SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.08394 · 2021

Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learning

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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 0 have no contract verdict; 2 failures of our instrument; 0 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/2110.08394.json · badge: /api/ran/2110.08394.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
ljaiverson/pfl-apple canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
read_results Ran
ran; our contract draft was wrong, not the code
ljaiverson/pfl-apple/plot_results.py
code served (permissive licence) · get_code("5adccbc662722d6a")
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 dict. 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 json
import os
import tempfile

# Create a temporary directory to hold test JSON files
temp_dir = tempfile.mkdtemp()

# Create test JSON files that the function will try to read
dsents_names = ['Dataset1', 'Dataset2']
methods_names = ['method_a', 'method_b']
distribution = 'uniform'

# Write test JSON files
for dn in dsents_names:
    for mn in methods_names:
        filename = os.path.join(temp_dir, '%s-%s-%s.json' % (dn.lower(), distribution, mn))
        test_data = {'score': 0.95, 'metrics': [1, 2, 3]}
        with open(filename, 'w') as f:
            json.dump(test_data, f)

# Define the arguments
ARGS = {
    'dsents_names': dsents_names,
    'methods_names': methods_names,
    'distribution': distribution,
    'path': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
val_with_local_model Ran
ran; our contract draft was wrong, not the code
ljaiverson/pfl-apple/train_APPLE.py
code served (permissive licence) · get_code("f4eb9862793a3597")
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 torch
import torch.nn as nn

torch.manual_seed(0)

# Define a small neural network model
class SimpleModel(nn.Module):
    def __init__(self, input_dim=4, num_classes=3):
        super(SimpleModel, self).__init__()
        self.fc = nn.Linear(input_dim, num_classes)
    
    def forward(self, x):
        return self.fc(x)

# Create client models
client_models = [
    SimpleModel(input_dim=4, num_classes=3),
    SimpleModel(input_dim=4, num_classes=3),
]

# Create criterion
criterion = nn.CrossEntropyLoss(reduction='mean')

# Set device to CPU
device = 'cpu'

# Create data loaders
# Each loader should yield (data, target) tuples
# We need 2 clients with small datasets
loader1_data = [
    (torch.randn(2, 4), torch.randint(0, 3, (2,))),
    (torch.randn(2, 4), torch.randint(0, 3, (2,))),
]

loader2_data = [
    (torch.randn(2, 4), torch.randint(0, 3, (2,))),
]

# Create a simple dataset wrapper
class SimpleDataset:
    def __init__(self, data):
        self.data = data
    
    def __len__(self):
        return len(self.data)

# Create simple loader wrappers
class SimpleLoader:
    def __init__(self, data):
        self.data = data
        self.dataset = SimpleDataset(data)
    
    def __iter__(self):
        return iter(self.data)

loader1 = SimpleLoader(loader1_data)
loader2 = SimpleLoader(loader2_data)

# Create client_data_pack: list of (client, loader) tuples
client_data_pack = [
    ("client_0", loader1),
    ("client_1", loader2),
]

ARGS = {
    'client_models': client_models,
    'criterion': criterion,
    'device': device,
    'client_data_pack': client_data_pack,
    'mode': 'Test',
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 0 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
read_results 1 other paper
1 later
ijcai2022_0301 (2022 (year only))
Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learning *
val_with_local_model 1 other paper
1 later
ijcai2022_0301 (2022 (year only))
Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learning *

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

Conventional federated learning (FL) trains one global model for a federation of clients with decentralized data, reducing the privacy risk of centralized training. However, the distribution shift across non-IID datasets, often poses a challenge to this one-model-fits-all solution. Personalized FL aims to mitigate this issue systematically. In this work, we propose APPLE, a personalized cross-silo FL framework that adaptively learns how much each client can benefit from other clients' models. We also introduce a method to flexibly control the focus of training APPLE between global and local objectives. We empirically evaluate our method's convergence and generalization behaviors, and perform extensive experiments on two benchmark datasets and two medical imaging datasets under two non-IID settings. The results show that the proposed personalized FL framework, APPLE, achieves state-of-the-art performance compared to several other personalized FL approaches in the literature. The code is publicly available at https://github.com/ljaiverson/pFL-APPLE.

For agents

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

get_harvested_code_for_paper("2110.08394")
get_code_for_paper("2110.08394")
have("2110.08394")

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

curl https://syntology.ai/api/ran/2110.08394.json

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

[![Syntology run record](https://syntology.ai/api/ran/2110.08394.svg)](https://syntology.ai/paper/2110.08394)

Connect an agent — have() is free.