinyu Gong
Xinyu Gong
JWJunru Wu
Junru Wu
YWYunchao Wei
Yunchao Wei
HSHumphrey Shi
Humphrey Shi
ZWZhangyang (Atlas) Wang
Zhangyang (Atlas) Wang
This work targets designing a principled and unified training-free framework for Neural Architecture Search (NAS), with high performance, low cost, and in-depth interpretation. NAS has been explosively studied to automate the discovery of top-performer neural networks, but suffers from heavy resource consumption and often incurs search bias due to truncated training or approximations. Recent NAS works Mellor et al. 2021, Chen et al. 2021, Abdelfattah et al. 2021 start to explore indicators that can predict a network's performance without training. However, they either leveraged limited properties of deep networks, or the benefits of their training-free indicators were not applied to more extensive search methods. By rigorous correlation analysis, we present a unified framework to understand and accelerate NAS, by disentangling “ TEG ” characteristics of searched networks – T rainability, E xpressivity, G eneralization – all assessed in a training-free manner. The TEG indicators could be scaled up and integrated with various NAS search methods, including both supernet and single-path NAS approaches. Extensive studies validate the effective and efficient guidance from our TEG-NAS framework, leading to both improved search accuracy and over 56% reduction in search time cost. Moreover, we visualize search trajectories on three landscapes of “TEG” characteristics, observing that a good local minimum is easier to find on NAS-Bench-201 given its simple topology, whereas balancing “TEG” characteristics is much harder on the DARTS space due to its complex landscape geometry.

18 January 2021
Verified
Conference Paper
Closed access
LSLiu Shuguang
Liu Shuguang
XZXingxing Zhang
Xingxing Zhang
CWChen Wuyang
Chen Wuyang
ZWZhang Wenpu
Zhang Wenpu
The implementation of "collaborative innovation" is a major strategic deployment for China to improve its national innovation system. The triple-helix theory provides academic support for "collaborative innovation" among universities, industries and governments. The triple-helix innovation model emphasizes that the three main bodies realize innovation synergy through the opening of organizational boundary, the reorganization of organizational structure and the aggregation of organizational resources, which is a typical "collaborative innovation" model. A triple-helix "collaborative innovation" model is studied, in view of the problems existing in the current collaborative innovation mechanism in colleges and universities, a targeted idea to promote the triple-helix collaborative innovation mechanism is put forward, and the path to build the triple-helix innovation mechanism is also given.

16 March 2021 in arXiv
Verified
Preprint
Open access
PDF file
WCWuyang Chen
Wuyang Chen
XGXinyu Gong
Xinyu Gong
ZWZhangyang Wang
Zhangyang Wang
Neural Architecture Search (NAS) has been explosively studied to automate the discovery of top-performer neural networks. Current works require heavy training of supernet or intensive architecture evaluations, thus suffering from heavy resource consumption and often incurring search bias due to truncated training or approximations. Can we select the best neural architectures without involving any training and eliminate a drastic portion of the search cost? We provide an affirmative answer, by proposing a novel framework called training-free neural architecture search (TE-NAS). TE-NAS ranks architectures by analyzing the spectrum of the neural tangent kernel (NTK) and the number of linear regions in the input space. Both are motivated by recent theory advances in deep networks and can be computed without any training and any label. We show that: (1) these two measurements imply the trainability and expressivity of a neural network; (2) they strongly correlate with the network's test accuracy. Further on, we design a pruning-based NAS mechanism to achieve a more flexible and superior trade-off between the trainability and expressivity during the search. In NAS-Bench-201 and DARTS search spaces, TE-NAS completes high-quality search but only costs 0.5 and 4 GPU hours with one 1080Ti on CIFAR-10 and ImageNet, respectively. We hope our work inspires more attempts in bridging the theoretical findings of deep networks and practical impacts in real NAS applications. Code is available at: https://github.com/VITA-Group/TENAS.

27 September 2022 in ACM Transactions on Design Automation of Electronic Systems
Verified
Journal Article
Open access
CLChaojian Li
Chaojian Li
WCWuyang Chen
Wuyang Chen
YGYuchen Gu
Yuchen Gu
Tianlong ChenTianlong Chen
Tianlong Chen
YFYonggan Fu
Yonggan Fu
YLYingyan Lin
Yingyan Lin
Semantic segmentation for scene understanding is nowadays widely demanded, raising significant challenges for the algorithm efficiency, especially its applications on resource-limited platforms. Current segmentation models are trained and evaluated on massive high-resolution scene images (“data-level”) and suffer from the expensive computation arising from the required multi-scale aggregation (“network level”). In both folds, the computational and energy costs in training and inference are notable due to the often desired large input resolutions and heavy computational burden of segmentation models. To this end, we propose DANCE, general automated DA ta- N etwork C o-optimization for E fficient segmentation model training and inference . Distinct from existing efficient segmentation approaches that focus merely on light-weight network design, DANCE distinguishes itself as an automated simultaneous data-network co-optimization via both input data manipulation and network architecture slimming. Specifically, DANCE integrates automated data slimming which adaptively downsamples/drops input images and controls their corresponding contribution to the training loss guided by the images’ spatial complexity. Such a downsampling operation, in addition to slimming down the cost associated with the input size directly, also shrinks the dynamic range of input object and context scales, therefore motivating us to also adaptively slim the network to match the downsampled data. Extensive experiments and ablating studies (on four SOTA segmentation models with three popular segmentation datasets under two training settings) demonstrate that DANCE can achieve “all-win” towards efficient segmentation (reduced training cost, less expensive inference, and better mean Intersection-over-Union (mIoU)). Specifically, DANCE can reduce ↓25%–↓77% energy consumption in training, ↓31%–↓56% in inference, while boosting the mIoU by ↓0.71%–↑ 13.34%.

1 August 2022 in Academy of Management Proceedings
Verified
Journal Article
Closed access
WCWuyang Chen
Wuyang Chen
AOAmy Y. Ou
Amy Y. Ou
QSQin Su
Qin Su
LSLynda Jiwen Song
Lynda Jiwen Song
The relationship between overqualification and performance exists puzzle, and the social influence of overqualification on employees, especially during the socialization process, received less atte...