Publications

On the Iterative Refinement of Densely Connected Representation Levels for Semantic Segmentation
Arantxa Casanova
Guillem Cucurull
Michal Drozdzal
Adriana Romero
Yoshua Bengio
State-of-the-art semantic segmentation approaches increase the receptive field of their models by using either a downsampling path composed … (voir plus)of poolings/strided convolutions or successive dilated convolutions. However, it is not clear which operation leads to best results. In this paper, we systematically study the differences introduced by distinct receptive field enlargement methods and their impact on the performance of a novel architecture, called Fully Convolutional DenseResNet (FC-DRN). FC-DRN has a densely connected backbone composed of residual networks. Following standard image segmentation architectures, receptive field enlargement operations that change the representation level are interleaved among residual networks. This allows the model to exploit the benefits of both residual and dense connectivity patterns, namely: gradient flow, iterative refinement of representations, multi-scale feature combination and deep supervision. In order to highlight the potential of our model, we test it on the challenging CamVid urban scene understanding benchmark and make the following observations: 1) downsampling operations outperform dilations when the model is trained from scratch, 2) dilations are useful during the finetuning step of the model, 3) coarser representations require less refinement steps, and 4) ResNets (by model construction) are good regularizers, since they can reduce the model capacity when needed. Finally, we compare our architecture to alternative methods and report state-of-the-art result on the Camvid dataset, with at least twice fewer parameters.
2018-06-17
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (publié)
doi.org
arxiv.org
Towards Gene Expression Convolutions using Gene Interaction Graphs
Francis Dutil
Joseph Paul Cohen
Martin Weiss
Georgy Derevyanko
Yoshua Bengio
We study the challenges of applying deep learning to gene expression data. We find experimentally that there exists non-linear signal in the… (voir plus) data, however is it not discovered automatically given the noise and low numbers of samples used in most research. We discuss how gene interaction graphs (same pathway, protein-protein, co-expression, or research paper text association) can be used to impose a bias on a deep model similar to the spatial bias imposed by convolutions on an image. We explore the usage of Graph Convolutional Neural Networks coupled with dropout and gene embeddings to utilize the graph information. We find this approach provides an advantage for particular tasks in a low data regime but is very dependent on the quality of the graph used. We conclude that more work should be done in this direction. We design experiments that show why existing methods fail to capture signal that is present in the data when features are added which clearly isolates the problem that needs to be addressed.
2018-06-17
ArXiv (prépublication)
arxiv.org
arxiv.org
Manifold Mixup: Better Representations by Interpolating Hidden States
Vikas Verma
Alex Lamb
Christopher Beckham
Aaron Courville
Ioannis Mitliagkas
Yoshua Bengio
Deep neural networks excel at learning the training data, but often provide incorrect and confident predictions when evaluated on slightly d… (voir plus)ifferent test examples. This includes distribution shifts, outliers, and adversarial examples. To address these issues, we propose Manifold Mixup, a simple regularizer that encourages neural networks to predict less confidently on interpolations of hidden representations. Manifold Mixup leverages semantic interpolations as additional training signal, obtaining neural networks with smoother decision boundaries at multiple levels of representation. As a result, neural networks trained with Manifold Mixup learn class-representations with fewer directions of variance. We prove theory on why this flattening happens under ideal conditions, validate it on practical situations, and connect it to previous works on information theory and generalization. In spite of incurring no significant computation and being implemented in a few lines of code, Manifold Mixup improves strong baselines in supervised learning, robustness to single-step adversarial attacks, and test log-likelihood.
2018-06-12
arXiv.org (prépublication)
doi.org
arxiv.org
Learning to rank for censored survival data
Margaux Luck
Tristan Sylvain
Joseph Paul Cohen
Heloise Cardinal
Andrea Lodi
Yoshua Bengio
Survival analysis is a type of semi-supervised ranking task where the target output (the survival time) is often right-censored. Utilizing t… (voir plus)his information is a challenge because it is not obvious how to correctly incorporate these censored examples into a model. We study how three categories of loss functions, namely partial likelihood methods, rank methods, and our classification method based on a Wasserstein metric (WM) and the non-parametric Kaplan Meier estimate of the probability density to impute the labels of censored examples, can take advantage of this information. The proposed method allows us to have a model that predict the probability distribution of an event. If a clinician had access to the detailed probability of an event over time this would help in treatment planning. For example, determining if the risk of kidney graft rejection is constant or peaked after some time. Also, we demonstrate that this approach directly optimizes the expected C-index which is the most common evaluation metric for ranking survival models.
2018-06-05
ArXiv (prépublication)
arxiv.org
arxiv.org
Diffusion Models
Saeid Naderiparizi
painting of an artificial intelligent agent
2018-06-04
Financial Econometrics (publié)
doi.org
Coarse Lexical Frame Acquisition at the Syntax–Semantics Interface Using a Latent-Variable PCFG Model
Laura Kallmeyer
Behrang QasemiZadeh
Jackie CK Cheung
We present a method for unsupervised lexical frame acquisition at the syntax–semantics interface. Given a set of input strings derived fro… (voir plus)m dependency parses, our method generates a set of clusters that resemble lexical frame structures. Our work is motivated not only by its practical applications (e.g., to build, or expand the coverage of lexical frame databases), but also to gain linguistic insight into frame structures with respect to lexical distributions in relation to grammatical structures. We model our task using a hierarchical Bayesian network and employ tools and methods from latent variable probabilistic context free grammars (L-PCFGs) for statistical inference and parameter fitting, for which we propose a new split and merge procedure. We show that our model outperforms several baselines on a portion of the Wall Street Journal sentences that we have newly annotated for evaluation purposes.
2018-05-31
Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics (publié)
doi.org
Commonsense mining as knowledge base completion? A study on the impact of novelty
Stanisław Jastrzębski
Dzmitry Bahdanau
Seyedarian Hosseini
Michael Noukhovitch
Yoshua Bengio
Jackie Chi Kit Cheung
Commonsense knowledge bases such as ConceptNet represent knowledge in the form of relational triples. Inspired by the recent work by Li et a… (voir plus)l., we analyse if knowledge base completion models can be used to mine commonsense knowledge from raw text. We propose novelty of predicted triples with respect to the training set as an important factor in interpreting results. We critically analyse the difficulty of mining novel commonsense knowledge, and show that a simple baseline method outperforms the previous state of the art on predicting more novel.
2018-05-31
Proceedings of the Workshop on Generalization in the Age of Deep Learning (publié)
doi.org
arxiv.org
A Generalized Knowledge Hunting Framework for the Winograd Schema Challenge
Ali Emami
Adam Trischler
Kaheer Suleman
Jackie CK Cheung
We introduce an automatic system that performs well on two common-sense reasoning tasks, the Winograd Schema Challenge (WSC) and the Choice … (voir plus)of Plausible Alternatives (COPA). Problem instances from these tasks require diverse, complex forms of inference and knowledge to solve. Our method uses a knowledge-hunting module to gather text from the web, which serves as evidence for candidate problem resolutions. Given an input problem, our system generates relevant queries to send to a search engine. It extracts and classifies knowledge from the returned results and weighs it to make a resolution. Our approach improves F1 performance on the WSC by 0.16 over the previous best and is competitive with the state-of-the-art on COPA, demonstrating its general applicability.
2018-05-31
North American Chapter of the Association for Computational Linguistics (publié)
doi.org
Resolving Event Coreference with Supervised Representation Learning and Clustering-Oriented Regularization
Kian Kenyon-Dean
Jackie CK Cheung
Doina Precup
We present an approach to event coreference resolution by developing a general framework for clustering that uses supervised representation … (voir plus)learning. We propose a neural network architecture with novel Clustering-Oriented Regularization (CORE) terms in the objective function. These terms encourage the model to create embeddings of event mentions that are amenable to clustering. We then use agglomerative clustering on these embeddings to build event coreference chains. For both within- and cross-document coreference on the ECB+ corpus, our model obtains better results than models that require significantly more pre-annotated information. This work provides insight and motivating results for a new general approach to solving coreference and clustering problems with representation learning.
2018-05-31
Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics (publié)
doi.org
arxiv.org
Traceability in the Wild: Automatically Augmenting Incomplete Trace Links
Michael Rath
Jacob Rendall
Jin L.C. Guo
Jane Cleland-Huang
Patrick Mäder
Software and systems traceability is widely accepted as an essential element for supporting many software development tasks. Today's version… (voir plus) control systems provide inbuilt features that allow developers to tag each commit with one or more issue ID, thereby providing the building blocks from which project-wide traceability can be established between feature requests, bug fixes, commits, source code, and specific developers. However, our analysis of six open source projects showed that on average only 60% of the commits were linked to specific issues. Without these fundamental links the entire set of project-wide links will be incomplete, and therefore not trustworthy. In this paper we address the fundamental problem of missing links between commits and issues. Our approach leverages a combination of process and text-related features characterizing issues and code changes to train a classifier to identify missing issue tags in commit messages, thereby generating the missing links. We conducted a series of experiments to evaluate our approach against six open source projects and showed that it was able to effectively recommend links for tagging issues at an average of 96% recall and 33% precision. In a related task for augmenting a set of existing trace links, the classifier returned precision at levels greater than 89% in all projects and recall of 50%.
2018-05-26
Proceedings of the 40th International Conference on Software Engineering (publié)
doi.org
arxiv.org
Dyna Planning using a Feature Based Generative Model
Ryan Faulkner
Doina Precup
Dyna-style reinforcement learning is a powerful approach for problems where not much real data is available. The main idea is to supplement … (voir plus)real trajectories, or sequences of sampled states over time, with simulated ones sampled from a learned model of the environment. However, in large state spaces, the problem of learning a good generative model of the environment has been open so far. We propose to use deep belief networks to learn an environment model for use in Dyna. We present our approach and validate it empirically on problems where the state observations consist of images. Our results demonstrate that using deep belief networks, which are full generative models, significantly outperforms the use of linear expectation models, proposed in Sutton et al. (2008)
2018-05-22
ArXiv (prépublication)
arxiv.org
arxiv.org
MINE: Mutual Information Neural Estimation
Ishmael Belghazi
Sai Rajeswar
Aristide Baratin
R Devon Hjelm
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.
2018-05-03
ICLR.cc/2018/Conference (inconnu)
openreview.net
openreview.net