Yang Luo (罗旸) - Homepage
I am a Ph.D. candidate in the School of Computer Science and Engineering at Shanghai Jiao Tong University (SJTU), enrolled in a combined master-doctor program since 2024. I am co-supervised by Prof. Guihai Chen and Prof. Xiaofeng Gao.
🔍 Research Interests
My research sits at the intersection of time series analysis, service resource scheduling, and data mining. I focus on translating advanced forecasting and scheduling algorithms into deployable systems that address critical industrial pain points in high-performance cloud service systems, urban computing, and advanced manufacturing.
📰 News
- 2026.08: Receive the Best Paper Award at KDD 2026 Workshop on Uncertainty Reasoning and Quantification in Decision Making.
- 2026.07: Be selected for the Chinese Institute of Electronics - Tencent Doctoral Incentive Program (Hunyuan Large Model Special Project, Top 44 nationwide).
👨🎓 Research Philosophy: From Algorithms to Production
I believe the ultimate value of data mining research lies in its tangible impact on real-world systems. My work follows a full-stack methodology: identifying operational bottlenecks in production environments → designing theoretically grounded predictive models → deploying and validating solutions at scale.
🌐 Industrial Experience
🤝 Cloud Service Resource Autoscaling — Ant Group | 2023.06 – Present
- Long-term research intern designing a cross-service joint prediction and auto-scaling framework for GPU inference clusters.
- Replaced traditional single-service threshold-based scaling by modeling dynamic inter-service dependencies via spatio-temporal graph neural networks.
- Online A/B experiments demonstrated a 33.10% reduction in CPU core-hour consumption, directly contributing to greener computing and lower inference costs.
🤝 Database Workload Prediction — ByteDance | 2022.07 – 2023.05
- Research intern on dynamic database workload prediction.
- Developed an ensemble online adaptive tracking algorithm with a theoretical linear convergence guarantee.
- Deployed to improve cluster resource allocation efficiency in production environments.
💡 Broader Impact
Beyond cloud infrastructure, my techniques have been applied to:
- Urban Management: Spatio-temporal event forecasting for uncivilized urban events and ride-hailing demand prediction under weather-conditioned multi-graph networks.
- Advanced Manufacturing: Quality control and traceability for manufacturing processes under the National Key R&D Program, collaborating with NIO and the China Electronics Standardization Institute.
📜 Academic Service
- Senior Area Chair, KDD ADS Track, 2026
- Program Committee Member: KDD, WWW, ICDM, CIKM
📰 Publications
2026
- Yang Luo, Yiheng Wang, Linyi Long, Tengwei Cai, Xiaofeng Gao, Guihai Chen. STDPS: State-Aware Spatio-Temporal Workload Distribution Prediction for Cloud Service Scaling. IEEE Transactions on Services Computing (TSC), 2026. CCF-A
- Yang Luo, Zhemeng Yu, Yikang Fu, Wei Lu, Lintao Ma, Xiaofeng Gao, Guihai Chen. JointScaler: A Hierarchical Multi-Indicator Distribution Forecasting Approach for Uncertainty-Aware Joint Scaling in Cloud Services. International Joint Conference on Artificial Intelligence (IJCAI), 2026. CCF-A
- Jiadong Chen, Yang Luo, Xiuqi Huang, Fuxin Jiang, Yangguang Shi, Tieying Zhang, Xiaofeng Gao. Uncertainty-Aware Online Time Series Multi-Step Forecasting Framework in Cloud Systems. IEEE Transactions on Knowledge and Data Engineering (TKDE), 2026. CCF-A
- Mohan Gao, Zhemeng Yu, Yang Luo, Lintao Ma, Yinbo Sun, Yuchen Fang, Xiaofeng Gao. Macro-Micro Collaborative Learning for Logical Data Center Microservice Indicators Forecasting. The Web Conference (WWW), 2026. CCF-A
- Chen Hu, Yujie Wan, Yang Luo, Xiaofeng Gao. DBE-Net: A Dual-dimensional Band Encoder Network for Unsupervised Anomaly Detection in Self-Piercing Riveting. KDD Workshop on Uncertainty Reasoning and Quantification in Decision Making (UDM@KDD), 2026.
2025
- Zhemeng Yu, Yang Luo, Yucen Gao, Yinbo Sun, Xiaofeng Gao, Lintao Ma, Guihai Chen. CausalScaler: A Causality-Driven Autoscaling Framework for the Cloud. DASFAA (4), 2025. CCF-B: 488-498
- Jiale Zhang, Yang Luo, Yunlong Cheng, Leixia Wang, Xiaofeng Gao, Xiaochun Yang, Guihai Chen. Timely Watchers: Cost-Effective Schedule for Urban Sensor Patrols. International Workshop on Web-Age Information Management (WASA), 2025. CCF-C 🏆 Best Paper Award
2024
- Yang Luo, Mohan Gao, Zhemeng Yu, Haoyuan Ge, Xiaofeng Gao, Tengwei Cai, Guihai Chen. Integrating System State into Spatio Temporal Graph Neural Network for Microservice Workload Prediction. SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2024. CCF-A
- Mengjin Liu, Yuxin Zuo, Yang Luo, Daiqiang Wu, Peng Zhen, Jiecheng Guo, Xiaofeng Gao. Weather-Conditioned Multi-graph Network for Ride-Hailing Demand Forecasting. International Conference on Service-Oriented Computing (ICSOC), 2024. CCF-B
- Shiyang Zhou, Zehao Gu, Yun Xiong, Yang Luo, Qiang Wang, Xiaofeng Gao. REDI: Recurrent Diffusion Model for Probabilistic Time Series Forecasting. International Conference on Information and Knowledge Management (CIKM), 2024. CCF-B
- Zehao Gu, Shiyang Zhou, Yun Xiong, Yang Luo, Hongrun Ren, Qiang Wang, Xiaofeng Gao, Philip S. Yu. MSTEM: Masked Spatiotemporal Event Series Modeling for Urban Undisciplined Events Forecasting. International Conference on Information and Knowledge Management (CIKM), 2024. CCF-B
2023
- Jiadong Chen, Yang Luo, Xiuqi Huang, Fuxin Jiang, Yangguang Shi, Tieying Zhang, Xiaofeng Gao. IPOC: An Adaptive Interval Prediction Model based on Online Chasing and Conformal Inference for Large-Scale Systems. SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2023. CCF-A
- Yang Luo, Zehao Gu, Shiyang Zhou, Yun Xiong, Xiaofeng Gao. Meteorology-Assisted Spatio-Temporal Graph Network for Uncivilized Urban Event Prediction. IEEE International Conference on Data Mining (ICDM), 2023. CCF-B
💼 Research Projects
📌 National Key R&D Program of China (2024.12 – 2027.11)
- Title: Intelligent Quality Control and Traceability Technology for Manufacturing Process
- Role: Core Team Member
- Industrial Cooperators: NIO, China Electronics Standardization Institute, Shanghai Instrument and Electronics Research Institute
📌 Joint Key Program of National Natural Science Foundation of China (2024.01 – 2027.12)
- Title: Collaborative Perception & Data Management for Intelligent Aircraft Manufacturing
- Role: Core Team Member
📌 CCF-Ant Green Computing Special Research Fund (2024.09 – Present)
- Full Title: Dynamic Scaling Scheduling Scheme for GPU Services Oriented to Cloud Resources
- Role: Student Lead
- Core Responsibilities: Propose cross-service joint prediction and hierarchical auto-scaling algorithms for heterogeneous GPU inference clusters; conduct offline simulation and full-scale online deployment on Ant production GPU clusters.
📌 CCF-Ant Green Computing Special Research Fund (2023.06 – 2024.05)
- Title: Exploration of Intelligent Serverless Capabilities Based on Time Series Forecasting and Machine Learning
- Role: Student Lead
- Core Responsibilities: Design time-series prediction pipelines for Serverless workloads; build baseline forecasting models to quantify resource waste in serverless clusters; deliver preliminary joint prediction framework prototype.
📌 ByteDance Academic Cooperation Project (2022.06 – 2023.06)
- Full Title: Exploration of Online Learning Mechanisms Based on Dynamic Database Workloads
- Role: Student Lead (Principal Student Investigator)
📌 National Key R&D Program of China (2020.11 – 2023.10)
- Title: Theory and Methodology of Manufacturing Big Data Value Mining
- Role: Core Team Member
🎓 Education Background
Doctor of Philosophy (2024.04 – 2028.03 (expected))
- Institution: Shanghai Jiao Tong University, School of Computer Science
- Program: Combined Master-PhD Track
Master of Electronic Information (2022.09 – 2024.03)
- Institution: Shanghai Jiao Tong University, Department of Computer Science
Bachelor of Science (2018.09 – 2022.06)
- Institution: Shanghai Jiao Tong University, Department of Computer Science
🏆 Honors & Awards
- 🎓 Master Academic Scholarship, SJTU (2022)
- 🎓 Doctoral Academic Scholarship, SJTU (2023)
- 🎓 Doctoral Academic Scholarship, SJTU (2024)
- 🎓 Doctoral Academic Scholarship, SJTU (2025)
- 🎖 Huatai Technology Securities Scholarship (2024)
- 🥇 Best Paper Award, WASA 2025
- 🎖 Chinese Institute of Electronics - Tencent Doctoral Incentive Program (Hunyuan Large Model Special Project), 2026 (Top 44 nationwide)
- 🥇 Best Paper Award, KDD 2026 Workshop on Uncertainty Reasoning and Quantification in Decision Making
📝 Patents
- 📌 Resource allocation determination, model training method, and device Patent No.: CN202510905893.2 | 1st Inventor | Status: Under Substantive Examination
- 📌 Workload prediction method and device for service clusters Patent No.: CN202410195025.5 | 1st Inventor | Status: Under Substantive Examination
- 📌 Resource scheduling method and system Patent No.: CN202510283272.5 | 2nd Inventor | Status: Under Substantive Examination
