@inproceedings{vasisht2014active,
author = {Vasisht, Deepak and Damianou, Andreas and Varma, Manik and Kapoor, Ashish},
title = {Active Learning for Sparse Bayesian Multilabel Classification},
booktitle = {Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
year = {2014},
month = {August},
abstract = {We study the problem of active learning for multilabel classification. We focus on the real-world scenario where the average number of positive (relevant) labels per data point is small leading to positive label sparsity. Carrying out mutual information based near-optimal active learning in this setting is a challenging task since the computational complexity involved is exponential in the total number of labels. We propose a novel inference algorithm for the sparse Bayesian multilabel model of [17]. The benefit of this alternate inference scheme is that it enables a natural approximation of the mutual information objective. We prove that the approximation leads to an identical solution to the exact optimization problem but at a fraction of the optimization cost. This allows us to carry out ecient, non-myopic, and near-optimal active learning for sparse multilabel classification. Extensive experiments reveal the effectiveness of the method.},
publisher = {ACM - Association for Computing Machinery},
url = {http://approjects.co.za/?big=en-us/research/publication/active-learning-for-sparse-bayesian-multilabel-classification/},
edition = {Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
}