TY - GEN
T1 - Predict and constrain
T2 - 35th International Conference on Machine Learning, ICML 2018
AU - Brukhim, Nataly
AU - Globerson, Amir
N1 - Publisher Copyright:
© 2018 by the Authors. All rights reserved.
PY - 2018
Y1 - 2018
N2 - Many machine learning problems require the prediction of multi-dimensional labels. Such structured prediction models can benefit from modeling dependencies between labels. Recently, several deep learning approaches to structured prediction have been proposed. Here we focus on capturing cardinality constraints in such models. Namely, constraining the number of non-zero labels that the model outputs. Such constraints have proven very useful in previous structured prediction approaches, but it is a challenge to introduce them into a deep learning framework. Here we show how to do this via a novel deep architecture. Our approach outperforms strong baselines, achieving state-of-the-art results on multi-label classification benchmarks.
AB - Many machine learning problems require the prediction of multi-dimensional labels. Such structured prediction models can benefit from modeling dependencies between labels. Recently, several deep learning approaches to structured prediction have been proposed. Here we focus on capturing cardinality constraints in such models. Namely, constraining the number of non-zero labels that the model outputs. Such constraints have proven very useful in previous structured prediction approaches, but it is a challenge to introduce them into a deep learning framework. Here we show how to do this via a novel deep architecture. Our approach outperforms strong baselines, achieving state-of-the-art results on multi-label classification benchmarks.
UR - http://www.scopus.com/inward/record.url?scp=85057281800&partnerID=8YFLogxK
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85057281800
T3 - 35th International Conference on Machine Learning, ICML 2018
SP - 1046
EP - 1054
BT - 35th International Conference on Machine Learning, ICML 2018
A2 - Dy, Jennifer
A2 - Krause, Andreas
PB - International Machine Learning Society (IMLS)
Y2 - 10 July 2018 through 15 July 2018
ER -