Timezone: »

 
Poster
Efficient High-Order Interaction-Aware Feature Selection Based on Conditional Mutual Information
Alexander Shishkin · Anastasia Bezzubtseva · Alexey Drutsa · Ilia Shishkov · Ekaterina Gladkikh · Gleb Gusev · Pavel Serdyukov

Mon Dec 05 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #127
in Monday Posters »

This study introduces a novel feature selection approach CMICOT, which is a further evolution of filter methods with sequential forward selection (SFS) whose scoring functions are based on conditional mutual information (MI). We state and study a novel saddle point (max-min) optimization problem to build a scoring function that is able to identify joint interactions between several features. This method fills the gap of MI-based SFS techniques with high-order dependencies. In this high-dimensional case, the estimation of MI has prohibitively high sample complexity. We mitigate this cost using a greedy approximation and binary representatives what makes our technique able to be effectively used. The superiority of our approach is demonstrated by comparison with recently proposed interaction-aware filters and several interaction-agnostic state-of-the-art ones on ten publicly available benchmark datasets.

Keywords: (Other) Applications · Sparsity and Feature Selection

Author Information

Alexander Shishkin (Yandex)
Anastasia Bezzubtseva (Yandex)
Alexey Drutsa (Yandex)
Ilia Shishkov (Yandex)
Ekaterina Gladkikh (Yandex)
Gleb Gusev (Yandex LLC)
Pavel Serdyukov (Yandex)

More from the Same Authors