Comments (4)
Hi there, thanks for posting this. One thing to note is unsupervised models, especially anomaly detection algorithms, are notoriously hard to tune. We have some recent works in this direction for unsupervised outlier model selection/tuning [1], while it is still unclear how to do this deep models like GNNs.
You are welcome to propose or bring some new ideas for this. Let us whether we could work something out together. Thanks
[1] Zhao, Y., Rossi, R. and Akoglu, L., 2021. Automatic Unsupervised Outlier Model Selection. Advances in Neural Information Processing Systems, 34.
from pygod.
Hi, thankyou for the response.
Aa a start I am planning to use it for time series data.
Data: https://github.com/d-ailin/GDN
from pygod.
Hi, thankyou for the response.
Aa a start I am planning to use it for time series data.
Let me know if this works
from pygod.
Our library is designed for handling anomalies in graph data, we would not consider applying it to time-series data for now.
from pygod.
Related Issues (20)
- loss of GAAN is nan HOT 1
- Doesn’t benchmark’s main.py support the implementation of CoLA and RADAR methods? HOT 1
- Reproduced performance is different from the report HOT 1
- Unable to load graphs HOT 1
- Out of memory HOT 1
- same parameters but result varys HOT 1
- Why DOMINANT model has struct decoder? HOT 4
- LOF model HOT 1
- Unclear if pygod is for supervised outlier detection only HOT 1
- Hard to run benchmark scripts directly HOT 3
- How do you divide the training set and the testing set? HOT 1
- Inconsistency with BOND paper HOT 6
- Edge level anomaly detection HOT 1
- benchmark/main.py torch.mean(auc) throws error HOT 1
- Is any method to track metrics like loss? HOT 1
- Curious about the ANEMONE algorithm HOT 2
- The model is not using GPU when I run benchmark/main.py. HOT 2
- Running issues with GAAN (Prediction probabilities are all NANs) HOT 2
- Edge Features HOT 3
- Sometimes loss of AdONE becomes 'nan'. HOT 8
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pygod.