Graph convolutional neural networks with global attention for improved materials property prediction
نویسندگان
چکیده
منابع مشابه
Graph Convolutional Neural Networks for ADME Prediction in Drug Discovery
ADME in-silico methods have grown increasingly powerful over the past twenty years, driven by advances in machine learning and the abundance of high-quality training data generated by laboratory automation. Meanwhile, in the technology industry, deep-learning has taken o↵, driven by advances in topology design, computation, and data. The key premise of these methods is that the model is able to...
متن کاملDisease Protein Prediction with Graph Convolutional Networks
Human phenotypes – i.e. our characteristics, conditions and diseases – are not merely a product of our genetic constitution, but rather arise out of an intricate system of interactions between the proteins and other molecules in our cells. 1 This fact has inspired a huge effort to document and understand the network of those protein-protein interactions which we’ll refer to collectively as the ...
متن کاملGraph Classification with 2D Convolutional Neural Networks
Graph learning is currently dominated by graph kernels, which, while powerful, suffer some significant limitations. Convolutional Neural Networks (CNNs) offer a very appealing alternative, but processing graphs with CNNs is not trivial. To address this challenge, many sophisticated extensions of CNNs have recently been introduced. In this paper, we reverse the problem: rather than proposing yet...
متن کاملAdaptive Graph Convolutional Neural Networks
Graph Convolutional Neural Networks (Graph CNNs) are generalizations of classical CNNs to handle graph data such as molecular data, point could and social networks. Current filters in graph CNNs are built for fixed and shared graph structure. However, for most real data, the graph structures varies in both size and connectivity. The paper proposes a generalized and flexible graph CNN taking dat...
متن کاملKernel Graph Convolutional Neural Networks
Graph kernels have been successfully applied to many graph classification problems. Typically, a kernel is first designed, and then an SVM classifier is trained based on the features defined implicitly by this kernel. This two-stage approach decouples data representation from learning, which is suboptimal. On the other hand, Convolutional Neural Networks (CNNs) have the capability to learn thei...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Physical Chemistry Chemical Physics
سال: 2020
ISSN: 1463-9076,1463-9084
DOI: 10.1039/d0cp01474e