Jonathan Shihao Ji's Photo         

Jonathan Shihao Ji

Associate Professor
Department of Computer Science
Georgia State University
  
Office: One Park Place, Room 637
Email: sji@gsu.edu

[Google Scholar, Publications, Teaching, Software, Demo, Resource, Sponsor, Internal]


I am looking for self-motivated students with strong mathematical and programming skills to work with me on machine learning, deep learning and HPC projects. If you are interested, please email me your CV and indicate your goals.

I am an associate professor in the Department of Computer Science at Georgia State University. I received my Ph.D. in Electrical and Computer Engineering from Duke University, where I worked with Dr. Lawrence Carin. I was then a research associate at Duke for about 1.5 year. After that, I was in industry research labs for about 10 years.


Research Interests

My principal research interests lie in the area of machine learning and deep learning with an emphasis on high-performance computing. I’m interested in developing efficient algorithms that can learn from a variety of data sources (e.g., image, audio, and text) on a large scale and automate decision-making processes in dynamic environments.

Education

  • Ph.D., Electrical and Computer Engineering, Duke University, USA, 2006
  • M.S., Electrical Engineering, Xidian University, China, 2001
  • B.S., Electrical Engineering, Xidian University, China, 1998

Publications

Submitted Manuscripts

Refereed Publications

  • Xiulong Yang, Shihao Ji, "Learning with Multiplicative Perturbations," International Conference on Pattern Recognition (ICPR), Milan, Italy, Jan. 2021. [arXiv | code]

  • Xiang Li, Shihao Ji, "Defense-VAE: A Fast and Accurate Defense against Adversarial Attacks," Machine Learning for Cybersecurity (ECML workshop on MLCS), Würzburg, Germany, Sept. 2019. [arXiv | code]

  • Yang Li, Shihao Ji, "L0-ARM: Network Sparsification via Stochastic Binary Optimization," The European Conference on Machine Learning (ECML, acceptance rate 18%), Würzburg, Germany, Sept. 2019. [arXiv | demo]

  • J. Chen, Xiang Li, V. Calhoun, J. Turner, T.G.M. Erp, L. Wang, O. Andreassen, I. Agartz, L. Westlye, J. Liu, and Shihao Ji, "Sparse Deep Neural Networks on Imaging Genetics for Schizophrenia Discrimination," The Organization for Human Brain Mapping (OHBM), Montreal, June 2020.

  • A. Ahmadzadeh, S. Mahajan, D. Kempton, R. Angryk, and Shihao Ji, "Toward Filament Segmentation Using Deep Neural Networks," 2019 IEEE International Conference on Big Data, Los Angeles, USA, Dec. 2019. [paper]

  • Shihao Ji, Nadathur Satish, Sheng Li, and Pradeep Dubey, "Parallelizing Word2Vec in Shared and Distributed Memory," IEEE Transactions on Parallel and Distributed Systems (IEEE TPDS), Volume 30, Issue 9, Pages 2090-2100, Sept. 1 2019. [paper | code]

  • J. Zhang, P. Raman, Shihao Ji, H. Yu, S.V.N. Vishwanathan, I. S. Dhillon, "Extreme Stochastic Variational Inference: Distributed Inference for Large Scale Mixture Models," The 22nd International Conference on Artificial Intelligence and Statistics (AIStats), Naha, Okinawa, Japan, Apr., 2019. [pdf file]

  • Krishanu Sarker, Mohamed Masoud, Saeid Belkasim, and Shihao Ji, "Towards Robust Human Activity Recognition from RGB Video Stream with Limited Labeled Data," IEEE International Conference on Machine Learning and Applications (ICMLA, acceptance rate 31%), Dec. 2018. [arXiv | SCD'18 Best Poster Award]

  • Shihao Ji, Nadathur Satish, Sheng Li, and Pradeep Dubey, "Parallelizing Word2Vec in Multi-Core and Many-Core Architectures," NIPS workshop on Efficient Methods for Deep Neural Networks, Barcelona, Spain, Dec., 2016. [arXiv | code]

  • Shihao Ji, Hyokun Yun, Pinar Yanardag, Shin Matsushima, and S. V. N. Vishwanathan, "WordRank: Learning Word Embeddings via Robust Ranking," Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov., 2016. [pdf file | code]

  • Shihao Ji, S. V. N. Vishwanathan, Nadathur Satish, Michael J. Anderson, and Pradeep Dubey, "Blackout: Speeding up recurrent neural network language models with very large vocabularies," International Conference on Learning Representations (ICLR Oral, acceptance rate 6%), May, 2016. [pdf file | code]

  • O. Chapelle, Shihao Ji, C. Liao, E. Velipasaoglu, L. Lai, and S.-L. Wu, "Intent-based diversification of web search results: Metrics and algorithms," Information Retrieval Journal, May, 2011. [pdf file]

  • Shihao Ji, K. Zhou, C. Liao, Z. Zheng, G.-R. Xue, O. Chapelle, G. Sun, and H. Zha, "Global ranking by exploiting user clicks," In SIGIR '09: Proceedings of the 32nd Annual International ACM SIGIR conference on Research and development in information retrieval, July, 2009. [pdf file]

  • T. Moon, Shihao Ji, G. Dupret, C. Liao, and Z. Zheng, "User behavior driven ranking without editorial judgment," To appear in 19th ACM International Conference on Information and Knowledge Management (CIKM), Oct. 2010. [pdf file]

  • F. Li, X. Li, Shihao Ji, and Z. Zheng, "Comparing both relevance and robustness in selection of web ranking functions," In SIGIR '09: Proceedings of the 32nd Annual International ACM SIGIR Conference, July 2009.

  • Shihao Ji, D. Dunson, and L. Carin, "Multi-task compressive sensing," IEEE Trans. Signal Processing, vol. 57, no. 1, pp. 92-106, Jan. 2009. [pdf file | code]

  • Shihao Ji, Y. Xue, and L. Carin, "Bayesian compressive sensing," IEEE Trans. Signal Processing, vol. 56, no. 6, pp. 2346-2356, June 2008. [pdf file | code]

  • T. Wang, T. Furey, J. Connelly, Shihao Ji, S. Nelson, S. Heber, S. Gregory, and E. Hauser, "A general integrative genomic feature transcription factor binding site prediction method applied to analysis of USF1 binding in cardiovascular disease," Human Genomics, vol. 3, no. 3, pp. 221-235, Apr. 2009.

  • Shihao Ji, L. T. Watson, and L. Carin, "Semi-supervised learning of hidden Markov models via a homotopy method," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 31, no. 2, pp. 275-287, Feb. 2009. [pdf file | data | demo]

  • J. Fang, Shihao Ji, Y. Xue, and L.Carin, "Multi-task classification by learning the task relevance," IEEE Signal Processing Letters, vol. 15, pp. 593-596, 2008.

  • Shihao Ji, R. Parr, H. Li, X. Liao, and L. Carin, "Point-based policy iteration," In the 22nd National Conference on Artificial Intelligence (AAAI), Vancouver, Canada, July 22-26, 2007. [pdf file]

  • Shihao Ji and L. Carin, "Bayesian compressive sensing and projection optimization," In the 24th International Conference on Machine Learning (ICML), Corvallis, Oregon, June 20-24, 2007. [pdf file]

  • Shihao Ji and L. Carin, "Cost-sensitive feature acquisition and classification," Pattern Recognition, vol. 40, no. 5, pp. 1474-1485, May 2007. [pdf file]

  • Shihao Ji, R. Parr, and L. Carin, "Non-myopic multi-aspect sensing with partially observable Markov decision processes," IEEE Trans. Signal Processing, vol. 55, no. 6, pp. 2720-2730 June 2007. [pdf file | demo1 ,demo2 ,demo3]

  • L. He, Shihao Ji, W.R. Scott, and L. Carin, "Adaptive multi-modality sensing of landmines," IEEE Trans. Geoscience and Remote Sensing, vol. 45, no. 6, pp.1756-1774, June 2007. [pdf file]

  • Shihao Ji, B. Krishnapuram, and L. Carin, "Variational Bayes for continuous hidden Markov models and its application to active learning," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, no. 4, pp. 522-532, Apr. 2006. [pdf file | data]

  • N. Dasgupta, Shihao Ji, and L. Carin, "Homotopy-based semi-supervised hidden Markov tree for texture analysis," in Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2006. [pdf file]

  • L. He, Shihao Ji, and L. Carin, "Application of partially observable Markov decision processes to robot navigation in a minefield," in ICAPS Workshop on POMDP, Classification and Regression: Relationships and Joint Utilization, June 2006. [pdf file]

  • Shihao Ji, X. Liao, and L. Carin, "Adaptive multi-aspect target classification and detection with hidden Markov models," IEEE Sensors Journal, vol. 5, no. 5, pp. 1035-1042, Oct. 2005. [pdf file]

  • Shihao Ji, X. Liao, and L. Carin, "Adaptive multi-aspect target classification and detection with hidden Markov models," in Proc. of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 2, pp. 125-128, May 2004. [pdf file]

Teaching

Software

  • xVAT: Learning with Multiplicative Perturbations
  • L0-arm: Network Sparsification via Stochastic Binary Optimization
  • Defense-VAE: A Fast and Accurate Defense against Adversarial Attacks
  • Parallel Word2Vec: Parallelizing Word2Vec in Shared and Distributed Memory
  • BlackOut: Speeding up RNNLMs with very large vocabularies
  • WordRank: Learning Word Embeddings via Robust Ranking
  • BCS: a Bayesian framework for solving the inverse problem of compressive sensing

Demo

1. Visualization of part of the neurons in (a) conv-layer and (b) fully-connected layer of the LeNet-5-Caffe sparsified by L0-ARM.

2. Visualization of neural plasticity networks on sythetic "moons" dataset for (a) network sparsification and (b) network expansion.

moons sparsification
moons expansion