POSTDOC POSITION: HUMAN-IN-THE-LOOP DATA MINING AND DEEP LEARNING ON GRAPH DAT
Human-in-the-loop Data Mining and Deep Learning on Graph Data: Graph data, e.g., social and biological networks, financial transactions, transportation systems, and telecommunication networks are pervasive in the natural world, where nodes are entities with features and edges represent relations among them. Machine learning and deep learning over graphs become ubiquitous, for instance, in cheminformatics (drug discovery, designing molecular structures with desired properties, virtual screening) and bioinformatics (drug-disease association and protein interaction prediction), detecting malwares and abnormal transactions, classifying customers based on calling behavior, feeds on Twitter, Facebook, and churn prediction. Despite deep learning models often achieving state-of-the-art performance in many tasks, they are “black-box”: It is difficult to understand which aspects of the input graph data drive the decisions of the model. Interpretability can improve the model’s transparency related to fairness, privacy, and other safety challenges, thus enhancing the trust in decision-critical applications and ease their adoption in life science, health, law enforcement, and financial domains. To this aim, we shall design a user-in-the-loop interpretation framework that translates deep learning-based findings back to users, supports “why” and “why-not” questions over prediction results (e.g., “why a new app is classified as a malware”? Or “what minimum, valid changes in a molecule structure would optimize desired chemical and biological properties”?), assists users in formulating relevant questions with minimum efforts, and incorporate users’ interactive feedback to improve training data and deep learning models.
The aim will be publishing several research papers at top-tier data mining, data management, or machine learning conferences based on the research work. The project’s principal supervisor is Associate Professor Arijit Khan, Department of Computer Science. His research works can be found at here, here, and here
Within the area, the position comes with many freedoms in terms of the specific research direction, methodology, and approaches taking the specific project needs into consideration. Accordingly, in addition to the detailed CV and recommendation letters (if any), the applicant should provide a short cover letter which describes the applicant’s background, interests, and initial thoughts and ideas.
Regarding the host institution: The Computer Science Department at Aalborg University takes a leading international position within data management and verification. It is a very young university (1974) but with a strong international profile in Mathematics, and Computer Science & Engineering, also hosting the two most highly cited Computer Scientists of the country. According to the CWTS Leiden Ranking 2014 measuring the scientific performance of 750 major universities worldwide, Aalborg University is ranked no. 117 worldwide and is the highest ranked Danish university within Mathematics, Computer Science & Engineering. In THE Impact Ranking, Aalborg University is ranked as no. 6 in the world. According to US News World Ranking, Aalborg University ranks as no. 250 in the overall world university rankings and as no. 8 in the world, and best in Europe, within the field of Engineering.
Aalborg is an attractive student city located at the Fjord and close to the Sea, and is well-connected (by car, train, but also via Aalborg Airport). Denmark in general and Aalborg in particular are known for their excellent quality of life. Denmark took the top spot on the United Nation’s World Happiness Report, 2013 & 2014 & 2016.
You may obtain further professional information from Professor Christian S. Jensen email@example.com.
Appointment as Postdoc presupposes scientific qualifications at PhD–level or similar scientific qualifications. The research potential of each applicant will be emphasized in the overall assessment. Appointment as a Postdoc cannot exceed a period of four years in total at Aalborg University.
The application must contain the following:
A motivated text wherein the reasons for applying, qualifications in relation to the position, and intentions and visions for the position are stated.
A current curriculum vitae.
Copies of relevant diplomas (Master of Science and PhD). On request you could be asked for an official English translation.
Scientific qualifications. A complete list of publications must be attached with an indication of the works the applicant wishes to be considered. You may attach up to 5 publications.
Dissemination qualifications, including participation on committees or boards, participation in organisations and the like.
Additional qualifications in relation to the position. References/recommendations.
The applications are only to be submitted online by using the “Apply online” button below.
Shortlisting will be applied. After the review of any objections regarding the assessment committee, the head of department, with assistance from the chair of the assessment committee, selects the candidates to be assessed. All applicants will be informed as to whether they will advance to assessment or not.
AAU wishes to reflect the diversity of society and welcomes applications from all qualified candidates regardless of personal background or belief.
For further information concerning the application procedure please contact Søren Kjelst Klausen by mail firstname.lastname@example.org or phone (+45) 9940 3939. Information regarding guidelines, ministerial circular in force and procedures can be seen here
Employment is in accordance with the Ministerial Order on the Appointment of Academic Staff at Universities (the Appointment Order) and the Ministry of Finance’s current Job Structure for Academic Staff at Universities. Employment and salary are in accordance with the collective agreement for state-employed academics.
Mon Jun 20 00:00:00 CEST 2022