Hello, thanks for visiting my website! I’m Felix, an aspiring computer science researcher specialising in machine learning. Currently, I am a PhD student in Artificial Intelligence at the University of Cambridge.

I was born and raised in Regensburg, a small town in Bavaria, Germany. After attending high school there, I moved to Munich to study Computer Science at the Technical University of Munich in 2015. During my undergraduate degree, I have developed a strong interest in machine learning and ended up doing research on using machine learning methods for drug discovery and later protein structure prediction in my final year.

After graduating in 2018, I enrolled in a master’s degree at the University of Cambridge to work on unsupervised representation learning with neural networks for graph-structured data. In October 2019, I started my PhD in Cambridge to continue with my research on machine learning methods.

In my free time, I enjoy writing and I headed my high school’s student newspaper for many years as well as the student council’s newspaper during my time in Munich. Besides that, I enjoy running, hiking, and skiing.

Publications

  • Opolka, FL., Liò, P. (2020) Graph Convolutional Gaussian Processes for Link Prediction. Workshop on Graph Representation Learning and Beyond (GRL+) at the 37th International Conference on Machine Learning (ICML 2020) [PDF]

  • Yeghikyan G., Opolka, FL., Nanni M., Lepri B., Liò, P. (2020) Learning Mobility Flows from Urban Features with Spatial Interaction Models and Neural Networks. 6th IEEE International Conference on Smart Computing (SMARTCOMP 2020) [arXiv preprint]

  • Opolka, FL.*, Solomon, A.*, Cangea, C., Veličković, P., Liò, P. and Hjelm, RD. (2019) Spatio-Temporal Deep Graph Infomax. Workshop on Representation Learning on Graphs and Manifolds (RLGM) at the 7th International Conference on Learning Representations (ICLR 2019) [arXiv preprint]

Pre-prints

  • Opolka, FL., Liò, P. (2020) Graph Convolutional Gaussian Processes For Link Prediction. arXiv [arXiv preprint]