UKNN Explicit

This page analyzes the hyperparameter tuning results for the ItemKNN scorer in explicit-feedback mode.

Parameter Search Space

Parameter Type Distribution Values Selected
max_nbrs Integer Uniform 2 ≤ \(x\) ≤ 50 44
min_nbrs Integer Uniform 1 ≤ \(x\) ≤ 5 2
min_sim Float LogUniform 1e-06 ≤ \(x\) ≤ 0.1 0.00133

Final Result

Searching selected the following configuration:

{'max_nbrs': 44, 'min_nbrs': 2, 'min_sim': 0.001330337565464905}

With these metrics:

{
    'RBP': 0.00336892276149632,
    'LogRBP': -1.898922271289102,
    'NDCG': 0.17841618026896675,
    'RecipRank': 0.0224189871977336,
    'RMSE': 0.9440722221104556,
    'TrainTask': '169daea6-6bd4-4083-ac8c-a8e7f9bfa905',
    'TrainTime': 0.03493551997235045,
    'TrainCPU': 0.03678500000000007,
    'TestTask': '705dd83d-b432-44ec-a826-f5edd4f263d8',
    'TestTime': 0.8614842239767313,
    'TestCPU': 0.8692889999999999,
    'timestamp': 1746652185,
    'checkpoint_dir_name': None,
    'done': True,
    'training_iteration': 1,
    'trial_id': '1d455681',
    'date': '2025-05-07_17-09-45',
    'time_this_iter_s': 1.0597987174987793,
    'time_total_s': 1.0597987174987793,
    'pid': 1242791,
    'hostname': 'gracehopper1',
    'node_ip': '192.168.225.60',
    'config': {'max_nbrs': 44, 'min_nbrs': 2, 'min_sim': 0.001330337565464905},
    'time_since_restore': 1.0597987174987793,
    'iterations_since_restore': 1,
    'experiment_tag': '56_max_nbrs=44,min_nbrs=2,min_sim=0.0013'
}

Parameter Behavior

Neighborhood Size

The neighborhood size is key argument to consider, let’s look at RMSE with repspect to that:

Filtering

There are two filtering parameters we also test — minimum neighbors and mininmum simialrity.