Publications

Learning representations of Logical Formulae using Graph Neural Networks
Xavier Glorot
Ankit Anand
Eser Aygün
Shibl Mourad
Pushmeet Kohli
Doina Precup
We explore the use of Graph Neural Networks(GNNs) for learning representations of propositional and first-order logical formulae. Tradition… (voir plus)al non-graphical based approaches like CNNs and LSTMs do not exploit invariant properties like variable renaming and order invariance predominantly present in logical formulae. In this work, we explicitly try to encode these logical invariances using GNNs. We use the task of entailment proposed in Evans et al. [2018] for propositional logic. We also explore our approach for the task of proof length prediction in first-order logic. We use the Mizar-40 dataset to evaluate several representation learning approaches for proof length prediction task. We observe that GNNs significantly outperform the other traditional approaches on both these tasks.
2018-12-31
(publié)
www.semanticscholar.org
LF-PPL: A Low-Level First Order Probabilistic Programming Language for Non-Differentiable Models
Yuanshuo Zhou
Bradley Gram-Hansen
Tobias Kohn
Tom Rainforth
Hongseok Yang
Frank N. Wood
We develop a new Low-level, First-order Probabilistic Programming Language~(LF-PPL) suited for models containing a mix of continuous, discre… (voir plus)te, and/or piecewise-continuous variables. The key success of this language and its compilation scheme is in its ability to automatically distinguish parameters the density function is discontinuous with respect to, while further providing runtime checks for boundary crossings. This enables the introduction of new inference engines that are able to exploit gradient information, while remaining efficient for models which are not everywhere differentiable. We demonstrate this ability by incorporating a discontinuous Hamiltonian Monte Carlo (DHMC) inference engine that is able to deliver automated and efficient inference for non-differentiable models. Our system is backed up by a mathematical formalism that ensures that any model expressed in this language has a density with measure zero discontinuities to maintain the validity of the inference engine.
2018-12-31
AISTATS (publié)
proceedings.mlr.press
proceedings.mlr.press
MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
Kundan Kumar
Rithesh Kumar
Thibault De Boissière
Lucas Gestin
Wei Zhen Teoh
Jose Sotelo
Alexandre De Brébisson
Yoshua Bengio
Aaron Courville
2018-12-31
Advances in Neural Information Processing Systems 32 (NeurIPS 2019) (publié)
arxiv.org
arxiv.org
Meta-Learning State-based Eligibility Traces for More Sample-Efficient Policy Evaluation
Mingde Zhao
Ian Porada
Sitao Luan
Xiao-Wen Chang
Doina Precup
Temporal-Difference (TD) learning is a standard and very successful reinforcement learning approach, at the core of both algorithms that lea… (voir plus)rn the value of a given policy, as well as algorithms which learn how to improve policies. TD-learning with eligibility traces provides a way to boost sample efficiency by temporal credit assignment, i.e. deciding which portion of a reward should be assigned to predecessor states that occurred at different previous times, controlled by a parameter
2018-12-31
arXiv (prépublication)
doi.org
arxiv.org
Multi-objective training of Generative Adversarial Networks with multiple discriminators
Isabela Albuquerque
Joao Monteiro
Thang Doan
Breandan Considine
Tiago Falk
Ioannis Mitliagkas
Recent literature has demonstrated promising results for training Generative Adversarial Networks by employing a set of discriminators, in c… (voir plus)ontrast to the traditional game involving one generator against a single adversary. Such methods perform single-objective optimization on some simple consolidation of the losses, e.g. an arithmetic average. In this work, we revisit the multiple-discriminator setting by framing the simultaneous minimization of losses provided by different models as a multi-objective optimization problem. Specifically, we evaluate the performance of multiple gradient descent and the hypervolume maximization algorithm on a number of different datasets. Moreover, we argue that the previously proposed methods and hypervolume maximization can all be seen as variations of multiple gradient descent in which the update direction can be computed efficiently. Our results indicate that hypervolume maximization presents a better compromise between sample quality and computational cost than previous methods.
2018-12-31
ICML (publié)
proceedings.mlr.press
proceedings.mlr.press
Neural Multisensory Scene Inference
Jae Hyun Lim
Pedro O. Pinheiro
Negar Rostamzadeh
Christopher Pal
Sungjin Ahn
For embodied agents to infer representations of the underlying 3D physical world they inhabit, they should efficiently combine multisensory … (voir plus)cues from numerous trials, e.g., by looking at and touching objects. Despite its importance, multisensory 3D scene representation learning has received less attention compared to the unimodal setting. In this paper, we propose the Generative Multisensory Network (GMN) for learning latent representations of 3D scenes which are partially observable through multiple sensory modalities. We also introduce a novel method, called the Amortized Product-of-Experts, to improve the computational efficiency and the robustness to unseen combinations of modalities at test time. Experimental results demonstrate that the proposed model can efficiently infer robust modality-invariant 3D-scene representations from arbitrary combinations of modalities and perform accurate cross-modal generation. To perform this exploration we have also developed a novel multi-sensory simulation environment for embodied agents.
2018-12-31
NeurIPS (publié)
arxiv.org
arxiv.org
Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks
Yikang Shen
Shawn Tan
Alessandro Sordoni
Aaron Courville
Natural language is hierarchically structured: smaller units (e.g., phrases) are nested within larger units (e.g., clauses). When a larger c… (voir plus)onstituent ends, all of the smaller constituents that are nested within it must also be closed. While the standard LSTM architecture allows different neurons to track information at different time scales, it does not have an explicit bias towards modeling a hierarchy of constituents. This paper proposes to add such an inductive bias by ordering the neurons; a vector of master input and forget gates ensures that when a given neuron is updated, all the neurons that follow it in the ordering are also updated. Our novel recurrent architecture, ordered neurons LSTM (ON-LSTM), achieves good performance on four different tasks: language modeling, unsupervised parsing, targeted syntactic evaluation, and logical inference.
2018-12-31
ICLR.cc/2019/Conference (présentation orale)
openreview.net
openreview.net
Prediction of Disease Progression in Multiple Sclerosis Patients using Deep Learning Analysis of MRI Data
Adrian Tousignant
Paul Lemaitre
Doina Precup
Douglas L. Arnold
Tal Arbel
2018-12-31
International Conference on Medical Imaging with Deep Learning (publié)
proceedings.mlr.press
proceedings.mlr.press
No Press Diplomacy: Modeling Multi-Agent Gameplay
Philip Paquette
Yuchen Lu
Steven Bocco
Max O. Smith
Satya Ortiz-Gagné
Jonathan K. Kummerfeld
Satinder Singh
Joelle Pineau
Aaron Courville
Diplomacy is a seven-player non-stochastic, non-cooperative game, where agents acquire resources through a mix of teamwork and betrayal. Rel… (voir plus)iance on trust and coordination makes Diplomacy the first non-cooperative multi-agent benchmark for complex sequential social dilemmas in a rich environment. In this work, we focus on training an agent that learns to play the No Press version of Diplomacy where there is no dedicated communication channel between players. We present DipNet, a neural-network-based policy model for No Press Diplomacy. The model was trained on a new dataset of more than 150,000 human games. Our model is trained by supervised learning (SL) from expert trajectories, which is then used to initialize a reinforcement learning (RL) agent trained through self-play. Both the SL and RL agents demonstrate state-of-the-art No Press performance by beating popular rule-based bots.
2018-12-31
Advances in Neural Information Processing Systems 32 (NeurIPS 2019) (publié)
doi.org
arxiv.org
Probability Distillation: A Caveat and Alternatives
Chin-wei Huang
Faruk Ahmed
Kundan Kumar
Alexandre Lacoste
Aaron Courville
Due to Van den Oord et al. (2018), probability distillation has recently been of interest to deep learning practitioners, where, as a practi… (voir plus)cal workaround for deploying autoregressive models in real-time applications, a student network is used to obtain quality samples in parallel. We identify a pathological optimization issue with the adopted stochastic minimization of the reverse-KL divergence: the curse of dimensionality results in a skewed gradient distribution that renders training inefficient. This means that KL-based “evaluative” training can be susceptible to poor exploration if the target distribution is highly structured. We then explore alternative principles for distillation, including one with an “instructive” signal, and show that it is possible to achieve qualitatively better results than with KL minimization.
2018-12-31
Conference on Uncertainty in Artificial Intelligence (publié)
proceedings.mlr.press
proceedings.mlr.press
Quaternion Recurrent Neural Networks
Titouan Parcollet
Mirco Ravanaelli
Mohamed Morchid
Georges Linarès
Chiheb Trabelsi
Renato De Mori
Yoshua Bengio
Recurrent neural networks (RNNs) are powerful architectures to model sequential data, due to their capability to learn short and long-term d… (voir plus)ependencies between the basic elements of a sequence. Nonetheless, popular tasks such as speech or images recognition, involve multi-dimensional input features that are characterized by strong internal dependencies between the dimensions of the input vector. We propose a novel quaternion recurrent neural network (QRNN), alongside with a quaternion long-short term memory neural network (QLSTM), that take into account both the external relations and these internal structural dependencies with the quaternion algebra. Similarly to capsules, quaternions allow the QRNN to code internal dependencies by composing and processing multidimensional features as single entities, while the recurrent operation reveals correlations between the elements composing the sequence. We show that both QRNN and QLSTM achieve better performances than RNN and LSTM in a realistic application of automatic speech recognition. Finally, we show that QRNN and QLSTM reduce by a maximum factor of 3.3x the number of free parameters needed, compared to real-valued RNNs and LSTMs to reach better results, leading to a more compact representation of the relevant information.
2018-12-31
ICLR.cc/2019/Conference (poster)
openreview.net
openreview.net
Real-Time Reinforcement Learning
Simon Ramstedt
Christopher Pal
2018-12-31
Advances in Neural Information Processing Systems 32 (NeurIPS 2019) (publié)
arxiv.org
arxiv.org