Zobrazeno 1 - 10
of 41
pro vyhledávání: '"ZÜGNER, DANIEL"'
Autor:
Yang, Han, Hu, Chenxi, Zhou, Yichi, Liu, Xixian, Shi, Yu, Li, Jielan, Li, Guanzhi, Chen, Zekun, Chen, Shuizhou, Zeni, Claudio, Horton, Matthew, Pinsler, Robert, Fowler, Andrew, Zügner, Daniel, Xie, Tian, Smith, Jake, Sun, Lixin, Wang, Qian, Kong, Lingyu, Liu, Chang, Hao, Hongxia, Lu, Ziheng
Accurate and fast prediction of materials properties is central to the digital transformation of materials design. However, the vast design space and diverse operating conditions pose significant challenges for accurately modeling arbitrary material
Externí odkaz:
http://arxiv.org/abs/2405.04967
Autor:
Zeni, Claudio, Pinsler, Robert, Zügner, Daniel, Fowler, Andrew, Horton, Matthew, Fu, Xiang, Shysheya, Sasha, Crabbé, Jonathan, Sun, Lixin, Smith, Jake, Nguyen, Bichlien, Schulz, Hannes, Lewis, Sarah, Huang, Chin-Wei, Lu, Ziheng, Zhou, Yichi, Yang, Han, Hao, Hongxia, Li, Jielan, Tomioka, Ryota, Xie, Tian
The design of functional materials with desired properties is essential in driving technological advances in areas like energy storage, catalysis, and carbon capture. Generative models provide a new paradigm for materials design by directly generatin
Externí odkaz:
http://arxiv.org/abs/2312.03687
Autor:
Gosch, Lukas, Geisler, Simon, Sturm, Daniel, Charpentier, Bertrand, Zügner, Daniel, Günnemann, Stephan
Despite its success in the image domain, adversarial training did not (yet) stand out as an effective defense for Graph Neural Networks (GNNs) against graph structure perturbations. In the pursuit of fixing adversarial training (1) we show and overco
Externí odkaz:
http://arxiv.org/abs/2306.15427
Autor:
Arts, Marloes, Satorras, Victor Garcia, Huang, Chin-Wei, Zuegner, Daniel, Federici, Marco, Clementi, Cecilia, Noé, Frank, Pinsler, Robert, Berg, Rianne van den
Coarse-grained (CG) molecular dynamics enables the study of biological processes at temporal and spatial scales that would be intractable at an atomistic resolution. However, accurately learning a CG force field remains a challenge. In this work, we
Externí odkaz:
http://arxiv.org/abs/2302.00600
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 stochastic gradient descent is the de facto standard for training neural
Externí odkaz:
http://arxiv.org/abs/2301.00738
Autor:
Ayle, Morgane, Charpentier, Bertrand, Rachwan, John, Zügner, Daniel, Geisler, Simon, Günnemann, Stephan
The robustness and anomaly detection capability of neural networks are crucial topics for their safe adoption in the real-world. Moreover, the over-parameterization of recent networks comes with high computational costs and raises questions about its
Externí odkaz:
http://arxiv.org/abs/2207.04227
Autor:
Rachwan, John, Zügner, Daniel, Charpentier, Bertrand, Geisler, Simon, Ayle, Morgane, Günnemann, Stephan
Pruning, the task of sparsifying deep neural networks, received increasing attention recently. Although state-of-the-art pruning methods extract highly sparse models, they neglect two main challenges: (1) the process of finding these sparse models is
Externí odkaz:
http://arxiv.org/abs/2206.10451
Time series data are often corrupted by outliers or other kinds of anomalies. Identifying the anomalous points can be a goal on its own (anomaly detection), or a means to improving performance of other time series tasks (e.g. forecasting). Recent dee
Externí odkaz:
http://arxiv.org/abs/2112.14436
Autor:
Geisler, Simon, Schmidt, Tobias, Şirin, Hakan, Zügner, Daniel, Bojchevski, Aleksandar, Günnemann, Stephan
Graph Neural Networks (GNNs) are increasingly important given their popularity and the diversity of applications. Yet, existing studies of their vulnerability to adversarial attacks rely on relatively small graphs. We address this gap and study how t
Externí odkaz:
http://arxiv.org/abs/2110.14038
Autor:
Stadler, Maximilian, Charpentier, Bertrand, Geisler, Simon, Zügner, Daniel, Günnemann, Stephan
The interdependence between nodes in graphs is key to improve class predictions on nodes and utilized in approaches like Label Propagation (LP) or in Graph Neural Networks (GNN). Nonetheless, uncertainty estimation for non-independent node-level pred
Externí odkaz:
http://arxiv.org/abs/2110.14012