Ericsson Careers

Master thesis: Federated Learning in Mobile Networks

Stockholm, Sweden
Students and Young Professionals

Apply
English (US)

Job Description

Date: Nov 29, 2018

The Research Area Machine Intelligence and Automation combines Machine Learning and Artificial Intelligence methods, tools, and techniques to create data driven, intelligent, non-fragile systems for automation, augmentation, and amplification. The Cognitive Automation Lab group at Ericsson Research in Stockholm is a research group within the Machine Intelligence and Automation research area working on all aspects of artificial intelligence, such as knowledge representation, deduction, reasoning and problem solving, image processing, natural language processing, automated planning and applied machine learning.

 

We are now looking for a talented student to work with us on experimenting and testing Federated Learning using various machine learning models in the mobile networks.

Mobile network nodes have several measurement points that continuously measure and record Quality of Service (QoS) performance metrics. Then, these measurements are used to predict the future state of the network and enable the implementation of proactive decisions to prevent critical events from happening. One example use case is KPI (Key Performance Indicator) degradation that predicts whether, for instance, an important performance indicator in the network will decrease or not in the near future. Developing a model that serves this task necessitates lots of data being collected on the mobile network elements. Conventional methods for training a machine learning model are based on collecting data from all network elements into one central node, and then train a supervised ML model. This necessitates tough requirements with respect to the privacy and also the transmission bandwidth limitations in between the network elements nodes and the central node. Therefore, for some cases transmission of data from the nodes is not an option, and the only way to do this is by training each network elements individually or in a federated manner and then the individual nodes share the obtained model parameters instead of the data. In the scope of this thesis, the student is expected to implement, test and compare various federated machine learning models and suggest the most suitable ones to deploy in a real product.

You will work together with an experienced research team from Ericsson and our partners in academia.

 

The project will be performed in Kista.

 

Qualifications

 

We are looking for a motivated individual with the following qualifications

  • Master’s student with most courses completed and good grades
  • Strong programming skills, specifically Python
  • Good knowledge of machine learning, statistics and packages such as Python/Scikit-learn, Tensorflow, and Keras
  • Good knowledge of computer networks, cloud and virtualization
  • Excellent communication
  • Excellent written and spoken English, ability to work as part of an international team

 

As the work is research oriented we expect an analytical mindset, ability to learn quickly, work independently and being able to identify problems and solutions.

 

Applications should include a short motivation letter, CV, and transcripts of records. Candidates are invited to send their applications as soon as possible.

Contact person: Konstantinos Vandikas  Konstantinos.Vandikas@ericsson.com

 

Ericsson provides equal employment opportunities (EEO) to all employees and applicants for employment without regard to race, color, religion, sex, sexual orientation, marital status, pregnancy, parental status, national origin, ethnic background, age, disability, political opinion, social status, veteran status, union membership or genetics.

Ericsson complies with applicable country, state and all local laws governing nondiscrimination in employment in every location across the world in which the company has facilities. In addition, Ericsson supports the UN Guiding Principles for Business and Human Rights and the United Nations Global Compact.

This policy applies to all terms and conditions of employment, including recruiting, hiring, placement, promotion, termination, layoff, recall, transfer, leaves of absence, compensation, training and development.

Ericsson expressly prohibits any form of workplace harassment based on race, color, religion, sex, sexual orientation, marital status, pregnancy, parental status, national origin, ethnic background, age, disability, political opinion, social status, veteran status, union membership or genetic information.

 

Primary country and city: Sweden (SE) || || Stockholm || Stud&YP

Req ID: 265412