Reliably transmitting messages despite information loss due to a noisy channel is a core problem of information theory. One of the most important aspects of real world communication, e.g. via wifi, is that it may happen at varying levels of information transfer. The bandwidth-limited channel models this phenomenon. In this study we consider learning coding with the bandwidth-limited channel (BWLC). Recently, neural communication models such as variational autoencoders have been studied for the task of source compression. We build upon this work by studying neural communication systems with the BWLC. Specifically,we find three modelling choices that are relevant under expected information loss. First, instead of separating the sub-tasks of compression (source coding) and error correction (channel coding), we propose to model both jointly. Framing the problem as a variational learning problem, we conclude that joint systems outperform their separate counterparts when coding is performed by flexible learnable function approximators such as neural networks. To facilitate learning, we introduce a differentiable and computationally efficient version of the bandwidth-limited channel. Second, we propose a design to model missing information with a prior, and incorporate this into the channel model. Finally, sampling from the joint model is improved by introducing auxiliary latent variables in the decoder. Experimental results justify the validity of our design decisions through improved distortion and FID scores.
Diffusion-Driven Semantic Communication for Generative Models with Bandwidth Constraints
State Key Laboratory of Advanced Rail Autonomous Operation（先进轨道交通自主运行国家重点实验室）；School of Electronic and Information Engineering（电子与信息工程学院）；Department of Computer and Information Science（计算机与信息科学系）；Information Systems Technology and Design（信息系统技术与设计）
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 p…
In this work, we study emergent communication through the lens of cooperative multi-agent behavior in nature. Using insights from animal communication, we propose a spectrum from low-bandwidth (e.g. pheromone trails) to high-bandwidth (e.g. compositional language) communication that is based on the cognitive, perceptual, and behavioral capabilities of social agents. Through a series of experiments with pursuit-evasion games, we identify multi-agent reinforcement learning algorithms as a computational model for the low-bandwidth end of the communication spectrum.
Communication is a crucial factor for the big multi-agent world to stay organized and productive. Recently, Deep Reinforcement Learning (DRL) has been applied to learn the communication strategy and the control policy for multiple agents. However, the practical \emph{\textbf{limited bandwidth}} in multi-agent communication has been largely ignored by the existing DRL methods. Specifically, many methods keep sending messages incessantly, which consumes too much bandwidth. As a result, they are inapplicable to multi-agent systems with limited bandwidth. To handle this problem, we propose a gatin…
Federated learning (FL) in a bandwidth-limited network with energy-limited user equipments (UEs) is under-explored. In this paper, to jointly save energy consumed by the battery-limited UEs and accelerate the convergence of the global model in FL for the bandwidth-limited network, we propose the sliding differential evolution-based scheduling (SDES) policy. To this end, we first formulate an optimization that aims to minimize a weighted sum of energy consumption and model training convergence. Then, we apply the SDES with parallel differential evolution (DE) operations in several small-scale w…
Distributed learning techniques such as federated learning have enabled multiple workers to train machine learning models together to reduce the overall training time. However, current distributed training algorithms (centralized or decentralized) suffer from the communication bottleneck on multiple low-bandwidth workers (also on the server under the centralized architecture). Although decentralized algorithms generally have lower communication complexity than the centralized counterpart, they still suffer from the communication bottleneck for workers with low network bandwidth. To deal with t…
Large-scale distributed training requires significant communication bandwidth for gradient exchange that limits the scalability of multi-node training, and requires expensive high-bandwidth network infrastructure. The situation gets even worse with distributed training on mobile devices (federated learning), which suffers from higher latency, lower throughput, and intermittent poor connections. In this paper, we find 99.9% of the gradient exchange in distributed SGD is redundant, and propose Deep Gradient Compression (DGC) to greatly reduce the communication bandwidth. To preserve accuracy dur…
Bandwidth estimation and congestion control for real-time communications (i.e., audio and video conferencing) remains a difficult problem, despite many years of research. Achieving high quality of experience (QoE) for end users requires continual updates due to changing network architectures and technologies. In this paper, we apply reinforcement learning for the first time to the problem of real-time communications (RTC), where we seek to optimize user-perceived quality. We present initial proof-of-concept results, where we learn an agent to control sending rate in an RTC system, evaluating u…
Communication is an important factor for the big multi-agent world to stay organized and productive. Recently, the AI community has applied the Deep Reinforcement Learning (DRL) to learn the communication strategy and the control policy for multiple agents. However, when implementing the communication for real-world multi-agent applications, there is a more practical limited-bandwidth restriction, which has been largely ignored by the existing DRL-based methods. Specifically, agents trained by most previous methods keep sending messages incessantly in every control cycle; due to emitting too m…
NSC-SL: A Bandwidth-Aware Neural Subspace Compression for Communication-Efficient Split Learning
School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China（厦门理工学院计算机与信息工程学院）；Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, China（香港大学电子与电气工程系）；Department of Computer Science, City University of Hong Kong, Hong Kong, China（香港城市大学计算机科学系）；Department of Computer Science, The University of Hong Kong, Hong Kong, China（香港大学计算机科学系）；School of Computing, National University of Singapore, Singapore（新加坡国立大学计算机学院）
Remote Awareness of Seafloor Images Collected by AUVs over Low-Bandwidth Communication Links
School of Engineering, University of Southampton（南安普顿大学工程学院）；Institute of Industrial Science, The University of Tokyo（东京大学工业科学研究所）；Ocean Infinity（Ocean Infinity公司）；Marine Autonomous and Robotic Systems, National Oceanography Centre（国家海洋学中心海洋自主与机器人系统）；Voyis Imaging Inc.（Voyis Imaging Inc公司）
Taming Latency and Bandwidth: A Theoretical Framework and Adaptive Algorithm for Communication-Constrained Training
Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Tsinghua University（清华大学）；Shenzhen Technology University（深圳科技大学）；University of Science and Technology of China（中国科学技术大学）
Robust Bandwidth Estimation for Real-Time Communication with Offline Reinforcement Learning
School of Electronic Information and Communications, Huazhong University of Science and Technology, China（电子信息学院，华中科技大学）；Zhongxing Telecommunication Equipment Corporation, China（中兴电信设备有限公司）
Bandwidth-Aware and Overlap-Weighted Compression for Communication-Efficient Federated Learning
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Hong Kong Baptist University（香港浸会大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））
