GOOD.ood_algorithms.algorithms.GIL

Implementation of the GIL algorithm from “Learning Invariant Graph Representations for Out-of-Distribution Generalization” paper

Classes

GIL(config)

Implementation of the GIL algorithm from "Learning Invariant Graph Representations for Out-of-Distribution Generalization" paper

class GOOD.ood_algorithms.algorithms.GIL.GIL(config: Union[CommonArgs, Munch])

Bases: BaseOODAlg

Implementation of the GIL algorithm from “Learning Invariant Graph Representations for Out-of-Distribution Generalization” paper

Args:

config (Union[CommonArgs, Munch]): munchified dictionary of args (config.device, config.dataset.num_envs, config.ood.ood_param)

loss_postprocess(loss: Tensor, data: Batch, mask: Tensor, config: Union[CommonArgs, Munch], **kwargs) → Tensor

Process loss based on IGA algorithm

Parameters

• loss (Tensor) – base loss between model predictions and input labels

• data (Batch) – input data

• mask (Tensor) – NAN masks for data formats

• config (Union[CommonArgs, Munch]) – munchified dictionary of args (config.device, config.dataset.num_envs, config.ood.ood_param)

config = munchify({device: torch.device('cuda'),
                       dataset: {num_envs: int(10)},
                       ood: {ood_param: float(0.1)}
                       })

Returns (Tensor):

loss based on DIR algorithm

output_postprocess(model_output: Tensor, **kwargs) → Tensor

Process the raw output of model

Parameters

model_output (Tensor) – model raw output

Returns (Tensor):

model raw predictions.

stage_control(config: Union[CommonArgs, Munch])

Set valuables before each epoch. Largely used for controlling multi-stage training and epoch related parameter settings.

Parameters

config – munchified dictionary of args.