Adversarial Learning with Local Coordinate Coding

Jiezhang Cao, Yong Guo, Qingyao Wu, Chunhua Shen, Junzhou Huang, Mingkui Tan
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:707-715, 2018.

Abstract

Generative adversarial networks (GANs) aim to generate realistic data from some prior distribution (e.g., Gaussian noises). However, such prior distribution is often independent of real data and thus may lose semantic information (e.g., geometric structure or content in images) of data. In practice, the semantic information might be represented by some latent distribution learned from data, which, however, is hard to be used for sampling in GANs. In this paper, rather than sampling from the pre-defined prior distribution, we propose a Local Coordinate Coding (LCC) based sampling method to improve GANs. We derive a generalization bound for LCC based GANs and prove that a small dimensional input is sufficient to achieve good generalization. Extensive experiments on various real-world datasets demonstrate the effectiveness of the proposed method.

Cite this Paper


BibTeX
@InProceedings{pmlr-v80-cao18a, title = {Adversarial Learning with Local Coordinate Coding}, author = {Cao, Jiezhang and Guo, Yong and Wu, Qingyao and Shen, Chunhua and Huang, Junzhou and Tan, Mingkui}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {707--715}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/cao18a/cao18a.pdf}, url = {https://proceedings.mlr.press/v80/cao18a.html}, abstract = {Generative adversarial networks (GANs) aim to generate realistic data from some prior distribution (e.g., Gaussian noises). However, such prior distribution is often independent of real data and thus may lose semantic information (e.g., geometric structure or content in images) of data. In practice, the semantic information might be represented by some latent distribution learned from data, which, however, is hard to be used for sampling in GANs. In this paper, rather than sampling from the pre-defined prior distribution, we propose a Local Coordinate Coding (LCC) based sampling method to improve GANs. We derive a generalization bound for LCC based GANs and prove that a small dimensional input is sufficient to achieve good generalization. Extensive experiments on various real-world datasets demonstrate the effectiveness of the proposed method.} }
Endnote
%0 Conference Paper %T Adversarial Learning with Local Coordinate Coding %A Jiezhang Cao %A Yong Guo %A Qingyao Wu %A Chunhua Shen %A Junzhou Huang %A Mingkui Tan %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-cao18a %I PMLR %P 707--715 %U https://proceedings.mlr.press/v80/cao18a.html %V 80 %X Generative adversarial networks (GANs) aim to generate realistic data from some prior distribution (e.g., Gaussian noises). However, such prior distribution is often independent of real data and thus may lose semantic information (e.g., geometric structure or content in images) of data. In practice, the semantic information might be represented by some latent distribution learned from data, which, however, is hard to be used for sampling in GANs. In this paper, rather than sampling from the pre-defined prior distribution, we propose a Local Coordinate Coding (LCC) based sampling method to improve GANs. We derive a generalization bound for LCC based GANs and prove that a small dimensional input is sufficient to achieve good generalization. Extensive experiments on various real-world datasets demonstrate the effectiveness of the proposed method.
APA
Cao, J., Guo, Y., Wu, Q., Shen, C., Huang, J. & Tan, M.. (2018). Adversarial Learning with Local Coordinate Coding. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:707-715 Available from https://proceedings.mlr.press/v80/cao18a.html.

Related Material