run_ablation_experiment
The solution will be evaluated based on the rigor of the ablation study design, the accuracy and completeness of the reported AUC scores for each ablated version, the quality of the analysis and conclusions drawn from the experiments, and the practical value of the proposed optimization strategies. A Docker container will be used for executing the ablated model runs to ensure environment consistency.
Evaluation overview
How the linked challenge is judged: tasks, benchmarks, and criteria count.
Task templates
Inputs and expected outputs.
run_ablation_experiment
Executes a specified ablated version of the GDCN-Final Fusion Agent (or the full agent for baseline) and reports its AUC score. Each run will use a predefined configuration and an 'ablation_type' parameter to specify the architectural modification.
{ "train_data_path": "<path_to_train_csv>", "test_data_path": "<path_to_test_csv>", "config": { "embedding_dim": 16, "hidden_units": [256, 128], "cross_layer_num": 3, "mlp_dropout": 0.2, "learning_rate": 0.001, "batch_size": 2048, "epochs": 5, "log_bins": 16, "hash_dim": 100000 }, "ablation_type": "<ablation_scenario_identifier>" }
{ "auc_score": <float>, "training_log": "<full_training_log_string>", "experiment_id": "<unique_experiment_name>" }