Build and benchmark Graph Neural Networks with PyTorch Geometric.
npx skills add https://github.com/swaruplab/operon --skill torch-geometric-swaruplab
Please help me install this Agent Skill. Skill: torch-geometric Source: https://github.com/swaruplab/operon/tree/main/src-tauri/protocols/torch-geometric Command: npx skills add https://github.com/swaruplab/operon --skill torch-geometric-swaruplab
Graph Neural Network development and benchmarking on PyTorch Geometric, enabling researchers and engineers to implement, train, and evaluate node/graph classification, link prediction, and molecular-property tasks with practical guidance.
Install PyTorch and PyG, load a small dataset like Cora, and run a minimal Graph Neural Network example to see results.
High-intent search queries and answers about installing and using this skill.
To build Graph Neural Networks for node classification, this Skill provides ready-to-use templates and benchmark scripts using PyTorch Geometric. You can implement and evaluate models like GCN and GraphSAGE on standard citation datasets such as Cora.
Yes, you can implement link prediction and graph classification using PyG layers. It supplies model templates and examples for diverse graph architectures including GAT and GIN across social and molecular domains.
The best way to benchmark molecular property prediction tasks is using the provided benchmark scripts and PyG datasets. These templates allow researchers to efficiently train and evaluate graph neural networks on molecular data.
Yes, you need PyTorch, PyG, and NumPy installed as dependencies to run heterogeneous graph benchmarks. These frameworks provide the foundational tensor computations and graph structures required by the templates.
Yes, there are ready-to-use templates for social network graph analysis. The Skill includes examples covering social networks and citation networks to help developers quickly deploy graph neural network architectures.
OwnLabAITrain graph neural networks using PyG templates, datasets, and benchmarks.
danishsyed-devAutomate deployment of trained machine learning models into production environments.
jaechang-hitsCreate, manipulate, and analyze graphs with NetworkX centrality and pathfinding.
jackspaceDevelop and train graph neural networks with PyTorch Geometric.
