scholarly journals Feature Interactions in Highly Configurable Systems: A Dynamic Analysis Approach with Varxplorer

2020 ◽  
Author(s):  
Larissa Rocha Soares ◽  
Eduardo Almeida ◽  
Ivan Machado ◽  
Christian Kästner
Keyword(s):  
Dynamic Analysis ◽  
State Of The Art ◽  
Interaction Analysis ◽  
Empirical Studies ◽  
The State ◽  
Feature Interaction ◽  
Iterative Detection ◽  
Iterative Approach ◽  
Feature Interactions ◽  
Configurable Systems

Highly-configurable systems provide significant reuse opportunities by tailoring system variants based on a set of features. Those features can interact in undesired ways which may result in faults. Thus, we propose VarXplorer, a dynamic and iterative approach to detect suspicious interactions. To evaluate whether VarXplorer helps improving the performance of identifying suspicious interactions, we performed two empirical studies. Our results shows that from the VarXplorer graphs, participants are able to identify suspicious interactions more than 3 times faster compared to the state-of-the-art tool. Additionally, the iterative detection process provides a more efficient feature interaction analysis, reducing the data developers needs to check to find problematic interactions.

scholarly journals Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks

2017 ◽  
Author(s):  
Jun Xiao ◽  
Hao Ye ◽  
Xiangnan He ◽  
Hanwang Zhang ◽  
Fei Wu ◽  
...  
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Feature Interaction ◽  
Model Parameters ◽  
Learning Approach ◽  
Attention Networks ◽  
Feature Interactions ◽  
Factorization Machine ◽  
Real World Datasets ◽  
Novel Model

Factorization Machines (FMs) are a supervised learning approach that enhances the linear regression model by incorporating the second-order feature interactions. Despite effectiveness, FM can be hindered by its modelling of all feature interactions with the same weight, as not all feature interactions are equally useful and predictive. For example, the interactions with useless features may even introduce noises and adversely degrade the performance. In this work, we improve FM by discriminating the importance of different feature interactions. We propose a novel model named Attentional Factorization Machine (AFM), which learns the importance of each feature interaction from data via a neural attention network. Extensive experiments on two real-world datasets demonstrate the effectiveness of AFM. Empirically, it is shown on regression task AFM betters FM with a 8.6% relative improvement, and consistently outperforms the state-of-the-art deep learning methods Wide&Deep [Cheng et al., 2016] and DeepCross [Shan et al., 2016] with a much simpler structure and fewer model parameters. Our implementation of AFM is publicly available at: https://github.com/hexiangnan/attentional_factorization_machine

scholarly journals Does Workplace Diversity Matter? A Survey Of Empirical Studies On Diversity And Firm Performance, 2000-09

2011 ◽  
Vol 5 (2) ◽  
Author(s):  
Anne M. McMahon
Keyword(s):  
Firm Performance ◽  
State Of The Art ◽  
Empirical Studies ◽  
Academic Research ◽  
The State ◽  
Workplace Diversity ◽  
Research Questions ◽  
Leading Journals

This study seeks to assess the state-of-the-art on the workplace diversity – firm performance relationship. Based on a review of academic research on workplace diversity and firm performance published in nine leading journals in the field of management during the period 2000-2009, it addresses the following research questions: a. How are diversity and firm performance constructs defined? b. What are the findings of research linking workplace diversity and firm performance? c. What factors mediate and/or moderate the diversity-performance relationship? Based on the findings of extant research, we develop a model to explain and interpret the diversity – firm performance relationship, and understand its implications.

scholarly journals Tutorial-Articles: The Importance of Data and Code Sharing

2021 ◽  
Vol 25 (1) ◽  
Author(s):  
Henrique Castro Martins
Keyword(s):  
State Of The Art ◽  
Empirical Studies ◽  
Open Data ◽  
Short Description ◽  
The State ◽  
Code Sharing ◽  
The Future ◽  
Open Code

ABSTRACT Context: this document is designed to be along with those that are in the first edition of the new section of the Journal of Contemporary Administration (RAC): the tutorial-articles section. Objective: the purpose is to present the new section and discuss relevant topics of tutorial-articles. Method: I divide the document into three main parts. First, I provide a summary of the state of the art in open data and open code at the current date that, jointly, create the context for tutorial-articles. Second, I provide some guidance to the future of the section on tutorial-articles, providing a structure and some insights that can be developed in the future. Third, I offer a short R script to show examples of open data that, I believe, can be used in the future in tutorial-articles, but also in innovative empirical studies. Conclusion: finally, I provide a short description of the first tutorial-articles accepted for publication in this current RAC’s edition.

scholarly journals Classification of Hyperspectral Image Based on Double-Branch Dual-Attention Mechanism Network

2019 ◽  
Author(s):  
Li Rui ◽  
Zheng Shunyi ◽  
Duan Chenxi ◽  
Yang Yang ◽  
Wang Xiqi
Keyword(s):  
Spatial Information ◽  
Hyperspectral Image ◽  
State Of The Art ◽  
Empirical Studies ◽  
The State ◽  
Attention Mechanism ◽  
Spatial Features ◽  
Better Than

In recent years, more and more researchers have gradually paid attention to Hyperspectral Image (HSI) classification. It is significant to implement researches on how to use HSI's sufficient spectral and spatial information to its fullest potential. To capture spectral and spatial features, we propose a Double-Branch Dual-Attention mechanism network (DBDA) for HSI classification in this paper, Two branches aer designed to extract spectral and spatial features separately to reduce the interferences between these two kinds of features. What is more, because distinguishing characteristics exist in the two branches, two types of attention mechanisms are applied in two branches above separately, ensuring to exploit spectral and spatial features more discriminatively. Finally, the extracted features are fused for classification. A series of empirical studies have been conducted on four hyperspectral datasets, and the results show that the proposed method performs better than the state-of-the-art method.

Not Ready for Prime Time

2011 ◽  
Vol 2 (4) ◽  
pp. 49-61 ◽  
Author(s):  
Jostein Jensen ◽  
Martin Gilje Jaatun
Keyword(s):  
Software Development ◽  
Empirical Research ◽  
State Of The Art ◽  
Empirical Studies ◽  
Empirical Work ◽  
The State ◽  
Prime Time ◽  
Special Focus ◽  
Model Driven Development ◽  
Model Driven

Model Driven Development (MDD) is by many considered a promising approach for software development. This article reports the results of a systematic survey to identify the state-of-the-art within the topic of security in model driven development, with a special focus on finding empirical studies. The authors provide an introduction to the major secure MDD initiatives, but the survey shows that there is a lack of empirical work on the topic. The authors conclude that better standardization initiatives and more empirical research in the field is necessary before it can be considered mature.

Not Ready for Prime Time

2012 ◽  
pp. 77-90
Author(s):  
Jostein Jensen ◽  
Martin Gilje Jaatun
Keyword(s):  
Software Development ◽  
Empirical Research ◽  
State Of The Art ◽  
Empirical Studies ◽  
Empirical Work ◽  
The State ◽  
Prime Time ◽  
Special Focus ◽  
Model Driven Development ◽  
Model Driven

Model Driven Development (MDD) is by many considered a promising approach for software development. This article reports the results of a systematic survey to identify the state-of-the-art within the topic of security in model driven development, with a special focus on finding empirical studies. The authors provide an introduction to the major secure MDD initiatives, but the survey shows that there is a lack of empirical work on the topic. The authors conclude that better standardization initiatives and more empirical research in the field is necessary before it can be considered mature.

scholarly journals Interaction-Aware Factorization Machines for Recommender Systems

2019 ◽  
Vol 33 ◽  
pp. 3804-3811 ◽  
Author(s):  
Fuxing Hong ◽  
Dongbo Huang ◽  
Ge Chen
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Interaction Effect ◽  
State Of The Art ◽  
Feature Interaction ◽  
Learning Approach ◽  
Field Interaction ◽  
Feature Interactions ◽  
Factorization Machine ◽  
Novel Model

Factorization Machine (FM) is a widely used supervised learning approach by effectively modeling of feature interactions. Despite the successful application of FM and its many deep learning variants, treating every feature interaction fairly may degrade the performance. For example, the interactions of a useless feature may introduce noises; the importance of a feature may also differ when interacting with different features. In this work, we propose a novel model named Interaction-aware Factorization Machine (IFM) by introducing Interaction-Aware Mechanism (IAM), which comprises the feature aspect and the field aspect, to learn flexible interactions on two levels. The feature aspect learns feature interaction importance via an attention network while the field aspect learns the feature interaction effect as a parametric similarity of the feature interaction vector and the corresponding field interaction prototype. IFM introduces more structured control and learns feature interaction importance in a stratified manner, which allows for more leverage in tweaking the interactions on both feature-wise and field-wise levels. Besides, we give a more generalized architecture and propose Interaction-aware Neural Network (INN) and DeepIFM to capture higher-order interactions. To further improve both the performance and efficiency of IFM, a sampling scheme is developed to select interactions based on the field aspect importance. The experimental results from two well-known datasets show the superiority of the proposed models over the state-of-the-art methods.

Applying design in public administration: a literature review to explore the state of the art

2020 ◽  
Vol 48 (1) ◽  
pp. 21-48 ◽  
Author(s):  
Margot Hermus ◽  
Arwin van Buuren ◽  
Victor Bekkers
Keyword(s):  
Literature Review ◽  
Public Administration ◽  
Systematic Literature Review ◽  
State Of The Art ◽  
Design Science ◽  
Empirical Studies ◽  
Wicked Problems ◽  
The State ◽  
Societal Relevance ◽  
The Impact

The attention for applying design-oriented approaches in public administration has increased significantly. Applying design is seen as a promising way to deal with wicked problems and create more responsive policies and services. We aim to contribute to the debate on the value of design for public administration and the development of the latter into a design science by conducting a systematic literature review into the empirical applications of design. We analyse the goals, processes and outcomes of 92 empirical studies. Based upon this we distil six design approaches, varying from traditional scientific and informational approaches to innovative, user-driven and thus more ‘inspirational’ approaches. The more traditional (science-driven) approaches still dominate the field. The impact of these types of studies is correspondingly low. We argue that further developing and refining the whole range of design approaches can foster both the scientific rigour and the societal relevance of a design-oriented public administration.

scholarly journals InteractE: Improving Convolution-Based Knowledge Graph Embeddings by Increasing Feature Interactions

2020 ◽  
Vol 34 (03) ◽  
pp. 3009-3016 ◽  
Author(s):  
Shikhar Vashishth ◽  
Soumya Sanyal ◽  
Vikram Nitin ◽  
Nilesh Agrawal ◽  
Partha Talukdar
Keyword(s):  
Link Prediction ◽  
State Of The Art ◽  
Source Code ◽  
Prediction Performance ◽  
Reproducible Research ◽  
Feature Interaction ◽  
Feature Interactions ◽  
Central Hypothesis ◽  
Low Dimensional ◽  
Better Than

Most existing knowledge graphs suffer from incompleteness, which can be alleviated by inferring missing links based on known facts. One popular way to accomplish this is to generate low-dimensional embeddings of entities and relations, and use these to make inferences. ConvE, a recently proposed approach, applies convolutional filters on 2D reshapings of entity and relation embeddings in order to capture rich interactions between their components. However, the number of interactions that ConvE can capture is limited. In this paper, we analyze how increasing the number of these interactions affects link prediction performance, and utilize our observations to propose InteractE. InteractE is based on three key ideas – feature permutation, a novel feature reshaping, and circular convolution. Through extensive experiments, we find that InteractE outperforms state-of-the-art convolutional link prediction baselines on FB15k-237. Further, InteractE achieves an MRR score that is 9%, 7.5%, and 23% better than ConvE on the FB15k-237, WN18RR and YAGO3-10 datasets respectively. The results validate our central hypothesis – that increasing feature interaction is beneficial to link prediction performance. We make the source code of InteractE available to encourage reproducible research.

scholarly journals Humanitarian–business partnerships in managing humanitarian logistics

2017 ◽  
Vol 22 (1) ◽  
pp. 82-94 ◽  
Author(s):  
N. Nurmala ◽  
Sander de Leeuw ◽  
Wout Dullaert
Keyword(s):  
Literature Review ◽  
Systematic Literature Review ◽  
State Of The Art ◽  
Empirical Studies ◽  
Humanitarian Logistics ◽  
The State ◽  
Future Research ◽  
Business Partnerships ◽  
Content Type ◽  
Humanitarian Organizations

Purpose The aim of this paper is to conduct a systematic literature review to understand the state of the art of partnerships between humanitarian organizations and business corporations in managing humanitarian logistics. Design/methodology/approach A systematic literature review is conducted based on the steps proposed by Denyer and Tranfield (2009). The context-intervention-mechanism-outcome (CIMO) logic is applied to identify the state of the art of partnerships between humanitarian organizations and business corporations in humanitarian logistics. Thirty-six papers related to the topic are extracted from recognized journal databases and then classified into four categories based on the CIMO logic: situational context, intervention factors, mechanisms and outcomes. Findings The study shows that while the context and mechanisms for developing cross-sector partnerships between the humanitarian and the business sector have been examined and illuminated by many researchers, additional research (in particular, empirical studies) is needed to measure outcomes as well as the contributions of partnerships to the performance of humanitarian logistics. In addition to synthesizing the literature in this area, this study also presents challenges of such partnerships. Practical implications The study improves the understanding of the state of cross-sector partnerships in humanitarian logistics as well as identifies opportunities for future research in this area. The study provides reasons and motives of initiating humanitarian–business partnerships in humanitarian logistics as well as their mechanisms and potential outcomes. This may help in developing successful logistics partnerships with each other. Originality/value This is the first systematic literature review to examine the nature of partnerships between humanitarian organizations and business corporations in humanitarian logistics using CIMO logic.

Sign in / Sign up

Export Citation Format

Share Document