HEC Montréal

About: HEC Montréal is a(n) education organization based out in Montreal, Quebec, Canada. It is known for research contribution in the topic(s): Vehicle routing problem & Corporate governance. The organization has 1221 authors who have published 5708 publication(s) receiving 196862 citation(s). The organization is also known as: Ecole des Hautes Etudes Commerciales de Montreal & HEC Montreal.

Graph Attention Networks

Abstract: We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over their neighborhoods' features, we enable (implicitly) specifying different weights to different nodes in a neighborhood, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront. In this way, we address several key challenges of spectral-based graph neural networks simultaneously, and make our model readily applicable to inductive as well as transductive problems. Our GAT models have achieved or matched state-of-the-art results across four established transductive and inductive graph benchmarks: the Cora, Citeseer and Pubmed citation network datasets, as well as a protein-protein interaction dataset (wherein test graphs remain unseen during training).

Model assisted survey sampling

Abstract: PART I: Principles of Estimation for Finite Populations and Important Sampling Designs: Survey Sampling in Theory and Practice. Basic Ideas in Estimation from Probability Samples. Unbiased Estimation for Element Sampling Designs. Unbiased Estimation for Cluster Sampling and Sampling in Two or More Stages. Introduction to More Complex Estimation Problems.- PART II: Estimation through Linear Modeling, Using Auxiliary Variables: The Regression Estimator. Regression Estimators for Element Sampling Designs. Regression Estimators for Cluster Sampling and Two-Stage Sampling.- PART III: Further Questions in Design and Analysis of Surveys: Two-Phase Sampling. Estimation for Domains. Variance Estimation. Searching for Optimal Sampling Designs. Further Statistical Techniques for Survey Data.- PART IV: A Broader View of Errors in Surveys: Nonsampling Errors and Extensions of Probability Sampling Theory. Nonresponse. Measurement Errors. Quality Declarations for Survey Data.- Appendix A - D.- References.

BIONJ: An Improved Version of the NJ Algorithm Based on a Simple Model of Sequence Data

Abstract: We propose an improved version of the neighbor-joining (NJ) algorithm of Saitou and Nei. This new algorithm, BIONJ, follows the same agglomerative scheme as NJ, which consists of iteratively picking a pair of taxa, creating a new mode which represents the cluster of these taxa, and reducing the distance matrix by replacing both taxa by this node. Moreover, BIONJ uses a simple first-order model of the variances and covariances of evolutionary distance estimates. This model is well adapted when these estimates are obtained from aligned sequences. At each step it permits the selection, from the class of admissible reductions, of the reduction which minimizes the variance of the new distance matrix. In this way, we obtain better estimates to choose the pair of taxa to be agglomerated during the next steps. Moreover, in comparison with NJ's estimates, these estimates become better and better as the algorithm proceeds. BIONJ retains the good properties of NJ--especially its low run time. Computer simulations have been performed with 12-taxon model trees to determine BIONJ's efficiency. When the substitution rates are low (maximum pairwise divergence approximately 0.1 substitutions per site) or when they are constant among lineages, BIONJ is only slightly better than NJ. When the substitution rates are higher and vary among lineages,BIONJ clearly has better topological accuracy. In the latter case, for the model trees and the conditions of evolution tested, the topological error reduction is on the average around 20%. With highly-varying-rate trees and with high substitution rates (maximum pairwise divergence approximately 1.0 substitutions per site), the error reduction may even rise above 50%, while the probability of finding the correct tree may be augmented by as much as 15%.

BIONJ: an improved version of the NJ algorithm based on a simple model of sequence data.

Abstract: We propose an improved version of the neighbor-joining (NJ) algorithm of Saitou and Nei. This new algorithm, BIONJ, follows the same agglomerative scheme as NJ, which consists of iteratively picking a pair of taxa, creating a new mode which represents the cluster of these taxa, and reducing the distance matrix by replacing both taxa by this node. Moreover, BIONJ uses a simple first-order model of the variances and covariances of evolutionary distance estimates. This model is well adapted when these estimates are obtained from aligned sequences. At each step it permits the selection, from the class of admissible reductions, of the reduction which minimizes the variance of the new distance matrix. In this way, we obtain better estimates to choose the pair of taxa to be agglomerated during the next steps. Moreover, in comparison with NJ's estimates, these estimates become better and better as the algorithm proceeds. BIONJ retains the good properties of NJ--especially its low run time. Computer simulations have been performed with 12-taxon model trees to determine BIONJ's efficiency. When the substitution rates are low (maximum pairwise divergence approximately 0.1 substitutions per site) or when they are constant among lineages, BIONJ is only slightly better than NJ. When the substitution rates are higher and vary among lineages,BIONJ clearly has better topological accuracy. In the latter case, for the model trees and the conditions of evolution tested, the topological error reduction is on the average around 20%. With highly-varying-rate trees and with high substitution rates (maximum pairwise divergence approximately 1.0 substitutions per site), the error reduction may even rise above 50%, while the probability of finding the correct tree may be augmented by as much as 15%.

Rigor in information systems positivist case research: current practices, trends, and recommendations

Abstract: Case research has commanded respect in the information systems (IS) discipline for at least a decade Notwithstanding the relevance and potential value of case studies, this methodological approach was once considered to be one of the least systematic Toward the end of the 1980s, the issue of whether IS case research was rigorously conducted was first raised Researchers from our field (eg, Benbasat et al 1987; Lee 1989) and from other disciplines (eg, Eisenhardt 1989; Yin 1994) called for more rigor in case research and, through their recommendations, contributed to the advancement of the case study methodology Considering these contributions, the present study seeks to determine the extent to which the field of IS has advanced in its operational use of case study method Precisely, it investigates the level of methodological rigor in positivist IS case research conducted over the past decade To fulfill this objective, we identified and coded 183 case articles from seven major IS journals Evaluation attributes or criteria considered in the present review focus on three main areas, namely, design issues, data collection, and data analysis While the level of methodological rigor has experienced modest progress with respect to some specific attributes, the overall assessed rigor is somewhat equivocal and there are still significant areas for improvement One of the keys is to include better documentation particularly regarding issues related to the data collection and analysis processes