Shen Yan

yanshen6 at msu dot edu

My name is Shen Yan (严珅). I am a final year PhD at the Computer Science Department at Michigan State Univiersity, where I work on representation learning, AutoML and their applications. I am advised by Mi Zhang.

I got my M.S. in Computer Engineering from RWTH Aachen University, where I worked with Hermann Ney on face recognition and Jens-Rainer Ohm on image retrieval. I have a B.S. in Telecommunications engineering from Xidian University.

GitHub  /  Google Scholar / Twitter / LinkedIn / CV

profile photo

Research

My general interests lie in machine learning and computer vision. Currently, I focus on representation learning and architecture search, mostly in the context of visual recognition. Representative papers are highlighted.

Multiview Transformers for Video Recognition
Shen Yan, Xuehan Xiong, Anurag Arnab, Zhichao Lu, Mi Zhang, Chen Sun, Cordelia Schmid
CVPR, 2022  
arXiv / code / leaderboard / bibtex

A simple method for capturing multiresolution temporal context in transformers. State-of-the-art results on popular video classification datasets.

Deep AutoAugment
Yu Zheng, Zhi Zhang, Shen Yan, Mi Zhang
ICLR, 2022  
arXiv / code / bibtex / slides

Build deep data augmentation policies progressively based on regularized gradient matching.

NAS-Bench-x11 and the Power of Learning Curves
Shen Yan*, Colin White*, Yash Savani, Frank Hutter
NeurIPS, 2021  
arXiv / code / bibtex / slides

A surrogate method to create multi-fidelity NAS benchmarks.

CATE: Computation-aware Neural Architecture Encoding with Transformers
Shen Yan, Kaiqiang Song, Fei Liu, Mi Zhang
ICML, 2021 (Long Presentation)
video: 17 min/ arXiv / code / bibtex / poster

Pre-training computation-aware architecture embeddings help architecture search too.

Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?
Shen Yan, Yu Zheng, Wei Ao, Xiao Zeng, Mi Zhang
NeurIPS, 2020  
video: 3 min/ arXiv / code / bibtex / poster

Pre-training structure-aware architecture embeddings help architecture search.

MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution
Taojiannan Yang, Sijie Zhu, Chen Chen, Shen Yan, Mi Zhang, Andrew Wills
ECCV, 2020   (Oral)
video: 10 min/ arXiv / code / bibtex

Mutual learning with input resolution and network width improves the accuracy-efficiency tradeoffs.

Improve Unsupervised Domain Adaptation with Mixup Training
Shen Yan, Huan Song, Nanxiang Li, Lincan Zou, Liu Ren
arXiv, 2020
arXiv / code / bibtex

MixMatch helps unsupervised domain adaptation too.

HM-NAS: Efficient Neural Architecture Search via Hierarchical Masking
Shen Yan, Biyi Fang, Faen Zhang, Yu Zheng, Xiao Zeng, Hui Xu, Mi Zhang
ICCV Neural Architects Workshop, 2019   (Best Paper Nomination)
arXiv / bibtex

Highlight the importance of topology learning in differentialable NAS.

Deep Fisher Faces
Harald Hanselmann, Shen Yan, Hermann Ney
BMVC, 2017
bibtex

Extend the center loss with an inter-class loss reminiscent of the popular early face recognition approach Fisherfaces.

Experience

Research Intern, Summer 2022
Google Research, Brain Team, Mountain View, USA
Host: Jiahui Yu, Tao Zhu, Yuan Cao

Research on large video Transformers.

Research Intern, Student Researcher, Summer 2021, Fall 2021
Google Research, Perception Team, Mountain View, USA
Host: Xuehan Xiong, Zhichao Lu, Chen Sun, Cordelia Schmid

Research on large video Transformers.

Research Intern, Spring 2021
Abacus.AI, San Francisco, USA
Host: Colin White

Research on multi-fidelity AutoML.

Applied Machine Learning Intern, Summer 2020
ByteDance Inc., Mountain View, USA
Host: Ming Chen, Youlong Cheng

Neural architecture search for large scale advertising models.

Research Intern, Summer 2019
Bosch Research, Sunnyvale, USA
Host: Huan Song, Liu Ren

Unsupervised domain adaptation with image and time-series data.

Research Intern, Summer 2017
eBay Research, Aachen, Germany
Host: Shahram Khadivi, Evgeny Matusov

Adapt neural machine translation to e-commerce domains.

Service

PC member, AutoML Workshop, ICML 2021

PC member, NAS Workshop, ICLR 2021

Reviewer, NeurIPS 2020, 2021, 2022

Reviewer, ICML 2020, 2021, 2022

Reviewer, ICLR 2021, 2022

Reviewer, CVPR 2021, 2022

Reviewer, ICCV 2021

Reviewer, ECCV 2022

Reviewer, TMLR 2022
TA for Bachelor, Kinect Programming, Fall 2015


Talks

New Insights in Neural Architecture Search, UT Austin, Dec 2021

This guy makes a nice webpage.