108 citations · 204 across the 10 of their papers we have counts for
10 papers
MatterSim-MT: A multi-task foundation model for in silico materials characterization
Han Yang, Xixian Liu, Chenxi Hu +25
Accurate property characterization is a major bottleneck in materials design. While first-principles methods and task-specific machine-learning models have driven important progres…
Probing the Limit of Heat Transfer in Inorganic Crystals with Deep Learning
Jielan Li, Zekun Chen, Qian Wang +21
Heat transfer is a fundamental property of matter. Research spanning decades has attempted to discover materials with exceptional thermal conductivity, yet the upper limit remains…
MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures
Han Yang, Chenxi Hu, Yichi Zhou +19
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 p…
Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions
Lukas Gosch, Simon Geisler, Daniel Sturm +3
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…
On the Robustness and Anomaly Detection of Sparse Neural Networks
Morgane Ayle, Bertrand Charpentier, John Rachwan +3
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 netwo…
Winning the Lottery Ahead of Time: Efficient Early Network Pruning
John Rachwan, Daniel Zügner, Bertrand Charpentier +3
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…
Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification
Maximilian Stadler, Bertrand Charpentier, Simon Geisler +2
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). N…
Robustness of Graph Neural Networks at Scale
Simon Geisler, Tobias Schmidt, Hakan Şirin +3
Graph Neural Networks (GNNs) are increasingly important given their popularity and the diversity of applications. Yet, existing studies of their vulnerability to adversarial attack…
Natural Posterior Network: Deep Bayesian Uncertainty for Exponential Family Distributions
Bertrand Charpentier, Oliver Borchert, Daniel Zügner +2
Uncertainty awareness is crucial to develop reliable machine learning models. In this work, we propose the Natural Posterior Network (NatPN) for fast and high-quality uncertainty e…
Language-Agnostic Representation Learning of Source Code from Structure and Context
Daniel Zügner, Tobias Kirschstein, Michele Catasta +2
Source code (Context) and its parsed abstract syntax tree (AST; Structure) are two complementary representations of the same computer program. Traditionally, designers of machine l…