Pengtao Xie

Assistant Professor

Electrical and Computer Engineering

University of California San Diego

I obtained my PhD from the Machine Learning Department, School of Computer Science, Carnegie Mellon University. My research interests include sample-efficient learning (e.g., meta learning, domain adaptation, neural symbolic reasoning, etc.), ML for healthcare, deep learning for natural language processing and computer vision, deep generative models, large-scale distributed learning.

pengtaoxie2008@gmail.com

I am looking for summmer research interns and visiting students.

News

• 2019/9/10. Our work on specific and shared causal relation modeling is accepted by NeurIPS 2019.
• Invited talks at UCLA, UCSD, Columbia, NYU, Johns Hopkins, Geogia Tech, University of Wisconsin-Madison, UMass Amherst.
• 2018/12/18. Our work on ellipse detection of optic disc-and-cup boundary in fundus image is accepted by the IEEE International Symposium on Biomedical Imaging.
• 2018/11/20. Our work on clinical notes summarization was accepted by the NIPS ML for Healthcare Workshop as a spotlight oral presentation.
• 2018/11/20. We won the 1st Place (out of 400+ participating teams) in both Defenses and Targeted Attacks, 3rd Place in Untargeted Attacks, in the NIPS Adversarial Vision Challenge 2018.
• 2018/10/20. I won the 2018 Innovator Award presented by the Pittsburgh Business Times.
• 2018/10/5. I was invited as a panelist at Citi’s 4th Annual Private Company Innovation Summit.
• 2018/08/04. One paper is accepted by SOCC 2018.
• 2018/06/24. I am a program committee member of ICML 2019, CVPR 2019, ICLR 2019, AISTATS 2019, AAAI 2019.
• 2018/06/24. One paper is accepted by MLHC 2018.
• 2018/05/11. Two papers are accepted by ICML 2018.

Pre-prints

• Xuehai He, Yichen Zhang, Luntian Mou, Eric P. Xing, Pengtao Xie. PathVQA: 30000+ Questions for Medical Visual Question Answering. Preprint
• Jinyu Zhao, Yichen Zhang, Xuehai He, Pengtao Xie. COVID-CT-Dataset: A CT Scan Dataset about COVID-19. Preprint
• Yuxiao Liang, Pengtao Xie. Identifying Radiological Findings Related to COVID-19 from Medical Literature. Preprint

Publications

• B. Huang, K. Zhang, P. Xie, M. Gong, E. P. Xing. Specific and Shared Causal Relation Modeling and Mechanism-based Clustering. Advances in Neural Information Processing Systems (NeurIPS 2019).
• K. Xu, M. Lam, J. Pang, X. Gao, C. Band, P. Mathur, F. Papay, A. K. Khanna, J. B. Cywinski, K. Maheshwari, P. Xie, E. P. Xing. Multimodal Machine Learning for Automated ICD Coding. Conference on Machine Learning for Healthcare (MLHC 2019).
• Z.Wang, N.Dong, S.Rosario, M.Xu, P.Xie, and E.P.Xing. Ellipse Detection of Optic Disc-and-Cup Boundary in Fundus Image with Unsupervised Domain Adaption. The IEEE International Symposium on Biomedical Imaging (ISBI 2019).
• P.Xie, W.Wu, Y.Zhu and E.P.Xing. Orthogonality-Promoting Distance Metric Learning: Convex Relaxation and Theoretical Analysis. The 35th International Conference on Machine Learning (ICML 2018) (Long Oral Presentation).
• P.Xie, H.Zhang, Y.Zhu and E.P.Xing. Nonoverlap-Promoting Variable Selection. The 35th International Conference on Machine Learning (ICML 2018) (Short Oral Presentation).
• P.Xie, H.Shi, M.Zhang and E.P.Xing. A Neural Architecture for Automated ICD Coding. The 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018) (Oral Presentation)
• B.Jing, P.Xie and E.P.Xing. On the Automatic Generation of Medical Imaging Reports. The 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018).
• P.Xie, J.Zhu and E.P.Xing. Diversity-Promoting Bayesian Learning of Latent Variable Models. To appear in the Journal of Machine Learning Research (JMLR), 2018.
• P.Xie, J.Kim, Q.Ho, Y.Yu and E.P.Xing. Orpheus: Efficient Distributed Machine Learning via System and Algorithm Co-design. Symposium of Cloud Computing (SoCC 2018).
• D.Sachan, P.Xie and E.P.Xing. Effective Use of Bidirectional Language Modeling for Medical Named Entity Recognition. Conference on Machine Learning for Healthcare (MLHC 2018).
• X.Liu, K.Xu, P.Xie and E.P.Xing. Unsupervised Pseudo-Labeling for Extractive Summarization on Electronic Health Records. NIPS ML for Healthcare Workshop, 2018 (Spotlight Presentation).
• P.Xie, R.Salakhutdinov, L.Mou and E.P.Xing. Deep Conditional Determinantal Point Process for Large-Scale Multi-Label Classification. International Conference on Computer Vision (ICCV 2017).
• P.Xie, B.Poczos and E.P.Xing. Near-Orthogonality Regularization in Kernel Methods. Conference on Uncertainty in Artificial Intelligence (UAI 2017) (Plenary Presentation).
• H.Zhang, Z.Zheng, S.Xu, X.Liang, W.Dai, Q.Ho, Z.Hu, J.Wei, P.Xie, and E.P.Xing. Poseidon: An Efficient Communication Architecture for Distributed Deep Learning on GPU Clusters. 2017 USENIX Annual Technical Conference (ATC 2017) (Oral Presentation).
• P.Xie, A.Singh and E.P.Xing. Uncorrelation and Evenness: A New Diversity-Promoting Regularizer. The 34th International Conference on Machine Learning (ICML 2017) (Oral Presentation).
• P.Xie, Y.Deng, Y.Zhou, A.Kumar, Y.Yu, J.Zou and E.P.Xing. Learning Latent Space Models with Angular Constraints. The 34th International Conference on Machine Learning (ICML 2017) (Oral Presentation).
• H.Zhou, J.Li, P.Xie and Y.Zhang. Improving the Generalization Performance of Multi-class SVM via Angular Regularization. The 26th International Joint Conference on Artificial Intelligence (IJCAI 2017).
• P.Xie and E.P.Xing. A Constituent-Centric Neural Architecture for Reading Comprehension. The 55th Annual Meeting of the Association for Computational Linguistics (ACL 2017).
• Y.Zhou, K.Yuan, Y.Yu, X.Ni, P.Xie, E.P.Xing and S.Xu. Inference of multiple-wave population admixture by modeling decay of linkage disequilibrium with polynomial functions. Heredity, 2017.
• E.P.Xing, Q.Ho, P.Xie and W.Dai. Strategies and Principles of Distributed Machine Learning on Big Data. Engineering, Transactions of Chinese Academy of Engineering (Engineering 2016).
• P.Xie, J.Kim, Y.Zhou, Q.Ho, A.Kumar, Y.Yu and E.P.Xing. Lighter-Communication Distributed Machine Learning via Sufficient Factor Broadcasting. The 32nd Conference on Uncertainty in Artificial Intelligence (UAI 2016).
• P.Xie, J.Zhu and E.P.Xing. Diversity-Promoting Bayesian Learning of Latent Variable Models. The 33rd International Conference on Machine Learning (ICML 2016) (Oral Presentation).
• E.P.Xing, Q.Ho, W.Dai, J.Kim, J.Wei, S.Lee, X.Zheng, P.Xie, A.Kumar and Y.Yu. Petuum: A New Platform for Distributed Machine Learning on Big Data. IEEE Transactions on Big Data (IEEE BigData 2015).
• P.Xie. Learning Compact and Effective Distance Metrics with Diversity Regularization. European Conference on Machine Learning (ECML 2015) (Oral Presentation).
• P.Xie, Y.Deng and E.P.Xing. Diversifying Restricted Boltzmann Machine for Document Modeling. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2015) (Oral Presentation).
• E.P.Xing, Q.Ho, W.Dai, J.Kim, J.Wei, S.Lee, X.Zheng, P.Xie, A.Kumar and Y.Yu. Petuum: A New Platform for Distributed Machine Learning on Big Data. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2015) (Oral Presentation).
• P.Xie, D.Yang and E.P.Xing. Incorporating Word Correlation Knowledge into Topic Modeling. The 2015 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2015).
• P.Xie, Y.Pei, Y.Xie and E.P.Xing. Mining User Interests from Personal Photos. The 29th AAAI Conference on Artificial Intelligence (AAAI 2015).
• P.Xie and E.P.Xing. Integrating Image Clustering and Codebook Learning. The 29th AAAI Conference on Artificial Intelligence (AAAI 2015) (Oral Presentation).
• P.Xie and E.P.Xing. Multi-Modal Distance Metric Learning. The 23rd International Joint Conference on Artificial Intelligence (IJCAI 2013) (Oral Presentation).
• P.Xie and E.P.Xing. Integrating Document Clustering and Topic Modeling. Proceedings of the 29th International Conference on Uncertainty in Artificial Intelligence (UAI 2013).

Teaching

Guest lecturer at Carnegie Mellon University for:

• 10-708 Probabilistic Graphical Models (Instructor: Eric Xing), Spring 2017.

Teaching assistants at Carnegie Mellon University for:

• 10-708 Probabilistic Graphical Models (Instructor: Eric Xing), Spring 2015.
• 10-701 Machine Learning (Instructors: Barnabas Poczos and Aarti Singh), Spring 2014.
• 10-601 Machine Learning (Instructors: William Cohen and Eric Xing), Fall 2013.

Professional Activities

Program Committee Members or Reviewers for:

• Conferences: ICML (2014, 2018-2019), NIPS (2016, 2018), AISTATS (2017-2019), UAI (2018), ICLR (2019), AAAI (2019), CVPR (2016-2019), ICCV (2015, 2017), ECCV (2016, 2018), ACL (2015-2018), EMNLP (2015), KDD (2015), ECML (2016-2017), ACCV (2016), BMVC (2017)
• Journals: TPAMI (2018), TKDE (2015-2018), TMM (2016-2017), PLOS ONE (2017-2018), TNNLS (2015-2016, 2018), JASA (2015)

Selected Awards and Honors

• Innovator Award, 2018 (presented by the Pittsburgh Business Times).
• 1st Place (out of 400+ participating teams) in both Defenses and Targeted Attacks, 3rd Place in Untargeted Attacks, in NIPS Adversarial Vision Challenge, 2018.
• Siebel Scholarship, 2014 (85 graduate students from around the world).
• National Scholarship of China, 2009.
• National First Prize in China Undergraduate Mathematical Contest of Modeling, 2008.
• Goldman Sachs Global Leader Scholarship, 2008 (150 undergraduate students from around the world).

Recent Invited Talks

• Machine Learning for Medical Decision Support
  • Nov 2019, Department of Biomedical Informatics, University of Pittsburgh
  • Oct 2019, AI NEXTCon Developer Conference
  • Apr 2019, New York University
  • Apr 2019, University of Massachusetts Amherst
  • Mar 2019, University of California San Diego
  • Feb 2019, Columbia University
  • Feb 2019, Johns Hopkins University
  • Feb 2019, University of California Los Angeles
  • Jan 2019, University of Wisconsin-Madison