GOOD.networks.models.EERM
The implementation of Handling Distribution Shifts on Graphs: An Invariance Perspective.
Classes
|
EERM implementation adapted from https://github.com/qitianwu/GraphOOD-EERM. |
|
EERM's graph editer adapted from https://github.com/qitianwu/GraphOOD-EERM. |
- class GOOD.networks.models.EERM.EERMGCN(config)[source]
Bases:
GNNBasicEERM implementation adapted from https://github.com/qitianwu/GraphOOD-EERM.
- forward(*args, **kwargs)[source]
Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Moduleinstance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
- class GOOD.networks.models.EERM.Graph_Editer(K, n, device)[source]
Bases:
ModuleEERM’s graph editer adapted from https://github.com/qitianwu/GraphOOD-EERM.
- forward(edge_index, num_sample, k)[source]
Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Moduleinstance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.