FlexMF Explicit

This page analyzes the hyperparameter tuning results for the FlexMF scorer in explicit-feedback mode (a biased matrix factorization model trained with PyTorch).

Parameter Search Space

/home/mde48/lenskit/lenskit-codex/.venv/lib/python3.12/site-packages/ray/tune/search/sample.py:700: RayDeprecationWarning: The `base` argument is deprecated. Please remove it as it is not actually needed in this method.
Parameter Type Distribution Values Selected
embedding_size Integer LogUniform 4 ≤ \(x\) ≤ 512 7
regularization Float LogUniform 0.0001 ≤ \(x\) ≤ 10 0.0684
learning_rate Float LogUniform 0.001 ≤ \(x\) ≤ 0.1 0.0138
reg_method Categorical Uniform L2, AdamW L2

Final Result

Searching selected the following configuration:

{
    'embedding_size': 7,
    'regularization': 0.06838895250370292,
    'learning_rate': 0.013750991205410215,
    'reg_method': 'L2',
    'epochs': 9
}

With these metrics:

{
    'RBP': 0.00796778659473439,
    'LogRBP': -1.0381085720761023,
    'NDCG': 0.1686059025449284,
    'RecipRank': 0.03311863852055791,
    'RMSE': 0.821408136161846,
    'TrainTask': 'c761cfea-e65d-453d-8674-58b9d079a975',
    'TrainTime': None,
    'TrainCPU': None,
    'max_epochs': 50,
    'done': True,
    'training_iteration': 9,
    'trial_id': '7bee5d84',
    'date': '2025-05-04_21-17-13',
    'timestamp': 1746407833,
    'time_this_iter_s': 2.425473690032959,
    'time_total_s': 22.48616647720337,
    'pid': 2508578,
    'hostname': 'CCI-ws21',
    'node_ip': '10.248.127.152',
    'config': {
        'embedding_size': 7,
        'regularization': 0.06838895250370292,
        'learning_rate': 0.013750991205410215,
        'reg_method': 'L2',
        'epochs': 9
    },
    'time_since_restore': 2.425473690032959,
    'iterations_since_restore': 1
}

Parameter Analysis

Embedding Size

The embedding size is the hyperparameter that most affects the model’s fundamental logic, so let’s look at performance as a fufnction of it:

Learning Parameters

Iteration Completion

How many iterations, on average, did we complete?

How did the metric progress in the best result?

How did the metric progress in the longest results?