2023 Fiscal Year Research-status Report
An Efficient Split In-network Learning Approach for Resource Constrained Wireless Networks
| Project/Area Number |
23K11080
|
|---|
| Research Institution | Ibaraki University |
|---|
Principal Investigator |
王 瀟岩 茨城大学, 理工学研究科(工学野), 准教授 (10725667)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
梅比良 正弘 南山大学, 理工学部, 教授 (00436239)
|
|---|
| Project Period (FY) |
2023-04-01 – 2026-03-31
|
| Keywords | split learning / in-network learning |
|---|
| Outline of Annual Research Achievements |
In FY2023, we have realized the efficient split in-network learning approach with fixed model and network settings. Specifically, we focused on the realization of BS-side model virtualization and UE-BS model’s gradient aggregation, under a given model partition and UE set. We validated the proposed approach’s convergence speed and model accuracy by simulations on PyTorch. Different from most of the previous studies that use MNIST dataset (i.e., handwritten digits from 0 to 9), we took into consideration the real mobile deep learning applications, and thus used an aerial view human action detection dataset for evaluation.
|
| Current Status of Research Progress |
Current Status of Research Progress
2: Research has progressed on the whole more than it was originally planned.
Reason
We consider that the research progresses smoothly. We have published 1 journal papers, 2 internal conference papers and multiple domestic conference papers in FY2023 under the support of this funding.
|
| Strategy for Future Research Activity |
In the following year, we will consider to refine the approach and clarify the performance tradeoff curve under various resource budget. Furthermore, we will consider to implement the proposed approach on testbed.
|
| Causes of Carryover |
Parts of the conferences were attended online, by which the grant originally planed has not been used. These used grant will be used to purchase the workstation and for the participation fee for conferences in FY2024.
|
Research Products
(3 results)
