Weiyang Liu

 

Google Scholar   Github   Twitter

 

University of Cambridge
Max Planck Institute for Intelligent Systems

About Me

I conduct research at Cambridge and MPI Tübingen with Adrian Weller and Bernhard Schölkopf. Previously, I spent wonderful years at Georgia Tech, working with Le Song. I have also spent time at Google Brain, Nvidia, and MERL.

 

My research interest broadly lies in Machine Learning. My research aims to tackle fundamental yet practical problems, and to develop "light-and-sweet" algorithms: (i) light: conceptually simple in methodology and easy to implement in practice, (ii) sweet: having clear intuitions and non-trivial theoretical guarantees. My research is/was generously supported by Leverhulme Center for the Future of Intelligence, Cambridge-Tübingen Fellowship and Baidu Fellowship. See some of my papers for an oversimplified research overview, and arXiv for most recent preprints.

 

I always believe that everything should be made as simple as possible, but not simpler. I try to follow certain research values.

    - Focus on creating novel ideas, not publishing papers
    - Follow curiosity and passion, not trends
    - Ideas are not owned, but come with debts to those who came before
    - Ideas become stronger when shared, discussed and criticized
    - Life is surprisingly short, so solve problems that interest and excite you most
    - It is good to be quick, but it is more important to be deep
    - Think like an amateur, do as an expert
    - This is not only about how to do research, but also how to live your life

Publications

Structural Causal 3D Reconstruction
Weiyang Liu*, Zhen Liu*, Liam Paull, Adrian Weller, Bernhard Schölkopf

ECCV 2022

arXiv | code | talk | slides | bib

  @article{Liu2022SCR,
      title={Structural Causal 3D Reconstruction},
      author={Liu, Weiyang and Liu, Zhen and Paull, Liam and Weller, Adrian and Schölkopf, Bernhard},
      booktitle = {ECCV},
      year={2022}}

Towards Principled Disentanglement for Domain Generalization
Hanlin Zhang*, Yi-Fan Zhang*, Weiyang Liu, Adrian Weller, Bernhard Schölkopf, Eric Xing

CVPR 2022   Oral

arXiv | code | talk | bib

  @article{Zhang2022DDG,
      title={Towards Principled Disentanglement for Domain Generalization},
      author={Zhang, Hanlin and Zhang, Yi-Fan and Liu, Weiyang and Weller, Adrian and Sch{\"o}lkopf, Bernhard and Xing, Eric P},
      booktitle = {CVPR},
      year={2022}}

SphereFace Revived: Unifying Hyperspherical Face Recognition
Weiyang Liu*, Yandong Wen*, Bhiksha Raj, Rita Singh, Adrian Weller

TPAMI 2022

arXiv | code | opensphere | journal | bib

  @article{Liu2022SphereFaceR,
      title={SphereFace Revived: Unifying Hyperspherical Face Recognition},
      author={Liu, Weiyang and Wen, Yandong and Raj, Bhiksha and Singh, Rita and Weller, Adrian},
      journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
      year={2022}}

SphereFace2: Binary Classification is All You Need for Deep Face Recognition
Yandong Wen*, Weiyang Liu*, Adrian Weller, Bhiksha Raj, Rita Singh

ICLR 2022   Spotlight

arXiv | code | project | openreview | slides | bib

  @article{Wen2021SphereFace2,
      title={SphereFace2: Binary Classification is All You Need for Deep Face Recognition},
      author={Wen, Yandong and Liu, Weiyang and Weller, Adrian and Raj, Bhiksha and Singh, Rita},
      booktitle = {ICLR},
      year={2022}}

Pre-training Molecular Graph Representation with 3D Geometry
Shengchao Liu, Hanchen Wang, Weiyang Liu, Joan Lasenby, Hongyu Guo, Jian Tang

ICLR 2022

arXiv | code | project | openreview | talk | slides | bib

  @InProceedings{Liu2021GraphMVP,
      title={Pre-training Molecular Graph Representation with 3D Geometry},
      author={Liu, Shengchao and Wang, Hanchen and Liu, Weiyang and Lasenby, Joan and Guo, Hongyu and Tang, Jian},
      booktitle={ICLR},
      year={2022}}

Provable Lifelong Learning of Representations
Xinyuan Cao*, Weiyang Liu*, Santosh S. Vempala*

AISTATS 2022

arXiv | talk | slides | bib

  @InProceedings{Cao2021LLL,
      title={Provable Lifelong Learning of Representations},
      author={Cao, Xinyuan and Liu, Weiyang and Vempala, Santosh S},
      booktitle = {AISTATS},
      year={2022}}

Iterative Teaching by Label Synthesis
Weiyang Liu*, Zhen Liu*, Hanchen Wang*, Liam Paull, Bernhard Schölkopf, Adrian Weller

NeurIPS 2021   Spotlight

arXiv | code | openreview | talk | slides | video | bib

  @InProceedings{Liu2021LAST,
      title={Iterative Teaching by Label Synthesis},
      author={Liu, Weiyang and Liu, Zhen and Wang, Hanchen and Paull, Liam and Schölkopf, Bernhard and Weller, Adrian},
      booktitle = {NeurIPS},
      year={2021}}

Locality Sensitive Teaching
Zhaozhuo Xu, Beidi Chen, Chaojian Li, Weiyang Liu, Le Song, Yingyan Lin, Anshumali Shrivastava

NeurIPS 2021

arXiv | code | openreview | talk | slides | bib

  @InProceedings{Xu2021LST,
      title={Locality Sensitive Teaching},
      author={Xu, Zhaozhuo and Chen, Beidi and Li, Chaojian and Liu, Weiyang and Song, Le and Lin, Yingyan and Shrivastava, Anshumali},
      booktitle = {NeurIPS},
      year={2021}}

Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence
Xiang Bai, Hanchen Wang, ..., Weiyang Liu, ..., Carola Schönlieb, Tian Xia

Nature Machine Intelligence 2021

arXiv | code | project | news | bib

  @article{UCADI2021NMI,
      title={Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence},
      author={Bai, Xiang and Wang, Hanchen and Ma, Liya and Xu, Yongchao and Gan, Jiefeng and Fan, Ziwei and Yang, Fan and Ma, Ke and Yang, Jiehua and Bai, Song and others},
      journal={Nature Machine Intelligence},
      volume={3},
      number={12},
      pages={1081--1089},
      year={2021},
      publisher={Nature Publishing Group}}

Self-Supervised 3D Face Reconstruction via Conditional Estimation
Yandong Wen, Weiyang Liu, Bhiksha Raj, Rita Singh

ICCV 2021

arXiv | code | talk | poster | bib

  @InProceedings{Wen2021CEST,
      title={Self-Supervised 3D Face Reconstruction via Conditional Estimation},
      author={Wen, Yandong and Liu, Weiyang and Raj, Bhiksha and Singh, Rita},
      booktitle={ICCV},
      year={2021}}

Learning with Hyperspherical Uniformity
Weiyang Liu, Rongmei Lin, Zhen Liu, Li Xiong, Bernhard Schölkopf, Adrian Weller

AISTATS 2021

arXiv | code | talk | slides | bib

  @InProceedings{Liu2021SphereUni,
      title={Learning with Hyperspherical Uniformity},
      author={Liu, Weiyang and Lin, Rongmei and Liu, Zhen and Xiong, Li and Schölkopf, Bernhard and Weller, Adrian},
      booktitle={AISTATS},
      year={2021}}

Orthogonal Over-Parameterized Training
Weiyang Liu*, Rongmei Lin*, Zhen Liu, James Rehg, Liam Paull, Li Xiong, Le Song, Adrian Weller

CVPR 2021   Oral

arXiv | code | project | talk | slides | bib

  @InProceedings{Liu2021OPT,
      title={Orthogonal Over-Parameterized Training},
      author={Liu, Weiyang and Lin, Rongmei and Liu, Zhen and Rehg, James M. and Paull, Liam 
       and Xiong, Li and Song, Le and Weller, Adrian},
      booktitle={CVPR},
      year={2021}}

Angular Visual Hardness
Beidi Chen, Weiyang Liu, Zhiding Yu, Jan Kautz, Anshumali Shrivastava, Animesh Garg, Animashree Anandkumar

ICML 2020

arXiv | code | project | talk | long talk | slides | bib

  @InProceedings{Chen20AVH,
      title={Angular Visual Hardness},
      author={Chen, Beidi and Liu, Weiyang and Garg, Animesh and Yu, Zhiding 
       and Shrivastava, Anshumali and Anandkumar, Animashree},
      booktitle={ICML},
      year={2020}}

Regularizing Neural Networks via Minimizing Hyperspherical Energy
Rongmei Lin, Weiyang Liu*, Zhen Liu, Chen Feng, Zhiding Yu, James Rehg, Li Xiong, Le Song

CVPR 2020

arXiv | code | talk | slides | bib

  @InProceedings{Lin20CoMHE,
      title={Regularizing Neural Networks via Minimizing Hyperspherical Energy},
      author={Lin, Rongmei and Liu, Weiyang and Liu, Zhen and Feng, Chen and Yu, Zhiding 
       and Rehg, James M. and Xiong, Li and Song, Le},
      booktitle={CVPR},
      year={2020}}

Neural Similarity Learning
Weiyang Liu, Zhen Liu, James Rehg, Le Song

NeurIPS 2019

arXiv | code | talk | slides | bib

  @InProceedings{LiuNIPS19,
      title={Neural Similarity Learning},
      author={Liu, Weiyang and Liu, Zhen and Rehg, James and Song, Le},
      booktitle={NeurIPS},
      year={2019}}

Meta Architecture Search
Albert Shaw, Wei Wei, Weiyang Liu, Le Song, Bo Dai

NeurIPS 2019

arXiv | code | poster | bib

  @InProceedings{ShawNIPS19,
      title={Meta Architecture Search},
      author={Shaw, Albert and Wei, Wei and Liu, Weiyang and Song, Le and Dai, Bo},
      booktitle={NeurIPS},
      year={2019}}

Disjoint Mapping Network for Cross-modal Matching of Voices and Faces
Yandong Wen, Mahmoud Alismail, Weiyang Liu, Bhiksha Raj, Rita Singh

ICLR 2019

arXiv | code | openreview | poster | bib

  @InProceedings{Wen2019DIM,
      title={Disjoint Mapping Network for Cross-modal Matching of Voices and Faces},
      author={Wen, Yandong and Alismail, Mahmoud and Liu, Weiyang and Raj, Bhiksha and Singh, Rita},
      booktitle={ICLR},
      year={2019}}

Learning towards Minimum Hyperspherical Energy
Weiyang Liu*, Rongmei Lin*, Zhen Liu*, Lixin Liu*, Zhiding Yu, Bo Dai, Le Song

NeurIPS 2018

arXiv | code | project | sphereface+ | talk | slides | bib

  @InProceedings{LiuNIPS18,
      title={Learning towards Minimum Hyperspherical Energy},
      author={Liu, Weiyang and Lin, Rongmei and Liu, Zhen and Liu, Lixin and Yu, Zhiding and Dai, Bo and Song, Le},
      booktitle={NeurIPS},
      year={2018}}

Coupled Variational Bayes via Optimization Embedding
Bo Dai, Hanjun Dai, Niao He, Weiyang Liu, Zhen Liu, Jianshu Chen, Lin Xiao, Le Song

NeurIPS 2018

arXiv | code | poster | bib

  @InProceedings{DaiNIPS18,
      title={Coupled Variational Bayes via Optimization Embedding},
      author={Dai, Bo and Dai, Hanjun and He, Niao and Liu, Weiyang 
       and Liu, Zhen and Chen, Jianshu and Xiao, Lin and Song, Le},
      booktitle={NeurIPS},
      year={2018}}

Simultaneous Edge Alignment and Learning
Zhiding Yu, Weiyang Liu, Yang Zou, Chen Feng, Srikumar Ramalingam, Vijaya Kumar, Jan Kautz

ECCV 2018

arXiv | code | project | demo | slides | bib

  @article{YuECCV18,
      title={Simultaneous Edge Alignment and Learning},
      author={Yu, Zhiding and Liu, Weiyang and Zou, Yang and Feng, Chen
       and Ramalingam, Srikumar and Kumar, Vijaya and Kautz, Jan},
      journal={arXiv preprint arXiv:1807.04836},
      year={2018}}

Towards Black-box Iterative Machine Teaching
Weiyang Liu, Bo Dai, Xingguo Li, Zhen Liu, James Rehg, Le Song

ICML 2018    

arXiv | talk | slides | bib

  @InProceedings{Liu2018ICML,
      author={Liu, Weiyang and Dai, Bo and Li, Xingguo and Rehg, James M and Song, Le},
      title = {Towards Black-box Iterative Machine Teaching},
      booktitle = {ICML},
      year = {2018}}

Decoupled Networks
Weiyang Liu*, Zhen Liu*, Zhiding Yu, Bo Dai, Rongmei Lin, Yisen Wang, James Rehg, Le Song

CVPR 2018   Spotlight

arXiv | code | talk | slides | bib

  @InProceedings{Liu2018DCNets,
      author = {Liu, Weiyang and Liu, Zhen and Yu, Zhiding and Dai, Bo and Lin, Rongmei
       and Wang, Yisen and Rehg, James M. and Song, Le},
      title = {Decoupled Networks},
      booktitle = {CVPR},
      year = {2018}}

Iterative Learning with Open-set Noisy Labels
Yisen Wang, Weiyang Liu, Xingjun Ma, James Bailey, Hongyuan Zha, Le Song, Shu-Tao Xia

CVPR 2018   Spotlight

arXiv | code | slides | bib

  @InProceedings{Wang2018ONL,
      author={Wang, Yisen and Liu, Weiyang and Ma, Xingjun and Bailey, James
       and Zha, Hongyuan and Song, Le and Xia, Shu-Tao},
      title={Iterative Learning with Open-set Noisy Labels},
      booktitle = {CVPR},
      year = {2018}}

Additive Margin Softmax for Face Verification
Feng Wang, Weiyang Liu, Haijun Liu, Jian Cheng

ICLR 2018   Workshop   Most Popular Paper

arXiv | code | openreview | journal | bib

  @article{Wang2018ICLRW,
      title = {Additive Margin Softmax for Face Verification},
      author = {Wang, Feng and Liu, Weiyang and Liu, Haijun and Cheng, Jian},
      journal = {arXiv preprint arXiv:1801.05599},
      year = {2018}}

Deep Hyperspherical Learning
Weiyang Liu, Yan-Ming Zhang, Xingguo Li, Zhiding Yu, Bo Dai, Tuo Zhao, Le Song

NIPS 2017   Spotlight

arXiv | code | project | talk | slides | bib

  @inproceedings{Liu2017NIPS,
      title={Deep Hyperspherical Learning},
      author={Liu, Weiyang and Zhang, Yan-Ming and Li, Xingguo and Yu, Zhiding and Dai, Bo and Zhao, Tuo and Song, Le},
      booktitle={NIPS},
      year={2017}}

Iterative Machine Teaching
Weiyang Liu, Bo Dai, Ahmad Humayun, Charlene Tay, Yu Chen, Linda Smith, James Rehg, Le Song

ICML 2017

arXiv | code | demo | talk | slides | bib

  @inproceedings{Liu2017ICML,
      title={Iterative Machine Teaching},
      author={Liu, Weiyang and Dai, Bo and Humayun, Ahmad and Tay, Charlene and Yu, Chen
       and Smith, Linda B and Rehg, James M and Song, Le},
      booktitle={ICML},
      year={2017}}

SphereFace: Deep Hypersphere Embedding for Face Recognition
Weiyang Liu, Yandong Wen, Zhiding Yu, Ming Li, Bhiksha Raj, Le Song
CVPR 2017   Most Influential Paper

arXiv | code | project | demo | slides | bib

  @InProceedings{Liu2017CVPR,
      title = {SphereFace: Deep Hypersphere Embedding for Face Recognition},
      author = {Liu, Weiyang and Wen, Yandong and Yu, Zhiding and Li, Ming and Raj, Bhiksha and Song, Le},
      booktitle = {CVPR},
      year = {2017}}

Large-Margin Softmax Loss for Convolutional Neural Networks
Weiyang Liu, Yandong Wen, Zhiding Yu, Meng Yang
ICML 2016

arXiv | code | project | talk | slides | bib

  @inproceedings{Liu2016ICML,
      title={Large-Margin Softmax Loss for Convolutional Neural Networks},
      author={Liu, Weiyang and Wen, Yandong and Yu, Zhiding and Yang, Meng},
      booktitle={ICML},
      year={2016}}
Last updated on 10th Apr. 2022.
This site has been visisted Free Web Counter times in total.