Autoencoding any Data through Kernel Autoencoders

Laforgue, Pierre; Clémençon, Stephan; d’Alché‐Buc, Florence

doi:10.48550/arxiv.1805.11028

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Auto-encoders and derivations Goodfellow et al (2016); Laforgue et al (2018); Fard et al (2018) form a subclass of neural networks whose purpose is to build a suitable representation by learning encoding and decoding functions which capture the core properties of the input data. An adversarial auto-encoder (see Makhzani et al (2015)) is a specific kind of auto-encoders where the encoder plays the role of the generator of an adversarial network.…”

Section: Adversarial Learningmentioning

confidence: 99%

Heavy-tailed Representations, Text Polarity Classification & Data Augmentation

Jalalzai¹,

Colombo²,

Clavel³

et al. 2020

Preprint

View full text Add to dashboard Cite

The dominant approaches to text representation in natural language rely on learning embeddings on massive corpora which have convenient properties such as compositionality and distance preservation. In this paper, we develop a novel method to learn a heavy-tailed embedding with desirable regularity properties regarding the distributional tails, which allows to analyze the points far away from the distribution bulk using the framework of multivariate extreme value theory. In particular, a classifier dedicated to the tails of the proposed embedding is obtained which performance outperforms the baseline. This classifier exhibits a scale invariance property which we leverage by introducing a novel text generation method for label preserving dataset augmentation. Numerical experiments on synthetic and real text data demonstrate the relevance of the proposed framework and confirm that this method generates meaningful sentences with controllable attribute, e.g. positive or negative sentiment.

show abstract

Section: Adversarial Learningmentioning

confidence: 99%