Learn to Adapt to New Environment from Past Experience and Few Pilot

TL;DR

This paper introduces an attention-based few-shot learning approach for deep learning in communications, enabling models to adapt to new environments with minimal training data by leveraging past learning experiences.

Contribution

It proposes a novel attention-based method that incorporates learning experience from known environments to reduce training data needs in new environments.

Findings

Achieves better channel estimation performance with few pilot blocks.

Effectively learns environments with different power delay profiles.

Reduces data collection and retraining resources.

Abstract

In recent years, deep learning has been widely applied in communications and achieved remarkable performance improvement. Most of the existing works are based on data-driven deep learning, which requires a significant amount of training data for the communication model to adapt to new environments and results in huge computing resources for collecting data and retraining the model. In this paper, we will significantly reduce the required amount of training data for new environments by leveraging the learning experience from the known environments. Therefore, we introduce few-shot learning to enable the communication model to generalize to new environments, which is realized by an attention-based method. With the attention network embedded into the deep learning-based communication model, environments with different power delay profiles can be learnt together in the training process, which is called the learning experience. By exploiting the learning experience, the communication model only requires few pilot blocks to perform well in the new environment. Through an example of deep-learning-based channel estimation, we demonstrate that this novel design method achieves better performance than the existing data-driven approach designed for few-shot learning.