Publications

Introduction to NIPS 2017 Competition Track

Sergio Escalera

Markus Weimer

Mikhail Burtsev

Valentin Malykh

Varvara Logacheva

Ryan Lowe

Iulian V. Serban

Yoshua Bengio

Alexander Rudnicky

Alan W. Black

Shrimai Prabhumoye

Łukasz Kidziński

Sharada Prasanna Mohanty

Carmichael F. Ong

Jennifer L. Hicks

Sergey Levine

Marcel Salathé

Scott Delp

Iker Huerga

Alexander Grigorenko … (see 19 more)

Leifur Thorbergsson

Anasuya Das

Kyla Nemitz

Jenna Sandker

Stephen King

Alexander S. Ecker

Leon A. Gatys

Matthias Bethge

Jordan Boyd-Graber

Shi Feng

Pedro Rodriguez

Mohit Iyyer

He He

Hal Daumé III

Sean McGregor

Amir Banifatemi

Alexey Kurakin

Ian G Goodfellow

Samy Bengio

2018-09-27

The NIPS '17 Competition: Building Intelligent Systems (published)

doi.org

The First Conversational Intelligence Challenge

Mikhail Burtsev

Varvara Logacheva

Valentin Malykh

Iulian V. Serban

Ryan Lowe

Shrimai Prabhumoye

Alan W. Black

Alexander Rudnicky

Yoshua Bengio

2018-09-27

The NIPS '17 Competition: Building Intelligent Systems (published)

doi.org

Combining adaptive algorithms and hypergradient method: a performance and robustness study

Akram Erraqabi

Nicolas Roux

2018-09-26

(published)

openreview.net

Convergence Properties of Deep Neural Networks on Separable Data

Remi Tachet des Combes

Mohammad Pezeshki

Samira Shabanian

Aaron Courville

Yoshua Bengio

While a lot of progress has been made in recent years, the dynamics of learning in deep nonlinear neural networks remain to this day largely… (see more) misunderstood. In this work, we study the case of binary classification and prove various properties of learning in such networks under strong assumptions such as linear separability of the data. Extending existing results from the linear case, we confirm empirical observations by proving that the classification error also follows a sigmoidal shape in nonlinear architectures. We show that given proper initialization, learning expounds parallel independent modes and that certain regions of parameter space might lead to failed training. We also demonstrate that input norm and features’ frequency in the dataset lead to distinct convergence speeds which might shed some light on the generalization capabilities of deep neural networks. We provide a comparison between the dynamics of learning with cross-entropy and hinge losses, which could prove useful to understand recent progress in the training of generative adversarial networks. Finally, we identify a phenomenon that we baptize gradient starvation where the most frequent features in a dataset prevent the learning of other less frequent but equally informative features.

2018-09-26

(published)

openreview.net

Deep Graph Infomax

Petar Veličković

William Fedus

William L. Hamilton

Pietro Lio

Yoshua Bengio

R Devon Hjelm

We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised ma… (see more)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.

2018-09-26

ArXiv (preprint)

openreview.net

DEFactor: Differentiable Edge Factorization-based Probabilistic Graph Generation

Rim Assouel

Mohamed Ahmed

Marwin Segler

Amir Saffari

Yoshua Bengio

Generating novel molecules with optimal properties is a crucial step in many industries such as drug discovery. Recently, deep generative mo… (see more)dels have shown a promising way of performing de-novo molecular design. Although graph generative models are currently available they either have a graph size dependency in their number of parameters, limiting their use to only very small graphs or are formulated as a sequence of discrete actions needed to construct a graph, making the output graph non-differentiable w.r.t the model parameters, therefore preventing them to be used in scenarios such as conditional graph generation. In this work we propose a model for conditional graph generation that is computationally efficient and enables direct optimisation of the graph. We demonstrate favourable performance of our model on prototype-based molecular graph conditional generation tasks.

2018-09-26

ArXiv (preprint)

openreview.net

On Difficulties of Probability Distillation

Alexandre Lacoste

2018-09-26

(published)

openreview.net

Dopamine: A Research Framework for Deep Reinforcement Learning

Pablo Samuel Castro

Subhodeep Moitra

Carles Gelada

Saurabh Kumar

Bellemare Marc-Emmanuel

Deep reinforcement learning (deep RL) research has grown significantly in recent years. A number of software offerings now exist that provid… (see more)e stable, comprehensive implementations for benchmarking. At the same time, recent deep RL research has become more diverse in its goals. In this paper we introduce Dopamine, a new research framework for deep RL that aims to support some of that diversity. Dopamine is open-source, TensorFlow-based, and provides compact and reliable implementations of some state-of-the-art deep RL agents. We complement this offering with a taxonomy of the different research objectives in deep RL research. While by no means exhaustive, our analysis highlights the heterogeneity of research in the field, and the value of frameworks such as ours.

2018-09-26

ArXiv (preprint)

openreview.net