Prospective Interns and Students.
I am peacefully looking for unpaid interns (it is because USC does not allow remote paid interns) and prospective Ph.D. students (apply by Dec 15th for Fall 24 admission; full financial support).
In short, you are expected to have a relevant paper to my research topics and strong programming skills for open-source ML and/or systems.
See instructions (via email only; not WeChat) before reaching out.
Research Interests.
I build fast and automated machine learning (ML) and data mining (DM) systems, with a focus on but not limited to anomaly detection and graph neural networks.
- Accelerate large-scale learning tasks by leveraging ML systems techniques.
- Automate unsupervised ML by model selection and hyperparameter optimization.
- Develop open-source ML tools to support applications in healthcare, finance, and security.
Research Keywords: Anomaly/Outlier/Out-of-Distribution (OOD) Detection, Unsupervised ML, ML Systems, Automated ML, AI for Science, Graph Neural Networks.
Open-source ML. I have led more than 10 ML open-source initiatives,
receiving 16,000 GitHub stars (top 0.002%) and >20M downloads. Popular ones: PyOD, PyGOD, TDC, ADBench
Prior to USC. I got my Ph.D. in 4 years at CMU, working with Prof. Leman Akoglu, Prof. Zhihao Jia,
and Prof. George H. Chen.
I was a member of CMU Catalyst.
I also collaborated with Prof. Jure Leskovec and Prof. Philip S. Yu.
Social Presence. I am active on English-based Twitter,
LinkedIn, as well as 中文平台 知乎 (微调),
小红书 (微调).
I have more than 250,000 followers on social platforms in combination. 同时,我运营了一系列北美ML PhD工作申请讨论群,可以添加微信breaknever入群 (请注明来意)。
✈ News and Travel
I have lost track on some of these nice things, obviously :(
[Sep 2023] Diffusion Models: A Comprehensive Survey of Methods and Applications is accepted to ACM Computing Surveys. Congrats to Lin Yang and other coauthors!
[Sep 2023] ADGym: Design Choices for Deep Anomaly Detection is accepted to NeurIPS 2023; I will be in New Orleans, again.
🍭 Recent Publications (2021-)
See my Google Scholar,
DBLP,
ORCID,
and ResearchGate for the full publication list.
†Equal contribution; ♠Corresponding author
Preprints & Working Papers
[w23g] Fast Unsupervised Deep Outlier Model Selection with Hypernetworks, with Xueying Ding, Leman Akoglu. Preprint.
[w23a] Weakly Supervised Anomaly Detection: A Survey, with Minqi Jiang, Chaochuan Hou, Ao Zheng, Xiyang Hu, Songqiao Han, Hailiang Huang, Xiangnan He, Philip S. Yu. Preprint.
[w22e] Hyperparameter Optimization for Unsupervised Outlier Detection, with Leman Akoglu. Preprint.
Conference Papers
-
ADGym: Design Choices for Deep Anomaly Detection.
Minqi Jiang†, Chaochuan Hou†, Ao Zheng†, Songqiao Han, Hailiang Huang♠, Qingsong Wen, Xiyang Hu♠, Yue Zhao♠.
NeurIPS, 2023.
.
-
DSV: An Alignment Validation Loss for Self-supervised Outlier Model Selection.
Jaemin Yoo, Yue Zhao, Lingxiao Zhao, Leman Akoglu.
ECML/PKDD, 2023.
-
Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks.
Peng Xu†, Lin Zhang†, Xuanzhou Liu, Jiaqi Sun, Yue Zhao, Haiqin Yang, Bei Yu.
ICML, 2023.
-
TOD: GPU-accelerated Outlier Detection via Tensor Operations.
Yue Zhao, George H. Chen, Zhihao Jia.
VLDB, 2023.
-
ADMoE: Anomaly Detection with Mixture-of-Experts from Noisy Labels.
Yue Zhao, Guoqing Zheng, Subhabrata Mukherjee, Robert McCann, Ahmed Awadallah.
AAAI, 2023.
-
ADBench: Anomaly Detection Benchmark.
Songqiao Han†, Xiyang Hu†, Hailiang Huang†, Minqi Jiang†, Yue Zhao†♠.
NeurIPS, 2022.
-
BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs.
Kay Liu†, Yingtong Dou†, Yue Zhao†, Xueying Ding, Xiyang Hu, Ruitong Zhang, Kaize Ding, Canyu Chen, Hao Peng, Kai Shu, Lichao Sun, Jundong Li, George H. Chen, Zhihao Jia, Philip S. Yu.
NeurIPS, 2022.
-
ELECT: Toward Unsupervised Outlier Model Selection.
Yue Zhao, Sean Zhang, Leman Akoglu.
ICDM, 2022.
-
Automatic Unsupervised Outlier Model Selection.
Yue Zhao, Ryan Rossi, Leman Akoglu.
NeurIPS, 2021.
-
Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development.
Kexin Huang†, Tianfan Fu†, Wenhao Gao†, Yue Zhao, Yusuf Roohani, Jure Leskovec, Connor W. Coley, Cao Xiao, Jimeng Sun, Marinka Zitnik.
NeurIPS, 2021.
-
Revisiting Time Series Outlier Detection: Definitions and Benchmarks.
Kwei-Herng Lai†, Daochen Zha†, Junjie Xu, Yue Zhao, Guanchu Wang, Xia Hu.
NeurIPS, 2021.
-
SUOD: Accelerating Large-scale Unsupervised Heterogeneous Outlier Detection.
Yue Zhao†, Xiyang Hu†, Cheng Cheng, Cong Wang, Changlin Wan, Wen Wang, Jianing Yang, Haoping Bai, Zheng Li, Cao Xiao, Yunlong Wang, Zhi Qiao, Jimeng Sun, Leman Akoglu.
MLSys, 2021.
Journal Papers
-
Diffusion Models: A Comprehensive Survey of Methods and Applications.
Ling Yang†, Zhilong Zhang†, Yang Song, Shenda Hong, Runsheng Xu, Yue Zhao, Wentao Zhang, Bin Cui, Ming-Hsuan.
ACM Computing Surveys, 2023.
-
The Need for Unsupervised Outlier Model Selection: A Review and Evaluation of Internal Evaluation Strategies.
Martin Q. Ma†, Yue Zhao†, Xiaorong Zhang, Leman Akoglu.
ACM SIGKDD Explorations Newsletter, 2023.
-
Artificial Intelligence Foundation for Therapeutic Science.
Kexin Huang†, Tianfan Fu†, Wenhao Gao†, Yue Zhao, Yusuf Roohani, Jure Leskovec, Connor W. Coley, Cao Xiao, Jimeng Sun, Marinka Zitnik.
Nature Chemical Biology, 2022.
-
ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functions.
Zheng Li†, Yue Zhao†♠, Xiyang Hu, Nicola Botta, Cezar Ionescu, George H. Chen.
TKDE, 2022.
-
PyOD: A Python Toolbox for Scalable Outlier Detection.
Yue Zhao, Zain Nasrullah, Zheng Li.
JMLR, 2019.
💯 Teaching
USC (as instructor):
- Machine Learning (Spring 2024; to be finalized)
CMU (as teaching assistant):
- Intro to Artificial Intelligence (Spring 2020-Spring 2022)
- Digital Transformation (Spring 2022)
- Statistics for IT Managers (Fall 2021)
University of Toronto (as teaching assistant):
- Embedded Systems (Fall 2015)
🏋 Services
Conference Organizing Committee
External Reviewer for Funding Proposals
Journal Reviewer
- Journal of Machine Learning Research (JMLR),
Machine Learning,
TPAMI,
TKDE
- IEEE Internet of Things Journal (IoT-J),
IEEE Intelligent Systems,
IEEE Journal on Selected Areas in Communications (J-SAC),
Data Mining and Knowledge Discovery (DAMI),
ACM Transactions on Management Information Systems (TMIS),
Knowledge and Information Systems (KAIS),
INFORMS Journal on Computing (IJOC),
Neurocomputing,
Big Data,
Artificial Intelligence Review (AIRE),
IEEE Transactions on Systems, Man, and Cybernetics: Systems,
IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB),
IEEE Network Magazine,
- AISTATS 2024 (meta-reviewer)
- KDD 2020, KDD 2021, KDD 2022, KDD 2023
- IJCAI 2022, IJCAI 2023
- NeurIPS 2021, NeurIPS 2022, NeurIPS 2023
- AAAI 2021, AAAI 2022, AAAI 2023,
AAAI 2021 Demonstrations, AAAI 2022 Demonstrations
- MICCAI 2020, MICCAI 2021, MICCAI 2022
- KDD Workshop on Outlier Detection and Description (ODD), 2021,
KDD Workshop on Anomaly and Novelty Detection (ANDEA), 2021 & 2022,
IJCAI Workshop on Artificial Intelligence for Anomalies and Novelties (AI4AN), 2020 & 2021
👑 Automation, System, and APplication (ASAP) Lab
Openings.
I am peacefully looking for interns (from now) and Ph.D. student (from Fall 24).
Timeline for PhD Offer. We could chat now but no offer can be made prior to
Mid-Jan 2024.
Email for Connection - Please email the following (subject line: "Interested in {position, e.g., Ph.D.} at {expected time, e.g., Fall 24}"): Magic Words please add Trojan in the email title to show you read this carefully.
-
CV: Provide a concise background about yourself and your plan for future steps.
-
Research experience [at least 1 relevant publication in anomaly detection, (ML) systems, and HPC is required (likely in top ML/AI/System conferences)]
-
Why ASAP?: Do share if any of my research papers or topics are of interest to you. Also, feel free to suggest new topics that you would like to explore. I am always open to fresh perspectives and ideas.
General Expectations. Strong programming is essential as our work revolves around ML Systems and open-source ML. A solid foundation in statistics and mathematics will be a significant plus.
Don't fear making mistakes; they're a part of the learning curve in both research and life.
Compensation.
Ph.D. students will receive the full support (tuition waiver + stipend is $40,000 in 2023-24) outlined by the CS department.
We do not have paid opportunities for undergraduate and master RA; it is not allowed to pay remote interns at USC :(
Please consider this before reaching out.