例如BVAT(batch virtual adversarial training)算法,它的目的是通过产生虚拟对抗扰动(virtual adversarial perturbations)来感知图中节点间的连通模式(connectivity patterns),提高节点分类器输出分布的平滑性。 S-BVAT O-BVAT 文章A Survey of Adversarial Learning
In this survey, we comprehensively review the different types of deep learning methods on graphs. We divide the existing methods into five categories based on their model architectures and training strategies: graph recurrent neural networks, graph convolutional networks, graph autoencoders, graph ...
In recent years, variants of GNNs such as graph convolutional network (GCN), graph attention network (GAT), graph recurrent network (GRN) have demonstrated ground-breaking performances on many deep learning tasks. In this survey, we propose a general design pipeline for GNN models and discuss ...
If you find this repo useful, please cite: A Survey of Adversarial Learning on Graph, Arxiv'20, Link @article{chen2020survey, title={A Survey of Adversarial Learning on Graph}, author={Chen, Liang and Li, Jintang and Peng, Jiaying and Xie, Tao and Cao, Zengxu and Xu, Kun and He,...
Abstract&Introduction:Graph in deeping learning: 社交媒体、电商、生物网络、交通网络等等 不同的类别: 图循环、图卷积、图自编码、图增强学习、图对抗学习(graph recurrent neural networks, graph convolutional networks, graph autoencoders, graph reinforcement learning, and graph adversarial methods.) Graph RN...
(2021) conduct a comprehensive survey and analysis for embedding-based knowledge graph EA, and they divide the knowledge graph EA framework into two processes: embedding and alignment. Embedding history and methods based on TransE and graph convolutional networks are presented, and nearly 30 ...
A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challenges Wei Ju, Siyu Yi, Yifan Wang, Zhiping Xiao, Zhengyang Mao, Hourun Li, Yiyang Gu, Yifang Qin, Nan Yin, Senzhang Wang, Xinwang Liu, Xiao Luo, Philip S. Yu, Ming Zhang ...
graph diffusion graph sampling 1.2.1 Edge Addition/Dropping 即 保留原始节点顺序,对邻接矩阵种的元进行改写。 基于图稀疏性(graph sparsification)的图结构优化方法 [8、9],基于图结构整洁性(graph sanitation)的方法 [3],以及图采样(graph sampling)。
In graph-level representation learning tasks, graph neural networks have received much attention for their powerful feature learning capabilities. However,
CL aims to learn new knowledge incrementally without forgetting prior experience, approaches which follow the taxonomy as regularization-based, replay-based and architecture-based (Section 2.1.3). C…