Algorithm Design for Continual Learning in IoT Networks
This addresses continual learning efficiency for IoT networks like autonomous vehicles, though it appears incremental as it builds on existing CL work by adding routing optimization.
The paper tackles the problem of huge forgetting loss in continual learning when similar tasks appear continuously, by studying how to opportunistically route testing objects to alter task sequences in IoT networks. They formulate an NP-hard optimization problem and propose a polynomial-time algorithm achieving approximation ratios of 3/2 for underparameterized cases and 3/2 + r^(1-T) for overparameterized cases, with simulations showing close-to-optimum performance.
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.