SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.07002 · ICML · 2025

Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off

Jian Shen, Lei Yang, Zibin Zheng, Tong Wang, Bin Chen, Jian Lou, Yuecheng Li, Lele Fu, Chuan Chen

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 3 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2402.07002.json · badge: /api/ran/2402.07002.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
6lyc/fedceo_collaborate-with-each-other canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
average_weights Ran
ran; our contract draft was wrong, not the code
6lyc/fedceo_collaborate-with-each-other/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from danielmanu93/Conditional-GraphGANFed, is pointer only (licence: NONE) · get_code("ab2485d028020739")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 6lyc/fedceo_collaborate-with-each-other when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

emnist_iid Ran
ran on a synthesized input
6lyc/fedceo_collaborate-with-each-other/sampling.py
pointer only (licence: NONE) · get_code("68acb6b0de8d92ae")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 6lyc/fedceo_collaborate-with-each-other when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

emnist_noniid Ran
ran; our contract draft was wrong, not the code
6lyc/fedceo_collaborate-with-each-other/sampling.py
pointer only (licence: NONE) · get_code("4479328371a2c3d2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 6lyc/fedceo_collaborate-with-each-other when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

label_to_onehot Ran
ran; our contract draft was wrong, not the code
6lyc/fedceo_collaborate-with-each-other/utils.py
pointer only (licence: NONE) · get_code("16ef0bab10ecc30a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 6lyc/fedceo_collaborate-with-each-other when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

test_inference Ran
ran on a synthesized input
6lyc/fedceo_collaborate-with-each-other/update.py
pointer only (licence: NONE) · get_code("1ac4b0319ab8b7e4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 6lyc/fedceo_collaborate-with-each-other when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

emnist_noniid_unequal Not yet run
unverified (harvested, no recorded run)
6lyc/fedceo_collaborate-with-each-other/sampling.py
pointer only (licence: NONE) · get_code("1b8df5754bbe364e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 6lyc/fedceo_collaborate-with-each-other when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 1 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
average_weights 5 other papers
1 dated earlier, 4 later
1908.07873 (2019-08)
Federated Learning: Challenges, Methods, and Future Directions
2405.09771 (2024-05)
Harmonizing Generalization and Personalization in Federated Prompt Learning
2409.19610 (2024-09)
Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method
and 2 more not named here
test_inference 2 other papers
2 dated earlier
1908.07873 (2019-08)
Federated Learning: Challenges, Methods, and Future Directions
2110.13864 (2021-10)
FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

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

Abstract

To defend against privacy leakage of user data, differential privacy is widely used in federated learning, but it is not free. The addition of noise randomly disrupts the semantic integrity of the model and this disturbance accumulates with increased communication rounds. In this paper, we introduce a novel federated learning framework with rigorous privacy guarantees, named FedCEO, designed to strike a trade-off between model utility and user privacy by letting clients "Collaborate with Each Other". Specifically, we perform efficient tensor low-rank proximal optimization on stacked local model parameters at the server, demonstrating its capability to flexibly truncate high-frequency components in spectral space. This capability implies that our FedCEO can effectively recover the disrupted semantic information by smoothing the global semantic space for different privacy settings and continuous training processes. Moreover, we improve the SOTA utility-privacy trade-off bound by order of √ d, where d is the input dimension. We illustrate our theoretical results with experiments on representative datasets and observe significant performance improvements and strict privacy guarantees under different privacy settings. The code is available at https://github.com/6lyc/FedCEO_ Collaborate-with-Each-Other.

For agents

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

get_harvested_code_for_paper("2402.07002")
get_code_for_paper("2402.07002")
have("2402.07002")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.07002.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.07002.svg)](https://syntology.ai/paper/2402.07002)

Connect an agent — have() is free.