The Impact of Asynchrony on Parallel Model-Based EAs

Abstract

In a parallel EA one can strictly adhere to the generational clock, and wait for all evaluations in a generation to be done. However, this idle time limits the throughput of the algorithm and wastes computational resources. Alternatively, an EA can be made asynchronous parallel. However, EAs using classic recombination and selection operators (GAs) are known to suffer from an evaluation time bias, which also influences the performance of the approach. Model-Based Evolutionary Algorithms (MBEAs) are more scalable than classic GAs by virtue of capturing the structure of a problem in a model. If this model is learned through linkage learning based on the population, the learned model may also capture biases. Thus, if an asynchronous parallel MBEA is also affected by an evaluation time bias, this could result in learned models to be less suited to solving the problem, reducing performance. Therefore, in this work, we study the impact and presence of evaluation time biases on MBEAs in an asynchronous parallelization setting, and compare this to the biases in GAs. We find that a modern MBEA, GOMEA, is unaffected by evaluation time biases, while the more classical MBEA, ECGA, is affected, much like GAs are. CCS CONCEPTS• Mathematics of computing → Evolutionary algorithms; • Theory of computation → Parallel computing models.

Convolutional neural network architectures

“…Evidence of this effect can be seen in Figure 6 where the mean amount of time spent per generation is significantly lower for CoDeepNEAT-AES than for CoDeepNEAT. While asynchronous EAs are known to have such evaluation bias, and efforts have been developed to avoid it (Guijt et al, 2023), it is not undesirable in the case of neuroevolution. Discovering DNNs that are faster to train is often a secondary goal of many architecture search algorithms, and as Figures 5 and 7 show, CoDeepNEAT-AES is able to achieve the same quality of solutions as CoDeepNEAT while taking much less time.…”