Model Planner Options

Fine-grained control over encoders, training strategy, and the AutoML search space.

Suggest Edits

Column Processing

• encoder_overrides

Model Architecture

• activation

• aggregation

• channels

• handle_new_target_entities

• module

• normalization

• num_post_message_passing_layers

• num_pre_message_passing_layers

• ranking_embedding_loss_coeff

• output_embedding_dim

• target_embedding_mode

• use_seq_id

• distance_measure

Neighbor Sampling

• max_target_neighbors_per_entity

• num_neighbors

Optimization

• base_lr

• batch_size

• early_stopping

• lr_scheduler

• majority_sampling_ratio

• max_epochs

• max_steps_per_epoch

• max_test_steps

• max_val_steps

• weight_decay

• weight_mode

Training Job Plan

• refit_full

• refit_trainval

• run_mode

• metrics

• num_experiments

• tune_metric

Training Table Generation

• entity_candidate_aggregation

• forecast_length

• forecast_type

• lag_timesteps

• split

• timeframe_step

• train_end_offset

• train_start_offset