Publications

Analysis and Detection of Information Types of Open Source Software Issue Discussions
Deeksha M. Arya
Wenting Wang
Jin L.C. Guo
Jinghui Cheng
Most modern Issue Tracking Systems (ITSs) for open source software (OSS) projects allow users to add comments to issues. Over time, these co… (voir plus)mments accumulate into discussion threads embedded with rich information about the software project, which can potentially satisfy the diverse needs of OSS stakeholders. However, discovering and retrieving relevant information from the discussion threads is a challenging task, especially when the discussions are lengthy and the number of issues in ITSs are vast. In this paper, we address this challenge by identifying the information types presented in OSS issue discussions. Through qualitative content analysis of 15 complex issue threads across three projects hosted on GitHub, we uncovered 16 information types and created a labeled corpus containing 4656 sentences. Our investigation of supervised, automated classification techniques indicated that, when prior knowledge about the issue is available, Random Forest can effectively detect most sentence types using conversational features such as the sentence length and its position. When classifying sentences from new issues, Logistic Regression can yield satisfactory performance using textual features for certain information types, while falling short on others. Our work represents a nontrivial first step towards tools and techniques for identifying and obtaining the rich information recorded in the ITSs to support various software engineering activities and to satisfy the diverse needs of OSS stakeholders.
2019-05-24
2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE) (publié)
doi.org
arxiv.org
Fairwashing: the risk of rationalization
Ulrich Aivodji
Hiromi Arai
Olivier Fortineau
Sébastien Gambs
Satoshi Hara
Alain Tapp
Black-box explanation is the problem of explaining how a machine learning model -- whose internal logic is hidden to the auditor and general… (voir plus)ly complex -- produces its outcomes. Current approaches for solving this problem include model explanation, outcome explanation as well as model inspection. While these techniques can be beneficial by providing interpretability, they can be used in a negative manner to perform fairwashing, which we define as promoting the false perception that a machine learning model respects some ethical values. In particular, we demonstrate that it is possible to systematically rationalize decisions taken by an unfair black-box model using the model explanation as well as the outcome explanation approaches with a given fairness metric. Our solution, LaundryML, is based on a regularized rule list enumeration algorithm whose objective is to search for fair rule lists approximating an unfair black-box model. We empirically evaluate our rationalization technique on black-box models trained on real-world datasets and show that one can obtain rule lists with high fidelity to the black-box model while being considerably less unfair at the same time.
2019-05-23
Proceedings of the 36th International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
GeoMetrics: Exploiting Geometric Structure for Graph-Encoded Objects
Edward J. Smith
Scott Fujimoto
Adriana Romero
David Meger
Mesh models are a promising approach for encoding the structure of 3D objects. Current mesh reconstruction systems predict uniformly distrib… (voir plus)uted vertex locations of a predetermined graph through a series of graph convolutions, leading to compromises with respect to performance or resolution. In this paper, we argue that the graph representation of geometric objects allows for additional structure, which should be leveraged for enhanced reconstruction. Thus, we propose a system which properly benefits from the advantages of the geometric structure of graph encoded objects by introducing (1) a graph convolutional update preserving vertex information; (2) an adaptive splitting heuristic allowing detail to emerge; and (3) a training objective operating both on the local surfaces defined by vertices as well as the global structure defined by the mesh. Our proposed method is evaluated on the task of 3D object reconstruction from images with the ShapeNet dataset, where we demonstrate state of the art performance, both visually and numerically, while having far smaller space requirements by generating adaptive meshes
2019-05-23
Proceedings of the 36th International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
GMNN: Graph Markov Neural Networks
Meng Qu
Yoshua Bengio
Jian Tang
This paper studies semi-supervised object classification in relational data, which is a fundamental problem in relational data modeling. The… (voir plus) problem has been extensively studied in the literature of both statistical relational learning (e.g. relational Markov networks) and graph neural networks (e.g. graph convolutional networks). Statistical relational learning methods can effectively model the dependency of object labels through conditional random fields for collective classification, whereas graph neural networks learn effective object representations for classification through end-to-end training. In this paper, we propose the Graph Markov Neural Network (GMNN) that combines the advantages of both worlds. A GMNN models the joint distribution of object labels with a conditional random field, which can be effectively trained with the variational EM algorithm. In the E-step, one graph neural network learns effective object representations for approximating the posterior distributions of object labels. In the M-step, another graph neural network is used to model the local label dependency. Experiments on object classification, link classification, and unsupervised node representation learning show that GMNN achieves state-of-the-art results.
2019-05-23
Proceedings of the 36th International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
Off-Policy Deep Reinforcement Learning without Exploration
Scott Fujimoto
David Meger
Doina Precup
Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, … (voir plus)without offering further possibility for data collection. In this paper, we demonstrate that due to errors introduced by extrapolation, standard off-policy deep reinforcement learning algorithms, such as DQN and DDPG, are incapable of learning with data uncorrelated to the distribution under the current policy, making them ineffective for this fixed batch setting. We introduce a novel class of off-policy algorithms, batch-constrained reinforcement learning, which restricts the action space in order to force the agent towards behaving close to on-policy with respect to a subset of the given data. We present the first continuous control deep reinforcement learning algorithm which can learn effectively from arbitrary, fixed batch data, and empirically demonstrate the quality of its behavior in several tasks.
2019-05-23
Proceedings of the 36th International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
Per-Decision Option Discounting
Anna Harutyunyan
Peter Vrancx
Philippe Hamel
Ann Nowé
Doina Precup
In order to solve complex problems an agent must be able to reason over a sufficiently long horizon. Temporal abstraction, commonly modeled … (voir plus)through options, offers the ability to reason at many timescales, but the horizon length is still determined by the discount factor of the underlying Markov Decision Process. We propose a modification to the options framework that naturally scales the agent’s horizon with option length. We show that the proposed option-step discount controls a bias-variance trade-off, with larger discounts (counter-intuitively) leading to less estimation variance.
2019-05-23
Proceedings of the 36th International Conference on Machine Learning (publié)
proceedings.mlr.press
proceedings.mlr.press
State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations
Alex Lamb
Jonathan Binas
Anirudh Goyal
Sandeep Subramanian
Ioannis Mitliagkas
Denis Kazakov
Yoshua Bengio
Michael Mozer
Machine learning promises methods that generalize well from finite labeled data. However, the brittleness of existing neural net approaches … (voir plus)is revealed by notable failures, such as the existence of adversarial examples that are misclassified despite being nearly identical to a training example, or the inability of recurrent sequence-processing nets to stay on track without teacher forcing. We introduce a method, which we refer to as \emph{state reification}, that involves modeling the distribution of hidden states over the training data and then projecting hidden states observed during testing toward this distribution. Our intuition is that if the network can remain in a familiar manifold of hidden space, subsequent layers of the net should be well trained to respond appropriately. We show that this state-reification method helps neural nets to generalize better, especially when labeled data are sparse, and also helps overcome the challenge of achieving robust generalization with adversarial training.
2019-05-23
Proceedings of the 36th International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
Stroke Lesion Segmentation in FLAIR MRI Datasets Using Customized Markov Random Fields
Nagesh K. Subbanna
Deepthi Rajashekar
Bastian Cheng
Götz Thomalla
Jens Fiehler
Tal Arbel
Nils D. Forkert
Robust and reliable stroke lesion segmentation is a crucial step toward employing lesion volume as an independent endpoint for randomized tr… (voir plus)ials. The aim of this work was to develop and evaluate a novel method to segment sub-acute ischemic stroke lesions from fluid-attenuated inversion recovery (FLAIR) magnetic resonance imaging (MRI) datasets. After preprocessing of the datasets, a Bayesian technique based on Gabor textures extracted from the FLAIR signal intensities is utilized to generate a first estimate of the lesion segmentation. Using this initial segmentation, a customized voxel-level Markov random field model based on intensity as well as Gabor texture features is employed to refine the stroke lesion segmentation. The proposed method was developed and evaluated based on 151 multi-center datasets from three different databases using a leave-one-patient-out validation approach. The comparison of the automatically segmented stroke lesions with manual ground truth segmentation revealed an average Dice coefficient of 0.582, which is in the upper range of previously presented lesion segmentation methods using multi-modal MRI datasets. Furthermore, the results obtained by the proposed technique are superior compared to the results obtained by two methods based on convolutional neural networks and three phase level-sets, respectively, which performed best in the ISLES 2015 challenge using multi-modal imaging datasets. The results of the quantitative evaluation suggest that the proposed method leads to robust lesion segmentation results using FLAIR MRI datasets only as a follow-up sequence.
2019-05-23
Frontiers in Neurology (publié)
doi.org
The Value Function Polytope in Reinforcement Learning
Robert Dadashi
Adrien Ali Taiga
Nicolas Roux
Dale Schuurmans
Bellemare Marc-Emmanuel
We establish geometric and topological properties of the space of value functions in finite state-action Markov decision processes. Our main… (voir plus) contribution is the characterization of the nature of its shape: a general polytope (Aigner et al., 2010). To demonstrate this result, we exhibit several properties of the structural relationship between policies and value functions including the line theorem, which shows that the value functions of policies constrained on all but one state describe a line segment. Finally, we use this novel perspective to introduce visualizations to enhance the understanding of the dynamics of reinforcement learning algorithms.
2019-05-23
Proceedings of the 36th International Conference on Machine Learning (publié)
proceedings.mlr.press
proceedings.mlr.press
Understanding the impact of entropy on policy optimization
Zafarali Ahmed
Nicolas Roux
Mohammad Norouzi
Dale Schuurmans
Entropy regularization is commonly used to improve policy optimization in reinforcement learning. It is believed to help with \emph{explorat… (voir plus)ion} by encouraging the selection of more stochastic policies. In this work, we analyze this claim using new visualizations of the optimization landscape based on randomly perturbing the loss function. We first show that even with access to the exact gradient, policy optimization is difficult due to the geometry of the objective function. Then, we qualitatively show that in some environments, a policy with higher entropy can make the optimization landscape smoother, thereby connecting local optima and enabling the use of larger learning rates. This paper presents new tools for understanding the optimization landscape, shows that policy entropy serves as a regularizer, and highlights the challenge of designing general-purpose policy optimization algorithms.
2019-05-23
Proceedings of the 36th International Conference on Machine Learning (publié)
proceedings.mlr.press
proceedings.mlr.press
The Journey is the Reward: Unsupervised Learning of Influential Trajectories
Jonathan Binas
Sherjil Ozair
Yoshua Bengio
Unsupervised exploration and representation learning become increasingly important when learning in diverse and sparse environments. The inf… (voir plus)ormation-theoretic principle of empowerment formalizes an unsupervised exploration objective through an agent trying to maximize its influence on the future states of its environment. Previous approaches carry certain limitations in that they either do not employ closed-loop feedback or do not have an internal state. As a consequence, a privileged final state is taken as an influence measure, rather than the full trajectory. We provide a model-free method which takes into account the whole trajectory while still offering the benefits of option-based approaches. We successfully apply our approach to settings with large action spaces, where discovery of meaningful action sequences is particularly difficult.
2019-05-21
ArXiv (prépublication)
arxiv.org
arxiv.org
A Data-Efficient Framework for Training and Sim-to-Real Transfer of Navigation Policies
Homanga Bharadhwaj
Zihan Wang
Yoshua Bengio
Liam Paull
Learning effective visuomotor policies for robots purely from data is challenging, but also appealing since a learning-based system should n… (voir plus)ot require manual tuning or calibration. In the case of a robot operating in a real environment the training process can be costly, time-consuming, and even dangerous since failures are common at the start of training. For this reason, it is desirable to be able to leverage \textit{simulation} and \textit{off-policy} data to the extent possible to train the robot. In this work, we introduce a robust framework that plans in simulation and transfers well to the real environment. Our model incorporates a gradient-descent based planning module, which, given the initial image and goal image, encodes the images to a lower dimensional latent state and plans a trajectory to reach the goal. The model, consisting of the encoder and planner modules, is trained through a meta-learning strategy in simulation first. We subsequently perform adversarial domain transfer on the encoder by using a bank of unlabelled but random images from the simulation and real environments to enable the encoder to map images from the real and simulated environments to a similarly distributed latent representation. By fine tuning the entire model (encoder + planner) with far fewer real world expert demonstrations, we show successful planning performances in different navigation tasks.
2019-05-19
2019 International Conference on Robotics and Automation (ICRA) (publié)
doi.org
arxiv.org