mlsanityData to 14 Oct 2026

Communication-Efficient Split Learning Based on Analog Communication and Over the Air Aggregation

arXiv 2106.00999 ↗First posted 2 Jun 2021cs.LG cs.DC cs.ITcited by 8

Not on the map. Why?

Abstract (arXiv)

Split-learning (SL) has recently gained popularity due to its inherent privacy-preserving capabilities and ability to enable collaborative inference for devices with limited computational power. Standard SL algorithms assume an ideal underlying digital communication system and ignore the problem of scarce communication bandwidth. However, for a large number of agents, limited bandwidth resources, and time-varying communication channels, the communication bandwidth can become the bottleneck. To address this challenge, in this work, we propose a novel SL framework to solve the remote inference problem that introduces an additional layer at the agent side and constrains the choices of the weights and the biases to ensure over the air aggregation. Hence, the proposed approach maintains constant communication cost with respect to the number of agents enabling remote inference under limited bandwidth. Numerical results show that our proposed algorithm significantly outperforms the digital implementation in terms of communication-efficiency, especially as the number of agents grows large.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 8 of its 15 references that are in the map. First posted on arXiv 2 Jun 2021.

Builds on

8 of 15 references.

References · 8

  1. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 395
  2. 2018Distributed learning of deep neural network over multiple agentscited by 279
  3. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 191
  4. 2015Learning Deep Representations of Appearance and Motion for Anomalous Event Detectioncited by 75
  5. 2020End-to-End Evaluation of Federated Learning and Split Learning for Internet of Thingscited by 64
  6. 2019On Analog Gradient Descent Learning over Multiple Access Fading Channelscited by 62
  7. 2020Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learningcited by 24
  8. 2020Communication-Efficient Multimodal Split Learning for mmWave Received Power Predictioncited by 18

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 2; 2024: 1; 2025: 2.

8 papers.

  1. 2022A Survey on Over-the-Air Computationcited by 21
  2. 2021Communication-oriented Model Fine-tuning for Packet-loss Resilient Distributed Inference under Highly Lossy IoT Networkscited by 7
  3. 2023Distributed Machine Learning for UAV Swarms: Computing, Sensing, and Semanticscited by 5
  4. 2024COMSPLIT: A Communication-Aware Split Learning Design for Heterogeneous IoT Platformscited by 5
  5. 2025Distributionally Robust Federated Learning with Client Drift Minimizationcited by 1
  6. 2022A Machine Learning Framework for Distributed Functional Compression over Wireless Channels in IoTcited by 0
  7. 2023When Computing Power Network Meets Distributed Machine Learning: An Efficient Federated Split Learning Frameworkcited by 0
  8. 2025Communication-Efficient and Interoperable Distributed Learningcited by 0