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

• URL: http://arxiv.org/abs/2106.00999v1
• Date: Wed, 2 Jun 2021 07:49:41 GMT
• Title: Communication-Efficient Split Learning Based on Analog Communication and Over the Air Aggregation
• Authors: Mounssif Krouka, Anis Elgabli, Chaouki ben Issaid, and Mehdi Bennis
• Abstract summary: 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. 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.
• Score: 48.150466900765316
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• AI Flow at the Network Edge [58.31090055138711]
  AI Flow is a framework that streamlines the inference process by jointly leveraging the heterogeneous resources available across devices, edge nodes, and cloud servers. This article serves as a position paper for identifying the motivation, challenges, and principles of AI Flow.
  arXiv  Detail & Related papers  (2024-11-19T12:51:17Z)
• Hypergame Theory for Decentralized Resource Allocation in Multi-user Semantic Communications [60.63472821600567]
  A novel framework for decentralized computing and communication resource allocation in multiuser SC systems is proposed. The challenge of efficiently allocating communication and computing resources is addressed through the application of Stackelberg hyper game theory. Simulation results show that the proposed Stackelberg hyper game results in efficient usage of communication and computing resources.
  arXiv  Detail & Related papers  (2024-09-26T15:55:59Z)
• Overlay-based Decentralized Federated Learning in Bandwidth-limited Networks [3.9162099309900835]
  Decentralized federated learning (DFL) has the promise of boosting the deployment of artificial intelligence (AI) by directly learning across distributed agents without centralized coordination. Most existing solutions were based on the simplistic assumption that neighboring agents are physically adjacent in the underlying communication network. We jointly design the communication demands and the communication schedule for overlay-based DFL in bandwidth-limited networks without requiring explicit cooperation from the underlying network.
  arXiv  Detail & Related papers  (2024-08-08T18:05:11Z)
• Effective Communication with Dynamic Feature Compression [25.150266946722]
  We study a prototypal system in which an observer must communicate its sensory data to a robot controlling a task. We consider an ensemble Vector Quantized Variational Autoencoder (VQ-VAE) encoding, and train a Deep Reinforcement Learning (DRL) agent to dynamically adapt the quantization level. We tested the proposed approach on the well-known CartPole reference control problem, obtaining a significant performance increase.
  arXiv  Detail & Related papers  (2024-01-29T15:35:05Z)
• Dynamic Size Message Scheduling for Multi-Agent Communication under Limited Bandwidth [5.590219593864609]
  We present the Dynamic Size Message Scheduling (DSMS) method, which introduces a finer-grained approach to scheduling. Our contribution lies in adaptively adjusting message sizes using Fourier transform-based compression techniques. Experimental results demonstrate that DSMS significantly improves performance in multi-agent cooperative tasks.
  arXiv  Detail & Related papers  (2023-06-16T18:33:11Z)
• Semantic and Effective Communication for Remote Control Tasks with Dynamic Feature Compression [23.36744348465991]
  Coordination of robotic swarms and the remote wireless control of industrial systems are among the major use cases for 5G and beyond systems. In this work, we consider a prototypal system in which an observer must communicate its sensory data to an actor controlling a task. We propose an ensemble Vector Quantized Variational Autoencoder (VQ-VAE) encoding, and train a Deep Reinforcement Learning (DRL) agent to dynamically adapt the quantization level.
  arXiv  Detail & Related papers  (2023-01-14T11:43:56Z)
• Multi-agent Communication with Graph Information Bottleneck under Limited Bandwidth (a position paper) [92.11330289225981]
  In many real-world scenarios, communication can be expensive and the bandwidth of the multi-agent system is subject to certain constraints. Redundant messages who occupy the communication resources can block the transmission of informative messages and thus jeopardize the performance. We propose a novel multi-agent communication module, CommGIB, which effectively compresses the structure information and node information in the communication graph to deal with bandwidth-constrained settings.
  arXiv  Detail & Related papers  (2021-12-20T07:53:44Z)
• Federated Learning over Wireless IoT Networks with Optimized Communication and Resources [98.18365881575805]
  Federated learning (FL) as a paradigm of collaborative learning techniques has obtained increasing research attention. It is of interest to investigate fast responding and accurate FL schemes over wireless systems. We show that the proposed communication-efficient federated learning framework converges at a strong linear rate.
  arXiv  Detail & Related papers  (2021-10-22T13:25:57Z)
• Optimal Power Allocation for Rate Splitting Communications with Deep Reinforcement Learning [61.91604046990993]
  This letter introduces a novel framework to optimize the power allocation for users in a Rate Splitting Multiple Access network. In the network, messages intended for users are split into different parts that are a single common part and respective private parts.
  arXiv  Detail & Related papers  (2021-07-01T06:32:49Z)
• Reinforcement Learning for Mitigating Intermittent Interference in Terahertz Communication Networks [4.999585439793266]
  Uncoordinated transmissions by a large number of users can cause substantial interference in terahertz networks. New framework based on reinforcement learning is proposed that uses an adaptive multi-thresholding strategy.
  arXiv  Detail & Related papers  (2020-03-10T16:28:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.