1k citations · 4.2k across the 120 of their papers we have counts for
17 papers · 1 filter
Transition Path Sampling with Boltzmann Generator-based MCMC Moves
Michael Plainer, Hannes Stärk, Charlotte Bunne +1
Sampling all possible transition paths between two 3D states of a molecular system has various applications ranging from catalyst design to drug discovery. Current approaches to sa…
Adversarial Attacks and Defenses in Large Language Models: Old and New Threats
Leo Schwinn, David Dobre, Stephan Günnemann +1
Over the past decade, there has been extensive research aimed at enhancing the robustness of neural networks, yet this problem remains vastly unsolved. Here, one major impediment h…
Hierarchical Randomized Smoothing
Yan Scholten, Jan Schuchardt, Aleksandar Bojchevski +1
Real-world data is complex and often consists of objects that can be decomposed into multiple entities (e.g. images into pixels, graphs into interconnected nodes). Randomized smoot…
Assessing Robustness via Score-Based Adversarial Image Generation
Marcel Kollovieh, Lukas Gosch, Marten Lienen +3
Most adversarial attacks and defenses focus on perturbations within small -norm constraints. However, threat models cannot capture all relevant semantics-preservin…
Stream-based Active Learning by Exploiting Temporal Properties in Perception with Temporal Predicted Loss
Sebastian Schmidt, Stephan Günnemann
Active learning (AL) reduces the amount of labeled data needed to train a machine learning model by intelligently choosing which instances to label. Classic pool-based AL requires…
Expressivity of Graph Neural Networks Through the Lens of Adversarial Robustness
Francesco Campi, Lukas Gosch, Tom Wollschläger +2
We perform the first adversarial robustness study into Graph Neural Networks (GNNs) that are provably more powerful than traditional Message Passing Neural Networks (MPNNs). In par…
Density-based Feasibility Learning with Normalizing Flows for Introspective Robotic Assembly
Jianxiang Feng, Matan Atad, Ismael Rodríguez +3
Machine Learning (ML) models in Robotic Assembly Sequence Planning (RASP) need to be introspective on the predicted solutions, i.e. whether they are feasible or not, to circumvent…
The power of motifs as inductive bias for learning molecular distributions
Johanna Sommer, Leon Hetzel, David Lüdke +2
Machine learning for molecules holds great potential for efficiently exploring the vast chemical space and thus streamlining the drug discovery process by facilitating the design o…
From Zero to Turbulence: Generative Modeling for 3D Flow Simulation
Marten Lienen, David Lüdke, Jan Hansen-Palmus +1
Simulations of turbulent flows in 3D are one of the most expensive simulations in computational fluid dynamics (CFD). Many works have been written on surrogate models to replace nu…
Revisiting Robustness in Graph Machine Learning
Lukas Gosch, Daniel Sturm, Simon Geisler +1
Many works show that node-level predictions of Graph Neural Networks (GNNs) are unrobust to small, often termed adversarial, changes to the graph structure. However, because manual…
Edge Directionality Improves Learning on Heterophilic Graphs
Emanuele Rossi, Bertrand Charpentier, Francesco Di Giovanni +3
Graph Neural Networks (GNNs) have become the de-facto standard tool for modeling relational data. However, while many real-world graphs are directed, the majority of today's GNN mo…
Efficient MILP Decomposition in Quantum Computing for ReLU Network Robustness
Nicola Franco, Tom Wollschläger, Benedikt Poggel +2
Emerging quantum computing technologies, such as Noisy Intermediate-Scale Quantum (NISQ) devices, offer potential advancements in solving mathematical optimization problems. Howeve…
Towards Efficient MCMC Sampling in Bayesian Neural Networks by Exploiting Symmetry
Jonas Gregor Wiese, Lisa Wimmer, Theodore Papamarkou +3
Bayesian inference in deep neural networks is challenging due to the high-dimensional, strongly multi-modal parameter posterior density landscape. Markov chain Monte Carlo approach…
Accuracy is not the only Metric that matters: Estimating the Energy Consumption of Deep Learning Models
Johannes Getzner, Bertrand Charpentier, Stephan Günnemann
Modern machine learning models have started to consume incredible amounts of energy, thus incurring large carbon footprints (Strubell et al., 2019). To address this issue, we have…
Training, Architecture, and Prior for Deterministic Uncertainty Methods
Bertrand Charpentier, Chenxiang Zhang, Stephan Günnemann
Accurate and efficient uncertainty estimation is crucial to build reliable Machine Learning (ML) models capable to provide calibrated uncertainty estimates, generalize and detect O…
Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks
Jan Schuchardt, Aleksandar Bojchevski, Johannes Gasteiger +1
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…
Training Differentially Private Graph Neural Networks with Random Walk Sampling
Morgane Ayle, Jan Schuchardt, Lukas Gosch +2
Deep learning models are known to put the privacy of their training data at risk, which poses challenges for their safe and ethical release to the public. Differentially private st…