Events

(27/09/2025) Two papers have been accepted by ACM SoCC 2025. These works investigate new approaches to cost-efficient LLM serving (Cauchy) and effective job packing for DL model training (Cuckoo), both on heterogeneous GPUs. Big congrats to Yihui, Yuzhang and the entire RAIDS-Kuaishou joint team!

(13/09/2025) Our works on AIOps and straggler detection in AI infrastructure have been accepted by ASE 2025. Big congrats to Zeying and Yitang!

(10/09/2025) Our works on releasing differentially private features has been accepted by TIFS 2025. Big congrats to Xinyue and Xiaoyu!

(10/12/2024) Our work on optimized pareto front of hypernetwork has been accepted by AAAI 2025. Big congrats to Hui!

(20/11/2024) I will serve as Associate Editor of CCF Computer Engineering and Design Journal for the next 4 years!

(26/09/2024) A new approach to defense attacks to LLM serving has been accepted by, and will be presented in the poster session of ACM SOSP 2024.

(26/09/2024) Our work on Elastic GPU Scheduling for Online DL Model Training is accepted by ACM SoCC 2024. Big Congrats to Ziyang, Weihan and Tianyu!

(22/08/2024) Our work on Advanced Feature Engineering for Intelligent Traffic Analysis Applications is accepted by ACM EuroSys 2025. Big Congrats!

[Call for Papers] "Machine Learning for Dependable Edge Computing Systems and Services" Special Issue in the journal of Big Data and Cognitive Computing (BDCC), (SCI-indexed), deadline: April 2024

[Call for Papers] "The 11th IEEE International Conference on Big Data Computing and Communications (BigCom 2025)" deadline: 3rd March 2025

[Call for Papers] "The 16th IEEE Joint Cloud Conference (JCC 2025)" deadline: 15th April 2025

[Call for Papers] "Machine Intelligent Information and Efficient Systems" Special Issue in the journal of Electronics (SCI-indexed, IF=2.690), deadline extended to 14 October 2024

(20/07/2024) Our work on GNN-based resource estimation for microservices received the best paper award of IEEE JCC 2024. Congrats to Jinghao!

(17/05/2024) Two papers are accepted by ACM KDD 2024. Big congrats to Rui, Xudong and Yingguang!

(16/04/2024) Our work on Dynamic Graph Transformers for Bot Detection is accepted by IJCAI 2024.

(08/12/2023) Our work on Recovering from Poisoning Attacks is accepted by ICDE 2024.

(29/08/2023) Our work on IoT streaming management is accepted by IEEE Trans. on Services Computing.

(20/04/2023) I presented a poster on Resilient QoS-Aware Workload Co-Scheduling and User Anomaly Detection in Shared Computing Clusters in the UK Alan Turing Workshop on Edge-Cloud Infrastructure for Distributed Intelligent Computing.

(01/03/2023) I will be joining Beihang University as Associate Professor in Summer 2023. I'm actively looking for strong and motivated students and welcome applicants from diverse backgrounds.

(21/02/2023) Our work on affinity-aware multi-dimensional time-varying resource packing is accepted by Journal of Parallel and Distributed Computing (JPDC). The algorithm suite is publicly available.

(25/01/2023) Two papers are accepted by the Web Conference (WWW'23). Many congrats to Yingguang, Dongcheng and Xiang!

(20/10/2022) Our work on Reinforced Self-supervised GNN Architecture Search is accepted by ACM Trans. on the Web. Congrats to Yingguang!

(23/08/2022) Our work on QoS-Aware Co-Scheduling is accepted by IEEE Trans. on Parallel and Distributed Systems. Big congrats to Jianyong and Xiaoyang!

(18/07/2022) Our work on "Incentivizing Online Edge Caching via Auction-Based Subsidization" is accepted by 19th IEEE International Conference on Sensing, Communication, and Networking (SECON)! Big congrats to Youmei!

(14/06/2022) Our work on "STRONGHOLD: Fast and Affordable Billion-scale Deep Learning Model Training" is accepted by the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC) 2022! Big congrats to Xiaoyang and Shenghao!

(27/01/2022) received Alan Turing Institute Post-Doctoral Enrichment Award 2022.

(01/11/2021) One survey paper on text classification is accepted by ACM Trans. on Intelligent Systems and Technology (TIST).

(01/10/2021) Our work on UAV anomaly detection through contrastive learning and work on RL Guided Multi-Relational Graph Neural Networks have been accepted by IEEE Trans. on Knowledge and Data Engineering (TKDE) and ACM Trans. on Information Systems (TOIS), respectively.

(12/09/2021) Our work on lifelong house price prediction and work on malware detection have been accepted by IEEE Trans. on Knowledge and Data Engineering (TKDE) and IEEE Trans. on Neural Networks and Learning Systems (TNNLS) respectively.

(10/07/2021) I will serve as PC member for International Joint Conferences on Artificial Intelligence 2022 (IJCAI'22), European Conference on Artificial Intelligence (ECAI'22), IEEE CLOUD'22.

(20/06/2021) Our work on joint optmization of cache placement and request routing is accepted by Journal of Parallel and Distributed Computing (JPDC).

(27/04/2021) Our work on GPU cluster scheduling is accepted by IEEE Trans. on Parallel and Distributed Systems (TPDS).

(23/02/2021) I will serve as Track Chair for IEEE International Conference on Cloud Computing (CLOUD'21). See the Call for Papers

(31/01/2021) Our work on resource efficient incremental learning for heterogenous information networks is accepted by IEEE Trans. on Computers (TC).

(17/01/2021) Our work on streaming social event detection is accepted by ACM Trans. on Knowledge Discovery from Data (TKDD).

(19/10/2020) I will serve as PC member for International Joint Conferences on Artificial Intelligence 2021 (IJCAI'21).

(25/01/2020) Our paper "Orchestrating Development Lifecycle of ML-Based IoT Applications" has been accepted to publish in ACM Computing Surveys (CSUR) 2020.

(25/01/2020) Our paper "Performance-aware Speculative Resource Oversubscription for Large-scale Clusters" has been accepted to publish in IEEE Trans. on Parallel and Distributed Systems (TPDS).

(10/10/2019) A recent survey study on the management of development lifecycle for ML-Based IoT Applications [arxiv]

(15/07/2019) Our work "GA-Par: Dependable Microservice Orchestration Framework for Geo-Distributed Clouds" has been accepted to publish in IEEE Trans. on Parallel and Distributed Systems (TPDS).

(02/2019) Edgetic datacentre management solution and preliminary case study link

"Old" Events Before 2019

(09/03/2013) the paper "improved Energy-Efficiency in Cloud Datacenters with Interference-Aware Virtual Machine Placement" has been awarded as the best Paper during the International Symposium of Autonomous Distributed Systems" ISADS 2013

(21/10/2015) Our paper has been accepted by IEEE HASE 2016

(25/09/2015) Our paper has been accepted by Springer IoV 2015

(18/12/2015) Two papers are submitted to IEEE ICDCS 2016 and Transactions on Services Computing and currently under review.

(18/01/2016) The visionary paper "Computing at Massive Scale: Scalability and Dependability Challenges" is invited to publish and present at IEEE SOSE 2016

(04/03/2016) Our paper "Reliable Computing Service in Massive-scale Systems Through Rapid Low-cost Failover" is accepted by IEEE Transactions on Services Computing(TSC). Big congrats!

(28/03/2016) I attend IEEE SOSE 2016 at Oxford, UK. In April I visited University of Oxford, University of Leeds and University of Edinburgh, working with my collaborators on our recent joint projects and papers.

(28/03/2016) PC Member of IEEE FiCloud 2016 and IEEE/ACM BDCAT 2016

(20/04/2016) Our paper "Reducing Late-Timing Failure at Scale: Straggler Root-Cause Analysis in Cloud Datacenters" is accepted by IEEE DSN 2016.

(01/09/2016) Our paper that focuses on RDF data management is accepted by IEEE ICPADS 2016.

(05/09/2016) Our paper "Straggler Root-cause and Impact Analysis for Massive-scale Virtualized Cloud Datacenters"  is accepted by IEEE Transactions on Services Computing(TSC).

(03/10/2016) Our paper "An Optimized Storage Method for Vehicle Trajectory Data Exploiting Trajectory Patterns"  is accepted by IEEE HPCC 2016

(21/11/2016) Our paper "Fog Orchestration for Internet of Things Services"  is accepted by IEEE Internet Computing magazine.

(07/01/2017) I passed the viva and obtained my Ph.D degree.

(18/08/2017) The work of rapid docker container deployment was accepted by IEEE HPCC 2017.

(01/09/2017) The work of machine learning based node performance analyzer was accepted by IEEE ICPADS 2017.

(28/09/2017) The work of efficient resource overselling was accepted by ACM SOSP 2017 poster session.

(08/11/2017) I moved to University of Leeds UK as a research fellow.

(18/11/2017) I was awarded the Grand Class of Scientific and Technological Progress Award of Chinese Institute of Electronics of year 2017 （2017中国电子学会科技进步特等奖） for the key participation and contributions to the reliable resource management and scheduling. The joint project is led by Alibaba Cloud, Beihang University and Tsinghua University.

(05/04/2018) The work of "ROSE: Cluster Resource Scheduling via Speculative Over-subscription" is accepted as a full paper and will appear in IEEE ICDCS 2018. Big Congrats!

(16/07/2018) I has been invited to serve as IEEE JCC 2019 PC co-chair.

(01/10/2018) The chapter entitled "Fog Orchestration and Simulation for IoT Services" is accepted to publish in the book of "Fog and Fogonomics: Challenges and Practices of Fog Computing, Networking, Strategy, and Economics" by Wiley .