Meta-Learning to Communicate: Fast End-to-End Training for Fading Channels

Abstract

When a channel model is available, learning how to communicate on fading noisy channels can be formulated as the (unsupervised) training of an autoencoder consisting of the cascade of encoder, channel, and decoder. An important limitation of the approach is that training should be generally carried out from scratch for each new channel. To cope with this problem, prior works considered joint training over multiple channels with the aim of finding a single pair of encoder and decoder that works well on a class of channels. As a result, joint training ideally mimics the operation of non-coherent transmission schemes. In this paper, we propose to obviate the limitations of joint training via meta-learning: Rather than training a common model for all channels, meta-learning finds a common initialization vector that enables fast training on any channel. The approach is validated via numerical results, demonstrating significant training speed-ups, with effective encoders and decoders obtained with as little as one iteration of Stochastic Gradient Descent.

arXiv commentsubmitted for conference publication

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Deep Joint Source-Channel Coding for Wireless Image Transmission
• Deep Learning-Based Communication Over the Air
• Learning to Demodulate from Few Pilots via Offline and Online Meta-Learning
• Monte Carlo Gradient Estimation in Machine Learning

Cited by in corpus (11)

• Learning to Demodulate from Few Pilots via Offline and Online Meta-Learning
• From Learning to Meta-Learning: Reduced Training Overhead and Complexity for Communication Systems
• End-to-End Fast Training of Communication Links Without a Channel Model via Online Meta-Learning
• End-to-End Learning for VCSEL-based Optical Interconnects: State-of-the-Art, Challenges, and Opportunities
• Embedding Model Based Fast Meta Learning for Downlink Beamforming Adaptation
• Transfer Learning and Meta Learning Based Fast Downlink Beamforming Adaptation
• Semantic Communication Systems for Speech Transmission
• Learning-to-Learn the Wave Angle Estimation
• Meta-ViterbiNet: Online Meta-Learned Viterbi Equalization for Non-Stationary Channels
• Meta-Reinforcement Learning for Trajectory Design in Wireless UAV Networks
• End-to-end Learning of Waveform Generation and Detection for Radar Systems