IEEE R10 VTS Chengdu Chapter Supported Distinguished Lecture Talk for Prof. Xianhao Chen

#Split #Learning #6G #Edge #Intelligence

The next-generation mobile network aims to natively support distributed intelligence, such as federated learning, across massive wireless edge devices. Unfortunately, in the era of large models, the deployment of federated learning faces significant obstacles due to the limited resources on edge devices. In this talk, I will briefly introduce split learning (SL) and elucidate how it overcomes resource limitations via device-server co-training, thereby transforming next-generation edge AI. Then, I will present our recent work on adaptive split federated learning (AdaptSFL) in resource-constrained edge networks. Specifically, our work first provides a unified convergence analysis of split federated learning (SFL) to quantify the impact of model splitting and client-side model aggregation on the learning performance, based on which the AdaptSFL framework is developed to adaptively control model splitting and client-side model aggregation to balance communication-computing latency and training convergence in SFL. Simulation results demonstrate the effectiveness of our approach in accelerating SFL under resource constraints. At last, I will conclude the talk by discussing open problems in SL at the wireless edge.

• Add Event to Calendar
  iCal
  Google Calendar

• Chengdu, Sichuan
• China

---

• Contact Event Host
• Co-sponsored by the School of Information Science and Technology, Southwest Jiaotong University