Github page for the paper "Variational Recurrent Neural Networks for Graph Classification" presented at the RLGM workshop of ICLR 2019

Given a set of time series of individual activities, our goal is to identify periods of coordinated activity, find factions of coordination if more than one exist, as well as identify leaders of ea…

Learning Topological Representation for Networks via Hierarchical Sampling

Reference: @article{chen2019lstm, title={E-LSTM-D: A Deep Learning Framework for Dynamic Network Link Prediction}, author={Chen, Jinyin and Zhang, Jian and Xu, Xuanheng and Fu, Chengbo and Zhang, D…

Dynamic Network Analysis library

This is the releasing code for the paper: "Temporal Motif-based Attentional Graph Convolutional Network for Dynamic Link Prediction"

Use ML to predict missing links in a graph

Link Prediction with Signed Latent Factors in Signed Social Networks (KDD 2019)

A Python API for NOESIS

DEBS 2021: Graph Stream Analytics tutorial

This repository shows an implementation of the VGAE based model with PyTorch.

A graph mining problem where the task was to predict a link between the given nodes. Engineered different features like Jaccard Distance, Cosine-Similarity, Shortest Path, Page Rank, Adar Index, HI…

Python 3 supported version for DySAT

Bipartite-network link prediction in Python

Continuous-Time Relationship Prediction in Dynamic Heterogeneous Information Networks (TKDD 2019)

LEAP (Learning Edges by Aggregation of Paths)

Link Prediction models on Networks

A GP-GPU/CPU Dynamic Time Warping (DTW) implementation for the analysis of Multivariate Time Series (MTS).

Reference implementation of the paper VERSE: Versatile Graph Embeddings from Similarity Measures

Algorithms for learning network structure from effective resistances and other random-walk-based similarities.

基于某城市移动终端用户的运营商数据预测未来三月内用户是否会终端变迁(用户从当前使用的手机品牌更换为其他手机品牌)。应用xgboost算法和随机森林算法组合成多学习器预测模型。

Update

Easy link prediction tool

k-hop Graph Neural Networks

Official repository for the paper "Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting" (TPAMI'22) https://arxiv.org/abs/2006.09252

Code for "Weisfeiler and Leman go sparse: Towards higher-order graph embeddings"

A Persistent Weisfeiler–Lehman Procedure for Graph Classification

Dynamic Network Embedding by Modeling Triadic Closure Process

Evolving Network Representation Learning Based on Random Walks

Representation learning on dynamic graphs using self-attention networks