TY - JOUR
T1 - Improved Representation Learning Through Tensorized Autoencoders
AU - Esser, Pascal
AU - Mukherjee, Satyaki
AU - Sabanayagam, Mahalakshmi
AU - Ghoshdastidar, Debarghya
N1 - Publisher Copyright:
Copyright © 2023 by the author(s)
PY - 2023
Y1 - 2023
N2 - The central question in representation learning is what constitutes a good or meaningful representation. In this work we argue that if we consider data with inherent cluster structures, where clusters can be characterized through different means and covariances, those data structures should be represented in the embedding as well. While Autoencoders (AE) are widely used in practice for unsupervised representation learning, they do not fulfil the above condition on the embedding as they obtain a single representation of the data. To overcome this we propose a meta-algorithm that can be used to extend an arbitrary AE architecture to a tensorized version (TAE) that allows for learning cluster-specific embeddings while simultaneously learning the cluster assignment. For the linear setting we prove that TAE can recover the principle components of the different clusters in contrast to principle component of the entire data recovered by a standard AE. We validate this on planted models and for general, non-linear and convolutional AEs we empirically illustrate that tensorizing the AE is beneficial in clustering and de-noising tasks.
AB - The central question in representation learning is what constitutes a good or meaningful representation. In this work we argue that if we consider data with inherent cluster structures, where clusters can be characterized through different means and covariances, those data structures should be represented in the embedding as well. While Autoencoders (AE) are widely used in practice for unsupervised representation learning, they do not fulfil the above condition on the embedding as they obtain a single representation of the data. To overcome this we propose a meta-algorithm that can be used to extend an arbitrary AE architecture to a tensorized version (TAE) that allows for learning cluster-specific embeddings while simultaneously learning the cluster assignment. For the linear setting we prove that TAE can recover the principle components of the different clusters in contrast to principle component of the entire data recovered by a standard AE. We validate this on planted models and for general, non-linear and convolutional AEs we empirically illustrate that tensorizing the AE is beneficial in clustering and de-noising tasks.
UR - http://www.scopus.com/inward/record.url?scp=85165207948&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:85165207948
SN - 2640-3498
VL - 206
SP - 8294
EP - 8307
JO - Proceedings of Machine Learning Research
JF - Proceedings of Machine Learning Research
T2 - 26th International Conference on Artificial Intelligence and Statistics, AISTATS 2023
Y2 - 25 April 2023 through 27 April 2023
ER -