AdaFlock: Adaptive Feature Discovery for Human-in-the-loop Predictive Modeling

Authors

  • Ryusuke Takahama scouty Inc.
  • Yukino Baba Kyoto University
  • Nobuyuki Shimizu Yahoo Japan Corporation
  • Sumio Fujita Yahoo Japan Corporation
  • Hisashi Kashima Kyoto University; RIKEN Center for AIP

Abstract

Feature engineering is the key to successful application of machine learning algorithms to real-world data. The discovery of informative features often requires domain knowledge or human inspiration, and data scientists expend a certain amount of effort into exploring feature spaces. Crowdsourcing is considered a promising approach for allowing many people to be involved in feature engineering; however, there is a demand for a sophisticated strategy that enables us to acquire good features at a reasonable crowdsourcing cost. In this paper, we present a novel algorithm called AdaFlock to efficiently obtain informative features through crowdsourcing. AdaFlock is inspired by AdaBoost, which iteratively trains classifiers by increasing the weights of samples misclassified by previous classifiers. AdaFlock iteratively generates informative features; at each iteration of AdaFlock, crowdsourcing workers are shown samples selected according to the classification errors of the current classifiers and are asked to generate new features that are helpful for correctly classifying the given examples. The results of our experiments conducted using real datasets indicate that AdaFlock successfully discovers informative features with fewer iterations and achieves high classification accuracy.

Downloads

Published

2018-04-25

How to Cite

Takahama, R., Baba, Y., Shimizu, N., Fujita, S., & Kashima, H. (2018). AdaFlock: Adaptive Feature Discovery for Human-in-the-loop Predictive Modeling. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11509

Issue

Section

AAAI Technical Track: Human-Computation and Crowd Sourcing