Neural Architecture Performance Prediction Using Graph Neural Networks
Published in DAGM German Conference on Pattern Recognition, 2020
CV
Education
- B.S. in GitHub, GitHub University, 2012
- M.S. in Jekyll, GitHub University, 2014
- Ph.D in Version Control Theory, GitHub University, 2018 (expected)
Work experience
- Summer 2015: Research Assistant
- Github University
- Duties included: Tagging issues
- Supervisor: Professor Git
- Fall 2015: Research Assistant
- Github University
- Duties included: Merging pull requests
- Supervisor: Professor Hub
Skills
- Skill 1
- Skill 2
- Sub-skill 2.1
- Sub-skill 2.2
- Sub-skill 2.3
- Skill 3
Publications
Smooth Variational Graph Embeddings for Efficient Neural Architecture Search
Published in International Joint Conference on Neural Networks, 2021
DARTS for Inverse Problems: a Study on Stability
Published in NeurIPS 2021 Deep Inverse Workshop, 2021
Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarks
Published in The Tenth International Conference on Learning Representations, 2022
Learning Where to Look – Generative NAS Is Surprisingly Efficient
Published in European Conference on Computer Vision, 2022
Neural Architecture Design and Robustness: A Dataset
Published in The Eleventh International Conference on Learning Representations, 2023
Differentiable Architecture Search: a One-Shot Method?
Published in AutoML Conference 2023 Workshops, 2023
An Evaluation of Zero-Cost Proxies - from Neural Architecture Performance to Model Robustness (oral)
Published in DAGM German Conference on Pattern Recognition, 2023
Implicit Representations for Image Segmentation
Published in Unireps@NeurIPS 2023, 2023
Improving Native CNN Robustness with Filter Frequency Regularization
Published in Transactions on Machine Learning Research, 2023
Implicit Representations for Constrained Image Segmentation
Published in Proceedings of the 41st International Conference on Machine Learning, 2024
Surprisingly Strong Performance Prediction with Neural Graph Features
Published in Proceedings of the 41st International Conference on Machine Learning, 2024
Talks
Inference given Summary Statistics
Inivted Talk at Fraunhofer ITWM- Comptence Center High Performance Computing Seminar, Kaiserslautern, Germany
Topology Learning for Prediction, Generation, and Robustness in Neural Architecture Search
Inivted Talk at Saarland University - Computer Vision and Machine Perception Lab, Saarbruecken, Germany
Topology Learning for Prediction, Generation, and Robustness in Neural Architecture Search
Inivted Talk at University of Siegen - Learning 2 Sense Talks, Siegen, Germany
AutoML, Trustworthiness and Alignment
Panelist at AutoML Conference - Panel Discussion, Potsdam, Germany
An Evaluation of Zero-Cost Proxies - from Neural Architecture Performance to Model Robustness
Conference Presentation at German Association for Pattern Recognition - German Confrence on Pattern Recognition, Heidelberg, Germany
Multi-Objective Performance Prediction for Neural Architectuer Search
Conference Presentation at British Machine Vision Conference - Doctoral Consortium, Aberdeen, United Kingdom
Neural Architecture Search - Towards Prediction beyong (CIFAR-10 Accuracy) Benchmarks
Inivted Talk at University of Cambridge - Center for Image Analysis Seminar, Cambridge, United Kingdom
Bridging the Gap between Industry and Academia
Panelist at AutoML Conference - Panel Discussion, Paris, France
Teaching
Service and leadership
- Currently signed in to 43 different slack teams