SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.17005 · NeurIPS · 2023

Aggregating Capacity in FL through Successive Layer Training for Computationally-Constrained Devices

Kilian Pfeiffer, Ramin Khalili, Jörg Henkel

arXiv · PDF · Open in the Atlas

Code that ran

None of the 6 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (6 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/2305.17005.json · badge: /api/ran/2305.17005.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
k1l1/slt canonical (classifier label)
classifier basis: classifier_2025
0 ran · 2 no recorded run
k1l1/SLT marked official in Papers with Code
Papers with Code archive
0 ran · 4 no recorded run
FunctionStatusWhere it lives
FedAvgEvaluation Not yet run
unverified (harvested, no recorded run)
k1l1/SLT/algorithms/slt.py
code served (permissive licence) · get_code("d455320ab88e0e8e")
How it ran

no invocation recorded.

FedAvgServer Not yet run
unverified (harvested, no recorded run)
k1l1/SLT/algorithms/slt.py
code served (permissive licence) · get_code("f23f9cc409eaf40f")
How it ran

no invocation recorded.

FederatedDropoutServer Not yet run
unverified (harvested, no recorded run)
k1l1/SLT/algorithms/slt.py
code served (permissive licence) · get_code("6d29716020da166d")
How it ran

no invocation recorded.

SLTServer Not yet run
unverified (harvested, no recorded run)
k1l1/SLT/algorithms/slt.py
code served (permissive licence) · get_code("6d2bd31e381d7d73")
How it ran

no invocation recorded.

dict_hash Not yet run
unverified (harvested, no recorded run)
k1l1/slt/run_fl.py
code served (permissive licence) · get_code("78184a9f3364adb2")
How it ran

no invocation recorded. this sample carries JSON test cases instead of a setup block; get_reference_implementation serves them with the level they back.

prepare Not yet run
unverified (harvested, no recorded run)
k1l1/slt/run_fl.py
code served (permissive licence) · get_code("09027058830d7ecf")
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, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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
FedAvgEvaluation
brick of this paper's assembly: metric
2 other papers
2 dated earlier
2010.01264 (2020-10)
HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients
2212.01548 (2022-12)
FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction
FedAvgServer
brick of this paper's assembly: helper
2 other papers
2 dated earlier
2010.01264 (2020-10)
HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients
2212.01548 (2022-12)
FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction
FederatedDropoutServer
brick of this paper's assembly: helper
2 other papers
2 dated earlier
2010.01264 (2020-10)
HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients
2212.01548 (2022-12)
FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction
dict_hash 2 other papers
2 dated earlier
2203.05468 (2022-03)
CoCoFL: Communication- and Computation-Aware Federated Learning via Partial NN Freezing and Quantization
2212.01548 (2022-12)
FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction
prepare 1 other paper
1 dated earlier
2212.01548 (2022-12)
FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction

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

Federated learning (FL) is usually performed on resource-constrained edge devices, e.g., with limited memory for the computation. If the required memory to train a model exceeds this limit, the device will be excluded from the training. This can lead to a lower accuracy as valuable data and computation resources are excluded from training, also causing bias and unfairness. The FL training process should be adjusted to such constraints. The state-of-the-art techniques propose training subsets of the FL model at constrained devices, reducing their resource requirements for training. However, these techniques largely limit the co-adaptation among parameters of the model and are highly inefficient, as we show: it is actually better to train a smaller (less accurate) model by the system where all the devices can train the model end-to-end than applying such techniques. We propose a new method that enables successive freezing and training of the parameters of the FL model at devices, reducing the training's resource requirements at the devices while still allowing enough co-adaptation between parameters. We show through extensive experimental evaluation that our technique greatly improves the accuracy of the trained model (by 52.4 p.p.) compared with the state of the art, efficiently aggregating the computation capacity available on distributed devices.

For agents

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

get_harvested_code_for_paper("2305.17005")
get_code_for_paper("2305.17005")
have("2305.17005")

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

curl https://syntology.ai/api/ran/2305.17005.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.17005.svg)](https://syntology.ai/paper/2305.17005)

Connect an agent — have() is free.