SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2001.01523 · NeurIPS · 2020

Think Locally, Act Globally: Federated Learning with Local and Global Representations

Paul Liang, Terrance Liu, Ziyin Liu, Nicholas Allen, Randy Auerbach, David Brent, Ruslan Salakhutdinov, Louis-Philippe Morency

arXiv · PDF · Open in the Atlas

Code that ran

2 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 1 has no contract verdict; 1 failure of our instrument; 4 no recorded run), measured 2026-11-21; 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/2001.01523.json · badge: /api/ran/2001.01523.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
equialgo/fairness-in-ml canonical (classifier label)
classifier basis: census
2 ran · 1 no recorded run
TsingZ0/PFL-Non-IID community
Papers with Code archive
0 ran · 2 no recorded run
pliang279/LG-FedAvg marked official in Papers with Code
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
load_ICU_data Ran
ran on a synthesized input
equialgo/fairness-in-ml/fairness/helpers.py
code served (permissive licence) · get_code("0181c19a421956e8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import pandas as pd
import io

# Create a minimal CSV string that matches the expected format
csv_data = """25,Private,226802,11th,7,Never-married,Machine-op-inspct,Own-child,White,Male,0,0,40,United-States,<=50K
50,Self-emp-inc,191910,HS-grad,9,Married-civ-spouse,Exec-managerial,Husband,White,Female,15024,0,60,United-States,>50K
38,Private,215646,HS-grad,9,Divorced,Handlers-cleaners,Not-in-family,Black,Male,0,0,50,United-States,<=50K
53,Private,234721,1st-4th,1,Married-civ-spouse,Farming-fishing,Husband,Black,Female,0,0,40,United-States,<=50K
"""

# Write to a temporary file path
import tempfile
import os

temp_dir = tempfile.gettempdir()
temp_file = os.path.join(temp_dir, 'test_icu_data.csv')

with open(temp_file, 'w') as f:
    f.write(csv_data)

ARGS = {
    'path': temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
p_rule Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
equialgo/fairness-in-ml/fairness/helpers.py
pointer only (licence: MIT); the stored copy get_code serves, from vincent-grari/FAGTB, is pointer only (licence: NONE) · get_code("a2d149f660861fa8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from vincent-grari/FAGTB, and GitHub detected no licence in that repository 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.

Client Not yet run
unverified (harvested, no recorded run)
TsingZ0/PFL-Non-IID/system/flcore/clients/clientlg.py
code served (permissive licence) · get_code("f4e73be5aa126345")
How it ran

no invocation recorded.

LocalUpdateMTL Not yet run
unverified (harvested, no recorded run)
pliang279/LG-FedAvg/models/Update.py
code served (permissive licence) · get_code("f65212878af7e7e8")
How it ran

no invocation recorded.

clientLG Not yet run
unverified (harvested, no recorded run)
TsingZ0/PFL-Non-IID/system/flcore/clients/clientlg.py
code served (permissive licence) · get_code("6131bb5c52732f46")
How it ran

no invocation recorded.

plot_distributions Not yet run
unverified (harvested, no recorded run)
equialgo/fairness-in-ml/fairness/helpers.py
code served (permissive licence) · get_code("d664e568b39b2254")
How it ran

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
Client
brick of this paper's assembly: helper
9 other papers
1 dated earlier, 8 later · 2 only as an assembly brick
1602.05629 (2016-02)
Communication-Efficient Learning of Deep Networks from Decentralized Data
2012.04221 (2020-12)
Ditto: Fair and Robust Federated Learning Through Personalization
2102.07623 (2021-02)
FedBN: Federated Learning on Non-IID Features via Local Batch Normalization
and 6 more not named here
p_rule 1 other paper
1 dated earlier
1911.05369 (2019-11)
Fair Adversarial Gradient Tree Boosting

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Federated learning is a method of training models on private data distributed over multiple devices. To keep device data private, the global model is trained by only communicating parameters and updates which poses scalability challenges for large models. To this end, we propose a new federated learning algorithm that jointly learns compact local representations on each device and a global model across all devices. As a result, the global model can be smaller since it only operates on local representations, reducing the number of communicated parameters. Theoretically, we provide a generalization analysis which shows that a combination of local and global models reduces both variance in the data as well as variance across device distributions. Empirically, we demonstrate that local models enable communication-efficient training while retaining performance. We also evaluate on the task of personalized mood prediction from real-world mobile data where privacy is key. Finally, local models handle heterogeneous data from new devices, and learn fair representations that obfuscate protected attributes such as race, age, and gender.

For agents

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

get_harvested_code_for_paper("2001.01523")
get_code_for_paper("2001.01523")
have("2001.01523")

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

curl https://syntology.ai/api/ran/2001.01523.json

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

[![Syntology run record](https://syntology.ai/api/ran/2001.01523.svg)](https://syntology.ai/paper/2001.01523)

Connect an agent — have() is free.