You are here: Home

Welcome page

Relea Logo 

The Representation Learning Lab (RELEA) led by J.-Prof. Dr. Josif Grabocka was founded in 01.12.2019 and focuses on exploring Deep Learning representations to tackle diverse Machine Learning tasks arising in practical data-driven application domains. In particular, the lab is focused on Neural Architecture Search, Hyper-Parameter Optimization, as well as designing end-to-end architectures for sequential data (time-series) and Recommender System prediction tasks.

 

Recent News

Article icon.   14.09.2022  Our latest work, Supervising the Multi-Fidelity Race of Hyperparameter Configurations is accepted in the Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022).
Article icon.   08.03.2022  RELEA will participate in the project “Responsible and Scalable Learning for Robots Assisting Humans” (ReScaLe) starting on 1 May 2022. Prof. Dr. Grabocka will lead a work package on meta-learning with meta-features for Reinforcement Learning. 

Article icon.   11.10.2021  We release HPO-B, a new benchmark for Black-Box HPO that is additionally published as a research paper at the Conference on Neural Information Processing Systems, Datasets and Benchmarks Track (NeurIPS 2021). For more, read here.

Article icon.   28.09.2021   Our newest paper Well-tuned Simple Nets Excel on Tabular Datasets is accepted in the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021). 

Article icon.   13.08.2021   Prof. Grabocka gave an invited talk titled “Deep Learning for Tabular Datasets” at the Freiburg Center for Data Analysis and Modeling’s seminar on "Data Analysis and Modeling".

Article icon.   12.01.2021   Our newest paper Few-Shot Bayesian Optimization with Deep Kernel Surrogates is accepted in the Ninth International Conference on Learning Representations (ICLR 2021).