Code & Data
Below you find an overview of the supplementary material (Code, Data, Appendices, ...) for some of our recent works:
- UnHiPPO: Uncertainty-aware Initialization for State Space Models (ICML 2025)
- Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification
- Expressivity and Generalization: Fragment-Biases for Molecular GNNs (ICML 2024)
- Uncertainty for Active Learning on Graphs (ICML 2024)
- From Zero to Turbulence: Generative Modeling for 3D Flow Simulation (ICLR 2024)
- Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More (NeurIPS 2023)
- Generalizing Neural Wave Functions (ICML 2023)
- Uncertainty Estimation for Molecules: Desiderata and Methods (ICML 2023)
- Ewald-based Long-Range Message Passing for Molecular Graphs (ICML 2023)
- Localized Randomized Smoothing for Collective Robustness Certification (ICLR 2023)
- Sampling-free Inference of Ab-initio Potential Energy Surface Networks (ICLR 2023)
- Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks (NeurIPS 2022)
- Invariance-Aware Randomized Smoothing Certificates (NeurIPS 2022)
- Ab-Initio Potential Energy Surfaces by Pairing GNNs with Neural Wave Functions (ICLR 2022)
- Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness (ICLR 2022)
- Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks (ICLR 2022)
- Neural Flows: Efficient Alternative to Neural ODEs (NeurIPS 2021)
- Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification (NeurIPS 2021)
- Robustness of Graph Neural Networks at Scale (NeurIPS 2021)
- GemNet: Universal Directional Graph Neural Networks for Molecules (NeurIPS 2021)
- Directional Message Passing on Molecular Graphs via Synthetic Coordinates (NeurIPS 2021)
- Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More (ICML 2021)
- Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable? (ICML 2021)
- Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks
- Completing the Picture: Randomized Smoothing Suffers from the Curse of Dimensionality for a Large Family of Distributions
- Reliable Graph Neural Networks via Robust Aggregation (NeurIPS 2020)
- Fast and Flexible Temporal Point Processes with Triangular Maps (NeurIPS 2020)
- Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts (NeurIPS 2020)
- Efficient Robustness Certificates for Discrete Data (ICML 2020)
- Scaling Graph Neural Networks with Approximate PageRank (KDD 2020)
- Intensity-Free Learning of Temporal Point Processes (ICLR 2020)
- Directional Message Passing for Molecular Graphs (ICLR 2020)
- Certifiable Robustness to Graph Perturbations (NeurIPS 2019)
- Uncertainty on Asynchronous Time Event Prediction (Neurips 2019)
- Diffusion Improves Graph Learning (NeurIPS 2019)
- Adversarial Attacks on Node Embeddings via Graph Poisoning (ICML 2019)
- Certifiable Robustness and Robust Training for Graph Convolutional Networks (KDD 2019)
- Overlapping Community Detection with Graph Neural Networks (KDD 2019 Deep Learning on Graphs Workshop)
- Predict then Propagate: Graph Neural Networks meet Personalized PageRank (ICLR 2019)
- Adversarial Attacks on Graph Neural Networks via Meta Learning (ICLR 2019)
- Pitfalls of Graph Neural Network Evaluation (NeurIPS 2018 Relational Representation Learning Workshop)
- Adversarial Attacks on Neural Networks for Graph Data (KDD 2018)
- NetGAN: Generating Graphs via Random Walks (ICML 2018)
- Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking (ICLR 2018)
- Bayesian Robust Attributed Graph Clustering: Joint Learning of Partial Anomalies and Group Structure (AAAI 2018)
- Robust Spectral Clustering (KDD 2017)
- Hyperbolae Are No Hyperbole: Modelling Communities That Are Not Cliques (ICDM 2016)