Xin Jin

Associate Professor
Department of Computer Science and Technology
Peking University

Email: xinjinpku (at) pku (dot) edu (dot) cn

I am an Associate Professor in the Department of Computer Science and Technology at Peking University. I work on computer systems, with a focus on hardware-software co-design, programmable networks and machine learning systems. My research has received USENIX NSDI Best Paper Award (2018) and USENIX FAST Best Paper Award (2019).

---

Research

I work on computer systems. Here are some recent projects.

• Systems + Programmable Network Hardware
  • Programmable packet scheduling [AIFO, SIGCOMM'21]
  • In-network DDoS detection and mitigation [Jaqen, Security'21]
  • Hierarchical core-stateless fair queueing [HCSFQ, NSDI'21]
  • In-network rack-scale scheduling [RackSched, OSDI'20]
  • In-network coherence directories [Pegasus, OSDI'20]
  • In-network lock management [NetLock, SIGCOMM'20]
  • In-network conflict detection [Harmonia, VLDB'19]
  • Distributed in-network caching [DistCache, FAST'19, Best Paper Award]
  • In-network chain replication [NetChain, NSDI'18, Best Paper Award]
  • Fast in-network caching [NetCache, SOSP'17]
• Systems + AI and Big Data
  • Neural network planning [NeuroPlan, SIGCOMM'21]
  • Neural zero-day ReDoS recovery [RegexNet, S&P'21]
  • Compute and storage disaggregation [Kayak, NSDI'21]
  • Pipelined context switching [PipeSwitch, OSDI'20]
  • Efficient checkpoint for training [LC-Checkpoint, ICML'20]
  • Neural packet classification [NeuroCuts, SIGCOMM'19]
  • Graph pattern mining [ASAP, OSDI'18]
  • Wide-area streaming analytics [AWStream, SIGCOMM'18]
  • Network traffic analytics [SketchVisor, SIGCOMM'17]
• Software-Defined Networking
  • Managing big data transfers on optical WANs [Owan, SIGCOMM'16]
  • Controller composition [CoVisor, NSDI'15]
  • Fast network update [Dionysus, SIGCOMM'14]

---

Students

• Zhihao Bai
• Zhuolong Yu (with Vova Braverman)
• Hang Zhu