Jobid=627452380501518256 (0.0148)
ph3Postdoc Trustworthy Graph Machine Learning /h3 pbTrustworthy Graph Machine Learning for Population Scale Networks /b /p pWe invite applications for a postdoctoral researcher to work on fundamental techniques for trustworthy graph machine learning for the analysis of population‑scale networks. The position focuses on two pillars of trustworthiness: explainability and privacy‑preserving learning. /p pThis research direction connects closely to ongoing work by Dr. Megha Khosla on trustworthy graph machine learning, especially on the relationship between transparency and privacy in graph‑based models. Population‑scale network data are highly relational and often sensitive. Graph models for such data must therefore be accurate, interpretable and designed to reduce privacy risks. /p pA central aim of the position is to develop explainability methods for graph machine learning as a form of decision support. These methods should help researchers understand both model behaviour and the underlying data. They should explain why a model makes a prediction, what structural or demographic patterns the model captures, and when its decisions are reliable enough to support scientific interpretation or decision‑making. /p pAt the same time, explanations and learned graph representations can themselves reveal sensitive information. In population‑scale networks, privacy risks may arise from rare individuals, sensitive attributes, neighbourhood structures, etc. The postdoc will therefore investigate how explanations and graph learning methods can be made privacy‑aware. This may include studying privacy risks in developed models, designing explanations that avoid unnecessary disclosure, or developing new privacy‑preserving graph learning techniques. /p pThe project is funded by Macroscope, a Dutch national research infrastructure for studying social change, misinformation and trust at population scale. /p pWe are especially interested in candidates with strong expertise in either explainable graph machine learning or privacy‑preserving graph machine learning, together with a willingness to collaborate across the other area. /p pYou will work with the task PI, Dr. Megha Khosla, and her team of PhD and Master’s students, and collaborate with scientists from different fields across the Macroscope project, including computer science and computational social science. /p h3Job requirements /h3 ul liPhD in computer science, AI, machine learning, data science, network science, computational social science, or a related field. /li liExpertise in either explainable graph machine learning or privacy‑preserving graph learning. /li liWillingness to develop expertise across the other area. /li liStrong programming skills in Python, with experience using tools such as PyTorch, PyTorch Geometric, DGL, NetworkX, or scikit‑learn. /li liEngineering skills and willingness/patience to work with large, noisy datasets, including preprocessing, pipeline development, and scalable evaluation. /li liAbility to work in an interdisciplinary team and communicate research clearly in English. /li /ul h3Conditions of employment /h3 ul liDuration of contract is 2 years Temporary /li liJob of 38 hours per week. /li liSalary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities. /li liAn excellent pension scheme via the ABP. /li liThe possibility to compile an individual employment package every year. /li liDiscount with health insurers on supplemental packages. /li liEvery year, 232 leave hours (at 38 hours). You can also sell or buy additional leave hours via the individual choice budget. /li liPlenty of opportunities for education, training and courses. /li liPartially paid parental leave /li liAttention for working healthy and energetically with the vitality program. /li /ul /p #J-18808-Ljbffr
Deel deze vacature: