Node-level problems
- class NCMinibatchTrainer(model, scenario, optimizer_fn, loss_fn, device, **kwargs)[source]
The mini-batch trainer (with neighborhood sampler) for handling node classification (NC).
- Base:
NCTrainer
- afterInference(results, model, optimizer, _curr_batch, training_states)[source]
The event function to execute some processes right after the inference step (for training). We recommend performing backpropagation in this event function.
- Parameters
results (dict) – the returned dictionary from the event function inference.
model (torch.nn.Module) – the current trained model.
optimizer (torch.optim.Optimizer) – the current optimizer function.
curr_batch (object) – the data (or minibatch) for the current iteration.
curr_training_states (dict) – the dictionary containing the current training states.
- Returns
A dictionary containing the information from the results.
- inference(model, _curr_batch, training_states)[source]
The event function to execute inference step.
- Parameters
- Returns
A dictionary containing the inference results, such as prediction result and loss.
- prepareLoader(curr_dataset, curr_training_states)[source]
The event function to generate dataloaders from the given dataset for the current task.
- Parameters
- Returns
A tuple containing three dataloaders. The trainer considers the first dataloader, second dataloader, and third dataloader as dataloaders for training, validation, and test, respectively.
- processTrainingLogs(task_id, epoch_cnt, val_metric_result, train_stats, val_stats)[source]
(Optional) The event function to output the training logs.
- Parameters
task_id (int) – the index of the current task
epoch_cnt (int) – the index of the current epoch
val_metric_result (object) – the validation performance computed by the evaluator
train_stats (dict) – the reduced dictionary containg the final training outcomes.
val_stats (dict) – the reduced dictionary containg the final validation outcomes.
- class NCTrainer(model, scenario, optimizer_fn, loss_fn, device, **kwargs)[source]
The trainer for handling node classification (NC).
- Base:
BaseTrainer
- afterInference(results, model, optimizer, _curr_batch, training_states)[source]
The event function to execute some processes right after the inference step (for training). We recommend performing backpropagation in this event function.
- Parameters
results (dict) – the returned dictionary from the event function inference.
model (torch.nn.Module) – the current trained model.
optimizer (torch.optim.Optimizer) – the current optimizer function.
curr_batch (object) – the data (or minibatch) for the current iteration.
curr_training_states (dict) – the dictionary containing the current training states.
- Returns
A dictionary containing the information from the results.
- beforeInference(model, optimizer, _curr_batch, training_states)[source]
The event function to execute some processes right before inference (for training).
- inference(model, _curr_batch, training_states)[source]
The event function to execute inference step.
- Parameters
- Returns
A dictionary containing the inference results, such as prediction result and loss.
- initTrainingStates(scenario, model, optimizer)[source]
The event function to initialize the dictionary for storing training states (i.e., intermedeiate results).
- Parameters
scenario (begin.scenarios.common.BaseScenarioLoader) – the given ScenarioLoader to the trainer
model (torch.nn.Module) – the given model to the trainer
optmizer (torch.optim.Optimizer) – the optimizer generated from the given optimizer_fn
- Returns
Initialized training state (dict).
- predictionFormat(results)[source]
The helper function for formatting the prediction results before feeding the results to evaluator.
- Parameters
results (dict) – the dictionary containing the prediction results.
- prepareLoader(curr_dataset, curr_training_states)[source]
The event function to generate dataloaders from the given dataset for the current task.
- Parameters
- Returns
A tuple containing three dataloaders. The trainer considers the first dataloader, second dataloader, and third dataloader as dataloaders for training, validation, and test, respectively.
- processAfterEachIteration(curr_model, curr_optimizer, curr_training_states, curr_iter_results)[source]
The event function to execute some processes for every end of each epoch. Whether to continue training or not is determined by the return value of this function. If the returned value is False, the trainer stops training the current model in the current task.
Note
This function is called for every end of each epoch, and the event function
processAfterTrainingis called only when the learning on the current task has ended.- Parameters
curr_model (torch.nn.Module) – the current trained model.
curr_optimizer (torch.optim.Optimizer) – the current optimizer function.
curr_training_states (dict) – the dictionary containing the current training states.
curr_iter_results (dict) – the dictionary containing the training/validation results of the current epoch.
- Returns
A boolean value. If the returned value is False, the trainer stops training the current model in the current task.
- processAfterTraining(task_id, curr_dataset, curr_model, curr_optimizer, curr_training_states)[source]
The event function to execute some processes after training the current task.
Note
The event function
processAfterEachIterationis called for every end of each epoch, and this function is called only when the learning on the current task has ended.- Parameters
task_id (int) – the index of the current task.
curr_dataset (object) – The dataset for the current task.
curr_model (torch.nn.Module) – the current trained model.
curr_optimizer (torch.optim.Optimizer) – the current optimizer function.
curr_training_states (dict) – the dictionary containing the current training states.
- processBeforeTraining(task_id, curr_dataset, curr_model, curr_optimizer, curr_training_states)[source]
The event function to execute some processes before training.
- Parameters
task_id (int) – the index of the current task
curr_dataset (object) – The dataset for the current task.
curr_model (torch.nn.Module) – the current trained model.
curr_optimizer (torch.optim.Optimizer) – the current optimizer function.
curr_training_states (dict) – the dictionary containing the current training states.
- processEvalIteration(model, _curr_batch)[source]
The event function to handle every evaluation iteration.
- Parameters
model (torch.nn.Module) – the current trained model.
curr_batch (object) – the data (or minibatch) for the current iteration.
- Returns
A dictionary containing the outcomes (stats) during the evaluation iteration.
- processPretraining(pretrain_loader, curr_model, curr_training_states)[source]
The event function to execute some processes before training.
- Parameters
task_id (int) – the index of the current task
curr_dataset (object) – The dataset for the current task.
curr_model (torch.nn.Module) – the current trained model.
curr_optimizer (torch.optim.Optimizer) – the current optimizer function.
curr_training_states (dict) – the dictionary containing the current training states.
- processTrainIteration(model, optimizer, _curr_batch, training_states)[source]
The event function to handle every training iteration.
- Parameters
- Returns
A dictionary containing the outcomes (stats) during the training iteration.
- processTrainingLogs(task_id, epoch_cnt, val_metric_result, train_stats, val_stats)[source]
(Optional) The event function to output the training logs.
- Parameters
task_id (int) – the index of the current task
epoch_cnt (int) – the index of the current epoch
val_metric_result (object) – the validation performance computed by the evaluator
train_stats (dict) – the reduced dictionary containg the final training outcomes.
val_stats (dict) – the reduced dictionary containg the final validation outcomes.
- run(epoch_per_task=1)[source]
Run the overall process of graph continual learning optimization.
- Parameters
epoch_per_task (int) – maximum number of training epochs for each task
- Returns
The base trainer returns the dictionary containing the evaluation results on validation and test dataset. And each trainer for specific problem processes the results and outputs the matrix-shaped results for performances and the final evaluation metrics, such as AP, AF, INT, and FWT.