PODC 2020 Review

2021 ◽  
Vol 51 (4) ◽  
pp. 75-81
Author(s):  
Ahad Mirza Baig ◽  
Alkida Balliu ◽  
Peter Davies ◽  
Michal Dory
Keyword(s):  
Machine Learning ◽  
Distributed Computing ◽  
Keynote Speaker ◽  
Lively Discussion ◽  
Theoretical Understanding ◽  
New Directions ◽  
New Ideas ◽  
New Challenges ◽  
The Impact ◽  
Distributed Machine Learning

Rachid Guerraoui was the rst keynote speaker, and he got things o to a great start by discussing the broad relevance of the research done in our community relative to both industry and academia. He rst argued that, in some sense, the fact that distributed computing is so pervasive nowadays could end up sti ing progress in our community by inducing people to work on marginal problems, and becoming isolated. His rst suggestion was to try to understand and incorporate new ideas coming from applied elds into our research, and argued that this has been historically very successful. He illustrated this point via the distributed payment problem, which appears in the context of blockchains, in particular Bitcoin, but then turned out to be very theoretically interesting; furthermore, the theoretical understanding of the problem inspired new practical protocols. He then went further to discuss new directions in distributed computing, such as the COVID tracing problem, and new challenges in Byzantine-resilient distributed machine learning. Another source of innovation Rachid suggested was hardware innovations, which he illustrated with work studying the impact of RDMA-based primitives on fundamental problems in distributed computing. The talk concluded with a very lively discussion.

scholarly journals Zen and the art of model adaptation: Low-utility-cost attack mitigations in collaborative machine learning

2021 ◽  
Vol 2022 (1) ◽  
pp. 274-290
Author(s):  
Dmitrii Usynin ◽  
Daniel Rueckert ◽  
Jonathan Passerat-Palmbach ◽  
Georgios Kaissis
Keyword(s):  
Machine Learning ◽  
Collaborative Learning ◽  
Real Life ◽  
Model Adaptation ◽  
Theoretical Understanding ◽  
Model Inversion ◽  
Optimal Balance ◽  
Learning Scenarios ◽  
Utility Cost ◽  
The Impact

Abstract In this study, we aim to bridge the gap between the theoretical understanding of attacks against collaborative machine learning workflows and their practical ramifications by considering the effects of model architecture, learning setting and hyperparameters on the resilience against attacks. We refer to such mitigations as model adaptation. Through extensive experimentation on both, benchmark and real-life datasets, we establish a more practical threat model for collaborative learning scenarios. In particular, we evaluate the impact of model adaptation by implementing a range of attacks belonging to the broader categories of model inversion and membership inference. Our experiments yield two noteworthy outcomes: they demonstrate the difficulty of actually conducting successful attacks under realistic settings when model adaptation is employed and they highlight the challenge inherent in successfully combining model adaptation and formal privacy-preserving techniques to retain the optimal balance between model utility and attack resilience.

Preventing Model Overfitting and Underfitting in Convolutional Neural Networks

2018 ◽  
Vol 10 (4) ◽  
pp. 19-28 ◽  
Author(s):  
Andrei Dmitri Gavrilov ◽  
Alex Jordache ◽  
Maya Vasdani ◽  
Jack Deng
Keyword(s):  
Machine Learning ◽  
Image Recognition ◽  
Recognition Performance ◽  
Square Lattice ◽  
Training Set ◽  
Learning Methods ◽  
Theoretical Understanding ◽  
The Past ◽  
Machine Learning Methods ◽  
The Impact

The current discourse in the machine learning domain converges to the agreement that machine learning methods emerged as some of the most prominent learning and classification approaches over the past decade. The CNN became one of most actively researched and broadly-applied deep machine learning methods. However, the training set has a large influence on the accuracy of a network and it is paramount to create an architecture that supports its maximum training and recognition performance. The problem considered in this article is how to prevent overfitting and underfitting. The deficiencies are addressed by comparing the statistics of CNN image recognition algorithms to the Ising model. Using a two-dimensional square-lattice array, the impact that the learning rate and regularization rate parameters have on the adaptability of CNNs for image classification are evaluated. The obtained results contribute to a better theoretical understanding of a CNN and provide concrete guidance on preventing model overfitting and underfitting when a CNN is applied for image recognition tasks.

Forecasting US movies box office performances in Turkey using machine learning algorithms

2020 ◽  
Vol 39 (5) ◽  
pp. 6579-6590
Author(s):  
Sandy Çağlıyor ◽  
Başar Öztayşi ◽  
Selime Sezgin
Keyword(s):  
Machine Learning ◽  
Global Economy ◽  
Learning Algorithms ◽  
Forecast Model ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
High Stakes ◽  
Box Office ◽  
Industry Forecast ◽  
The Impact

The motion picture industry is one of the largest industries worldwide and has significant importance in the global economy. Considering the high stakes and high risks in the industry, forecast models and decision support systems are gaining importance. Several attempts have been made to estimate the theatrical performance of a movie before or at the early stages of its release. Nevertheless, these models are mostly used for predicting domestic performances and the industry still struggles to predict box office performances in overseas markets. In this study, the aim is to design a forecast model using different machine learning algorithms to estimate the theatrical success of US movies in Turkey. From various sources, a dataset of 1559 movies is constructed. Firstly, independent variables are grouped as pre-release, distributor type, and international distribution based on their characteristic. The number of attendances is discretized into three classes. Four popular machine learning algorithms, artificial neural networks, decision tree regression and gradient boosting tree and random forest are employed, and the impact of each group is observed by compared by the performance models. Then the number of target classes is increased into five and eight and results are compared with the previously developed models in the literature.

Influence of social networks on business processes’ development

2020 ◽  
Vol 19 (12) ◽  
pp. 2225-2252
Author(s):  
E.V. Popov ◽  
V.L. Simonova ◽  
O.V. Komarova ◽  
S.S. Kaigorodova
Keyword(s):  
Social Networks ◽  
Social Media ◽  
Business Models ◽  
Business Processes ◽  
Digital Economy ◽  
Theoretical Understanding ◽  
Sales Channels ◽  
A Value ◽  
The Impact

Subject. The emergence of new ways of interaction between sellers and buyers, the formation of new sales channels and product promotion based on the use of digital economy tools is at the heart of improving the business processes. Social networks became a tool for development; their rapid growth necessitates theoretical understanding and identification of potential application in enterprise's business process digitalization. Objectives. We explore the role of social media in the digitalization of business processes, systematize the impact of social networks on business processes of enterprises in the digital economy. Methods. The theoretical and methodological analysis of social networks as a tool for digitalization of company's business processes rests on the content analysis of domestic and foreign scientific studies, comparison, generalization and systematization. Results. We highlight the key effects of the impact of social networks on the business processes of the company; show that the digitalization of business processes should be considered in the context of a value-based approach, aimed at creating a value through the algorithmization of company operations. We determine that social networks are one of the most important tools for digitalization of company's business processes, as they have a high organizational and management potential. We also systematize the effects of social media on company's business processes. Conclusions. We present theoretical provisions of the impact of social networks on business processes of enterprises, which will enable to model and organize ideas about the development of digital ecosystems and the formation of business models.

Toxic Political Leadership and the Problems of Professionals in Free State Municipalities

2019 ◽  
Vol 48 (1) ◽  
Author(s):  
David Matheakuena Mohale
Keyword(s):  
Good Governance ◽  
Political Leadership ◽  
Primary Source ◽  
Free State ◽  
Audit Report ◽  
Theoretical Understanding ◽  
Number Of Factors ◽  
Auditor General ◽  
Appointed Officials ◽  
The Impact

The 2016–17 Audit Report by the Auditor General points to the deterioration in audit results of South African municipalities. This deterioration confirms the perennial dysfunctionality of municipalities, at least from the governance perspective. Corporate governance is a function of leadership. Municipal councils are, therefore, responsible for the overall performance of municipalities they lead. Sound regulatory framework, good plans, clear strategies, policies, and systems are inadequate if not supported by highly gifted and ethical leadership. The Auditor General’s Audit Report suggests that local government struggles the most in the area of ethics. The Principal-Agent Theory argues that appointed officials are more likely to subvert the interests of an organisation. However, this article argues that the primary source of problems in municipalities is a combination of ineptitude and unethical political leadership taking root. This conclusion is based on the empirical comparative cases of eight municipalities in the Free State Province.  The conduct of councillors makes it difficult to attract and retain professionals in municipalities, resulting in notable deficiencies in the delivery of services. Essentially, councillors are the root cause for governance failure in municipalities arising from a number of factors. Findings in this study contribute towards the understanding of the impact of leadership in the failure of municipalities to meet good governance and developmental objectives. Further, they deepen the theoretical understanding of the political-administrative interface.

Book Review: New Challenges for Greek Letter Organizations: Transforming Fraternities and Sororities into Learning Communities

NASPA Journal ◽  
2000 ◽  
Vol 37 (4) ◽  
Author(s):  
Susan Kraft Fussell
Keyword(s):  
Learning Communities ◽  
Student Services ◽  
Greek Letter ◽  
Educational Value ◽  
New Directions ◽  
New Challenges ◽  
Greek Letter Organizations

The newest book in the New Directions for Student Services series from Jossey-Bass, "New Challenges for Greek Letter Organizations: Transforming Fraternities and Sororities into Learning Communities," examines issues surrounding Greek letter organizations and their educational value.

The European Union and Global Governance

2017 ◽  
Author(s):  
Thomas Christiansen
Keyword(s):  
European Union ◽  
Global Governance ◽  
Final Section ◽  
The European Union ◽  
Test Bed ◽  
Way Of Life ◽  
New Ideas ◽  
The Impact ◽  
Global Powers

This chapter discusses whether the European Union has a distinctive take on, and may make a particular contribution to, global governance, as well as the reverse image of the impact that global governance has in the development of integration in Europe. This includes a focus on collective norms and interests as expressed through common institutions, policies, and activities. In doing so, the chapter compares and contrasts the evolution of a supranational order in Europe with the growth of global regimes and the emergence of a multipolar world, and explores the nature of the EU’s relationships with other global powers and regions. In a final section, the chapter asks whether the EU’s relationship with global developments is best seen as a test-bed for new ideas, procedures, and concepts; a construction for the defence of a privileged way of life; or an archaic remnant of a different era.

Sign in / Sign up

Export Citation Format

Share Document