The document summarizes a presentation on machine learning methods for graph data and recent trends. It introduces graph data and common graph neural network (GNN) approaches, including Recurrent GNNs, Convolutional GNNs, Graph Autoencoders, Graph Adversarial Methods, and Spatial-Temporal GNNs. It then discusses the GNNExplainer method for explaining GNN predictions and concludes with an overview and outlook for future developments in the field.
SchNet: A continuous-filter convolutional neural network for modeling quantum...Kazuki Fujikawa
The document summarizes a paper about modeling quantum interactions using a continuous-filter convolutional neural network called SchNet. Some key points:
1) SchNet performs convolution using distances between nodes in 3D space rather than graph connectivity, allowing it to model interactions between arbitrarily positioned nodes.
2) This is useful for cases where graphs have different configurations that impact properties, or where graph and physical distances differ.
3) The paper proposes a continuous-filter convolutional layer and interaction block to incorporate distance information into graph convolutions performed by the SchNet model.
The document summarizes a presentation on machine learning methods for graph data and recent trends. It introduces graph data and common graph neural network (GNN) approaches, including Recurrent GNNs, Convolutional GNNs, Graph Autoencoders, Graph Adversarial Methods, and Spatial-Temporal GNNs. It then discusses the GNNExplainer method for explaining GNN predictions and concludes with an overview and outlook for future developments in the field.
SchNet: A continuous-filter convolutional neural network for modeling quantum...Kazuki Fujikawa
The document summarizes a paper about modeling quantum interactions using a continuous-filter convolutional neural network called SchNet. Some key points:
1) SchNet performs convolution using distances between nodes in 3D space rather than graph connectivity, allowing it to model interactions between arbitrarily positioned nodes.
2) This is useful for cases where graphs have different configurations that impact properties, or where graph and physical distances differ.
3) The paper proposes a continuous-filter convolutional layer and interaction block to incorporate distance information into graph convolutions performed by the SchNet model.