Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A PyTorch implementation of "Signed Graph Convolutional Network" (ICDM 2018).
| Date | Stars |
|---|---|
| 2026-07-24 | 275 |
| 2026-07-25 | 275 |
| 2026-07-28 | 275 |
| 2026-07-30 | 275 |
| 2026-08-06 | 275 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
SGCN ==================== [](https://arxiv.org/abs/1808.06354) [](https://github.com/benedekrozemberczki/SGCN/archive/master.zip) [](https://codebeat.co/projects/github-com-benedekrozemberczki-sgcn-master) [](https://twitter.com/intent/follow?screen_name=benrozemberczki) A **PyTorch** implementation of **Signed Graph Convolutional Network (ICDM 2018)**. <div style="text-align:center"><img src ="sgcn.jpg" ,width=600/></div> ### Abstract <p align="justify"> Due to the fact much of today's data can be represented as graphs, there has been a demand for generalizing neural network models for graph data. One recent direction that has shown fruitful results, and therefore growing interest, is the usage of graph convolutional neural networks (GCNs). They have been shown to provide a significant improvement on a wide range of tasks in network analysis, one of which being node representation learning. The task of learning low-dimensional node representations has shown to increase performance on a plethora of other tasks from link prediction and node classification, to community detection and visualization. Simultaneously, signed networks (or graphs having both positive and negative links) have become ubiquitous with the growing popularity of social media. However, since previous GCN models have primarily focused on unsigned networks (or graphs consisting of only positive links), it is unclear how they could be applied to signed networks due to the challenges presented by negative links. The primary challenges are based on negative links having not only a different semantic meaning as compared to positive links, but their principles are inherently different and they form complex relations with positive links. Therefore we propose a dedicated and principled effort that utilizes balance theory to correctly aggregate and propagate the information across layers of a signed GCN model. We perform empirical experiments comparing our proposed signed GCN against state-of-the-art baselines for learning node representations in signed networks. More specifically, our experiments are performed on four real-world datasets for the classical link sign prediction problem that is commonly used as the benchmark for signed network embeddings algorithms. </p> This repository provides an implementation for SGCN as described in the paper: > Signed Graph Convolutional Network. > Tyler Derr, Yao Ma, and Jiliang Tang > ICDM, 2018. > [[Paper]](https://arxiv.org/abs/1808.06354) The original implementation is available [[here]](https://www.cse.msu.edu/~derrtyle/code/SGCN.zip) and SGCN is also available in [[PyTorch Geometric]](https://github.com/rusty1s/pytorch_geometric). ### Requirements The codebase is implemented in Python 3.5.2. package versions used for development are just below. ``` networkx 2.4 tqdm 4.28.1 numpy 1.15.4 pandas 0.23.4 texttable 1.5.0 scipy 1.1.0 argparse 1.1.0 sklearn 0.20.0 torch 1.1.0 torch-scatter 1.4.0 torch-sparse 0.4.3 torch-cluster 1.4.5 torch-geometric 1.3.2 torchvision 0.3.0 ``` -------------------------------------------- ### Datasets <p align="justify"> The code takes an input graph in a csv file. Every row indicates an edge between two nodes separated by a comma. The first row is a header. Nodes should be indexed starting with 0. Sample graphs for the `Bitcoin Alpha` and `Bitcoin OTC` graphs are included in the `input/` directory. The structure of the edge dataset is the following: </p> | **NODE ID 1**| **NODE ID 2** | **Sign** | | --- | --- | --- | | 0 |
Excerpt of 7,952 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:d3714931e185f765, topic:deep-learning, topic:neural-network, topic:pytorch