SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1811.03604 · 2018

Federated Learning for Mobile Keyboard Prediction

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 11 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
google-parfait/tensorflow-federated pwc_unofficial 5 of 5
gregor160300/federated pwc_unofficial 0 of 6
FunctionStatusWhere it lives
adaptive_clip_noise_params Ran google-parfait/tensorflow-federated/tensorflow_federated/python/aggregators/differential_privacy.py
code served (permissive licence) · get_code("743db060f22b2c34")
estimate_wrapped_gaussian_stddev Ran google-parfait/tensorflow-federated/tensorflow_federated/python/aggregators/modular_clipping.py
code served (permissive licence) · get_code("7c56380675f7c9e3")
fast_walsh_hadamard_transform Ran google-parfait/tensorflow-federated/tensorflow_federated/python/aggregators/hadamard.py
code served (permissive licence) · get_code("74f52a4a9d3443b5")
inflated_l2_norm_bound Ran google-parfait/tensorflow-federated/tensorflow_federated/python/aggregators/discretization.py
code served (permissive licence) · get_code("a93ebbc383daefa0")
modular_clip_by_value Ran google-parfait/tensorflow-federated/tensorflow_federated/python/aggregators/modular_clipping.py
code served (permissive licence) · get_code("65c9f24a1a06cade")
build_linear_regression_keras_sequential_model Not yet run gregor160300/federated/tensorflow_federated/python/learning/model_examples.py
code served (permissive licence) · get_code("86ff254159d502d5")
build_linear_regression_ones_regularized_keras_sequential_model Not yet run gregor160300/federated/tensorflow_federated/python/learning/model_examples.py
code served (permissive licence) · get_code("79a8babc34f2bd53")
build_linear_regression_regularized_keras_sequential_model Not yet run gregor160300/federated/tensorflow_federated/python/learning/model_examples.py
code served (permissive licence) · get_code("dd6ab888da5ee0a5")
check_callable Not yet run gregor160300/federated/tensorflow_federated/python/common_libs/py_typecheck.py
code served (permissive licence) · get_code("ec3b2ce65cc7f139")
check_subclass Not yet run gregor160300/federated/tensorflow_federated/python/common_libs/py_typecheck.py
code served (permissive licence) · get_code("b7ba69da4f1670f1")
check_type Not yet run gregor160300/federated/tensorflow_federated/python/common_libs/py_typecheck.py
code served (permissive licence) · get_code("32a9add4ffaaa75e")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We train a recurrent neural network language model using a distributed, on-device learning framework called federated learning for the purpose of next-word prediction in a virtual keyboard for smartphones. Server-based training using stochastic gradient descent is compared with training on client devices using the Federated Averaging algorithm. The federated algorithm, which enables training on a higher-quality dataset for this use case, is shown to achieve better prediction recall. This work demonstrates the feasibility and benefit of training language models on client devices without exporting sensitive user data to servers. The federated learning environment gives users greater control over the use of their data and simplifies the task of incorporating privacy by default with distributed training and aggregation across a population of client devices.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1811.03604")
get_code_for_paper("1811.03604")
have("1811.03604")

Connect an agent — have() is free.