DeepAI AI Chat
Log In Sign Up

Scalable Transfer Evolutionary Optimization: Coping with Big Task Instances

by   Mojtaba Shakeri, et al.

In today's digital world, we are confronted with an explosion of data and models produced and manipulated by numerous large-scale IoT/cloud-based applications. Under such settings, existing transfer evolutionary optimization frameworks grapple with satisfying two important quality attributes, namely scalability against a growing number of source tasks and 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 big source instances as well as simultaneously 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 two orders of magnitude scale-up in the number of tasks; i.e., we efficiently handle scenarios with up to thousands of source problem 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 problem instances, of which only a small fraction show source-target relatedness. The experimental results strongly validate the efficacy of our proposed framework with two salient features of scalability and online learning agility.


page 1

page 9


Transfer from Multiple MDPs

Transfer reinforcement learning (RL) methods leverage on the experience ...

Learning to Transfer Learn

We propose a novel framework, learning to transfer learn (L2TL), to impr...

Self-adaptive Multi-task Particle Swarm Optimization

Multi-task optimization (MTO) studies how to simultaneously solve multip...

Incentive Compatible Pareto Alignment for Multi-Source Large Graphs

In this paper, we focus on learning effective entity matching models ove...

Scalable Neural Data Server: A Data Recommender for Transfer Learning

Absence of large-scale labeled data in the practitioner's target domain ...

Accumulating Knowledge for Lifelong Online Learning

Lifelong learning can be viewed as a continuous transfer learning proced...