Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Wollschläger, Tom"'
Publikováno v:
International Conference on Quantum Computing and Engineering (QCE), 2024
Quantum machine learning uses principles from quantum mechanics to process data, offering potential advances in speed and performance. However, previous work has shown that these models are susceptible to attacks that manipulate input data or exploit
Externí odkaz:
http://arxiv.org/abs/2408.01200
Publikováno v:
International Conference on Quantum Computing and Engineering, 2024
Breakthroughs in machine learning (ML) and advances in quantum computing (QC) drive the interdisciplinary field of quantum machine learning to new levels. However, due to the susceptibility of ML models to adversarial attacks, practical use raises sa
Externí odkaz:
http://arxiv.org/abs/2408.00895
We introduce a new framework for molecular graph generation with 3D molecular generative models. Our Synthetic Coordinate Embedding (SyCo) framework maps molecular graphs to Euclidean point clouds via synthetic conformer coordinates and learns the in
Externí odkaz:
http://arxiv.org/abs/2406.10513
Publikováno v:
International Conference on Machine Learning. 2024. Oral
Although recent advances in higher-order Graph Neural Networks (GNNs) improve the theoretical expressiveness and molecular property predictive performance, they often fall short of the empirical performance of models that explicitly use fragment info
Externí odkaz:
http://arxiv.org/abs/2406.08210
In domains with interdependent data, such as graphs, quantifying the epistemic uncertainty of a Graph Neural Network (GNN) is challenging as uncertainty can arise at different structural scales. Existing techniques neglect this issue or only distingu
Externí odkaz:
http://arxiv.org/abs/2406.04043
Autor:
Fuchsgruber, Dominik, Wollschläger, Tom, Charpentier, Bertrand, Oroz, Antonio, Günnemann, Stephan
Uncertainty Sampling is an Active Learning strategy that aims to improve the data efficiency of machine learning models by iteratively acquiring labels of data points with the highest uncertainty. While it has proven effective for independent data it
Externí odkaz:
http://arxiv.org/abs/2405.01462
Autor:
Geisler, Simon, Wollschläger, Tom, Abdalla, M. H. I., Gasteiger, Johannes, Günnemann, Stephan
Current LLM alignment methods are readily broken through specifically crafted adversarial prompts. While crafting adversarial prompts using discrete optimization is highly effective, such attacks typically use more than 100,000 LLM calls. This high c
Externí odkaz:
http://arxiv.org/abs/2402.09154
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 particular, we use adversarial robustness as a tool to uncover a signific
Externí odkaz:
http://arxiv.org/abs/2308.08173
Autor:
Wollschläger, Tom, Gao, Nicholas, Charpentier, Bertrand, Ketata, Mohamed Amine, Günnemann, Stephan
Graph Neural Networks (GNNs) are promising surrogates for quantum mechanical calculations as they establish unprecedented low errors on collections of molecular dynamics (MD) trajectories. Thanks to their fast inference times they promise to accelera
Externí odkaz:
http://arxiv.org/abs/2306.14916
Autor:
Franco, Nicola, Wollschläger, Tom, Poggel, Benedikt, Günnemann, Stephan, Lorenz, Jeanette Miriam
Emerging quantum computing technologies, such as Noisy Intermediate-Scale Quantum (NISQ) devices, offer potential advancements in solving mathematical optimization problems. However, limitations in qubit availability, noise, and errors pose challenge
Externí odkaz:
http://arxiv.org/abs/2305.00472