Representation Topology Divergence: A Method for Comparing Neural Network Representations

Serguei Barannikov, Ilya Trofimov, Nikita Balabin, Evgeny Burnaev. Representation Topology Divergence: A Method for Comparing Neural Network Representations. In Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvári, Gang Niu 0001, Sivan Sabato, editors, International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA. Volume 162 of Proceedings of Machine Learning Research, pages 1607-1626, PMLR, 2022. [doi]

Authors

Serguei Barannikov

This author has not been identified. Look up 'Serguei Barannikov' in Google

Ilya Trofimov

This author has not been identified. Look up 'Ilya Trofimov' in Google

Nikita Balabin

This author has not been identified. Look up 'Nikita Balabin' in Google

Evgeny Burnaev

This author has not been identified. It may be one of the following persons: Look up 'Evgeny Burnaev' in Google