Geometry-Aware Active Learning of Pattern Rankings via Choquet-Based Aggregation
This work addresses pattern mining for users needing efficient ranking, though it appears incremental by building on existing aggregation methods.
The paper tackles the pattern explosion problem in pattern mining by introducing an interactive learning framework that models user preferences with a Choquet integral and uses geometry-aware query selection to improve efficiency. Experiments on UCI datasets show it outperforms existing methods like ChoquetRank, achieving better ranking accuracy with fewer user interactions.
We address the pattern explosion problem in pattern mining by proposing an interactive learning framework that combines nonlinear utility aggregation with geometry-aware query selection. Our method models user preferences through a Choquet integral over multiple interestingness measures and exploits the geometric structure of the version space to guide the selection of informative comparisons. A branch-and-bound strategy with tight distance bounds enables efficient identification of queries near the decision boundary. Experiments on UCI datasets show that our approach outperforms existing methods such as ChoquetRank, achieving better ranking accuracy with fewer user interactions.