GNNLens2 is an interactive visualization tool designed for Graph Neural Networks (GNNs), enabling users to analyze, present, and explain GNN models. It offers seamless integration with the Deep Graph Library (DGL) and caters to diverse visualization needs for researchers and practitioners working with GNNs.

How It Works

GNNLens2 provides an interactive web-based interface for visualizing graph structures, node features, edge weights, and model explanations. It leverages DGL for efficient graph data handling and integrates with PyTorch, allowing users to explore GNN computations and outputs in a dynamic, visual manner.

Quick Start & Requirements

• Install via pip: pip install gnnlens
• Prerequisites: PyTorch, DGL, Flask-CORS.
• Installation from source is also supported for experimental features.
• Verification: import gnnlens; print(gnnlens.version)

Highlighted Details

• Interactive visualization of graph structures, node labels, edge weights, and attention.
• Supports weighted subgraphs and explanation methods.
• Seamless integration with Deep Graph Library (DGL).

Maintenance & Community

Developed by teams from HKUST VisLab, AWS Shanghai AI Lab, and SMU. Further community or roadmap information is not detailed in the README.

Licensing & Compatibility

The README does not explicitly state the license. Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

The project appears to be in its early stages, with the version listed as 0.1.0. Specific limitations, unsupported features, or known issues are not detailed in the provided README.