CLOOME: contrastive learning unlocks bioimaging databases for queries with chemical structures

Author(s):	Ana Sanchez-Fernandez, Elisabeth Rumetshofer, Sepp Hochreiter, Günter Klambauer
Published:	Nat Commun 14, 7339 (2023). https://doi.org/10.1038/s41467-023-42328-w, opens an external URL in a new window

In Defense of Metrics: Metrics Sufficiently Encode Typical Human Preferences Regarding Hydrological Model Performance

Author(s):	Martin Gauch, Frederik Kratzert, Oren Gilon, Hoshin Gupta, Juliane Mai, Grey Nearing, Bryan Tolson, Sepp Hochreiter, Daniel Klotz
Published:	Water Resources Research 59 (6), https://doi.org/10.1029/2022WR033918, opens an external URL in a new window

Using emergency department triage for machine learning-based admission and mortality prediction

Author(s):	Thomas Tschoellitsch, Philipp Seidl, Carl Böck, Alexander Maletzky, Philipp Moser, Stefan Thumfart, Michael Giretzlehner, Sepp Hochreiter, Jens Meier
Published:	European Journal of Emergency Medicine, LWW, 2023, Vol. 30(6), pp. 408-416 https://doi.org/10.1097/MEJ.0000000000001068, opens an external URL in a new window

VN-EGNN: Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identification

Author(s):	Florian Sestak, Lisa Schneckenreiter, Sepp Hochreiter, Andreas Mayr, Günter Klambauer
Published:	Conference Neural Information Processing Systems Foundation (NeurIPS 2023), Oral Presentation at Workshop on New Frontiers in Graph Learning, December 10 - December 16, 2023, New Orleans, USA PDF, opens an external URL in a new window

VN-EGNN: Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identification

Author(s):	Florian Sestak, Lisa Schneckenreiter, Sepp Hochreiter, Andreas Mayr, Günter Klambauer
Published:	Conference Neural Information Processing Systems Foundation (NeurIPS 2023), Workshop on Machine Learning in Structural Biology, December 10 - December 16, 2023, New Orleans, USA PDF, opens an external URL in a new window

VN-EGNN: Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identification

Florian Sestak, Lisa Schneckenreiter, Sepp Hochreiter, Andreas Mayr, Günter Klambauer

ELLIS Workshop, Advancing Molecular Machine Learning - Overcoming Limitations, virtuell Dezember 2023 Homepage, opens an external URL in a new window

VN-EGNN: Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identification

Author(s):	Florian Sestak, Lisa Schneckenreiter, Sepp Hochreiter, Andreas Mayr, Günter Klambauer
Published:	Conference Neural Information Processing Systems Foundation (NeurIPS 2023), Workshop on New Frontiers of AI for Drug Discovery and Development, December 10 - December 16, 2023, New Orleans, USA PDF, opens an external URL in a new window

Hopfield Boosting for Out-of-Distribution Detection

Author(s):	Claus Hofmann, Simon Lucas Schmid, Bernhard Lehner, Daniel Klotz, Sepp Hochreiter
Published:	Conference Neural Information Processing Systems Foundation (NeurIPS 2023), Workshop on Associative Memory & Hopfield Networks, December 10 - December 16, 2023, New Orleans, USA PDF, opens an external URL in a new window

Lie Point Symmetry and Physics Informed Networks

Author(s):	Tara Akhound-Sadegh, Laurence Perreault-Levasseur, Johannes Brandstetter, Max Welling, Siamak Ravanbakhsh
Published:	Conference Neural Information Processing Systems Foundation (NeurIPS 2023), December 10 - December 16, 2023, New Orleans, USA arXiv.2311.04293, opens an external URL in a new window

PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers

Author(s):	Phillip Lippe, Bas Veeling, Paris Perdikaris, Richard Turner, Johannes Brandstetter
Published:	Conference Neural Information Processing Systems Foundation (NeurIPS 2023), December 10 - December 16, 2023, New Orleans, USA, Spotlight Poster Link, opens an external URL in a new window

Clifford Group Equivariant Neural Networks

Author(s):	David Ruhe, Johannes Brandstetter, Patrick Forré
Published:	Conference Neural Information Processing Systems Foundation (NeurIPS 2023), December 10 - December 16, 2023, New Orleans, USA arXiv.2305.11141, opens an external URL in a new window

Principled Weight Initialisation for Input-Convex Neural Networks

Author(s):	Pieter-Jan Hoedt, Günter Klambauer
Published:	Conference Neural Information Processing Systems Foundation (NeurIPS 2023), December 10 - December 16, 2023, New Orleans, USA PDF, opens an external URL in a new window

Conformal Prediction for Time Series with Modern Hopfield Networks

Author(s):	Andreas Auer, Martin Gauch, Daniel Klotz, Sepp Hochreiter
Published:	Conference Neural Information Processing Systems Foundation (NeurIPS 2023), December 10 - December 16, 2023, New Orleans, USA arXiv:2303.12783, opens an external URL in a new window

Learning to Modulate pre-trained Models in RL

Author(s):	Thomas Schmied, Markus Hofmarcher, Fabian Paischer, Razvan Pascanu, Sepp Hochreiter
Published:	Conference Neural Information Processing Systems Foundation (NeurIPS 2023), December 10 - December 16, 2023, New Orleans, USA arXiv:2306.14884, opens an external URL in a new window

Semantic HELM: A Human-Readable Memory for Reinforcement Learning

Author(s):	Fabian Paischer, Thomas Adler, Markus Hofmarcher, Sepp Hochreiter
Published:	Conference Neural Information Processing Systems Foundation (NeurIPS 2023), December 10 - December 16, 2023, New Orleans, USA arXiv:2306.09312, opens an external URL in a new window

Variational Annealing on Graphs for Combinatorial Optimization

Author(s):	Sebastian Sanokowski, Wilhelm Berghammer, Sepp Hochreiter, Sebastian Lehner
Published:	Conference Neural Information Processing Systems Foundation (NeurIPS 2023), December 10 - December 16, 2023, New Orleans, USA PDF, opens an external URL in a new window

Elementary Neural Architecture Search

Author(s):	Lukas Aichberger, Günter Klambauer
Published:	AutoML Conference 2023 PDF, opens an external URL in a new window

Quantification of Uncertainty with Adversarial Models

Author(s):	Kajetan Schweighofer, Lukas Aichberger, Mykyta Ielanskyi, Günter Klambauer, Sepp Hochreiter
Published:	Conference Neural Information Processing Systems Foundation (NeurIPS 2023), December 10 - December 16, 2023, New Orleans, USA arXiv:2307.03217, opens an external URL in a new window

Boundary Graph Neural Networks for 3D Simulations

Author(s):	Andreas Mayr, Sebastian Lehner, Arno Mayrhofer, Christoph Kloss, Sepp Hochreiter, Johannes Brandstetter
Published:	37th AAAI Conference on Artificial Intelligence, Washington, USA, Feb 7-14, 2023 arXiv:2106.11299, opens an external URL in a new window

Learning to Modulate pre-trained Models in RL

Author(s):	Thomas Schmied, Markus Hofmarcher, Fabian Paischer, Razvan Pascanu, Sepp Hochreiter
Published:	Workshop on Reincarnating Reinforcement Learning at ICLR 2023, 2023 PDF, opens an external URL in a new window

Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation

Author(s):	Marius-Constantin Dinu, Markus Holzleitner, Maximilian Beck, Hoan Duc Nguyen, Andrea Huber, Hamid Eghbal-zadeh, Bernhard A. Moser, Sergei Pereverzyev, Sepp Hochreiter, Werner Zellinger
Published:	International Conference On Learning Representations (ICLR) 2023 PDF, opens an external URL in a new window

The persistence of errors: How evaluating models over data
partitions relates to a global evaluation

Author(s):	Daniel Klotz, Martin Gauch, Grey Nearing, Sepp Hochreiter, Frederik Kratzert
Published:	EGU General Assembly 2023 DOI, opens an external URL in a new window

Learning Retinal Representations from Multi-modal Imaging via Contrastive Pre-training

Author(s):	Emese Sükei, Elisabeth Rumetshofer, Niklas Schmidinger, Ursula Schmidt-Erfurth, Günter Klambauer, Hrvoje Bogunović
Published:	Medical Imaging with Deep Learning (MIDL), short paper track PDF, opens an external URL in a new window

SITTA: A Semantic Image-Text Alignment for Image Captioning

Author(s):	Fabian Paischer, Thomas Adler, Markus Hofmarcher, Sepp Hochreiter
Published:	arXiv.2307.05591 https://arxiv.org/abs/2307.05591, opens an external URL in a new window

Functional trustworthiness of AI systems by statistically valid testing

Author(s):	Bernhard Nessler, Thomas Doms, Sepp Hochreiter
Published:	arXiv:2310.02727 https://arxiv.org/abs/2310.02727, opens an external URL in a new window

Semantic HELM: An Interpretable Memory for Reinforcement Learning

Author(s):	Fabian Paischer, Thomas Adler, Markus Hofmarcher, Sepp Hochreiter
Published:	arXiv:2306.09312 https://arxiv.org/abs/2306.09312, opens an external URL in a new window

Context-enriched molecule representations improve few-shot drug discovery

Author(s):	Johannes Schimunek, Philipp Seidl, Lukas Friedrich, Daniel Kuhn, Friedrich Rippmann, Sepp Hochreiter, Günter Klambauer
Published:	arXiv:2305.09481 https://arxiv.org/abs/2305.09481, opens an external URL in a new window

Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget

Author(s):	Johannes Lehner, Benedikt Alkin, Andreas Fürst, Elisabeth Rumetshofer, Lukas Miklautz, Sepp Hochreiter
Published:	arXiv:2304.10520 https://arxiv.org/abs/2304.10520, opens an external URL in a new window

Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Language

Author(s):	Philipp Seidl, Andreu Vall, Sepp Hochreiter, Günter Klambauer
Published:	arXiv:2303.03363 https://arxiv.org/abs/2303.03363, opens an external URL in a new window

G-Signatures: Global Graph Propagation With Randomized Signatures

Author(s):	Bernhard Schäfl, Lukas Gruber, Johannes Brandstetter, Sepp Hochreiter
Published:	arXiv:2302.08811 https://arxiv.org/abs/2302.08811, opens an external URL in a new window