291 citations · 328 across the 6 of their papers we have counts for
Showing stat.MLShow all
3 papers · 1 filter
stat.ML2021★ 1 cited
Disentanglement Analysis with Partial Information Decomposition
Seiya Tokui, Issei Sato
We propose a framework to analyze how multivariate representations disentangle ground-truth generative factors. A quantitative analysis of disentanglement has been based on metrics…
stat.ML2017★ 291 cited
Learning Discrete Representations via Information Maximizing Self-Augmented Training
Weihua Hu, Takeru Miyato, Seiya Tokui +2
Learning discrete representations of data is a central machine learning task because of the compactness of the representations and ease of interpretation. The task includes cluster…
stat.ML2016★ 8 cited
Reparameterization trick for discrete variables
Seiya Tokui, Issei sato
Low-variance gradient estimation is crucial for learning directed graphical models parameterized by neural networks, where the reparameterization trick is widely used for those wit…