Papers › On Privacy and Personalization in Cross-Silo Federated Learning

On Privacy and Personalization in Cross-Silo Federated Learning

16 Jun 2022arXiv:2206.07902archive 2025-07-28

Ziyu Liu, Shengyuan Hu, Zhiwei Steven Wu, Virginia Smith

While the application of differential privacy (DP) has been well-studied in cross-device federated learning (FL), there is a lack of work considering DP and its implications for cross-silo FL, a setting characterized by a limited number of clients each containing many data subjects. In cross-silo FL, usual notions of client-level DP are less suitable as real-world privacy regulations typically concern the in-silo data subjects rather than the silos themselves. In this work, we instead consider an alternative notion of silo-specific sample-level DP, where silos set their own privacy targets for their local examples. Under this setting, we reconsider the roles of personalization in federated learning. In particular, we show that mean-regularized multi-task learning (MR-MTL), a simple personalization framework, is a strong baseline for cross-silo FL: under stronger privacy requirements, silos are incentivized to federate more with each other to mitigate DP noise, resulting in consistent improvements relative to standard baseline methods. We provide an empirical study of competing methods as well as a theoretical characterization of MR-MTL for mean estimation, highlighting the interplay between privacy and cross-silo data heterogeneity. Our work serves to establish baselines for private cross-silo FL as well as identify key directions of future work in this area.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2206.07902")

Code

Syntology Ran 0 of 15 code samples harvested from 1 repository linked to this paper; 15 have no recorded run.

By repository: official repository: 15 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

kenziyuliu/private-cross-silo-fl officialmentioned in papermentioned on GitHubjaxMIT 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.

Code Syntology ran Syntology

15 samples harvested; 0 ran; 0 honoured the contract we drafted; 15 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

15unverified

Licence: 0 of the 15 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 kenziyuliu/private-cross-silo-fl. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

adni_model_fn kenziyuliu/private-cross-silo-fl/model_utils.py official repository unverified MIT (permissive) · d0ad384613d1ddd7 · report
bce_loss_hk kenziyuliu/private-cross-silo-fl/jax_utils.py official repository unverified MIT (permissive) · 8d57c71462cecacc · report
client_selection kenziyuliu/private-cross-silo-fl/utils.py official repository unverified MIT (permissive) · 8e1f359e172ce751 · report
hinge_loss_hk kenziyuliu/private-cross-silo-fl/jax_utils.py official repository unverified MIT (permissive) · 3ff20cad26a0cbfa · report
linear_model_fn kenziyuliu/private-cross-silo-fl/model_utils.py official repository unverified MIT (permissive) · 1e50f08e3b522640 · report
mnist kenziyuliu/private-cross-silo-fl/data_utils/rotated_mnist.py official repository unverified MIT (permissive) · ba51367756a7ee91 · report
mnist_model_fn kenziyuliu/private-cross-silo-fl/model_utils.py official repository unverified MIT (permissive) · 96103f2020a4840b · report
read_data kenziyuliu/private-cross-silo-fl/data_utils/adni_dataset.py official repository unverified MIT (permissive) · c9a99bc81bc03fae · report
read_gleam_data kenziyuliu/private-cross-silo-fl/utils.py official repository unverified MIT (permissive) · 08e7e8d3e346c69d · report
read_image kenziyuliu/private-cross-silo-fl/data_utils/adni_dataset.py official repository unverified MIT (permissive) · 50f93eef977f4e82 · report
read_vehicle_data kenziyuliu/private-cross-silo-fl/utils.py official repository unverified MIT (permissive) · fce14827432eb2fc · report
rotated_mnist kenziyuliu/private-cross-silo-fl/data_utils/rotated_mnist.py official repository unverified MIT (permissive) · 50a1d1d5aed7afad · report
rotated_patched_mnist kenziyuliu/private-cross-silo-fl/data_utils/rotated_mnist.py official repository unverified MIT (permissive) · 48ee242f558e091a · report
sce_loss_hk kenziyuliu/private-cross-silo-fl/jax_utils.py official repository unverified MIT (permissive) · 5dca586694a038ce · report
trunc_neg_binom_expectation kenziyuliu/private-cross-silo-fl/plot_hparam_cost.py official repository unverified MIT (permissive) · 659cdbeeafbc296c · report

Tasks

Federated LearningMulti-Task Learning

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