Shouxi Luo

I am an Associate Professor with the School of Computing and Artificial Intelligence, Southwest Jiaotong University. Currently, I am working on building flexible and performance-optimized network protocols for emerging networked systems/applications like distributed machine learning and serverless computing.

Prior to joining Southwest Jiaotong University, I was an engineer working on cloud storage systems at Huawei for one year. I obtained my Ph.D. degree in communication and information system from the University of Electronic Science and Technology of China in 2016. During my PhD, I also spent one year at ETH Zurich working with Prof. Laurent Vanbever. Before that, I earned my bachelor's degree in communication engineering from the University of Electronic Science and Technology of China in 2011.

To contact me, drop me an email at what at what .

Selected Publications [Google Scholar, ResearchGate]

Meeting Coflow Deadlines in Data Center Networks with Policy-based Selective Completion
Eliminating Communication Bottlenecks in Cross-Device Federated Learning with In-Network Processing at the Edge
Fast Parameter Synchronization for Distributed Learning with Selective Multicast
Softwarized IP Multicast in the Cloud
Efficient File Dissemination in Data Center Networks with Priority-based Adaptive Multicast
Efficient Multisource Data Delivery in Edge Cloud With Rateless Parallel Push
Selective Coflow Completion for Time-sensitive Distributed Applications with Poco
Near-Optimal Multicast Tree Construction in Leaf-Spine Data Center Networks
Customizable network update planning in SDN
Swing State: Consistent Updates for Stateful and Programmable Data Planes
Towards Practical and Near-Optimal Coflow Scheduling for Data Center Networks
Arrange your network updates as you wish
Decentralized deadline-aware coflow scheduling for datacenter networks
Practical flow table aggregation in SDN
Consistency is Not Easy: How to Use Two-Phase Update for Wildcard Rules?
Minimizing average coflow completion time with decentralized scheduling
Traffic-aware VDC embedding in data center: A case study of fattree
Fast incremental flow table aggregation in SDN

Code:

  1. CREW, an efficient partial reduce execution scheme for fully connected workers, paper, code