Scalable Transfer Evolutionary Optimization: Coping with Big Task Instances

TL;DR

This paper introduces a scalable transfer evolutionary optimization framework capable of handling over 1000 source tasks, improving efficiency and effectiveness in large-scale, sparse, multi-source scenarios.

Contribution

It proposes a novel co-evolutionary framework with two species for joint evolution in knowledge and solution spaces, enabling scalability and online learning in big task-instances.

Findings

Efficiently handles over 1000 source tasks.

Scales well with increasing source tasks.

Effective in sparse source-target relatedness scenarios.

Abstract

In today's digital world, we are faced with an explosion of data and models produced and manipulated by numerous large-scale cloud-based applications. Under such settings, existing transfer evolutionary optimization frameworks grapple with simultaneously satisfying two important quality attributes, namely (1) scalability against a growing number of source tasks and (2) online learning agility against sparsity of relevant sources to the target task of interest. Satisfying these attributes shall facilitate practical deployment of transfer optimization to scenarios with big task-instances, while curbing the threat of negative transfer. While applications of existing algorithms are limited to tens of source tasks, in this paper, we take a quantum leap forward in enabling more than two orders of magnitude scale-up in the number of tasks; i.e., we efficiently handle scenarios beyond 1000 source task-instances. We devise a novel transfer evolutionary optimization framework comprising two co-evolving species for joint evolutions in the space of source knowledge and in the search space of solutions to the target problem. In particular, co-evolution enables the learned knowledge to be orchestrated on the fly, expediting convergence in the target optimization task. We have conducted an extensive series of experiments across a set of practically motivated discrete and continuous optimization examples comprising a large number of source task-instances, of which only a small fraction indicate source-target relatedness. The experimental results show that not only does our proposed framework scale efficiently with a growing number of source tasks but is also effective in capturing relevant knowledge against sparsity of related sources, fulfilling the two salient features of scalability and online learning agility.