Module training 

Training utilities for GNN models.

Provides training loop utilities, optimizers, and loss functions.

Structs

Loss

Loss function implementations for neural network training.

OnlineConfig

Configuration for online learning

Optimizer

Optimizer for parameter updates

TrainConfig

Configuration for contrastive learning training

TrainingConfig

TODO: Implement training configuration

Enums

LossType

Loss function types

OptimizerType

Optimizer types

Functions

info_nce_loss

Compute InfoNCE contrastive loss

local_contrastive_loss

Compute local contrastive loss for graph structures

sgd_step

Perform a single SGD (Stochastic Gradient Descent) optimization step