Embedding with Autoencoder Regularization

48 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

NetWalk: A Flexible Deep Embedding Approach for Anomaly Detection in Dynamic Networks (2018, background): “Recent advances in word embedding [8, 9, 22, 25, 26, 39, 41] open a new way to learn representations for words.”
Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributions (2018, methodology): “ent space to be similar to the pairwise distances of the minibatch in the original high-dimensional space. Similar methods for preserving within-batch structure have previously been used in both AEs (Yu et al., 2013) and GANs (Benaim & Wolf, 2017). 5 = 0:5, ˙ 25. We allow interpolations to go pa”