Biography

I am Si Si, a research scientist at Google Research. My research focus is developing scalable machine learning models. I was a Ph.D. student at UT Austin working with Prof. Inderjit Dhillon. I received my master degree from the University of Hong Kong under supervision of Prof. Dacheng Tao and Prof. Kwok-Ping Chan. I am the recipient of the MCD fellowship in 2010-2013, and the best paper award in ICDM 2012. I am serving as reviewers for many conferences and journals including ICML, NIPS, KDD and JMLR, etc.

• How Does Noise Help Robustness? Stabilizing Neural ODE Networks with Stochastic Noise
  Xuanqing Liu, Tesi Xiao, Si Si, Qin Cao, Sanjiv Kumar, Cho-Jui Hsieh
  In CVPR 2020(Oral)
• A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning
  Xuanqing Liu, Si Si, Jerry Zhu, Yang Li, Cho-Jui Hsieh
  In NeurIPS 2019
• Robustness Verification of Tree-based Models
  Hongge Chen, Huan Zhang, Si Si, Yang Li, Duane S. Boning, Cho-Jui Hsieh
  In NeurIPS 2019
• Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
  Wei-Lin Chiang, Xuanqing Liu, Si Si, Yang Li, Samy Bengio, Cho-Jui Hsieh
  In KDD 2019 (Oral)
• Area Attention
  Yang Li, Lukasz Kaiser, Samy Bengio, Si Si
  In ICML 2019
• GaterNet: Dynamic Filter Selection in Convolutional Neural Network via a Dedicated Global Gating Network
  Zhourong Chen, Yang Li, Samy Bengio, Si Si
  In CVPR 2019
• Learning to Screen for Fast Softmax Inference on Large Vocabulary Neural Network
  Patrick H. Chen, Si Si, Sanjiv Kumar, Yang Li, Cho-Jui Hsieh
  In ICLR 2019
• GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking
  Patrick H. Chen, Si Si, Yang Li, Ciprian Chelba, Cho-Jui Hsieh
  In NIPS 2018
• GPU-acceleration for Large-scale Tree Boosting
  Huan Zhang, Si Si, Cho-Jui Hsieh
  In SysML 2018
• Nonlinear Online Learning with Adaptive Nystrom Approximation
  Si Si, Sanjiv Kumar, Yang Li
  In arXiv:1802.07887
• Gradient Boosted Decision Trees for High Dimensional Sparse Output
  Si Si, Huan Zhang, Sathiya Keerthi, Dhruv Mahajan, Inderjit Dhillon, Cho-Jui Hsieh
  In ICML 2017
• Communication-Efficient Distributed Block Minimization for Nonlinear Kernel Machines
  Cho-Jui Hsieh, Si Si, Inderjit Dhillon
  In KDD 2017 (Oral)
• Memory efficient kernel approximation
  Si Si, Cho-Jui Hsieh, Inderjit Dhillon
  JMLR 2017
• Goal-directed inductive matrix completion
  Si Si, Cho-Jui Hsieh, Inderjit Dhillon
  In KDD 2016 (Oral)
• Computationally Efficient Nystrom Approximation using Fast Transforms
  Si Si, Cho-Jui Hsieh, Inderjit Dhillon
  In ICML 2016
• Kernel Ridge Regression via Partitioning
  Rashish Tandon, Si Si, Pradeep Ravikumar, Inderjit Dhillon
  In arXiv:1608.01976
• Fast prediction for large-scale kernel machines
  Cho-Jui Hsieh, Si Si, Inderjit Dhillon
  In NIPS 2014
• Multi-scale spectral decomposition of massive graphs
  Si Si, Donghyuk Shin, Inderjit S Dhillon, Beresford N Parlett
  In NIPS 2014
• Parallel matrix factorization for recommender systems
  Hsiang-Fu Yu, Cho-Jui Hsieh, Si Si, Inderjit S Dhillon
  Knowledge and Information Systems 2014
• A Divide-and-Conquer Solver for Kernel Support Vector Machines
  Cho-Jui Hsieh, Si Si, Inderjit Dhillon
  In ICML 2014
• Memory Efficient Kernel Approximation
  Si Si, Cho-Jui Hsieh, Inderjit Dhillon
  In ICML 2014
• Beyond modeling private actions: predicting social shares
  Si Si, Atish Das Sarma, Elizabeth F Churchill, Neel Sundaresan
  In WWW 2014 (short paper)
• The expression gap: do you like what you share?
  Atish Das Sarma, Si Si, Elizabeth F Churchill, Neel Sundaresan
  In WWW 2014 (short paper)
• Multi-scale link prediction
  Donghyuk Shin, Si Si, Inderjit S Dhillon
  In CIKM 2012
• Scalable coordinate descent approaches to parallel matrix factorization for recommender systems
  Hsiang-Fu Yu, Cho-Jui Hsieh, Si Si, I Dhillon
  In ICDM 2012 (best paper)
• Distribution calibration in Riemannian symmetric space
  Si Si, Wei Liu, Dacheng Tao, Kwok-Ping Chan
  IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 2011
• Evolutionary cross-domain discriminative Hessian eigenmaps
  Si Si, Dacheng Tao, Kwok-Ping Chan
  IEEE Transactions on Image Processing 2010
• Bregman divergence-based regularization for transfer subspace learning
  Si Si, Dacheng Tao, Bo Geng
  IEEE Transactions on Knowledge and Data Engineering 2010
• Discriminative Hessian Eigenmaps for face recognition
  Si Si, Dacheng Tao, Kwok-Ping Chan
  In ICASSP 2010

  Details BibTeX PDF Code

• contact (at) sisihku@gmail (dot) com