Multi-exit-based federated edge learning in industrial IoT networks

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and more.Subscribe

Networking and Internet Architecture

Multi-exit-based federated edge learning in industrial IoT networks

Computational Intelligence and Deep Learning for Next-Generation Edge-Enabled Industrial IoT

In this paper, we investigate how to deploy computational intelligence and deep learning (dl) in edge-enabled industrial iot networks.

Due to limited resources in the industrial iot networks, including computational power, bandwidth, and channel state, it is challengingfor many devices to accomplish local training and upload weights to the edgeserver in time.

To address this issue, we propose a novel multi-exit-based federated edge learning (me-feel) framework, where the deep model can be divided into several sub-models with different depths and output prediction from the exit in the corresponding sub-model.

In this way, the devices with insufficient computational power can choose the earlier exits and avoid training the complete model, which can help reduce computational latency andenable devices to participate into aggregation as much as possible within a latency threshold.

We also propose a greedy approach-based exit selection and bandwidth allocation algorithm to maximize the total number of exits in each communication round.

Simulation experiments are conducted on the classical fashion-mnist dataset under a non-independent and identically distributed (non-iid) setting, and it shows that the proposed strategy outperforms the conventional federated edge learning (fl) strategy.

In particular, the proposed me-feel can achieve an accuracygain up to 32.7% in the industrial iot networks with the severely limited resources.

Authors

Shunpu Tang, Lunyuan Chen, Ke HeJunjuan Xia, Lisheng Fan, Arumugam Nallanathan

Related Topics

Multi-exit - based federated edge learning (me-feel) framework

Greedy approach-based exit selection

Computational intelligence

Bandwidth allocation algorithm

Read the Paper

Read Paper

Bookmarks

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and more.Subscribe

Networking and Internet Architecture

Multi-exit-based federated edge learning in industrial IoT networks

Computational Intelligence and Deep Learning for Next-Generation Edge-Enabled Industrial IoT

In this paper, we investigate how to deploy computational intelligence and deep learning (dl) in edge-enabled industrial iot networks.

We also propose a greedy approach-based exit selection and bandwidth allocation algorithm to maximize the total number of exits in each communication round.

In particular, the proposed me-feel can achieve an accuracygain up to 32.7% in the industrial iot networks with the severely limited resources.

Authors

Shunpu Tang, Lunyuan Chen, Ke HeJunjuan Xia, Lisheng Fan, Arumugam Nallanathan

◐ Recommended Follows

◐ Latest Activity