2021年1月19日 · 本文提出了一种连续图神经网络(CGNN)，它利用离散动力学概括现有的图形神经网络，通过建立连续的动态系统来改进模型性能，解决了over-smoothing问题，允许构建更深层次的网络，以捕获节点之间的长期依赖关系。

This repository contains the original implementation of the CGNN architectures described in the paper "Crystal Graph Neural Networks for Data Mining in Materials Science". Gilmer, et al. investigated various graph neural networks for predicting molecular properties, and proposed the neural message passing framework that unifies them.

2019年12月2日 · We propose continuous graph neural networks (CGNN), which generalise existing graph neural networks with discrete dynamics in that they can be viewed as a specific discretisation scheme.

2021年10月19日 · In this paper, we present a chained graph model on the packet stream to keep the chained compositional sequence. Next, we propose CGNN, a graph neural network based traffic classification method, which builds a graph classifier over automatically extracted features over the chained graph.

2024年10月31日 · 论文提出了一种新的因果推断方法，称为因果生成神经网络（Causal Generative Neural Network, CGNN）。CGNN利用生成神经网络来学习多变量因果机制，这是不同于传统的回归网络的方法。通过神经网络建模观测变量的联合分布，CGNN能够处理复杂的因果关系和噪声结构。

Train a CGCNN model with a customized dataset. Predict material properties of new crystals with a pre-trained CGCNN model. The following paper describes the details of the CGCNN framework: Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties.

2024年7月14日 · CGNN（因果生成神经网络）基于的是（Functional Causal Model, FCM），而不是传统的结构性因果模型（Structural Causal Model, SCM）。 在论文中， CGNN 采用生成 神经网络 来学习多变量因果机制，允许在没有显式函数限制的情况下表示复杂的因果关系。

2020年7月13日 · We propose continuous graph neural networks (CGNN), which generalise existing graph neural networks with discrete dynamics in that they can be viewed as a specific discretisation scheme. The key idea is how to characterise the continuous dynamics of node representations, i.e. the derivatives of node representations, w.r.t. time. Inspired by ...

Replication code for the article "Learning Functional Causal Models with Generative Neural Networks" - GoudetOlivier/CGNN

The full architecture of CGNN is presented at CGNN's official site. Source: Crystal Graph Neural Networks for Data Mining in Materials Science