Publications

Combating False Negatives in Adversarial Imitation Learning
Konrad Żołna
Chitwan Saharia
Léonard Boussioux
David Y. T. Hui
Maxime Chevalier-Boisvert
Dzmitry Bahdanau
Yoshua Bengio
In adversarial imitation learning, a discriminator is trained to differentiate agent episodes from expert demonstrations representing the de… (see more)sired behavior. However, as the trained policy learns to be more successful, the negative examples (the ones produced by the agent) become increasingly similar to expert ones. Despite the fact that the task is successfully accomplished in some of the agent's trajectories, the discriminator is trained to output low values for them. We hypothesize that this inconsistent training signal for the discriminator can impede its learning, and consequently leads to worse overall performance of the agent. We show experimental evidence for this hypothesis and that the ‘False Negatives’ (i.e. successful agent episodes) significantly hinder adversarial imitation learning, which is the first contribution of this paper. Then, we propose a method to alleviate the impact of false negatives and test it on the BabyAI environment. This method consistently improves sample efficiency over the baselines by at least an order of magnitude.
2021-07-17
International Joint Conference on Neural Networks (published)
doi.org
arxiv.org
Equivariant Networks for Pixelized Spheres
Mehran Shakerinava
Siamak Ravanbakhsh
Pixelizations of Platonic solids such as the cube and icosahedron have been widely used to represent spherical data, from climate records to… (see more) Cosmic Microwave Background maps. Platonic solids have well-known global symmetries. Once we pixelize each face of the solid, each face also possesses its own local symmetries in the form of Euclidean isometries. One way to combine these symmetries is through a hierarchy. However, this approach does not adequately model the interplay between the two levels of symmetry transformations. We show how to model this interplay using ideas from group theory, identify the equivariant linear maps, and introduce equivariant padding that respects these symmetries. Deep networks that use these maps as their building blocks generalize gauge equivariant CNNs on pixelized spheres. These deep networks achieve state-of-the-art results on semantic segmentation for climate data and omnidirectional image processing. Code is available at https://git.io/JGiZA.
2021-07-17
International Conference on Machine Learning (unknown)
doi.org
proceedings.mlr.press
VirtualGAN: Reducing Mode Collapse in Generative Adversarial Networks Using Virtual Mapping
Adel Abusitta
Omar Abdel Wahab
Benjamin C. M. Fung
This paper introduces a new framework for reducing mode collapse in Generative adversarial networks (GANs). The problem occurs when the gene… (see more)rator learns to map several various input values (z) to the same output value, which makes the generator fail to capture all modes of the true data distribution. As a result, the diversity of synthetically produced data is lower than that of the real data. To address this problem, we propose a new and simple framework for training GANs based on the concept of virtual mapping. Our framework integrates two processes into GANs: merge and split. The merge process merges multiple data points (samples) into one before training the discriminator. In this way, the generator would be trained to capture the merged-data distribution rather than the (unmerged) data distribution. After the training, the split process is applied to the generator's output in order to split its contents and produce diverse modes. The proposed framework increases the chance of capturing diverse modes through enabling an indirect or virtual mapping between an input z value and multiple data points. This, in turn, enhances the chance of generating more diverse modes. Our results show the effectiveness of our framework compared to the existing approaches in terms of reducing the mode collapse problem.
2021-07-17
IEEE International Joint Conference on Neural Network (published)
doi.org
On generalized surrogate duality in mixed-integer nonlinear programming
Benjamin Müller
Gonzalo Muñoz
Maxime Gasse
Ambros Gleixner
Andrea Lodi
Felipe Serrano
The most important ingredient for solving mixed-integer nonlinear programs (MINLPs) to global epsilon-optimality with spatial branch and bou… (see more)nd is a tight, computationally tractable relaxation. Due to both theoretical and practical considerations, relaxations of MINLPs are usually required to be convex. Nonetheless, current optimization solver can often successfully handle a moderate presence of nonconvexities, which opens the door for the use of potentially tighter nonconvex relaxations. In this work, we exploit this fact and make use of a nonconvex relaxation obtained via aggregation of constraints: a surrogate relaxation. These relaxations were actively studied for linear integer programs in the 70s and 80s, but they have been scarcely considered since. We revisit these relaxations in an MINLP setting and show the computational benefits and challenges they can have. Additionally, we study a generalization of such relaxation that allows for multiple aggregations simultaneously and present the first algorithm that is capable of computing the best set of aggregations. We propose a multitude of computational enhancements for improving its practical performance and evaluate the algorithm's ability to generate strong dual bounds through extensive computational experiments.
2021-07-16
Mathematical Programming (published)
doi.org
arxiv.org
Symptom network analysis of the sleep disorders diagnostic criteria based on the clinical text of the ICSD‐3
Christophe Gauld
Régis Lopez
Charles Morin
Pierre A. GEOFFROY
Julien Maquet
Pierre Desvergnes
Aileen McGonigal
Yves Dauvilliers
Pierre Philip
Guillaume Dumas
Jean‐Arthur Micoulaud‐Franchi
2021-07-15
Journal of Sleep Research (published)
doi.org
Design of Hesitation Gestures for Nonverbal Human-Robot Negotiation of Conflicts
AJung Moon
Maneezhay Hashmi
H. F. Machiel Van Der Loos
Elizabeth A. Croft
Aude Billard
When the question of who should get access to a communal resource first is uncertain, people often negotiate via nonverbal communication to … (see more)resolve the conflict. What should a robot be programmed to do when such conflicts arise in Human-Robot Interaction? The answer to this question varies depending on the context of the situation. Learning from how humans use hesitation gestures to negotiate a solution in such conflict situations, we present a human-inspired design of nonverbal hesitation gestures that can be used for Human-Robot Negotiation. We extracted characteristic features of such negotiative hesitations humans use, and subsequently designed a trajectory generator (Negotiative Hesitation Generator) that can re-create the features in robot responses to conflicts. Our human-subjects experiment demonstrates the efficacy of the designed robot behaviour against non-negotiative stopping behaviour of a robot. With positive results from our human-robot interaction experiment, we provide a validated trajectory generator with which one can explore the dynamics of human-robot nonverbal negotiation of resource conflicts.
2021-07-10
ACM Transactions on Human-Robot Interaction (published)
doi.org
Random Forest-Based Diffusion Information Geometry for Supervised Visualization and Data Exploration
Jake S. Rhodes
Adele Cutler
Guy Wolf
Kevin R. Moon
Most dimensionality reduction techniques to date are unsupervised; they do not take class labels into account (e.g., PCA, MDS, t-SNE, Isomap… (see more)). Such methods require large amounts of data and are often sensitive to noise that may obfuscate important patterns in the data. Various attempts at supervised dimensionality reduction methods that take into account auxiliary annotations (e.g., class labels) have been successfully implemented with goals of increased classification accuracy or improved data visualization. In this paper, we describe a novel supervised visualization technique based on random forest proximities and a diffusion-based information geometry. We show, both qualitatively and quantitatively, the advantages of our approach in retaining local and global structure in data, while demonstrating the spatial relevance of features important for the supervised task. Importantly, our approach is robust to noise and parameter tuning, thus making it simple to use while producing reliable visualizations for data exploration.
2021-07-10
Symposium on Software Performance (published)
doi.org
TIE: A Framework for Embedding-based Incremental Temporal Knowledge Graph Completion
Jiapeng Wu
Yishi Xu
Yingxue Zhang
Chen Ma
Mark J. Coates
Jackie CK Cheung
Reasoning in a temporal knowledge graph (TKG) is a critical task for information retrieval and semantic search. It is particularly challengi… (see more)ng when the TKG is updated frequently. The model has to adapt to changes in the TKG for efficient training and inference while preserving its performance on historical knowledge. Recent work approaches TKG completion (TKGC) by augmenting the encoder-decoder framework with a time-aware encoding function. However, naively fine-tuning the model at every time step using these methods does not address the problems of 1) catastrophic forgetting, 2) the model's inability to identify the change of facts (e.g., the change of the political affiliation and end of a marriage), and 3) the lack of training efficiency. To address these challenges, we present the Time-aware Incremental Embedding (TIE) framework, which combines TKG representation learning, experience replay, and temporal regularization. We introduce a set of metrics that characterizes the intransigence of the model and propose a constraint that associates the deleted facts with negative labels. Experimental results on Wikidata12k and YAGO11k datasets demonstrate that the proposed TIE framework reduces training time by about ten times and improves on the proposed metrics compared to vanilla full-batch training. It comes without a significant loss in performance for any traditional measures. Extensive ablation studies reveal performance trade-offs among different evaluation metrics, which is essential for decision-making around real-world TKG applications.
2021-07-10
Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (published)
doi.org
arxiv.org
Tracking white and grey matter degeneration along the spinal cord axis in degenerative cervical myelopathy
Kevin Vallotton
Gergely David
Markus Hupp
Nikolai Pfender
Julien Cohen-Adad
Michael Fehlings
Rebecca S. Samson
Claudia A. M. Gandini Wheeler-Kingshott
Armin Curt
Patrick Freund
Maryam Seif
Tissue-specific neurodegeneration revealed by quantitative MRI, already apparent across the spinal cord in mild-moderate DCM prior to the on… (see more)set of severe clinical impairments. WM microstructural changes are particularly sensitive to remote pathologically and clinically eloquent changes in DCM.
2021-07-08
Journal of Neurotrauma (published)
doi.org
A Novel and Dedicated Machine Learning Model for Malware Classification
Miles Q. Li
Benjamin C. M. Fung
Philippe Charland
Steven H. H. Ding
: Malicious executables are comprised of functions that can be represented in assembly code. In the assembly code mining literature, many so… (see more)ftware reverse engineering tools have been created to disassemble executables, search function clones, and find vulnerabilities, among others. The development of a machine learning-based malware classification model that can simultaneously achieve excellent classification performance and provide insightful interpretation for the classification results remains to be a hot research topic. In this paper, we propose a novel and dedicated machine learning model for the research problem of malware classification. Our proposed model generates assembly code function clusters based on function representation learning and provides excellent interpretability for the classification results. It does not require a large or balanced dataset to train which meets the situation of real-life scenarios. Experiments show that our proposed approach outperforms previous state-of-the-art malware classification models and provides meaningful interpretation of classification results.
2021-07-05
Proceedings of the 16th International Conference on Software Technologies (published)
doi.org
Parallel and recurrent cascade models as a unifying force for understanding sub-cellular computation
Emerson F. Harkin
Peter R. Shen
Anish Goel
Blake A. Richards
Richard Naud
Neurons are very complicated computational devices, incorporating numerous non-linear processes, particularly in their dendrites. Biophysica… (see more)l models capture these processes directly by explicitly modelling physiological variables, such as ion channels, current flow, membrane capacitance, etc. However, another option for capturing the complexities of real neural computation is to use cascade models, which treat individual neurons as a cascade of linear and non-linear operations, akin to a multi-layer artificial neural network. Recent research has shown that cascade models can capture single-cell computation well, but there are still a number of sub-cellular, regenerative dendritic phenomena that they cannot capture, such as the interaction between sodium, calcium, and NMDA spikes in different compartments. Here, we propose that it is possible to capture these additional phenomena using parallel, recurrent cascade models, wherein an individual neuron is modelled as a cascade of parallel linear and non-linear operations that can be connected recurrently, akin to a multi-layer, recurrent, artificial neural network. Given their tractable mathematical structure, we show that neuron models expressed in terms of parallel recurrent cascades can themselves be integrated into multi-layered artificial neural networks and trained to perform complex tasks. We go on to discuss potential implications and uses of these models for artificial intelligence. Overall, we argue that parallel, recurrent cascade models provide an important, unifying tool for capturing single-cell computation and exploring the algorithmic implications of physiological phenomena.
2021-07-04
Neuroscience (published)
doi.org
The default mode network in cognition: a topographical perspective
Jonathan Smallwood
Boris C Bernhardt
Robert Leech
Danilo Bzdok
Elizabeth Jefferies
Daniel S. Margulies
2021-07-04
Nature Reviews Neuroscience (published)
doi.org