折 闪 电

Shandian Zhe Associate Professor School of Computing, University of Utah Office: Room 3466, MEB building Address: 50 Central Campus Dr #3190, School of Computing, University of Utah, Salt Lake City, UT 84112 I obtained the Ph.D. degree from the Computer Science Department of Purdue University in 2017. My research interests mainly lie in probabilistic machine learning. That is, using probabilistic frameworks to formulate learning problems and to infer/estimate model parameters. My research include but are not limited to probabilistic graphical models, Bayesian deep learning, Bayesian nonparametric, physics informed machine learning, approximate inference, sparse learning, large-scale machine learning and kernel methods. From application side, I have developed probabilistic methods for microarray data analysis, association study for Alzheimer's disease, functional magnetic resonance imaging (fMRI) data analysis, and click-through-rate prediction for online advertising. Email: zhe at cs.utah.edu Curriculum Vitae Post-Doc Position I am looking for a postdoc, expected to start soon. The research will be mainly on physics informed machine learning. Machine learning and data science background are preferred. The posting is Here. Feel free to contact me if you are interested. Graduate students I am looking for highly motivated students with solid background in probability, linear algebra and/or optimization, and good programming skills. If you are interested in joining my group, welcome to contact me via the email address above. Please attach your CV in the email. In particular, if you have a strong math and/or physics background (e.g., with a BS degree in math or physics) and also have coding experiences, e.g., matlab and python), feel free to schedule a meeting with me.

---

Group

Group Seminar

Teaching

News

Year 2023

• 2 NeurIPS papers accepted. Congrats to Zheng Wang, Shikai Fang, Shibo Li and Xin Yu! Congrats to Zheng for his paper being selected as a spotlight presentation!

• Zheng Wang has successfully defended his Ph.D. thesis. Congrats to Dr. Wang now. Zheng will join Celonis --- the unicorn in process mining! Given this is a hard time for international students to find jobs, Zheng has made a great achievement! Congrats!

• 2 ICML papers and 1 AISTATS papers accepted. Congrats to Shibo Li and Shikai Fang!

Year 2022

• Zhimeng Pan has successfully defended his Ph.D. thesis. Congrats to Dr. Pan now! Zhimeng will join Pinterest in his next step.

• 3 NeurIPS papers accpeted. Congrats to Shibo Li, Zheng Wang and Xin Yu. Especially, Shibo is the leading author for two papers!

• 7 ICML papers accpeted. Congratulations to Da Long and Xin Yu: they got ICML papers after joining our group for one semester! In particular, Da is a fresh Ph.D. student. Congratulations to Shikai for his paper being selected as a long presentation!

Grants

Publications

• Year 2024

• Shikai Fang, Qingsong Wen, Yingtao Luo, Shandian Zhe, Liang Sun, “BayOTIDE: Bayesian Online Multivariate Time series Imputation with functional decomposition”, The 41st International Conference on Machine Learning(ICML), 2024.


• Shikai Fang, Xin Yu, Zheng Wang, Shibo Li, Rboert M. Kirby, and Shandian Zhe, “Functional Bayesian Tucker Decomposition for Continuous-indexed Tensor”, The International Conference on Learning Representations (ICLR), 2024. [PDF][Code]


• Shikai Fang*, Madison Cooley*, Da Long*, Shibo Li, Robert M. Kirby, and Shandian Zhe, “Solving High Frequency and Multi-Scale PDEs with Gaussian Processes”, The International Conference on Learning Representations(ICLR), 2024. [PDF] [Code]


• Shibo Li, Xin Yu, Wei W. Xing, Robert M. Kirby, Akil Narayan, and Shandian Zhe, “Multi-Resolution Active Learning of Fourier Neural Operators”(oral presentation), The 27th International Conference on Artificial Intelligence and Statistics (AISTATS), 2024. [PDF] [Code]


• Da Long, Wei W. Xing, Aditi S. Krishnapriyan, Robert M. Kirby, Shandian Zhe, and Michael W. Mahoney, “Equation Discovery with Bayesian Spike-and-Slab Priors and Efficient Kernels”, The 27th International Conference on Artificial Intelligence and Statistics (AISTATS), 2024. [PDF] [Code]


• Da Long, Nicole Mrvaljevic, Shandian Zhe, and Bamdad Hosseini, “A Kernel Approach for PDE Discovery and Operator Learning”, In Physcia D: Nonlinear Phenomena.



• Year 2023

• Zheng Wang, Shikai Fang, Shibo Li, and Shandian Zhe, “Dynamic Tensor Decomposition via Neural Diffusion-Reaction Processes” (spotlight presentation), The 37th Conference on Neural Information Processing Systems (NeurIPS), 2023. [PDF] [Code]


• Shikai Fang, Xin Yu, Shibo Li, Zheng Wang, Robert M. Kirby, and Shandian Zhe, “Streaming Factor Trajectory Learning for Temporal Tensor Decomposition”, The 37th Conference on Neural Information Processing Systems (NeurIPS), 2023. [PDF][Code]


• Hongsup Oh, Roman Amici, Geoffrey Bomarito, Shandian Zhe, Robert M. Kirby and Jacob Hochhalter, “Inherently Interpretable Machine Learning Solutions to Differential Equations”, Engineering with Computers, In Press, 2023.


• Shikai Fang, Shandian Zhe, Hui-Ming Lin, Arun A. Azad, Heidi Fettke, Edmond M Kwan, Lisa Horvath, Blossom Mak, Tiantian Zheng, Pan Du, Shidong Jia, Robert M. Kirby, Manish Kohli MD, “Multi-Omic Integration of Blood-Based Tumor Associated Genomic and Lipidomic Profiles Using Machine Learning Models in Metastatic Prostate Cancer”, JCO Clinical Cancer Informatics.


• Shibo Li*, Michael Penwarden*, Yiming Xu, Conor Tillinghast, Akil Narayan, Robert Kirby, and Shandian Zhe, “Meta Learning of Interface Conditions for Multi-Domain Physics-Informed Neural Networks”, The 40th International Conference on Machine Learning (ICML), 2023 [PDF][Code]


• Yu Chen*, Wei Deng*, Shikai Fang*, Fengpei Li*, Tianjiao Nicole Yang, Yikai Zhang, Kashif Rasul, Shandian Zhe, Anderson Schneider, and Yuriy Nevmyvaka, “Provably Convergent Schrodinger Bridge with Applications to Probabilistic Time Series Imputation”, The 40th International Conference on Machine Learning (ICML), 2023.


• Shibo Li, Zheng Wang, Akil Narayan, Robert Kirby, and Shandian Zhe, “ Meta-Learning with Adjoint Methods ”, The 26th International Conference on Artificial Intelligence and Statistics (AISTATS) , 2023 [PDF] [Code]


• Michael Penwarden, Shandian Zhe, Akil Narayan, and Robert M. Kirby, “A Metalearning Approach for Physics-Informed Neural Networks (PINNs): Application to Parameterized PDEs”, Journal of Computational Physics, 2023


• M. Penwarden, A.D. Jagtap, Shandian Zhe, G.E. Karnidakis and R.M. Kirby, "A Unified Scalable Framework For Causal Sweeping Strategies For Physics-Informed Neural Networks (PINNs) and Their Temporal Decompositions", Journal of Computational Physics, 2023


• Junyang Cai, Khai-Nguyen Nguyen, Nishant Shrestha, Aidan Good, Ruisen Tu, Xin Yu, Shandian Zhe and Thiago Serra, “Getting away with more network pruning: From sparsity to geometry and linear regions”, 20th International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research (CPAIOR), 2023.



• Year 2022

• Shibo Li, Zheng Wang, Robert M. Kirby, and Shandian Zhe, “Infinite-Fidelity Coregionalization for Physical Simulation”, Thirty-Sixth Conference on Neural Information Processing Systems (NeurIPS), 2022 [PDF] [Code]


• Shibo Li*, Jeff Phillips*, Xin Yu, Robert M. Kirby, and Shandian Zhe, “Batch Multi-Fidelity Active Learning with Budget Constraints”, Thirty-Sixth Conference on Neural Information Processing Systems (NeurIPS), 2022 [PDF] [Code]


• Aidan Good*, Jacky Lin*, Xin Yu*, Hannah Sieg, Mikey Fergurson, Shandian Zhe, Jerzy Wieczorek, and Thiago Serra, “Recall Distortion in Neural Network Pruning and the Undecayed Pruning Algorithm”, Thirty-Sixth Conference on Neural Information Processing Systems (NeurIPS), 2022, to appear


• Shikai Fang, Akil Narayan, Robert M. Kirby, and Shandian Zhe, “Bayesian Continuous-Time Tucker Decomposition” (Long Talk), The 39th International Conference on Machine Learning (ICML), 2022, Baltimore, Maryland [PDF][Code]


• Shibo Li, Robert M. Kirby, and Shandian Zhe, “Decomposing Temporal High-Order Interactions via Latent ODEs”, The 39th International Conference on Machine Learning (ICML), 2022, Baltimore, Maryland [PDF][Code]


• Da Long, Zheng Wang, Aditi Krishnapriyan, Robert M. Kirby, Shandian Zhe, and Michael W. Mahoney, “AutoIP: A United Framework to Integrate Physics into Gaussian Processes”, The 39th International Conference on Machine Learning (ICML), 2022, Baltimore, Maryland [PDF][Code]


• Zheng Wang, and Shandian Zhe, “Nonparametric Factor Trajectory Learning for Dynamic Tensor Decomposition”, The 39th International Conference on Machine Learning (ICML), 2022, Baltimore, Maryland [PDF][Code]


• Zheng Wang, Yiming Xu, Conor Tillinghast, Shibo Li, Akil Narayan, and Shandian Zhe, “Nonparametric Embeddings of Sparse High-Order Interaction Events”, The 39th International Conference on Machine Learning (ICML), 2022, Baltimore, Maryland [PDF][Code]


• Conor Tillinghast, Zheng Wang, and Shandian Zhe, “Nonparametric Sparse Tensor Factorization with Hierarchical Gamma Processes”, The 39th International Conference on Machine Learning (ICML), 2022, Baltimore, Maryland [PDF][Code]


• Xin Yu, Thiago Serra, Srikumar Ramalingam, and Shandian Zhe, “The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks ”, The 39th International Conference on Machine Learning (ICML), 2022, Baltimore, Maryland [PDF][Code]


• Zheng Wang, Wei Xing, Robert M. Kirby, and Shandian Zhe, “Physics Informed Deep Kernel Learning”, The 25th International Conference on Artificial Intelligence and Statistics (AISTATS) , 2022 [PDF] [Code]


• Shibo Li, Zheng Wang, Robert M. Kirby, and Shandian Zhe, “Deep Multi-Fidelity Active Learning of High-Dimensional Outputs”, The 25th International Conference on Artificial Intelligence and Statistics (AISTATS) , 2022 [PDF] [Code]


• Zheng Wang, Shandian Zhe, Joshua Zimmerman, Candice Morrissey, Joseph E. Tonna, Vikas Sharma, and Ryan Metcalf, “Development and Validation of a Machine Learning Method to Predict Intraoperative Red Blood Cell Transfusions in Cardiothoracic Surgery”, Scientific Reports, 2022 [Paper]


• Michael Penwarden, Shandian Zhe, Akil Narayan, and Robert M. Kirby, “Multifidelity Modeling for Physics-Informed Neural Networks (PINNs)”, Journal of Computational Physics, Vol 451, 2022 [PDF]



• Year 2021

• Zhimeng Pan, Zheng Wang, Jeff Phillips, and Shandian Zhe, “Self-Adaptable Point Processes with Nonparametric Time Decays”, Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), 2021 [PDF][Appendix][Code]


• Shibo Li, Robert M. Kirby, and Shandian Zhe, “Batch Multi-Fidelity Bayesian Optimization with Deep Auto-Regressive Networks”, Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), 2021 [PDF][Code]


• Aditi Krishnapriyan, Amir Gholami, Shandian Zhe, Robert M. Kirby, and Michael W. Mahoney, “Characterizing Possible Failure Modes in Physics-Informed Neural Networks”, Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), 2021 [PDF][Code]


• Conor Tillinghast and Shandian Zhe, “Nonparametric Decomposition of Sparse Tensors”, The Thirty-eighth International Conference on Machine Learning (ICML), 2021[Paper][Appendix][Code]


• Shikai Fang, Zheng Wang, Zhimeng Pan, Ji Liu, and Shandian Zhe, “Streaming Bayesian Deep Tensor Factorization”, The Thirty-eighth International Conference on Machine Learning (ICML), 2021[Paper][Appendix][Code]


• Shikai Fang, Robert. M. Kirby, and Shandian Zhe, “Bayesian Streaming Sparse Tucker Decomposition”, The 37th Conference on Uncertainty in Artificial Intelligence (UAI), 2021 [Paper][Appendix][Code]


• Zheng Wang, Wei Xing, Robert M. Kirby, and Shandian Zhe, “Multi-Fidelity High-Order Gaussian Processes for Physical Simulation”, The 24th International Conference on Artificial Intelligence and Statistics (AISTATS), 2021 [PDF][Appendix][Code]


• Yuan Yun, Zhao Zhang, Xianfeng Terry Yang, and Shandian Zhe, “Macroscopic Traffic Flow Modeling with Physics Regularized Gaussian Process: A New Insight into Machine Learning Applications in Transportation.”, Transportation Research Part B: Methodological 146 (2021): 88-110.


• Wei Xing, Akeel A. Shah, Peng Wang, Shandian Zhe, Qian Fu, and Robert. M. Kirby, “Residual Gaussian Process: A Tractable Nonparametric Bayesian Emulator for Multi-Fidelity Simulations”, Applied Mathematical Modelling, Vol. 97, pages 36-56, 2021. [PDF]


• Wei Xing, Robert M. Kirby, and Shandian Zhe, “Deep Coregionalization for the Emulation of Simulation-Based Spatial-Temporal Fields”, Journal of Computational Physics, Vol 428, 2021[PDF][Code]



• Year 2020

• Shibo Li, Wei Xing, Robert M. Kirby, and Shandian Zhe, “Multi-Fidelity Bayesian Optimization via Deep Neural Networks”, Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS), 2020 [PDF][Appendix][Code]


• Zheng Wang, Xinqi Chu, Shandian Zhe, “Self-Modulating Nonparametric Event-Tensor Factorization”, Thirty-seventh International Conference on Machine Learning (ICML), 2020 [PDF] [Appendix]


• Zhimeng Pan, Zheng Wang, Shandian Zhe, “Streaming Nonlinear Bayesian Tensor Decomposition”, The Conference on Uncertainty in Artificial Intelligence (UAI), 2020 [PDF][Appendix][Code]


• Zhimeng Pan, Zheng Wang, Shandian Zhe, “Scalable Nonparametric Factorization for High-Order Interaction Events”, The 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), 2020, Palermo, Sicily, Italy[PDF][Code]


• Shikai Fang, Shandian Zhe, Kuang-chih Lee, Kai Zhang, and Jennifer Neville, “Online Bayesian Sparse Learning with Spike and Slab Priors”, IEEE International Conference on Data Mining (ICDM), 2020 [PDF][Code]


• Conor Tillinghast, Shikai Fang, Kai Zheng, and Shandian Zhe, “Probabilistic Neural-Kernel Tensor Decomposition”, IEEE International Conference on Data Mining (ICDM), 2020 [PDF][Code]


• Shibo Li, Wei Xing, Robert M. Kirby and Shandian Zhe, “Scalable Gaussian Process Regression Networks”, International Joint Conference on Artificial Intelligence - Pacific Rim International Conference on Artificial Intelligence (IJCAI-PRICAI) 2020 [PDF][Code]


• Wei Xing, Shireen Elhabian, Robert M Kirby, Ross T Whitaker, Shandian Zhe, “Infinite ShapeOdds: Nonparametric Bayesian Models for Shape Representations”, The 34th AAAI Conference on Artificial Intelligence (AAAI), 2020, New York, USA [PDF]


• Zheng Wang, Shandian Zhe, Joseph Tonna, Vikas Sharma and Ryan Metcalf, “Predicting Intraoperative Blood Utilization in Cardiothoracic Surgery with Machine Learning”, Advancing Transfusion and Cellular Therapies Worldwide (AABB) Annual Meeting, 2020.



• Year 2019

• Zheng Wang, Shandian Zhe, “Conditional Expectation Propagation” (oral presentation), The Conference on Uncertainty in Artificial Intelligence (UAI), 2019 [PDF][Appendix][Code]


• Shandian Zhe, Wei Xing, Robert Mike Kirby, “Scalable High-Order Gaussian Process Regression”, The 22nd International Conference on Artificial Intelligence and Statistics (AISTATS), 2019 [PDF][Code]



• Year 2018

• Shandian Zhe, Yishuai Du, “Stochastic Nonparametric Event-Tensor Decomposition” (spotlight presentation), Thirty-second Conference on Neural Information Processing Systems (NIPS), 2018. [PDF][Code]


• Ye Jinmian, Linnan Wang, Guangxi Li, Di Chen, Shandian Zhe, Xinqi Chu, and Zenglin Xu. "Learning Compact Recurrent Neural Networks with Block-Term Tensor Decomposition," The Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [PDF]


• Yishuai Du, Yimin Zheng, Kuang-chih Lee, and Shandian Zhe, “Probabilistic Streaming Tensor Decomposition” (oral presentation), The IEEE International Conference on Data Mining (ICDM), 2018 [PDF][Code]


• Lianjie Cao, Sonia Fahmy, Puneet Sharma, and Shandian Zhe, “Data-driven Resource Flexing for Network Functions Virtualization”, The Symposium on Architectures for Networking and Communications Systems, 2018 (ANCS'18) [PDF]


• Bin Liu, Zenglin Xu, Shandian Zhe, Haoli Bai, Zihan Wang, and Jennifer Neville. “Variational Random Function Model for Network Modeling”, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), Brief Paper, 2018 [PDF]


• Liang Lan, Zhuang Wang, Shandian Zhe, Wei Cheng, and Kai Zhang. “Scaling up Kernel SVM on Limited Resources: A Low-rank Linearization Approach”, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2018 [PDF]




• Year 2017 and before

• Shandian Zhe, Regularized Variational Sparse Gaussian Processes, NIPS 2017 Workshop on Advances in Approximate Bayesian Inference. [PDF]


• Bin Liu, Lirong He, Shandian Zhe, Yingming Li and Zenglin Xu, DeepCP: Nonlinear Tensor Decomposition as a Deep Generative Model, NIPS 2017 Workshop on Bayesian Deep Learning. [PDF]


• Hao Peng, Yifan Yang, Shandian Zhe, Jian Wang, Michael Gribskov and Yuan Qi, DEIsoM: A Hierarchical Bayesian Model for Identifying Differentially Expressed Isoforms Using Biological Replicates, Bioinformatics, Oxford, 2017 btx357. doi: 10.1093/bioinformatics/btx357. [PDF]


• Hao Peng, Shandian Zhe, Xiao Zhang, Yuan Qi, Asynchronous Distributed Variational Gaussian Processes for Regression, Proceedings of the 34th International Conference on Machine Learning (ICML), 2017. [PDF][Code]


• Shandian Zhe, Kuang-chih Lee, Kai Zhang, and Jennifer Neville, Online Spike-and-slab Inference with Stochastic Expectation Propagation, NIPS 2016 Workshop on Advances in Approximate Bayesian Inference. [PDF]


• Shandian Zhe, Kai Zhang, Pengyuan Wang, Kuang-chih Lee, Zenglin Xu, Yuan Qi and Zoubin Ghahramani, Distributed Flexible Nonlinear Tensor Factorization, Neural Information Processing Systems (NIPS 2016).[PDF]


• Zenglin Xu*, Shandian Zhe*, Yuan Qi and Peng Yu, Association Discovery and Diagnosis of Alzheimer's Disease with Bayesian Multiview Learning, Journal of Artificial Intelligence Research, Volume 56, pages 247-268 (* equal contribution).[PDF]


• Kai Zhang, Shandian Zhe, Chaoran Cheng, Zhi Wei, Zhengzhang Chen,Haifeng Chen, Guofei Jiang, Yuan Qi and Jieping Ye, Annealed Sparsity via Adaptive and Dynamic Shrinking, The 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2016), San Francisco, CA, August, 2016.[PDF]


• Shandian Zhe, Yuan Qi, Youngja Park, Zenglin Xu, Ian Molloy and Suresh Chari, DinTucker: Scaling up Gaussian Process Models on Large Multidimensional Arrays, AAAI-2016.[PDF]


• Syed Abbas Z. Naqvi, Shandian Zhe, Yuan Qi, Yifan Yang and Jieping Ye, Fast Laplace Approximation for Sparse Bayesian Spike and Slab Models,Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-16).[PDF]


• Shandian Zhe, Zenglin Xu, Xinqi Chu, Yuan Qi and Youngja Park , Scalable Nonparametric Multiway Data Analysis. Artificial Intelligence and Statistics (AISTATS), 2015.[PDF][Code] [Data]


• Changying Du, Shandian Zhe, Fuzhen Zhuang, Yuan Qi, Qing He, Zhongzhi Shi. Bayesian Maximum Margin PCA. The 29th AAAI Conference on Artificial Intelligence (AAAI-15), Austin, Texas, USA, January 25-29, 2015.[PDF]


• Shandian Zhe, Zenglin Xu, Yuan Qi and Peng Yu, Sparse Bayesian Multiview Learning for Simultaneous Association Discovery and Diagnosis of Alzheimer's Disease, AAAI 2015 (Outstanding Student Paper Honorable Mention).[PDF]


• Shandian Zhe, Zenglin Xu, Yuan Qi and Peng Yu, Joint Association Discovery and Diagnosis for Alzheimer's Disease by Supervised Heterogeneous Multiview Learning (oral presentation), in Proceedings of the Pacific Symposium on Biocomputing (PSB), The Big Island of Hawaii, 2014.[PDF]


• Shandian Zhe, Syed A.Z. Naqvi, Yifan Yang, and Yuan Qi, Joint Network and Node Selection for Pathway-based Genomic Data Analysis, Bioinformatics, Oxford, 2013.[PDF]


• Shandian Zhe, Tian Xia, Xueqi Cheng, Modeling Users' Information Goal Transitions and Satisfaction Judgment: Understanding the Full Search Process, In Proceeding of Web Intelligence, 2010.[PDF]


• Tian Xia, Shandian Zhe, Jinsong Su, Qun Liu: Conditional Random Fields for Machine Translation System Combination. In proceedings of the International Conference on Asian Language Processing, 2010.[PDF]

Alumini

• Zhimeng Pan (Pinterest)
• Zheng Wang (Celonis)
• Wei Xing (Lecturer, University of Sheffield)
• Yiming Zheng (Ph.D. program, Hong Kong University of Science and Technology)

Source Code

• A simple yet effective variational inference of Spike and Slab model for binary classification: [Download]
• NaNOS, joint network and node selection for pathway-based genomic data analysis: [Download]
• CrfAny, a C++ implementation of CRF package which supports parallel training, maximum likelihood and pseudolikelihood training, and all types of graphical structures, with junction tree algorithm for exact inference.
• Sparse Bayesian multiview learning for Alzheimer's disease study: [Download]
• Distributed infinite Tucker decomposition (DinTucker): [Download]
• Scalable Nonparametric Multiway Data Analysis: [Download]
• Distributed flexible nonlinear tensor factorization [Download]

Professional Serverices

• Guest editor of Frontiers in Big Data
• Panelist for National Science Foundation (NSF), 2019-2022
• Area Chair, AAAI 2023
• Program Chair, ICDM 2022 Workshop on Machine Learning on Higher-Order Structured Data (ML-HOS)
• Program Chair, KDD 2020 Workshop on Deep Learning Practice for High-Dimensional Sparse Data.
• Session Chair (KDD'19), "Machine Learning Themes I" and "Mining in Emerging Applications I"
• Programm Committee member for AAAI 2019, 2020
• Programm Committee member for KDD 2019, 2020
• Programm Committee member for ICLR 2019-2021
• Programm Committee member for AISTATS 2019-2021
• Programm Committee member for UAI 2019-2021
• Programm Committee member for SDM 2019, 2020
• PC member for International Conference for Machine Learning (ICML) 2014, 2015, 2018-2021
• PC member for Neural Information Processing Systems (NeurIPS) 2015-2022
• Reviewer for Journal of Machine Learning Research (JMLR)
• Reviewer for IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
• Reviewer for IEEE Transactions on Knowledge and Data Engineering (TKDE)
• Reviewer for Computer Methods in Applied Mechanics and Engineering (CMAME)
• Reviewer for IEEE Transactions on Multimedia (MM)
• Reviewer for SIAM Journal on Applied Dynamical Systems (SIADS)

Past Award