Papers › Federated Learning for Mobile Keyboard Prediction

Federated Learning for Mobile Keyboard Prediction

8 Nov 2018arXiv:1811.03604archive 2025-07-28

Andrew Hard, Kanishka Rao, Rajiv Mathews, Swaroop Ramaswamy, Françoise Beaufays, Sean Augenstein, Hubert Eichner, Chloé Kiddon, Daniel Ramage

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 11 code samples harvested from 2 repositories linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 11 samples from 2 repositories, 11 ran (11 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-25 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

LeoSerena/MSThesis mentioned on GitHubpytorchSyntology: not harvested report
MsAmberWelch/Privacy-Engineering mentioned on GitHubtfSyntology: not harvested report
google-parfait/tensorflow-federated mentioned on GitHubtfApache-2.0Syntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
gregor160300/federated mentioned on GitHubtfApache-2.0Syntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
steph-jung/GenieType mentioned on GitHubSyntology: not harvested report
tensorflow/federated mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Generative Models for Effective ML on Private, Decentralized Datasets (arXiv:1911.06679; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

11 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

11ran

Licence: 0 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

google-parfait/tensorflow-federated community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
adaptive_clip_noise_params tensorflow_federated/python/aggregators/differential_privacy.py ran Apache-2.0 (permissive) · 743db060f22b2c34 · report fixture: signature noise_multiplier:float/0/float, expected_clients_per_round:float/0/float, clipped_count_stddev:NoneType/0/? · returned tuple · level recorded 2026-09-25
estimate_wrapped_gaussian_stddev tensorflow_federated/python/aggregators/modular_clipping.py ran Apache-2.0 (permissive) · 7c56380675f7c9e3 · report fixture: signature values:EagerTensor/2/float, clip_lower:float/0/float, clip_upper:float/0/float · returned EagerTensor · level recorded 2026-09-25
fast_walsh_hadamard_transform tensorflow_federated/python/aggregators/hadamard.py ran Apache-2.0 (permissive) · 74f52a4a9d3443b5 · report fixture: signature x:ndarray/2/float · returned EagerTensor · level recorded 2026-09-25
inflated_l2_norm_bound tensorflow_federated/python/aggregators/discretization.py ran Apache-2.0 (permissive) · a93ebbc383daefa0 · report fixture: signature l2_norm_bound:float/0/float, gamma:float/0/float, beta:float/0/float, dim:int/0/int · returned EagerTensor · level recorded 2026-09-25
modular_clip_by_value tensorflow_federated/python/aggregators/modular_clipping.py ran Apache-2.0 (permissive) · 65c9f24a1a06cade · report fixture: signature value:EagerTensor/1/float, clip_range_lower:EagerTensor/0/float, clip_range_upper:EagerTensor/0/float · returned EagerTensor · level recorded 2026-09-25
gregor160300/federated community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
build_linear_regression_keras_sequential_model tensorflow_federated/python/learning/model_examples.py ran Apache-2.0 (permissive) · 86ff254159d502d5 · report fixture: signature feature_dims:int/0/int · returned Sequential · level recorded 2026-09-26
build_linear_regression_ones_regularized_keras_sequential_model tensorflow_federated/python/learning/model_examples.py ran Apache-2.0 (permissive) · 79a8babc34f2bd53 · report fixture: signature feature_dims:int/0/int, regularization_constant:float/0/float · returned Sequential · level recorded 2026-09-26
build_linear_regression_regularized_keras_sequential_model tensorflow_federated/python/learning/model_examples.py ran Apache-2.0 (permissive) · dd6ab888da5ee0a5 · report fixture: signature feature_dims:int/0/int, regularization_constant:float/0/float · returned Sequential · level recorded 2026-09-26
check_callable tensorflow_federated/python/common_libs/py_typecheck.py ran Apache-2.0 (permissive) · ec3b2ce65cc7f139 · report fixture: signature target:callable/0/?, label:str/0/str · returned function · level recorded 2026-09-26
check_subclass tensorflow_federated/python/common_libs/py_typecheck.py ran Apache-2.0 (permissive) · b7ba69da4f1670f1 · report fixture: signature target_class:callable/0/?, parent_class:callable/0/? · returned type · level recorded 2026-09-26
check_type in 6 papers tensorflow_federated/python/common_libs/py_typecheck.py ran Apache-2.0 (permissive) · 32a9add4ffaaa75e · report fixture: signature target:int/0/int, type_spec:callable/0/?, label:str/0/str · returned int · level recorded 2026-09-26

Tasks

Federated LearningLanguage ModelingLanguage ModellingPrediction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections