Algorithm Design for Continual Learning in IoT Networks

TL;DR

This paper introduces a novel approach for continual learning in IoT networks by optimizing task routing to minimize forgetting, with proven NP-hardness and efficient approximation algorithms validated through simulations.

Contribution

It formulates the first optimization problem for task routing in continual learning within IoT, providing polynomial-time algorithms with proven approximation ratios.

Findings

Algorithms achieve near-optimal performance in simulations.

Proven NP-hardness of the task routing optimization problem.

Effective approximation ratios for different parameter settings.

Abstract

Continual learning (CL) is a new online learning technique over sequentially generated streaming data from different tasks, aiming to maintain a small forgetting loss on previously-learned tasks. Existing work focuses on reducing the forgetting loss under a given task sequence. However, if similar tasks continuously appear to the end time, the forgetting loss is still huge on prior distinct tasks. In practical IoT networks, an autonomous vehicle to sample data and learn different tasks can route and alter the order of task pattern at increased travelling cost. To our best knowledge, we are the first to study how to opportunistically route the testing object and alter the task sequence in CL. We formulate a new optimization problem and prove it NP-hard. We propose a polynomial-time algorithm to achieve approximation ratios of $\frac{3}{2}$ for underparameterized case and $\frac{3}{2} + r^{1-T}$ for overparameterized case, respectively, where $r:=1-\frac{n}{m}$ is a parameter of feature number $m$ and sample number $n$ and $T$ is the task number. Simulation results verify our algorithm's close-to-optimum performance.