Rule Mining for Correcting Classification Models
This work addresses the need for controlled model updates in complex systems, though it appears incremental as it builds on existing frequent itemset mining techniques.
The paper tackles the problem of correcting classification models in scenarios where developers need to control specification changes, by proposing correction rule mining to identify and correct inaccurate subpopulations, resulting in an efficient algorithm that finds rules for data collection, output correction, and concept drift analysis.
Machine learning models need to be continually updated or corrected to ensure that the prediction accuracy remains consistently high. In this study, we consider scenarios where developers should be careful to change the prediction results by the model correction, such as when the model is part of a complex system or software. In such scenarios, the developers want to control the specification of the corrections. To achieve this, the developers need to understand which subpopulations of the inputs get inaccurate predictions by the model. Therefore, we propose correction rule mining to acquire a comprehensive list of rules that describe inaccurate subpopulations and how to correct them. We also develop an efficient correction rule mining algorithm that is a combination of frequent itemset mining and a unique pruning technique for correction rules. We observed that the proposed algorithm found various rules which help to collect data insufficiently learned, directly correct model outputs, and analyze concept drift.