Search Results for author: Johannes Gasteiger

Found 16 papers, 9 papers with code

Diffusion Improves Graph Learning

3 code implementations NeurIPS 2019 Johannes Gasteiger, Stefan Weißenberger, Stephan Günnemann

In this work, we remove the restriction of using only the direct neighbors by introducing a powerful, yet spatially localized graph convolution: Graph diffusion convolution (GDC).

Clustering Graph Learning +1

Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More

1 code implementation ICML 2020 Aleksandar Bojchevski, Johannes Gasteiger, Stephan Günnemann

Existing techniques for certifying the robustness of models for discrete data either work only for a small class of models or are general at the expense of efficiency or tightness.

GemNet: Universal Directional Graph Neural Networks for Molecules

4 code implementations NeurIPS 2021 Johannes Gasteiger, Florian Becker, Stephan Günnemann

Effectively predicting molecular interactions has the potential to accelerate molecular dynamics by multiple orders of magnitude and thus revolutionize chemical simulations.

Translation

Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More

no code implementations14 Jul 2021 Johannes Gasteiger, Marten Lienen, Stephan Günnemann

The current best practice for computing optimal transport (OT) is via entropy regularization and Sinkhorn iterations.

Distance regression

Directional Message Passing on Molecular Graphs via Synthetic Coordinates

no code implementations NeurIPS 2021 Johannes Gasteiger, Chandan Yeshwanth, Stephan Günnemann

We furthermore set the state of the art on ZINC and coordinate-free QM9 by incorporating synthetic coordinates in the SMP and DimeNet++ models.

Molecular Property Prediction Property Prediction

Influence-Based Mini-Batching for Graph Neural Networks

no code implementations18 Dec 2022 Johannes Gasteiger, Chendi Qian, Stephan Günnemann

Using graph neural networks for large graphs is challenging since there is no clear way of constructing mini-batches.

Graph Clustering

Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks

no code implementations6 Feb 2023 Jan Schuchardt, Aleksandar Bojchevski, Johannes Gasteiger, Stephan Günnemann

In tasks like node classification, image segmentation, and named-entity recognition we have a classifier that simultaneously outputs multiple predictions (a vector of labels) based on a single input, i. e. a single graph, image, or document respectively.

Adversarial Robustness Image Segmentation +5

Ewald-based Long-Range Message Passing for Molecular Graphs

1 code implementation8 Mar 2023 Arthur Kosmala, Johannes Gasteiger, Nicholas Gao, Stephan Günnemann

Neural architectures that learn potential energy surfaces from molecular data have undergone fast improvement in recent years.

Inductive Bias

Challenges with unsupervised LLM knowledge discovery

no code implementations15 Dec 2023 Sebastian Farquhar, Vikrant Varma, Zachary Kenton, Johannes Gasteiger, Vladimir Mikulik, Rohin Shah

We show that existing unsupervised methods on large language model (LLM) activations do not discover knowledge -- instead they seem to discover whatever feature of the activations is most prominent.

Language Modelling Large Language Model

Attacking Large Language Models with Projected Gradient Descent

no code implementations14 Feb 2024 Simon Geisler, Tom Wollschläger, M. H. I. Abdalla, Johannes Gasteiger, Stephan Günnemann

Current LLM alignment methods are readily broken through specifically crafted adversarial prompts.

Cannot find the paper you are looking for? You can Submit a new open access paper.