Publications

Continual Learning of New Sound Classes Using Generative Replay
Zhepei Wang
Cem (Yusuf) Subakan
Efthymios Tzinis
Paris Smaragdis
Laurent Charlin
Continual learning consists in incrementally training a model on a sequence of datasets and testing on the union of all datasets. In this pa… (see more)per, we examine continual learning for the problem of sound classification, in which we wish to refine already trained models to learn new sound classes. In practice one does not want to maintain all past training data and retrain from scratch, but naively updating a model with new data(sets) results in a degradation of already learned tasks, which is referred to as "catastrophic forgetting." We develop a generative replay procedure for generating training audio spectrogram data, in place of keeping older training datasets. We show that by incrementally refining a classifier with generative replay a generator that is 4% of the size of all previous training data matches the performance of refining the classifier keeping 20% of all previous training data. We thus conclude that we can extend a trained sound classifier to learn new classes without having to keep previously used datasets.
2019-10-20
2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) (published)
doi.org
arxiv.org
Propagating Uncertainty Across Cascaded Medical Imaging Tasks for Improved Deep Learning Inference
Raghav Mehta
Thomas Christinck
Tanya Nair
Aurélie Bussy
Paul Lemaitre
Swapna Premasiri
Douglas Arnold
Manuela Costantino
Tal Arbel
Mallar Chakravarty
Yarin Gal
Although deep networks have been shown to perform very well on a variety of medical imaging tasks, inference in the presence of pathology pr… (see more)esents several challenges to common models. These challenges impede the integration of deep learning models into real clinical workflows, where the customary process of cascading deterministic outputs from a sequence of image-based inference steps (e.g. registration, segmentation) generally leads to an accumulation of errors that impacts the accuracy of downstream inference tasks. In this paper, we propose that by embedding uncertainty estimates across cascaded inference tasks, performance on the downstream inference tasks should be improved. We demonstrate the effectiveness of the proposed approach in three different clinical contexts: (i) We demonstrate that by propagating T2 weighted lesion segmentation results and their associated uncertainties, subsequent T2 lesion detection performance is improved when evaluated on a proprietary large-scale, multi-site, clinical trial dataset acquired from patients with Multiple Sclerosis. (ii) We show an improvement in brain tumour segmentation performance when the uncertainty map associated with a synthesised missing MR volume is provided as an additional input to a follow-up brain tumour segmentation network, when evaluated on the publicly available BraTS-2018 dataset. (iii) We show that by propagating uncertainties from a voxel-level hippocampus segmentation task, the subsequent regression of the Alzheimer’s disease clinical score is improved.
2019-10-17
UNSURE/CLIP@MICCAI (published)
doi.org
Saliency Based Deep Neural Network for Automatic Detection of Gadolinium-Enhancing Multiple Sclerosis Lesions in Brain MRI
Joshua D. Durso-Finley
Douglas Arnold
Tal Arbel
2019-10-17
BrainLes@MICCAI (published)
doi.org
SGP: Spotting Groups Polluting the Online Political Discourse
Junhao Wang
Sacha Lévy
Ren Wang
Aayushi Kulshrestha
Reihaneh Rabbany
Social media sites are becoming a key factor in politics. These platforms are easy to manipulate for the purpose of distorting information s… (see more)pace to confuse and distract voters. It is of paramount importance for social media platforms, users engaged with online political discussions, as well as government agencies to understand the dynamics on social media, and identify malicious groups engaging in misinformation campaigns and thus polluting the general discourse around a topic of interest. Past works to identify such disruptive patterns are mostly focused on analyzing user-generated content such as tweets. In this study, we take a holistic approach and propose SGP to provide an informative birds eye view of all the activities in these social media sites around a broad topic and detect coordinated groups suspicious of engaging in misinformation campaigns. To show the effectiveness of SGP, we deploy it to provide a concise overview of polluting activity on Twitter around the upcoming 2019 Canadian Federal Elections, by analyzing over 60 thousand user accounts connected through 3.4 million connections and 1.3 million hashtags. Users in the polluting groups detected by SGP-flag are over 4x more likely to become suspended while majority of these highly suspicious users detected by SGP-flag escaped Twitter's suspending algorithm. Moreover, while few of the polluting hashtags detected are linked to misinformation campaigns, SGP-sig also flags others that have not been picked up on. More importantly, we also show that a large coordinated set of right-winged conservative groups based in the US are heavily engaged in Canadian politics.
2019-10-16
ArXiv (preprint)
arxiv.org
arxiv.org
Nash Games Among Stackelberg Leaders
Margarida Carvalho
Gabriele Dragotto
Felipe Feijoo
Andrea Lodi
Sriram Sankaranarayanan
We analyze Nash games played among leaders of Stackelberg games (NASP). We show it is Σ p 2 - hard to decide if the game has a mixed-strate… (see more)gy Nash equilibrium (MNE), even when there are only two leaders and each leader has one follower. We provide a finite time algorithm with a running time bounded by O (2 2 n ) which computes MNEs for NASP when it exists and returns infeasibility if no MNE exists. We also provide two ways to improve the algorithm which involves constructing a series of inner approximations (alternatively, outer approximations) to the leaders’ feasible region that will provably obtain the required MNE. Finally, we test our algorithms on a range of NASPs arising out of a game in the energy market, where countries act as Stackelberg leaders who play a Nash game, and the domestic producers act as the followers.
2019-10-14
arXiv.org (preprint)
dblp.uni-trier.de
Improving Pathological Structure Segmentation via Transfer Learning Across Diseases
Barleen Kaur
Paul Lemaitre
Raghav Mehta
Nazanin Mohammadi Sepahvand
Doina Precup
Douglas Arnold
Tal Arbel
2019-10-13
Domain Adaptation and Representation Transfer and Medical Image Learning with Less Labels and Imperfect Data (published)
doi.org
Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation
S. Meng
Sharan Vaswani
Issam Hadj Laradji
Mark Schmidt
Simon Lacoste-Julien
We consider stochastic second-order methods for minimizing smooth and strongly-convex functions under an interpolation condition satisfied b… (see more)y over-parameterized models. Under this condition, we show that the regularized subsampled Newton method (R-SSN) achieves global linear convergence with an adaptive step-size and a constant batch-size. By growing the batch size for both the subsampled gradient and Hessian, we show that R-SSN can converge at a quadratic rate in a local neighbourhood of the solution. We also show that R-SSN attains local linear convergence for the family of self-concordant functions. Furthermore, we analyze stochastic BFGS algorithms in the interpolation setting and prove their global linear convergence. We empirically evaluate stochastic L-BFGS and a "Hessian-free" implementation of R-SSN for binary classification on synthetic, linearly-separable datasets and real datasets under a kernel mapping. Our experimental results demonstrate the fast convergence of these methods, both in terms of the number of iterations and wall-clock time.
2019-10-11
ArXiv (preprint)
arxiv.org
arxiv.org
Old Dog Learns New Tricks: Randomized UCB for Bandit Problems
Sharan Vaswani
Abbas Mehrabian
Audrey Durand
Branislav Kveton
We propose …
2019-10-11
ArXiv (preprint)
arxiv.org
arxiv.org
Reinforcement Learning Models of Human Behavior: Reward Processing in Mental Disorders
Baihan Lin
Guillermo Cecchi
Djallel Bouneffouf
Jenna Reinen
Irina Rish
Drawing an inspiration from behavioral studies of human decision making, we propose here a general parametric framework for a reinforcement … (see more)learning problem, which extends the standard Q-learning approach to incorporate a two-stream framework of reward processing with biases biologically associated with several neurological and psychiatric conditions, including Parkinson's and Alzheimer's diseases, attention-deficit/hyperactivity disorder (ADHD), addiction, and chronic pain. For the AI community, the development of agents that react differently to different types of rewards can enable us to understand a wide spectrum of multi-agent interactions in complex real-world socioeconomic systems. Empirically, the proposed model outperforms Q-Learning and Double Q-Learning in artificial scenarios with certain reward distributions and real-world human decision making gambling tasks. Moreover, from the behavioral modeling perspective, our parametric framework can be viewed as a first step towards a unifying computational model capturing reward processing abnormalities across multiple mental conditions and user preferences in long-term recommendation systems.
2019-10-02
NeurIPS.cc/2019/Workshop/Neuro_AI (poster)
openreview.net
openreview.net
Evaluation of a web-based tool for labelling potential hospital outbreaks: a mixed methods study
B. Leclère
David Buckeridge
D. Lepelletier
2019-10-01
Journal of Hospital Infection (published)
doi.org
Patterns of autism symptoms: hidden structure in the ADOS and ADI-R instruments
Jeremy Lefort-Besnard
Kai Vogeley
Leonhard Schilbach
Gael Varoquaux
Bertrand Thirion
Guillaume Dumas
Danilo Bzdok
2019-09-27
Translational Psychiatry (published)
doi.org
Attraction-Repulsion Actor-Critic for Continuous Control Reinforcement Learning
Thang Doan
Bogdan Mazoure
Audrey Durand
Joelle Pineau
(Rex) Devon Hjelm
Continuous control tasks in reinforcement learning are important because they provide an important framework for learning in high-dimensiona… (see more)l state spaces with deceptive rewards, where the agent can easily become trapped into suboptimal solutions. One way to avoid local optima is to use a population of agents to ensure coverage of the policy space, yet learning a population with the "best" coverage is still an open problem. In this work, we present a novel approach to population-based RL in continuous control that leverages properties of normalizing flows to perform attractive and repulsive operations between current members of the population and previously observed policies. Empirical results on the MuJoCo suite demonstrate a high performance gain for our algorithm compared to prior work, including Soft-Actor Critic (SAC).
2019-09-17
ArXiv (preprint)
openreview.net
openreview.net