An Ensemble Approach to Adaptation-Guided Retrieval

Instance-based learning methods predict the solution of a case from the solutions of similar cases. However, solutions can be generated from less similar cases as well, provided appropriate “case adaptation” rules are available to adjust the prior solutions to account for dissimilarities. In fact, case-based reasoning research on adaptation-guided retrieval (AGR) shows that it may be beneficial to base retrieval decisions primarily on the availability of suitable adaptation knowledge, rather than on similarity. This paper proposes a new method for adaptation-guided retrieval for numerical prediction (regression) tasks. The method, EAGR (ensemble of adaptations-guided retrieval) works by retrieving an ensemble of cases, with a case favored for retrieval if there exists an ensemble of adaptation rules suitable for adapting its solution to the current problem. The solution for the input problem is then calculated by applying each retrieved case’s ensemble of adaptations to that case, and combining the generated values. The approach is evaluated on four sample domains compared to three baseline methods: k-NN, an adaptation-guided retrieval approach, and a previous approach using ensembles of adaptations without adaptation-guided retrieval. EAGR improves accuracy in the tested domains compared to the other methods.