tfr.keras.losses.YetiLogisticLoss
Stay organized with collections
Save and categorize content based on your preferences.
Computes Yeti logistic loss between y_true
and y_pred
.
tfr.keras.losses.YetiLogisticLoss(
reduction: tf.losses.Reduction = tf.losses.Reduction.AUTO,
name: Optional[str] = None,
lambda_weight: Optional[tfr.keras.losses.YetiDCGLambdaWeight
] = None,
temperature: float = 0.1,
sample_size: int = 8,
gumbel_temperature: float = 1.0,
seed: Optional[int] = None,
ragged: bool = False
)
Adapted to neural network models from the Yeti loss implemenation for GBDT in
(Lyzhin et al, 2022).
In this code base, we support Yeti loss with the DCG lambda weight option.
The default uses the YetiDCGLambdaWeight with default settings. To customize,
please set the lambda_weight to YetiDCGLambdaWeight.
For each list of scores s
in y_pred
and list of labels y
in y_true
:
loss = sum_a sum_i I[y_i > y_{i\pm 1}] * log(1 + exp(-(s^a_i - s^a_{i\pm 1})))
where
s^a_i = s_i + gumbel(0, 1)^a
Standalone usage:
y_true = [[1., 0.]]
y_pred = [[0.6, 0.8]]
loss = tfr.keras.losses.YetiLogisticLoss(sample_size=2, seed=1)
loss(y_true, y_pred).numpy()
0.90761846
# Using ragged tensors
y_true = tf.ragged.constant([[1., 0.], [0., 1., 0.]])
y_pred = tf.ragged.constant([[0.6, 0.8], [0.5, 0.8, 0.4]])
loss = tfr.keras.losses.YetiLogisticLoss(seed=1, ragged=True)
loss(y_true, y_pred).numpy()
0.43420443
Usage with the compile()
API:
model.compile(optimizer='sgd', loss=tfr.keras.losses.YetiLogisticLoss())
Definition:
\[
\mathcal{L}(\{y\}, \{s\}) =
\sum_a \sum_i \sum_{j=i\pm 1}I[y_i > y_j] \log(1 + \exp(-(s^a_i - s^a_j)))
\]
Args |
reduction
|
Type of tf.keras.losses.Reduction to apply to
loss. Default value is AUTO . AUTO indicates that the
reduction option will be determined by the usage context. For
almost all cases this defaults to SUM_OVER_BATCH_SIZE . When
used under a tf.distribute.Strategy , except via
Model.compile() and Model.fit() , using AUTO or
SUM_OVER_BATCH_SIZE will raise an error. Please see this
custom training tutorial
for more details.
|
name
|
Optional name for the instance.
|
Methods
from_config
View source
@classmethod
from_config(
config, custom_objects=None
)
Instantiates a Loss
from its config (output of get_config()
).
Args |
config
|
Output of get_config() .
|
get_config
View source
get_config() -> Dict[str, Any]
Returns the config dictionary for a Loss
instance.
__call__
View source
__call__(
y_true: tfr.keras.model.TensorLike
,
y_pred: tfr.keras.model.TensorLike
,
sample_weight: Optional[utils.TensorLike] = None
) -> tf.Tensor
See _RankingLoss.
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2023-09-29 UTC.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2023-09-29 UTC."],[],[],null,["# tfr.keras.losses.YetiLogisticLoss\n\n|--------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/ranking/blob/v0.5.3/tensorflow_ranking/python/keras/losses.py#L605-L715) |\n\nComputes Yeti logistic loss between `y_true` and `y_pred`. \n\n tfr.keras.losses.YetiLogisticLoss(\n reduction: tf.losses.Reduction = tf.losses.Reduction.AUTO,\n name: Optional[str] = None,\n lambda_weight: Optional[../../../tfr/keras/losses/YetiDCGLambdaWeight] = None,\n temperature: float = 0.1,\n sample_size: int = 8,\n gumbel_temperature: float = 1.0,\n seed: Optional[int] = None,\n ragged: bool = False\n )\n\nAdapted to neural network models from the Yeti loss implemenation for GBDT in\n([Lyzhin et al, 2022](https://arxiv.org/abs/2204.01500)).\n\nIn this code base, we support Yeti loss with the DCG lambda weight option.\nThe default uses the YetiDCGLambdaWeight with default settings. To customize,\nplease set the lambda_weight to YetiDCGLambdaWeight.\n\nFor each list of scores `s` in `y_pred` and list of labels `y` in `y_true`: \n\n loss = sum_a sum_i I[y_i \u003e y_{i\\pm 1}] * log(1 + exp(-(s^a_i - s^a_{i\\pm 1})))\n\nwhere \n\n s^a_i = s_i + gumbel(0, 1)^a\n\n#### Standalone usage:\n\n y_true = [[1., 0.]]\n y_pred = [[0.6, 0.8]]\n loss = tfr.keras.losses.YetiLogisticLoss(sample_size=2, seed=1)\n loss(y_true, y_pred).numpy()\n 0.90761846\n\n # Using ragged tensors\n y_true = tf.ragged.constant([[1., 0.], [0., 1., 0.]])\n y_pred = tf.ragged.constant([[0.6, 0.8], [0.5, 0.8, 0.4]])\n loss = tfr.keras.losses.YetiLogisticLoss(seed=1, ragged=True)\n loss(y_true, y_pred).numpy()\n 0.43420443\n\nUsage with the `compile()` API: \n\n model.compile(optimizer='sgd', loss=tfr.keras.losses.YetiLogisticLoss())\n\n#### Definition:\n\n\\\\\\[\n\\\\mathcal{L}(\\\\{y\\\\}, \\\\{s\\\\}) =\n\\\\sum_a \\\\sum_i \\\\sum_{j=i\\\\pm 1}I\\[y_i \\\u003e y_j\\] \\\\log(1 + \\\\exp(-(s\\^a_i - s\\^a_j)))\n\\\\\\]\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| References ---------- ||\n|---|---|\n| \u003cbr /\u003e - [Which Tricks are Important for Learning to Rank?, Lyzhin et al, 2022](https://arxiv.org/abs/2204.01500) ||\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `reduction` | Type of [`tf.keras.losses.Reduction`](https://www.tensorflow.org/api_docs/python/tf/keras/losses/Reduction) to apply to loss. Default value is `AUTO`. `AUTO` indicates that the reduction option will be determined by the usage context. For almost all cases this defaults to `SUM_OVER_BATCH_SIZE`. When used under a [`tf.distribute.Strategy`](https://www.tensorflow.org/api_docs/python/tf/distribute/Strategy), except via [`Model.compile()`](https://www.tensorflow.org/api_docs/python/tf/keras/Model#compile) and [`Model.fit()`](https://www.tensorflow.org/api_docs/python/tf/keras/Model#fit), using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see this custom training [tutorial](https://www.tensorflow.org/tutorials/distribute/custom_training) for more details. |\n| `name` | Optional name for the instance. |\n\n\u003cbr /\u003e\n\nMethods\n-------\n\n### `from_config`\n\n[View source](https://github.com/tensorflow/ranking/blob/v0.5.3/tensorflow_ranking/python/keras/losses.py#L310-L320) \n\n @classmethod\n from_config(\n config, custom_objects=None\n )\n\nInstantiates a `Loss` from its config (output of `get_config()`).\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ||\n|----------|---------------------------|\n| `config` | Output of `get_config()`. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ||\n|---|---|\n| A `Loss` instance. ||\n\n\u003cbr /\u003e\n\n### `get_config`\n\n[View source](https://github.com/tensorflow/ranking/blob/v0.5.3/tensorflow_ranking/python/keras/losses.py#L694-L701) \n\n get_config() -\u003e Dict[str, Any]\n\nReturns the config dictionary for a `Loss` instance.\n\n### `__call__`\n\n[View source](https://github.com/tensorflow/ranking/blob/v0.5.3/tensorflow_ranking/python/keras/losses.py#L703-L715) \n\n __call__(\n y_true: ../../../tfr/keras/model/TensorLike,\n y_pred: ../../../tfr/keras/model/TensorLike,\n sample_weight: Optional[utils.TensorLike] = None\n ) -\u003e tf.Tensor\n\nSee _RankingLoss."]]