Breaking Inter-Layer Co-Adaptation by Classifier Anonymization

Ikuro Sato, Kohta Ishikawa, Guoqing Liu, Masayuki Tanaka
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:5619-5627, 2019.

Abstract

This study addresses an issue of co-adaptation between a feature extractor and a classifier in a neural network. A naive joint optimization of a feature extractor and a classifier often brings situations in which an excessively complex feature distribution adapted to a very specific classifier degrades the test performance. We introduce a method called Feature-extractor Optimization through Classifier Anonymization (FOCA), which is designed to avoid an explicit co-adaptation between a feature extractor and a particular classifier by using many randomly-generated, weak classifiers during optimization. We put forth a mathematical proposition that states the FOCA features form a point-like distribution within the same class in a class-separable fashion under special conditions. Real-data experiments under more general conditions provide supportive evidences.

Cite this Paper

BibTeX
@InProceedings{pmlr-v97-sato19a, title = {Breaking Inter-Layer Co-Adaptation by Classifier Anonymization}, author = {Sato, Ikuro and Ishikawa, Kohta and Liu, Guoqing and Tanaka, Masayuki}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {5619--5627}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/sato19a/sato19a.pdf}, url = {https://proceedings.mlr.press/v97/sato19a.html}, abstract = {This study addresses an issue of co-adaptation between a feature extractor and a classifier in a neural network. A naive joint optimization of a feature extractor and a classifier often brings situations in which an excessively complex feature distribution adapted to a very specific classifier degrades the test performance. We introduce a method called Feature-extractor Optimization through Classifier Anonymization (FOCA), which is designed to avoid an explicit co-adaptation between a feature extractor and a particular classifier by using many randomly-generated, weak classifiers during optimization. We put forth a mathematical proposition that states the FOCA features form a point-like distribution within the same class in a class-separable fashion under special conditions. Real-data experiments under more general conditions provide supportive evidences.} }
Endnote
%0 Conference Paper %T Breaking Inter-Layer Co-Adaptation by Classifier Anonymization %A Ikuro Sato %A Kohta Ishikawa %A Guoqing Liu %A Masayuki Tanaka %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-sato19a %I PMLR %P 5619--5627 %U https://proceedings.mlr.press/v97/sato19a.html %V 97 %X This study addresses an issue of co-adaptation between a feature extractor and a classifier in a neural network. A naive joint optimization of a feature extractor and a classifier often brings situations in which an excessively complex feature distribution adapted to a very specific classifier degrades the test performance. We introduce a method called Feature-extractor Optimization through Classifier Anonymization (FOCA), which is designed to avoid an explicit co-adaptation between a feature extractor and a particular classifier by using many randomly-generated, weak classifiers during optimization. We put forth a mathematical proposition that states the FOCA features form a point-like distribution within the same class in a class-separable fashion under special conditions. Real-data experiments under more general conditions provide supportive evidences.
APA
Sato, I., Ishikawa, K., Liu, G. & Tanaka, M.. (2019). Breaking Inter-Layer Co-Adaptation by Classifier Anonymization. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:5619-5627 Available from https://proceedings.mlr.press/v97/sato19a.html.

Related Material