HEC Montréal

About: HEC Montréal is a education organization based out in Montreal, Quebec, Canada. It is known for research contribution in the topics: Context (language use) & Vehicle routing problem. The organization has 1221 authors who have published 5708 publications receiving 196862 citations. The organization is also known as: Ecole des Hautes Etudes Commerciales de Montreal & HEC Montreal.

A multilevel model of resistance to information technology implementation

Abstract: To better explain resistance to information technology implementation, we used a multilevel, longitudinal approach We first assessed extant models of resistance to IT Using semantic analysis, we identified five basic components of resistance: behaviors, object, subject, threats, and initial conditions We further examined extant models to (1) carry out a preliminary specification of the nature of the relationships between these components and (2) refine our understanding of the multilevel nature of the phenomenon Using analytic induction, we examined data from three case studies of clinical information systems implementations in hospital settings, focusing on physicians' resistance behaviors The resulting mixed-determinants model suggests that group resistance behaviors vary during implementation When a system is introduced, users in a group will first assess it in terms of the interplay between its features and individual and/or organizational-level initial conditions They then make projections about the consequences of its use If expected consequences are threatening, resistance behaviors will result During implementation, should some trigger occur to either modify or activate an initial condition involving the balance of power between the group and other user groups, it will also modify the object of resistance, from system to system significance If the relevant initial conditions pertain to the power of the resisting group vis-a-vis the system advocates, the object of resistance will also be modified, from system significance to system advocates Resistance behaviors will follow if threats are perceived from the interaction between the object of resistance and initial conditions We also found that the bottom-up process by which group resistance behaviors emerge from individual behaviors is not the same in early versus late implementation In early implementation, the emergence process is one of compilation, described as a combination of independent, individual behaviors In later stages of implementation, if group level initial conditions have become active, the emergence process is one of composition, described as the convergence of individual behaviors

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).

Goodness-of-fit tests for copulas: A review and a power study

Abstract: Many proposals have been made recently for goodness-of-fit testing of copula models. After reviewing them briefly, the authors concentrate on “blanket tests”, i.e., those whose implementation requires neither an arbitrary categorization of the data nor any strategic choice of smoothing parameter, weight function, kernel, window, etc. The authors present a critical review of these procedures and suggest new ones. They describe and interpret the results of a large Monte Carlo experiment designed to assess the effect of the sample size and the strength of dependence on the level and power of the blanket tests for various combinations of copula models under the null hypothesis and the alternative. To circumvent problems in the determination of the limiting distribution of the test statistics under composite null hypotheses, they recommend the use of a double parametric bootstrap procedure, whose implementation is detailed. They conclude with a number of practical recommendations.

The Pollution-Routing Problem

Abstract: The amount of pollution emitted by a vehicle depends on its load and speed, among other factors. This paper presents the Pollution-Routing Problem (PRP), an extension of the classical Vehicle Routing Problem (VRP) with a broader and more comprehensive objective function that accounts not just for the travel distance, but also for the amount of greenhouse emissions, fuel, travel times and their costs. Mathematical models are described for the PRP with or without time windows and computational experiments are performed on realistic instances. The paper sheds light on the tradeoffs between various parameters such as vehicle load, speed and total cost, and offers insight on economies of ‘environmental-friendly’ vehicle routing. The results suggest that, contrary to the VRP, the PRP is significantly more difficult to solve to optimality but has the potential of yielding savings in total cost.