SEGO: Structural Entropy Guided Unsupervised Graph Out-Of-Distribution Detection

SEGO is an unsupervised framework designed to improve the reliability of graph neural networks (GNNs) by detecting out-of-distribution (OOD) samples during testing. With the increasing amount of unlabeled data, OOD detection is crucial for ensuring the reliability of GNNs. Existing methods often struggle with redundant information in graph structures, impairing their ability to differentiate between in-distribution (ID) and OOD data. SEGO addresses this challenge by integrating structural entropy into OOD detection for graph classification. It introduces an anchor view in the form of a coding tree by minimizing structural entropy, effectively removing redundant information while preserving essential structural information. SEGO also presents a multi-grained contrastive learning scheme at local, global, and tree levels using triplet views. Extensive experiments on real-world datasets demonstrate SEGO's superior performance over state-of-the-art baselines in OOD detection.

Category: Machine Learning
Subcategory: Graph Neural Networks
Tags: OOD detectionGNNsstructural entropyunsupervised learning
AI Type: Machine Learning
Programming Languages: Python
Frameworks/Libraries: PyTorchDGL
Application Areas: Graph classificationanomaly detection
Manufacturer Company: N/A
Country: N/A
Algorithms Used

Contrastive learning, structural entropy

Model Architecture

Graph Neural Networks

Datasets Used

Real-world graph datasets

Performance Metrics

OOD detection accuracy, structural entropy

Deployment Options

Research environments

Cloud Based

No

On Premises

Yes

Features

Unsupervised OOD detection, structural entropy

Enterprise

No

Hardware Requirements

Standard computing resources

Supported Platforms

Linux, Windows, macOS

Interoperability

Compatible with GNN frameworks

Security Features

N/A

Compliance Standards

N/A

Certifications

N/A

Open Source

Yes

Source Code URL

http://N/A

Documentation URL

http://N/A

Community Support

Research community

Contributors

N/A

Training Data Size

Varies based on dataset

Inference Latency

Depends on model complexity

Energy Efficiency

Standard for GNNs

Explainability Features

N/A

Ethical Considerations

N/A

Known Limitations

Focus on specific OOD tasks

Industry Verticals

AI research, graph analysis

Use Cases

Improving GNN reliability

Customer Base

Researchers

Integration Options

Integrates with GNN frameworks

Scalability

Scalable with model size

Support Options

Community support

SLA

N/A

User Interface

Command-line

Multi-Language Support

No

Localization

N/A

Pricing Model

Open-source

Trial Availability

Yes

Partner Ecosystem

Research institutions

Patent Information

N/A

Regulatory Compliance

N/A

Version

N/A

Website URL

http://N/A

Service Type

Research tool

Has API

No

API Details

N/A

Business Model

Open-source

Price

0.00

Currency

N/A

License Type

Open-source

Release Date

01/01/1970

Last Update Date

01/01/1970

Contact Email

N/A

Contact Phone

N/A

Social Media Links

http://N/A

Other Features

N/A

Published

Yes