GOOD.networks.models
This module includes GNNs used in our leaderboard. It includes: GINs, GINvirtualnodes, and GCNs, in which GCNs are only for node classifications.
Modules
Base classes for Graph Neural Networks |
|
Implementation of the CIGA algorithm from "Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs" paper |
|
Applies a linear transformation to complete classification from representations. |
|
GCN implementation of the Deep Coral algorithm from "Deep CORAL: Correlation Alignment for Deep Domain Adaptation" paper |
|
GIN and GIN-virtual implementation of the Deep Coral algorithm from "Deep CORAL: Correlation Alignment for Deep Domain Adaptation" paper |
|
GCN implementation of the DANN algorithm from "Domain-Adversarial Training of Neural Networks" paper |
|
GIN and GIN-virtual implementation of the DANN algorithm from "Domain-Adversarial Training of Neural Networks" paper |
|
The implementation of Discovering Invariant Rationales for Graph Neural Networks. |
|
The implementation of Handling Distribution Shifts on Graphs: An Invariance Perspective. |
|
The Graph Neural Network from the "Semi-supervised Classification with Graph Convolutional Networks" paper. |
|
Implementation of the GIL algorithm from "Learning Invariant Graph Representations for Out-of-Distribution Generalization". |
|
The Graph Neural Network from the "How Powerful are Graph Neural Networks?" paper. |
|
The Graph Neural Network from the "Neural Message Passing for Quantum Chemistry" paper. |
|
Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism <https://arxiv.org/abs/2201.12987>`_. |
|
GCN implementation of the Mixup algorithm from "Mixup for Node and Graph Classification" paper |
|
GIN and GIN-virtual implementation of the Mixup algorithm from "Mixup for Node and Graph Classification" paper |
|
Atom (node) and bond (edge) feature encoding specified for molecule data. |
|
The pooling classes for the use of the GNNs. |
|
GCN implementation of the SRGNN algorithm from "Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data" paper |