Orthogonal Bases for Equivariant Graph Learning

Orthogonal Bases for Equivariant Graph Learning is a framework for learning graph-structured data using graph neural networks (GNNs). Due to the permutation-invariant requirement of graph learning tasks, invariant and equivariant linear layers are essential. Previous work provided a maximal collection of these layers and a simple deep neural network model, k-IGN, for graph data defined on k-tuples of nodes. However, the high complexity of these layers makes k-IGNs computationally infeasible for k >= 3. This framework shows that a smaller dimension for the linear layers is sufficient to achieve the same expressive power. Two sets of orthogonal bases for the linear layers are provided, each with only 3(2^k-1)-k basis elements. Based on these linear layers, neural network models GNN-a and GNN-b are developed, achieving the expressive power of the k-WL algorithm and the (k+1)-WL algorithm in graph isomorphism tests, respectively. In molecular prediction tasks on benchmark datasets, low-order neural network models with the proposed linear layers outperform other models.

Category: Artificial Intelligence
Subcategory: Graph Learning
Tags: graph neural networksequivariant learningorthogonal basesgraph isomorphism
AI Type: Deep Learning
Programming Languages: Python
Frameworks/Libraries: PyTorchDGL
Application Areas: Molecular predictiongraph isomorphism
Manufacturer Company: Academic institutions
Country: USA
Algorithms Used

Graph neural networks, orthogonal bases

Model Architecture

Graph neural networks

Datasets Used

Benchmark graph datasets

Performance Metrics

Expressive power, computational efficiency

Deployment Options

Cloud-based, on-premises

Cloud Based

Yes

On Premises

Yes

Features

Equivariant graph learning, orthogonal bases

Enterprise

Yes

Hardware Requirements

GPU for training

Supported Platforms

Linux, Windows, macOS

Interoperability

Compatible with existing graph learning frameworks

Security Features

None

Compliance Standards

None

Certifications

None

Open Source

No

Community Support

Limited community support

Contributors

Research team from leading universities

Training Data Size

Varies depending on the dataset

Inference Latency

Low

Energy Efficiency

Moderate

Explainability Features

None

Ethical Considerations

Ensuring ethical use of graph learning models

Known Limitations

Requires high-quality graph data

Industry Verticals

Chemistry, bioinformatics, data science

Use Cases

Molecular prediction, graph isomorphism tests

Customer Base

Research institutions, tech companies

Integration Options

Integrates with graph learning frameworks

Scalability

Scalable to large graph datasets

Support Options

Research team support

SLA

None

User Interface

Command-line interface

Multi-Language Support

Yes

Localization

English

Pricing Model

Research grant funded

Trial Availability

No

Partner Ecosystem

Academic collaborations

Patent Information

None

Regulatory Compliance

None

Version

1.0

Service Type

Research framework

Has API

No

Business Model

Academic research

Price

0.00

Currency

USD

License Type

Research license

Release Date

01/01/2023

Last Update Date

01/10/2023

Contact Phone

+1-800-555-0199

Social Media Links

http://None

Other Features

Supports efficient graph learning with orthogonal bases

Published

Yes