Continual Learning of Feedback-based Molecular Communication

TL;DR

This paper introduces a continual learning approach for sequentially estimating the performance of feedback-based molecular communication protocols, improving accuracy without forgetting past tasks.

Contribution

It demonstrates the application of continual learning algorithms to molecular communication, showing how they can effectively learn from sequential simulation data.

Findings

CL-based estimators improve estimation accuracy across various settings.

The proposed methods enhance neural network performance with different computational costs.

CL enables effective learning from continuous streams of molecular communication simulations.

Abstract

This paper proposes and evaluates a new performance estimation method that leverages continual learning (CL) algorithms to carry out sequential simulation experiments for a feedback-based molecular communication protocol. As the protocol is sequentially examined in various experimental settings, the proposed CL-based performance estimators incrementally learn a series of unexperienced estimation tasks without compromising those that have been learned in the past. They are designed to work on a standard neural network architecture by customizing regularization and replay strategies in the loss function. Experimental results demonstrate that the proposed estimators can effectively learn on a continuous stream of simulation results and enhance the baseline neural network by improving estimation accuracy at a variety of computational costs. This paper's contribution is to establish the implications of CL in the field of molecular communication.