Postdoc position in computing science with focus on federated learning - Befattningen är under tillsättning eller redan tillsatt, och det är inte längre möjligt att lämna in en ansökan

The Department of Computing science seeks a postdoc who will work with trustworthy federated learning. The employment is full-time for two years with starting date by agreement.

Department of Computing science

The department characterized by world-leading research in several scientific fields and a multitude of educations ranked highly in international comparison. The department has been growing rapidly in recent years where focus on an inclusive and bottom-up driven environment are key elements in our sustainable growth. As part of this growth, we now look for a Postdoc in trustworthy federated learning. The workplace consists of a diverse group from different nationalities, background and fields. If you work as a postdoc you receive the benefits of support in career development, networking, administrative and technical support functions along with good employment conditions. See more information at:

https://www.umu.se/en/department-of-computing-science/

The research group in distributed system is internationally well-known and comprising more than 20 people of 10 different nationalities, and is currently recruiting up to 15 more researchers. The group’s research focuses on the (semi-)autonomous management of resources and applications to support the future digitized society. Target infrastructures range from single large-scale cloud datacenters to mobile edge clouds and includes individual servers, clusters, or disaggregated systems, such as rack-scale systems. The research spans from basic to applied research, and even innovation via spin-off companies. Collaborations are performed with industries like Google, IBM, Intel, Red Hat, and Ericsson, as well as universities and institutes such as Princeton University, University of Massachusetts Amherst, Carnegie Mellon University, Princeton University, Lawrence Berkeley Lab, Nanyang Technical University in Singapore, Uppsala University, Lund University, Universidad Complutense de Madrid, Leeds University, Barcelona Supercomputer Center, TU Vienna, TU Delft, and many more. See www.cloudresearch.org for a presentation of the group as well as an overview of ongoing research projects and publication lists. For more information about the research group, please see: https://www.umu.se/en/research/groups/autonomous-distributed-systems-lab/

Project description and working tasks

The rapid increase of autonomous systems, connected devices, and distributed applications pose challenges in dealing with petabytes of data in diverse resource-constrained environments. Federated machine learning (FML) is collaborative learning to handle these problems without sharing data with centralized servers. However, several emerging threats target FML training, learning, and inference to fail or mislead models at early learning rounds. Attackers aim to break trustworthiness under different threat models such as insiders-outsiders attacks, semi-honest or fully malicious participants, and attacks in training, learning, or inference phases. As a result, the learning models fail to provide acceptable performance. Therefore, this project aims to develop and implement trustworthy federated learning algorithms for scarce and diverse non-iid (independent identically distributed) data under non-standard and adversarial settings, which are ideally suited for constraint environments and edge computing infrastructures. These goals can be achieved by inducing unique features in federated learning algorithms such as decentralized training, optimal device selection, secure learning and inference, fault-tolerance against failures and attacks, as well as resilient, fair and robust models. The ambition is to validate them in classical non-standard settings and apply them to solutions for constraint environments (i.e., Industrial Internet of Things (IIoT), healthcare systems) and edge infrastructures. Potentially, teaching up to a maximum of 20% can be included in the work tasks.

Wallenberg AI, Autonomous Systems and Software Program (WASP) is Sweden’s largest individual research program ever, a major national initiative for strategically motivated basic research, education and faculty recruitment. The program addresses research on artificial intelligence and autonomous systems acting in collaboration with humans, adapting to their environment through sensors, information and knowledge, and forming intelligent systems-of-systems. The vision of WASP is excellent research and competence in artificial intelligence, autonomous systems and software for the benefit of Swedish industry. Read more: https://wasp-sweden.org/

Qualifications

To be appointed under the postdoctoral agreement, the postdoctoral fellow is required to have completed a doctoral degree or a foreign degree deemed equivalent to a doctoral degree. This qualification requirements must be fulfilled no later than at the time of the appointment decision.

To be appointed under the postdoctoral agreement, priority should be given to candidates who completed their doctoral degree, according to what is stipulated in the paragraph above, no later than three years prior. If there are special reasons, candidates who completed their doctoral degree prior to that may also be eligible. Special reasons include absence due to illness, parental leave, appointments of trust in trade union organisations, military service, or similar circumstances, as well as clinical practice or other forms of appointment/assignment relevant to the subject area. Postdoctoral fellows who are to teach or supervise must have taken relevant courses in teaching and learning in higher education.

Ideal candidates are research-driven, organized, and would like to work on challenging problems and innovative solutions. We are open to candidates with strengths in federated machine learning under multi-constraints settings and relevant to the research environment. Knowledge and experience in federated learning algorithms, distributed algorithms, learning with data scarcity, data-centric optimization, resilient or fault-tolerant learning, trustworthy learning, mathematical statistics, anomaly detection, cloud-native systems, serverless systems, etc. is desirable.

Application

A full application should include:

Personal letter that clarifies how your background meets the needs and expectations of this position, Curriculum vitae (CV) with publication list, Verified copy of doctoral degree certificate or documentation that clarifies when the degree of doctor will likely be obtained, Verified copies of other diplomas, list of completed academic courses and grades, Copy of doctoral thesis and up to three relevant articles, Contact information for at least two reference persons, Other documents that the applicant wishes to claim.

The application must be written in English or Swedish. The application is made through our electronic recruitment system. Documents sent electronically must be in Word or PDF format. Log in to the system and apply via the button at the end of this page. The closing date is June 30, 2022.

Further details are provided by Assistant Professor Monowar Bhuyan at monowar@cs.umu.se or Professor Erik Elmroth at elmroth@cs.umu.se