← Authors

Johannes Gasteiger

13 papers · 2019–2025 · 4 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (12) 🌈 Renaissance Researcher (5) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🗺️ Taxonomy Completionist (15) 🌍 Conference Polyglot (4) 🏃 Academic Marathon (6) 🤝 Dynamic Duo (11) 👑 Triple Crown 💎 Century Club (13)

Conferences

ICML (5) NIPS (4) ICLR (3) UAI (1)

Top co-authors

Stephan Günnemann (11) Aleksandar Bojchevski (3) Vincent Cohen-Addad (2) Simon Geisler (2) Tom Wollschläger (2) Joshua V. Dillon (1) Sami Abu-El-Haija (1) Kyriakos Axiotis (1) Stefan Weißenberger (1) M. H. I. Abdalla (1)

Keywords

graph neural network (7) energy prediction (2) molecular property prediction (2) personalized pagerank (2) message passing (2) geometric deep learning (1) locality sensitive hashing (1) generative framework (1) graph diffusion (1) spectral method (1) entropy regularization (1) randomized smoothing (1) molecular graph (1) molecular dynamics (1) embedding alignment (1) graph convolution (1) equivariant representation (1) discrete datum (1) convex combination (1) word embedding (1)

Papers

The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence ICML 2025
REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective ICML 2025
Ewald-based Long-Range Message Passing for Molecular Graphs ICML 2023
Accelerating Molecular Graph Neural Networks via Knowledge Distillation NIPS 2023
SubMix: Learning to Mix Graph Sampling Heuristics UAI 2023
Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks ICLR 2021
GemNet: Universal Directional Graph Neural Networks for Molecules NIPS 2021
Directional Message Passing on Molecular Graphs via Synthetic Coordinates NIPS 2021
Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More ICML 2021
Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More ICML 2020
Directional Message Passing for Molecular Graphs ICLR 2020
Diffusion Improves Graph Learning NIPS 2019
Predict then Propagate: Graph Neural Networks meet Personalized PageRank ICLR 2019