Data

Tools

Indexes

Applications

Experiments

Open Source Science

036-graph-anomaly-detection-via-multi-scale-contrastive-learning-networks-with-augmented-view

https://github.com/szu-advtech-2024/036-graph-anomaly-detection-via-multi-scale-contrastive-learning-networks-with-augmented-view

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (10.0%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: SZU-AdvTech-2024
  • Default Branch: main
  • Size: 0 Bytes
Statistics
  • Stars: 0
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed over 1 year ago
Metadata Files
Citation

https://github.com/SZU-AdvTech-2024/036-Graph-Anomaly-Detection-via-Multi-Scale-Contrastive-Learning-Networks-with-Augmented-View/blob/main/ 

# Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View


   
    
      
    
        


Pytorch implement of paper [Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View](https://ojs.aaai.org/index.php/AAAI/article/view/25907) accepted by AAAI 2023.

An official source code for the paper: https://github.com/FelixDJC/GRADATE.

------



## Overview


    
    





    
    Figure 1: Overall framework of GRADATE.





## Requirements

This code requires the following:

- python==3.8

- torch==2.0.1

- dgl==0.4.3post2

- numpy==1.24.4

  

## Running the experiments

#### Step 1: Dataset Preparation and Anomaly Injection

Prepare the corresponding datasets. If the clean datasets downloaded from the official website or other datasets without anomalies, you need to manually run inject_anomaly.py to inject attribute and feature anomalies. Refer to the introduction of https://github.com/TrustAGI-Lab/CoLA.

#### Step 2: Anomaly Detection

This step is to run the framework to detect anomalies in the network datasets. Take Cora dataset as an example:

```
python run.py --dataset cora
```

The hyperparameters are set to be the values reported in the paper. 



## Citation

```
inproceedings{GRADATE,
  title={Graph anomaly detection via multi-scale contrastive learning networks with augmented view},
  author={Duan, Jingcan and Wang, Siwei and Zhang, Pei and Zhu, En and Hu, Jingtao and Jin, Hu and Liu, Yue and Dong, Zhibin},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={37},
  number={6},
  pages={7459--7467},
  year={2023}
}
```

Owner

  • Name: SZU-AdvTech-2024
  • Login: SZU-AdvTech-2024
  • Kind: organization

GitHub Events

Total
  • Push event: 2
  • Create event: 3
Last Year
  • Push event: 2
  • Create event: 3