Improving system performance in case-based iterative optimization through knowledge filtering

Adding knowledge to a knowledge-based system is not monotonically bene cial. We discuss and experimentally validate this observation in the context of CABINS, a system that learns control knowledge for iterative repair in ill-structured optimization problems. In CAB-INS, situation-dependent user's decisions that guide the repair process are captured in cases together with contextual problem information. During iterative revision in CABINS, cases are exploited for both selection of repair actions and evaluation of repair results. In this paper, we experimentally demonstrated that unltered learned knowledge can degrade problem solving performance. We developed and experimentally evaluated the e ectiveness of a set of knowledge ltering strategies that are designed to increase problem solving e ciency of the intractable iterative optimization process without sacri cing solution quality. These knowledge ltering strategies utilize progressive case base retrievals and failure information to (1) validate the e ectiveness of selected repair actions and (2) give-up further repair if the likelihood of success is low. The ltering strategies were experimentally evaluated in the context of job-shop scheduling, a well known ill-structured problem.