tff.learning.secure_aggregator
Stay organized with collections
Save and categorize content based on your preferences.
Creates secure aggregator with adaptive zeroing and clipping.
tff.learning.secure_aggregator(
*, zeroing: bool = True, clipping: bool = True, weighted: bool = True
) -> tff.aggregators.AggregationFactory
Zeroes out extremely large values for robustness to data corruption on
clients, clips to moderately high norm for robustness to outliers. After
weighting in mean, the weighted values are summed using cryptographic protocol
ensuring that the server cannot see individual updates until sufficient number
of updates have been added together. For details, see Bonawitz et al. (2017)
https://dl.acm.org/doi/abs/10.1145/3133956.3133982. In TFF, this is realized
using the tff.federated_secure_sum_bitwidth operator.
Args |
|---|
zeroing
|
Whether to enable adaptive zeroing for data corruption mitigation.
|
clipping
|
Whether to enable adaptive clipping in the L2 norm for robustness.
Note this clipping is performed prior to the per-coordinate clipping
required for secure aggregation.
|
weighted
|
Whether the mean is weighted (vs. unweighted).
|
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 2024-09-20 UTC.
[null,null,["Last updated 2024-09-20 UTC."],[],[],null,["# tff.learning.secure_aggregator\n\n\u003cbr /\u003e\n\n|-------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/federated/blob/v0.87.0 Version 2.0, January 2004 Licensed under the Apache License, Version 2.0 (the) |\n\nCreates secure aggregator with adaptive zeroing and clipping. \n\n tff.learning.secure_aggregator(\n *, zeroing: bool = True, clipping: bool = True, weighted: bool = True\n ) -\u003e ../../tff/aggregators/AggregationFactory\n\nZeroes out extremely large values for robustness to data corruption on\nclients, clips to moderately high norm for robustness to outliers. After\nweighting in mean, the weighted values are summed using cryptographic protocol\nensuring that the server cannot see individual updates until sufficient number\nof updates have been added together. For details, see Bonawitz et al. (2017)\nhttps://dl.acm.org/doi/abs/10.1145/3133956.3133982. In TFF, this is realized\nusing the [`tff.federated_secure_sum_bitwidth`](../../tff/federated_secure_sum_bitwidth) operator.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `zeroing` | Whether to enable adaptive zeroing for data corruption mitigation. |\n| `clipping` | Whether to enable adaptive clipping in the L2 norm for robustness. Note this clipping is performed prior to the per-coordinate clipping required for secure aggregation. |\n| `weighted` | Whether the mean is weighted (vs. unweighted). |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A [`tff.aggregators.AggregationFactory`](../../tff/aggregators/AggregationFactory). ||\n\n\u003cbr /\u003e"]]
View source on GitHub