Twin Graph-based Anomaly Detection via Attentive Multi-Modal Learning for Microservice System

This is the Pytorch implementation of MSTGAD in the ASE 2023: Twin Graph-based Anomaly Detection via Attentive Multi-Modal Learning for Microservice System. You may refer to our paper for more details.

Environment

The repository has some important dependencies below

Ubuntu 18.04
Python 3.8
Pytorch 1.12.0
Pytorch_geometric == 2.2.0

Install other dependencies can be installed by:

pip install -r requirements.txt

Dataset

The MSDS datasets used in this paper can be downloaded from the Multi-Source Distributed System Data for AI-powered Analytics | Zenodo

The other dataset that we don’t have a permission to publish

The downloaded datasets can be put in the ‘data’ directory. The directory structure looks like:

${CODE_ROOT}
    ......
    |-- data
        |-- MSDS
            |-- concurrent_data

Training

To preprocess the data, run:

python util/pre_MSDS.py

To start training, run:

python main.py

Architecture

fig

Citation

$@ i n p r o c e e d i n g s H u a n g 2023 M S T G A D, a u t h o r = H u a n g, J u n a n d Y a n g, Y a n g a n d Y u, H a n g a n d L i, J i a n g u o a n d Z h e n g, X i a o, t i t l e = T w i n G r a p h - b a s e d A n o m a l y D e t e c t i o n v i a A t t e n t i v e M u l t i - M o d a l L e a r n i n g f o r M i c r o s e r v i c e S y s t e m, b o o k t i t l e = 38 t h I E E E / A C M I n t e r n a t i o n a l C o n f e r e n c e o n A u t o m a t e d S o f t w a r e E n g i n e e r i n g, A S E 2023, y e a r = 2023, p a g e = 66 - 78,$

Contact

For any questions w.r.t. MSTGAD, please submit them to Github Issues .