Network for Distributed Intelligence

Takanori Hara
research

With the increasing scale of AI, distributed intelligence has gained significant attention. In particular, inference and learning based on model splitting are realized by coordinating multiple nodes over a network. Existing Multi-hop split inference/learning (MSI/MSL) relies on static communication paths, necessitating the establishment of flexible end-to-end communication paths tailored to the context of learning and inference. Leveraging the similarity between Service Function Chaining (SFC) and MSI, this research aims to establish an SFC infrastructure for MSI/MSL1. Additionally, we explore the realization of a high-speed inference/learning infrastructure using asynchronous learning and Multi-path TCP, as well as the formulation of optimization problems for model splitting, placement, and data routing2.

  1. T. Hara and M. Sasabe, “Service Function Chaining Architecture for Multi-hop Split Inference and Learning,” Sept. 12, 2025, arXiv: arXiv:2509.10001. doi: 10.48550/arXiv.2509.10001. ↩︎

  2. T. Hara and M. Sasabe, “Optimization of Model Splitting, Placement, and Chaining for Multi-hop Split Learning and Inference,” 2026, arXiv. doi: 10.48550/ARXIV.2604.25197. ↩︎

research top network machine learning AI eBPF XDP SmartNIC AF_XDP
Takanori Hara
Takanori Hara
Associate Professor