Shengyu Zhu

Shengyu Zhu

Principal Researcher, Huawei Noah's Ark Lab

Publications

Journal Articles

  1. Zhuangyan Fang*, Shengyu Zhu*, Jiji Zhang, Yue Liu, Zhitang Chen, Yangbo He, Low rank directed acyclic graphs and causal structure learning, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023. (*equal contribution)
  2. Ran Chen, Shoubo Hu, Zhitang Chen, Shengyu Zhu, et al., A unified framework for layout pattern analysis with deep causal estimation, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2022.
  3. Zitong Lu, Zhi Geng, Wei Li, Shengyu Zhu, Jinzhu Jia, Evaluating causes of effects by posterior effects of causes, Biometrika, 2022.
  4. Zhuangyan Fang, Yue Liu, Zhi Geng, Shengyu Zhu, Yangbo He, A local method for identifying causal relations under Markov equivalence, Artificial Intelligence (AIJ), Feburary, 2022.
  5. Shengyu Zhu, Biao Chen, Zhitang Chen, and Pengfei Yang, Asymptotically optimal one- and two-sample testing with kernels, IEEE Transactions on Information Theory (TIT), April 2021.
  6. Shengyu Zhu and Biao Chen, Distributed detection in ad hoc networks through quantized consensus, IEEE Transactions on Information Theory (TIT), August 2018.
  7. Shengyu Zhu and Biao Chen, Quantized consensus by the ADMM: Probabilistic versus deterministic quantizers, IEEE Transactions on Signal Processing (TSP), April 2016.
  8. Ge Xu, Shengyu Zhu, and Biao Chen, Decentralized data reduction with quantization constraints, IEEE Transactions on Signal Processing (TSP), April 2014. (corresponding author)

Referred Conference Proceedings

  1. Ruiqi Zhao, Lei Zhang, Shengyu Zhu, Zitong Lu, Zhenhua Dong, Chaoliang Zhang, Zhi Geng, Yangbo He, Conditional counterfactual causal effect for individual attribution, UAI, 2023. (spotlight presentation; first two authors were interns at Noah’s Ark Lab)
  2. Xiaoyu Tan, LIN Yong, Shengyu Zhu, Chao Qu, Xihe Qiu, Xu Yinghui, Peng Cui, Yuan Qi, Provably Invariance Learning without Domain Information”, ICML, 2023.
  3. Yong Lin, Shengyu Zhu, Lu Tan, Peng Cui, ZIN: When and how to learn invariance without environment partition?, NeurIPS, 2022. (spotlight presentation; corresponding author)
  4. Junlong Lyu, Zhitang Chen, Chang Feng, Wenjing Cun, Shengyu Zhu, Yanhui Geng, Zhijie Xu, Para-CFlows: $C^k$-universal diffeomorphism approximators as superior neural surrogates, NeurIPS, 2022.
  5. Xiaopeng Zhang, Shoubo Hu, Zhitang Chen, Shengyu Zhu, et al., RCANet: Root cause analysis via latent variable interaction modeling for yield improvement, IEEE International Test Conference (ITC), 2022.
  6. Xinwei Shen, Shengyu Zhu, Jiji Zhang, Shoubo Hu, Zhitang Chen, Reframed GES with a neural conditional dependence measure, Conference on Uncertainty in Artificial Intelligence (UAI), 2022.
  7. Ruoyu Wang, Mingyang Yi, Zhitang Chen, Shengyu Zhu, Out-of-distribution generalization with causal invariant transformations, IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), June 2022. (corresponding author)
  8. Iganvier Ng, Shengyu Zhu, Zhuangyan Fang, Haoyang Li, Zhitang Chen, Jun Wang, Masked gradient-based causal structure learning, SIAM Conference on Data Mining (SDM), May 2022. (corresponding author)
  9. Ran Chen, Shoubo Hu, Zhitang Chen, Shengyu Zhu, et al., A unified framework for layout pattern analysis with deep causal estimation, IEEE/ACM International Conference On Computer Aided Design (ICCAD), November 2021.
  10. Xiaoqiang Wang, Yali Du, Shengyu Zhu, Liangjun Ke, Zhitang Chen, Jianye Hao, Jun Wang, Ordering-based causal discovery with reinforcement learning, International Joint Conference on Artificial Intelligence (IJCAI), July 2021. (corresponding author)
  11. Shengyu Zhu, Ignavier Ng, and Zhitang Chen, Causal discovery with reinforcement learning, International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia, April 2020. (highest review score and oral presentation; top 1.6%)
  12. Shengyu Zhu, Biao Chen, Pengfei Yang, and Zhitang Chen, Universal hypothesis testing with kernels: Asymptotically optimal tests for goodness of fit, International Conference on Artificial Intelligence and Statistics (AISTATS), Naha, Okinawa, Japan, April 2019.
  13. Shengyu Zhu and Biao Chen, Distributed detection over connected networks via one-bit quantizer, IEEE International Symposium on Information Theory (ISIT), Barcelona, Spain, July 2016.
  14. Shengyu Zhu and Biao Chen, Distributed average consensus with bounded quantization, IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), Edinburgh, UK, July 2016.
  15. Shengyu Zhu, Mingyi Hong, and Biao Chen, Quantized consensus ADMM for multi-agent distributed optimization, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, China, March 2016.
  16. Shengyu Zhu and Biao Chen, Distributed average consensus with deterministic quantization: an ADMM approach, IEEE Global Conference on Signal and Information Processing (GlobalSIP), Orlando, FL, December 2015. (IEEE travel grant)
  17. Shengyu Zhu, Ge Xu, and Biao Chen, Are global sufficient statistics always sufficient: the impact of quantization on decentralized data reduction, Asilomar Conference on Signals, Systems, and Computers (Asilomar), Monterey, CA, November 2013. (invited paper)
  18. Shengyu Zhu and Biao Chen, Data reduction in tandem fusion systems, IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP), Beijing, China, July 2013.
  19. Shengyu Zhu, Earnest Akofor, and Biao Chen, Interactive distributed detection with conditionally independent observations, IEEE Wireless Communications and Networking Conference (WCNC), Shanghai, China, April 2013.

Some Preprints and Workshop Papers

  1. Ignavier Ng, Shengyu Zhu, Zhitang Chen, Zhuangyan Fang, A graph autoencoder approach to causal structure learning, NeurIPS Causality Workshop, 2019.
  2. Keli Zhang, Shengyu Zhu, Marcus Kalander, Ignavier Ng, Junjian Ye, Zhitang Chen, Lujia Pan, gCastle: A Python Toolbox for Causal Discovery

Patents

  1. Root cause positioning method for communication network fault and related equipment, granted, CN113923099B (in accordance to SDM’2022 paper, with modifications for new applications)
  2. Chip fault identification method and related equipment, under substantive examination (last round before granted), CN113657022A (in accordance to ICCAD’2021 and TCAD’2022 papers)
  3. Defect root cause determination method, defect root cause determination device and storage medium, under substantive examination, CN115238641A (in accordance to ITC’2022 paper)
  4. Data processing method and related equipment item, under substantive examination, CN115905932A (in accordance to CVPR’2022 paper)