Advances in Autoencoders (AEs)

Posted 2020-12-16 mlsquare

---

 

Announcements

- This repository provides references to recent advances in autoencoders (AEs), and will be updated once every month with the hope of expediting the development of this field.

- The main content of his repository consists of three components: (0) tutorials and reviews; (1) empirical advances section which contains references to various autoencoders of different architectures; (2) theoretical advances section which contains references to theoretical studies of AEs such as performance guarantees; (3) applications section which contains references to applications of AEs in different fields such as representation learning.

- This repository won‘t be possible without the efforts from many contributors who are listed in the end. If you want to contribute to this repository, you can simply put the reference information in the comment for this repository or send us an email. Please follow the following formats to help us: (1) send emails to [e-mail] ; (2) set the email title as "Refrences_AE_Institute"; (3) set the references format as Vancouver (available in Google Scholar) with hyperlinks to the reference and its implementation (if it‘s available), i.e.,

Kramer MA. Nonlinear principal component analysis using autoassociative neural networks. AIChE journal. 1991 Feb;37(2):233-43.

Kingma DP, Welling M. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114. 2013 Dec 20. Github

 

- If you have any constructive suggestions, please leave them as comments to this repository.

 

---

 

Tutorials and Reviews

- Zhang, G., Liu, Y. and Jin, X., 2020. A survey of autoencoder-based recommender systems. Frontiers of Computer Science, pp.1-21.

- Tschannen M, Bachem O, Lucic M. Recent advances in autoencoder-based representation learning. arXiv preprint arXiv:1812.05069. 2018 Dec 12.

 

To Be Added

 

---

 

Empirical Advances

 

To Be Added

---

 

Applications

To Be Added

---

Contributors

This repository will be impossible without the contributions from the following:

* UserID, Affiliation, contributing since, number of reference contribution

 

To Be Added

---

References

To Be Added