Papers on Dynamic Graph Representation Learning.
1.Goyal P, Kamra N, He X, et al. DynGEM: Deep Embedding Method for Dynamic Graphs. 2018. paper
DynGEM将动态图分成了K个graph snapshot, 第l+1层的参数由第l层的参数初始化,通过增加编码器的layer的宽度和深度来自动构建neural network,相邻的layer需满足自定义的PropSize条件,这样最终生成的embedding具有一定的稳定性(stable constant).
2.Pandhre S, Mittal H, Gupta M, et al. STWalk: Learning Trajectory Representations in Temporal Graphs. 2017. paper code
时空随机游走
3.Li J, Dani H, Hu X, et al. Attributed Network Embedding for Learning in a Dynamic Environment. 2017:387-396. paper
1.Bamler R, Mandt S. Dynamic Word Embeddings. 2017. ICML. paper
2.Rudolph M, Blei D. Dynamic Bernoulli Embeddings for Language Evolution. 2018. WWW. paper
1.Li Y, Yu R, Shahabi C, et al. Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting. 2017. paper code
2.Yang C, Liu M, Wang Z, et al. Graph Clustering with Dynamic Embedding. 2017. paper
3.multivariate time series imputation with generative adversarial networks. NIPS 2018.paper
1.Learning Graph Embeddings with Embedding Propagation. Alberto Garcia Duran, Mathias Niepert. NIPS 2017.
- Structual RNN: Deep Learning on Spatio-Temporal Graphs CVPR 2016