I am a PhD candidate in the computer vision and machine learning group at the Max-Planck-Institute for Informatics and in the focus group of Computer Vision in the Data and Web Science Group at the University of Mannheim. I am supervised by Prof Dr.-Ing. Margret Keuper. Together with Aaron Klein, Arber Zela and Giovanni Zappella I also organize the AutoML Seminars as part of the ELLIS units Berlin and Freiburg. I was part of the organization team of the second workshop on neural architecture search @ ICLR 2021.
My research mainly focuses on efficient, unsupervised graph representations and embeddings for supervised surrogate models for neural architecture search. My work was funded by the BMBF (Federal Ministry of Education and Research) in the project DeToL – Deep Topology Learning
News
- 01/2023 Our paper Neural Architecture Design and Robustness: A Dataset was accepted at ICLR 2023
- 09/2022 Our paper Learning Where to Look - Generative NAS is Surprisingly Efficient was accepted at ECCV 2022
Publications
Neural Architecture Design and Robustness: A Dataset
S. Jung*, J. Lukasik*, M. Keuper
accepted at ICLR 2023
Website | PDF | Code
Learning Where to Look - Generative NAS is Surprisingly Efficient
J. Lukasik* , S. Jung*, M. Keuper
ECCV 2022
PDF | Code | Poster
Surrogate NAS benchmarks: Going beyond the limited search spaces of tabular NAS benchmarks
A. Zela*, JN. Siems*, L. Zimmer*, J. Lukasik, M. Keuper, F. Hutter
ICLR 2022
PDF
DARTS for Inverse Problems: a Study on Sensitivity
J. Geiping*, J. Lukasik*, M. Keuper, M. Moeller
NeurIPS workshop on Inverse Problems
PDF | Poster
Smooth variational graph embeddings for efficient neural architecture search
J. Lukasik, D. Friede, A. Zela, F. Hutter, M. Keuper
IJCNN 2021
PDF | Code
Neural Architecture Performance Prediction Using Graph Neural Networks
J. Lukasik, D. Friede, H. Stuckenschmidt, M. Keuper
DAGM German Conference on Pattern Recognition, 188-201, 2020
PDF