(Rex) Devon Hjelm

2018-09-27

ArXiv (prépublication)

Deep Graph Infomax

Petar Veličković

William Fedus

William L. Hamilton

Pietro Lio

We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised ma… (voir plus)nner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs---both derived using established graph convolutional network architectures. The learnt patch representations summarize subgraphs centered around nodes of interest, and can thus be reused for downstream node-wise learning tasks. In contrast to most prior approaches to unsupervised learning with GCNs, DGI does not rely on random walk objectives, and is readily applicable to both transductive and inductive learning setups. We demonstrate competitive performance on a variety of node classification benchmarks, which at times even exceeds the performance of supervised learning.

2018-09-27

ArXiv (prépublication)

Deep Graph Infomax

Petar Veličković

William Fedus

William L. Hamilton

Pietro Lio

2018-09-27

ArXiv (prépublication)

Deep Graph Infomax

Petar Veličković

William Fedus

William L. Hamilton

Pietro Lio

2018-09-27

ArXiv (prépublication)

Deep Graph Infomax

Petar Veličković

William Fedus

William L. Hamilton

Pietro Lio

We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised ma… (voir plus)nner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs---both derived using established graph convolutional network architectures. The learnt patch representations summarize subgraphs centered around nodes of interest, and can thus be reused for downstream node-wise learning tasks. In contrast to most prior approaches to unsupervised learning with GCNs, DGI does not rely on random walk objectives, and is readily applicable to both transductive and inductive learning setups. We demonstrate competitive performance on a variety of node classification benchmarks, which at times even exceeds the performance of supervised learning.

2018-09-27

ArXiv (prépublication)

Deep Graph Infomax

Petar Veličković

William Fedus

William L. Hamilton

Pietro Lio

We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised ma… (voir plus)nner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs---both derived using established graph convolutional network architectures. The learnt patch representations summarize subgraphs centered around nodes of interest, and can thus be reused for downstream node-wise learning tasks. In contrast to most prior approaches to unsupervised learning with GCNs, DGI does not rely on random walk objectives, and is readily applicable to both transductive and inductive learning setups. We demonstrate competitive performance on a variety of node classification benchmarks, which at times even exceeds the performance of supervised learning.

2018-09-27

ArXiv (prépublication)

Deep Graph Infomax

Petar Veličković

William Fedus

William L. Hamilton

Pietro Lio

2018-09-27

ArXiv (prépublication)

Deep Graph Infomax

Petar Veličković

William Fedus

William L. Hamilton

Pietro Lio

2018-09-27

ArXiv (prépublication)

Mutual Information Neural Estimation

Ishmael Belghazi

Aristide Baratin

Sai Rajeswar

Sherjil Ozair

Aaron Courville

We argue that the estimation of mutual information between high dimensional continuous random variables can be achieved by gradient descent … (voir plus)over neural networks. We present a Mutual Information Neural Estimator (MINE) that is linearly scalable in dimensionality as well as in sample size, trainable through back-prop, and strongly consistent. We present a handful of applications on which MINE can be used to minimize or maximize mutual information. We apply MINE to improve adversarially trained generative models. We also use MINE to implement Information Bottleneck, applying it to supervised classification; our results demonstrate substantial improvement in flexibility and performance in these settings.

2018-07-03

Proceedings of the 35th International Conference on Machine Learning (publié)

proceedings.mlr.press

MINE: Mutual Information Neural Estimation

Ishmael Belghazi

Sai Rajeswar

Aristide Baratin

Aaron Courville

This paper presents a Mutual Information Neural Estimator (MINE) that is linearly scalable in dimensionality as well as in sample size. MINE… (voir plus) is back-propable and we prove that it is strongly consistent. We illustrate a handful of applications in which MINE is succesfully applied to enhance the property of generative models in both unsupervised and supervised settings. We apply our framework to estimate the information bottleneck, and apply it in tasks related to supervised classification problems. Our results demonstrate substantial added flexibility and improvement in these settings.

2018-05-04

ICLR.cc/2018/Conference (inconnu)

openreview.net

Boundary Seeking GANs

Athul Jacob

Adam Trischler

Gerry Che

Kyunghyun Cho

Generative adversarial networks are a learning framework that rely on training a discriminator to estimate a measure of difference between a… (voir plus) target and generated distributions. GANs, as normally formulated, rely on the generated samples being completely differentiable w.r.t. the generative parameters, and thus do not work for discrete data. We introduce a method for training GANs with discrete data that uses the estimated difference measure from the discriminator to compute importance weights for generated samples, thus providing a policy gradient for training the generator. The importance weights have a strong connection to the decision boundary of the discriminator, and we call our method boundary-seeking GANs (BGANs). We demonstrate the effectiveness of the proposed algorithm with discrete image and character-based natural language generation. In addition, the boundary-seeking objective extends to continuous data, which can be used to improve stability of training, and we demonstrate this on Celeba, Large-scale Scene Understanding (LSUN) bedrooms, and Imagenet without conditioning.

2018-02-15

International Conference on Learning Representations (publié)

dblp.uni-trier.de

Boundary Seeking GANs

Athul Jacob

Adam Trischler

Gerry Che

Kyunghyun Cho