Xuchao Zhang (张绪超) Principal Researcher @ Microsoft System Innovation and Privacy Preserving Machine Learning Innovation Address: 14820 NE 36th St (Building 99), Redmond, WA 98052 Email: xuchaozhang [AT] microsoft [DOT] com Google Scholar: https://scholar.google.com/citations?user=bWvMtN8AAAAJ&hl Microsoft Homepage: https://www.microsoft.com/en-us/research/people/xuchaozhang GitHub: https://github.com/xuczhang

About Me

I am a principal researcher in System Innovation and Privacy Preserving Machine Learning Innovation groups at Microsoft. Before joining Microsoft, I am a researcher in NEC Laboratories America. I received the Ph.D. in Computer Science Department at Virginia Tech, in 2019. My advisor is Prof. Chang-Tien Lu. Before starting my Ph.D. degree, I had some industry working experience in Microsoft, SAP, etc. I received my B.E. degree in Software Engineering from Shanghai Jiao Tong University in 2009. In the broad area of data mining, machine learning, and natural language processing, my research interests include: 1) Robust model learning in massive data sets under adversarial data corruption. 2) Text mining tasks such as uncertainty models in document classification, dynamic topic modeling, and user comments mining. 3) Interdisciplinary applications in areas such as multi-factor personality prediction, spatiotemporal event forecasting in hyper-local price data.

News

• [03/2024]: One paper was accepted by NAACL 2024
• [05/2023]: One paper was accepted by KDD 2023.
• [05/2023]: One paper was accepted by ACL 2023.
• [04/2023]: One paper was accepted by USENIX ATC 2023.
• [02/2023]: One paper was accepted by ICASSP 2023.
• [10/2022]: One paper was accepted by ICSE 2023.
• [01/2022]: One paper was accepted by ICASSP 2022.
• [12/2021]: One paper was accepted by AAAI 2022.
• [08/2021]: One paper was accepted by EMNLP 2021.
• [03/2021]: One paper was accepted by NAACL 2021.
• [11/2020]: Two papers were accepted by AAAI 2021.
• [11/2020]: Will serve as PC of SIGIR 2021.

Publications

• [FSE'24] Devjeet Roy, Xuchao Zhang, Rashi Bhave, Chetan Bansal, Pedro Las-Casas, Rodrigo Fonseca, Saravan Rajmohan "Exploring LLM-based Agents for Root Cause Analysis", The ACM International Conference on the Foundations of Software Engineering (FSE 2024 Industry Track), Porto de Galinhas, Brazil, July 2024.
• [FSE'24] Xuchao Zhang, Supriyo Ghosh, Chetan Bansal, Rujia Wang, Minghua Ma, Yu Kang, Saravan Rajmohan "Automated Root Causing of Cloud Incidents using In-Context Learning with GPT-4", The ACM International Conference on the Foundations of Software Engineering (FSE 2024 Industry Track), Porto de Galinhas, Brazil, July 2024.
• [FSE'24] Dylan Zhang, Xuchao Zhang, Chetan Bansal, Pedro Las-Casas, Rodrigo Fonseca, Saravan Rajmohan "LM-PACE: Confidence Estimation by Large Language Models for Effective Root Causing of Cloud Incidents", The ACM International Conference on the Foundations of Software Engineering (FSE 2024 Industry Track), Porto de Galinhas, Brazil, July 2024.
• [FSE'24] Drishti Goel, Fiza Husain, Aditya Singh, Supriyo Ghosh, Anjaly Parayil, Chetan Bansal, Xuchao Zhang, Saravan Rajmohan "X-lifecycle Learning for Cloud Incident Management using LLMs", The ACM International Conference on the Foundations of Software Engineering (FSE 2024 Industry Track), Porto de Galinhas, Brazil, July 2024.
• [NAACL'24] Chen Ling, Xujiang Zhao, Xuchao Zhang, Wei Cheng, Yanchi Liu, Yiyou Sun, Mika Oishi, Takao Osaki, Katsushi Matsuda, Jie Ji, Guangji Bai, Liang Zhao, Haifeng Chen, "Uncertainty Quantification for In-Context Learning of Large Language Models", Annual Conference of the North American Chapter of the Association for Computational Linguistics (Findings of NAACL'24), Mexico City, Mexico, June 2024.
• [ICLR'24] Chen Ling, Xujiang Zhao, Xuchao Zhang, Yanchi Liu, Wei Cheng, Haoyu Wang, Zhengzhang Chen, Mika Oishi, Takao Osaki, Katsushi Matsuda, Liang Zhao, Haifeng Chen "Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty", The Twelfth International Conference on Learning Representations (ICLR 2024 Workshop on Reliable and Responsible Foundation Models), Vienna, Austria, May 2024.
• [EuroSys'24] Yinfang Chen, Huaibing Xie, Minghua Ma, Yu Kang, Xin Gao, Liu Shi, Yunjie Cao, Xuedong Gao, Hao Fan, Ming Wen, Jun Zeng, Supriyo Ghosh, Xuchao Zhang, Chaoyun Zhang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang and Tianyin Xu "Automatic Root Cause Analysis via Large Language Models for Cloud Incidents", EuroSys '24, April 22–25, 2024, Athens, Greece.
• [EMNLP'23] Chen Ling, Xuchao Zhang, Xujiang Zhao, Yanchi Liu, Wei Cheng, Takao Osaki, Katsushi Matsuda, Haifeng Chen, Liang Zhao "Open-ended Commonsense Reasoning with Unrestricted Answer Candidates", 2023 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP), Singapore, Dec. 6-10, 2023
• [KDD'23] Jianfeng He, Xuchao Zhang, Shuo Lei, Abdulaziz Alhamadani, Fanglan Chen, Bei Xiao and Chang-Tien Lu "CLUR: Uncertainty Estimation for Few-Shot Text Classification with Contrastive Learning", Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Research Track, Long Beach, USA, August 2023.
• [ACL'23] Shuo Lei, Xuchao Zhang, Jianfeng He, Fanglan Chen and ChangTien Lu "TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformation", The 61st Annual Meeting of the Association for Computational Linguistics (ACL), Long Paper, Toronto, Canada, July 9-14, 2023.
• [USENIX ATC'23] Pradeep Dogga, Chetan Bansal, Richard Costleigh, Gopinath Jayagopal, Suman Nath, Xuchao Zhang "AutoARTS: Insights and Tools for Rootcausing Incidents in Microsoft Azure", The 2023 USENIX Annual Technical Conference (USENIX ATC '23), BOSTON, USA, July 10-12, 2023.
• [ICASSP'23] Xujiang Zhao, Xuchao Zhang, Chen Zhao, Jin-Hee Cho, Lance Kaplan, Dong Hyun Jeong, Audun Jøsang, Haifeng Chen, Feng Chen "Multi-Label Temporal Evidential Neural Networks for Early Event Detection", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), to appear, Rhodes Island, Greece, June 04- June 10, 2023.
• [ICSE'23] Toufique Ahmed, Supriyo GHOSH, Chetan Bansal, Tom Zimmermann, Xuchao Zhang, Saravan Rajmohan "Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models", Fourty-Fifth International Conference on Software Engineering (ICSE), to appear, Melbourne, Australia, May. 14-20, 2023. [paper]
• [AAAI'23] Dongsheng Luo, Wei Cheng, Yingheng Wang, Dongkuan Xu, Jiangchao Ni, Wenchao Yu, Xuchao Zhang, Yanchi Liu, Yuncong Chen, Haifeng Chen, Xiang Zhang "Time Series Contrastive Learning with Information-Aware Augmentations", The 37th AAAI Conference on Artificial Intelligence (AAAI), to appear, Washington DC, USA, Feb. 7-14, 2023.
• [ICDM'22] Chen Ling, Tanmoy Chowdhury, Junji Jiang, Junxiang Wang, Xuchao Zhang, Haifeng Chen, Liang Zhao "DeepGAR: Deep Graph Learning for Analogical Reasoning", Proceedings of the IEEE International Conference on Data Mining (ICDM), Orlando, FL, Nov. 28- Dec. 1, 2022.
• [ECCV'22] Shuo Lei, Xuchao Zhang, Jianfeng He, Fanglan Chen, Bowen Du and Chang-Tien Lu, "Cross-Domain Few-Shot Semantic Segmentation", European Conference on Computer Vision 2022 (ECCV), Tel-Aviv, Israel, Oct. 23-27, 2022.
• [Neurocomputing'22] Jianfeng He, Xuchao Zhang, Shuo Lei, Shuhui Wang, Chang-Tien Lu and Bei Xiao, "Semantic Inpainting on Segmentation Map via Multi-Expansion Loss", Neurocomputing, Elsevier, 2022
• [KDD'22] Shengming Zhang, Yanchi Liu, Xuchao Zhang, Wei Cheng, Haifeng Chen and Hui Xiong, "CAT: Beyond Efficient Transformer for Content-Aware Anomaly Detection in Event Sequences", Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Applied Science Track, Washington D.C, USA, August 2022.
• [LREC'22] Dheeraj Rajagopal, Xuchao Zhang, Michael Gamon, Sujay Kumar Jauhar, Diyi Yang and Eduard Hovy, "One Document, Many Revisions: A Dataset for Classification and Description of Edit Intents", Proceedings of the 14th Conference on Language Resources and Evaluation (LREC), Marseille, France, June 2022.
• [NAACL'22] Shuo Lei, Xuchao Zhang, Jianfeng He, Fanglan Chen and Chang-Tien Lu, "Uncertainty-Aware Cross-Lingual Transfer with Pseudo Partial Labels", Annual Conference of the North American Chapter of the Association for Computational Linguistics (Findings of NAACL'22), Seattle, Washington, USA, July 2022.
• [ICASSP'22] Xujiang Zhao, Xuchao Zhang, Wei Cheng, Wenchao Yu, Yuncong Chen, Haifeng Chen, Feng Chen "SEED: Sound Event Early Detection via Evidential Uncertainty", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), to appear, Singapore, May 22- May 27, 2022.
• [AAAI'22] Liyan Xu, Xuchao Zhang, Bo Zong, Yanchi Liu, Wei Cheng, Jingchao Ni, Haifeng Chen, Zhao Liang, Jinho D. Choi "Zero-Shot Cross-Lingual Machine Reading Comprehension via Inter-Sentence Dependency Graph", Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), to appear, Vancouver, BC, Banada, Feb. 22- March 1. [acceptance rate: 15%] [pdf]
• [ICDM'21] Lichen Wang, Bo Zong, Yunyu Liu, Can Qin, wei Cheng, Wenchao Yu, Xuchao Zhang, Haifeng Chen, and Yun Fu, "Aspect-based Sentiment Classification via Reinforcement Learning", Proceedings of the IEEE International Conference on Data Mining (ICDM), Auckland, New Zealand, Dec. 7-10, 2021.
• [EMNLP'21] Liyan Xu, Xuchao Zhang, Xujiang Zhao, Haifeng Chen, Feng Chen and Jinho D. Choi "Boosting Cross-Lingual Transfer via Self-Learning with Uncertainty Estimation", 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Short Paper, Nov. 7-11, 2021. [pdf]
• [CIKM'21] Jingchao Ni, Zhengzhang Chen, Wei Cheng, Bo Zong, Dongjin Song, Yanchi Liu, Xuchao Zhang and Haifeng Chen "Interpreting Convolutional Sequence Model by Learning Local Prototypes with Adaptation Regularization", The 30th ACM International Conference on Information and Knowledge Management (CIKM), to appear, Online, Nov 2021.
• [TKDD'21] Tian Shi, Xuchao Zhang, Ping Wang, Chandan Reddy, "Corpus-level and Concept-based Explanations for Interpretable Document Classification", ACM Transactions on Knowledge Discovery from Data (TKDD), 2021.
• [TKDD'21] Shuo Lei, Xuchao Zhang, Liang Zhao, Arnold P. Boedihardjo, Chang-Tien Lu, "Online and Distributed Robust Regressions with Extremely Noisy Labels", ACM Transactions on Knowledge Discovery from Data (TKDD), 2021.
• [NAACL'21] Xuchao Zhang, Bo Zong, Wei Cheng, Jingchao Ni, Yanchi Liu and Haifeng Chen. "Unsupervised Concept Representation Learning for Length-Varying Text Similarity", In Proceedings of The 2021 Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT'21), Mexico City, Mexico, June 6–11, 2021. [pdf]
• [ICME'21] Shuo Lei, Xuchao Zhang, Jianfeng He, Fanglan Chen and Chang-Tien Lu. "Few-Shot Semantic Segmenation via Prototype Augmentation with Image-level Annotations", IEEE International Conference on Multimedia and Expo (ICME), Virtual, Mexico, July 5–9, 2021.
• [AAAI'21] Yinjun Wu, Jingchao Ni, Wei Cheng, Bo Zong, Dongjin Song, Zhengzhang Chen, Yanchi Liu, Xuchao Zhang, Haifeng Chen and Susan Davidson "Dynamic Gaussian Mixture based Deep Generative Model For Robust Forecasting on Sparse Multivariate Time Series", Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), to appear, Feb. 2-9, 2021. [acceptance rate: 21%]
• [AAAI'21] Dongkuan Xu, Wei Cheng, Xin Dong, Bo Zong, Wenchao Yu, Jingchao Ni, Dongjin Song, Xuchao Zhang, Haifeng Chen and Xiang Zhang "Multi-Task Recurrent Modular Networks", Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), to appear, Feb. 2-9, 2021. [acceptance rate: 21%]
• [EMNLP'20] Jianfeng He, Xuchao Zhang, Shuo Lei, Zhiqian Chen, Fanglan Chen, Abdulaziz Alhamadani, Bei Xiao and ChangTien Lu "Towards More Accurate Uncertainty Estimation In Text Classification", 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Long Paper, Nov. 16-20, 2020. [acceptance rate: 22.4%]
• [ICDM'20] Xuchao Zhang, Yingwen Shao, "Robust Multi-Target Regression for Correlated Data Corruption", Proceedings of the IEEE International Conference on Data Mining (ICDM), Sorrento, Italy, Nov. 17-20, 2020. [acceptance rate: 19.7%]
• [AAAI'20] Xuchao Zhang, Xian Wu, Fanglan Chen, Liang Zhao, Chang-Tien Lu, "Self-Paced Robust Learning for Leveraging Clean Labels in Noisy Data", Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), to appear, New York, USA, Feb 2020. [acceptance rate: 20.6%] [pdf][supp]
• [AAAI'20] Xuchao Zhang*, Yifeng Gao*, Jessica Lin, Chang-Tien Lu, "TapNet: Multivariate Time Series Classification with Attentional Prototype Network", Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), to appear, New York, Feb 2020. *These two authors contributed equally. [acceptance rate: 20.6%] [pdf][full][code] *full version contains the experiment results with all 30 UEA datasets.
• [WSDM'20] Xuchao Zhang, Wei Cheng, Bo Zong, Yuncong Chen, Jianwu Xu, Ding Li, Haifeng Chen, "Temporal Context-Aware Representation Learning for Question Routing", The 13th ACM International WSDM Conference (WSDM), to appear, Houston, Taxas, Feb 2020. [acceptance rate: 15%] [pdf]
• [EMNLP'19] Xuchao Zhang, Dheeraj Rajagopal, Michael Gamon, Sujay Kumar Jauhar and ChangTien Lu, "Modeling the Relationship between User Comments and Edits in Document Revision", 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP), Long Paper, to appear, Hongkong, China, Nov 2019. [acceptance rate: 23.8%] [pdf][code]
• [CIKM'19] Xian Wu, Baoxu Shi, Xuchao Zhang, Chao Huang and Nitesh Chawla, "Similarity-aware Network Embedding with Self-paced Learning", The 28th ACM International Conference on Information and Knowledge Management (CIKM), to appear, Beijing, China, Nov 2019. [pdf]
• [CIKM'19] Chao Huang, Xian Wu, Xuchao Zhang, Suwen Lin and Nitesh Chawla, "Deep Prototypical Networks for Imbalanced Time Series Classification under Data Scarcity", The 28th ACM International Conference on Information and Knowledge Management (CIKM), to appear, Beijing, China, Nov 2019. [pdf]
• [ASONAM'19] Taoran Ji, Xuchao Zhang, Nathan Self, Kaiqun Fu, Chang-Tien Lu and Naren Ramakrishnan, "Feature Driven Learning Framework for Cybersecurity Event Detection", IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), Short Paper, to appear, Vancouver, Canada, Aug 2019. [pdf]
• [KDD'19] Chao Huang, Xian Wu, Xuchao Zhang, Chuxu Zhang, Jiashu Zhao, Dawei Yin and Nitesh Chawla, "Online Purchase Prediction via Multi-Scale Modeling of Behavior Dynamics", Proceedings of the 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Applied Science Track, to appear, Alaska, USA, Aug 2019. [pdf]
• [NAACL'19] Xuchao Zhang, Fanglan Chen, Chang-Tien Lu, Naren Ramakrishnan, "Mitigating Uncertainty in Document Classification", Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), pp. 3126-3136, Minneapolis, MN, USA, June 2019. [acceptance rate: 22.6%] [pdf][code]
• [TKDD'19] Xuchao Zhang, Shuo Lei, Liang Zhao, Arnold Boedihardjo, Chang-Tien Lu, "Robust Regression via Heuristic Corruption Thresholding and Its Adaptive Estimation Variation", ACM Transactions on Knowledge Discovery from Data (TKDD), 2019. [pdf]
• [BigData'18] Lei Zhang, Liang Zhao, Xuchao Zhang, Wenmo Kong, Zitong Sheng, Chang-Tien Lu, "Situation-Based Interaction Learning for Personality Prediction on Facebook", Proceedings of the IEEE International Conference on Big Data, Seattle, WA, Dec. 10-13, 2018. [pdf]
• [ICDM'18] Xuchao Zhang, Shuo Lei, Liang Zhao, Arnold Boedihardjo, Chang-Tien Lu, "Robust Regression via Online Feature Selection under Adversarial Data Corruption", Proceedings of the IEEE International Conference on Data Mining (ICDM), Singapore, Nov. 17-20, 2018. [acceptance rate: 19.94%] [pdf]
• [ICDM'18] Zhiqian Chen, Feng Chen, Rongjie Lai, Xuchao Zhang, and Chang-Tien Lu, "Rational Neural Networks for Approximating Jump Discontinuities of Graph Convolution Operator", Proceedings of the IEEE International Conference on Data Mining (ICDM), Singapore, Nov. 17-20, 2018. [acceptance rate: 8.86%] [pdf]
• [IJCAI'18] Xuchao Zhang, Liang Zhao, Zhiqian Chen, Chang-Tien Lu, "Distributed Self-Paced Learning in Alternating Direction Method of Multipliers", Proceeding of the 27th International Joint Conference on Artificial Intelligence (IJCAI), (to appear), Stockholm, Sweden, July 13-19, 2018. [acceptance rate: 20.6%] [pdf][extended][bib]
• [BigData'17] Xuchao Zhang, Liang Zhao, Zhiqian Chen, Arnold Boedihardjo, Dai Jing, Chang-Tien Lu, "Trendi: Tracking Stories in News and Microblogs via Emerging, Evolving and Fading Topics", Proceedings of the IEEE International Conference on Big Data, Boston, MA, Dec. 11-14, 2017. [pdf][bib]
• [BigData'17] Xuchao Zhang, Zhiqian Chen, Liang Zhao, Arnold Boedihardjo, Chang-Tien Lu, "TRACES: Generating Twitter Stories via Shared Subspace and Temporal Smoothness", Proceedings of the IEEE International Conference on Big Data, Boston, MA, Dec. 11-14, 2017. [pdf][bib]
• [ICDM'17] Xuchao Zhang, Liang Zhao, Arnold P. Boedihardjo, Chang-Tien Lu, "Online and Distributed Robust Regressions under Adversarial Data Corruption", Proceedings of the IEEE International Conference on Data Mining (ICDM), pages 625-634, New Orleans, Louisiana, Nov. 18-21, 2017. [acceptance rate: 9.25%] [pdf][code][bib]
• [CIKM'17] Xuchao Zhang, Liang Zhao, Arnold P. Boedihardjo, Chang-Tien Lu, Naren Ramakrishnan, "Spatiotemporal Event Forecasting from Incomplete Hyper-local Price Data", Proceedings of the 26th ACM International Conference on Information and Knowledge Management (CIKM), pages 507-516, Singapore, Nov. 6-10, 2017. [acceptance rate: 21%] [pdf][bib]
• [IJCAI'17] Xuchao Zhang, Liang Zhao, Arnold P. Boedihardjo, Chang-Tien Lu, "Robust Regression via Heuristic Hard Thresholding", Proceeding of the 26th International Joint Conference on Artificial Intelligence (IJCAI), pages 3434–3440, Melbourne, Australia, August 19-25, 2017. [acceptance rate: 26%] [pdf][code][bib]
• [IJCAI'17] Zhiqian Chen, Xuchao Zhang, Arnold P. Boedihardjo, Jing Dai, Chang-Tien Lu, "Multimodal Storytelling via Generative Adversarial Imitation Learning", Proceeding of the 26th International Joint Conference on Artificial Intelligence (IJCAI), pages 3967-3973, Melbourne, Australia, August 19-25, 2017. [acceptance rate: 26%] [pdf][bib]
• [BigData'16] Xuchao Zhang, Zhiqian Chen, Weisheng Zhong, Arnold P. Boedihardjo, Chang-Tien Lu, "Storytelling in Heterogeneous Twitter Entity Network based on Hierarchical Cluster Routing", Proceedings of the IEEE International Conference on Big Data, pp. 1522-1531 Washington, DC, Dec. 5-8, 2016. [pdf][bib]
• [CIKM'16] Ting Hua, Xuchao Zhang, Wei Wang, Chang-Tien Lu, Naren Ramakrishnan, "Automatical Storyline Generation with Help from Twitter", Proceedings of the 25th ACM International Conference on Information and Knowledge Management (CIKM), Indianapolis, IN, Oct. 24-28, 2016. [acceptance rate: 28.8%] [pdf][bib]

Preprints

• Bingsheng Wang*, Xuchao Zhang*, Chang-Tien Lu, Feng Chen, "Water Disaggregation via Shape Features based Bayesian Discriminative Sparse Coding", 2018. * These two authors contributed equally. [arxiv]