SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2607.08013 · 2026

Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems

Di Liu, Qian Lin, Xiangzhong Luo, Shuo Huai, Hao Kong, Weichen Liu, Ravi Subramaniam, Christian Makaya

arXiv · PDF · Open in the Atlas

Code that ran

3 of 9 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 6 no recorded run), measured 2026-11-22; 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/2607.08013.json · badge: /api/ran/2607.08013.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
ntuliuteam/Collate canonical (classifier label)
classifier basis: census
3 ran · 6 no recorded run
FunctionStatusWhere it lives
resnet18 Ran
ran; our contract draft was wrong, not the code
ntuliuteam/Collate/models/resnet.py
pointer only (licence: NOASSERTION) · get_code("8b2e165658bc9fe0")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ntuliuteam/Collate (NOASSERTION). 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_img Ran
ran, honoured the contract we drafted
ntuliuteam/Collate/utils/functions.py
pointer only (licence: NOASSERTION) · get_code("c922ec2a5c99531e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ntuliuteam/Collate (NOASSERTION). 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_save Ran
ran, honoured the contract we drafted
ntuliuteam/Collate/utils/functions.py
pointer only (licence: NOASSERTION) · get_code("515bcfab8e61d1d1")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ntuliuteam/Collate (NOASSERTION). 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.

classifier Not yet run
unverified (harvested, no recorded run)
ntuliuteam/Collate/tensorflow_support/trans_alexnet.py
pointer only (licence: NOASSERTION) · get_code("af880b413db5a323")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ntuliuteam/Collate (NOASSERTION). 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.

classifier Not yet run
unverified (harvested, no recorded run)
ntuliuteam/Collate/tensorflow_support/trans_lenet.py
pointer only (licence: NOASSERTION) · get_code("695ffda34ed5cdbc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ntuliuteam/Collate (NOASSERTION). 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.

classifier Not yet run
unverified (harvested, no recorded run)
ntuliuteam/Collate/tensorflow_support/trans_har.py
pointer only (licence: NOASSERTION) · get_code("78325ce26920c7b5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ntuliuteam/Collate (NOASSERTION). 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.

feature Not yet run
unverified (harvested, no recorded run)
ntuliuteam/Collate/tensorflow_support/trans_alexnet.py
pointer only (licence: NOASSERTION) · get_code("570187d904d61e4e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ntuliuteam/Collate (NOASSERTION). 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.

feature Not yet run
unverified (harvested, no recorded run)
ntuliuteam/Collate/tensorflow_support/trans_lenet.py
pointer only (licence: NOASSERTION) · get_code("a40f3d9010afc030")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ntuliuteam/Collate (NOASSERTION). 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.

feature Not yet run
unverified (harvested, no recorded run)
ntuliuteam/Collate/tensorflow_support/trans_har.py
pointer only (licence: NOASSERTION) · get_code("a84ce5abaadee3d9")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ntuliuteam/Collate (NOASSERTION). 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 9 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.

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) empowers multiple clients to collaboratively learn a model, enlarging the training data of each client for high accuracy while protecting data privacy. However, when deploying FL in real-time edge systems, the heterogeneity of devices among systems has a severe impact on the performance of the inferred model. Existing optimizations on FL focus on improving the training efficiency but fail to speed up inference, especially when there is a latency constraint. In this work, we propose Collate, a novel training framework that collaboratively learns heterogeneous models to meet the latency constraints of multiple edge systems simultaneously. We design a dynamic zeroizing-recovering method to adjust each local model architecture for high accuracy under its latency constraint. A proto-corrected federated aggregation scheme is also introduced to aggregate all heterogeneous local models, satisfying the latency constraint of different systems with only one training process and maintaining high accuracy. Extensive experiments indicate that, compared to state-of-the-art methods and under a latency constraint, our extended models can improve the accuracy by 1.96% on average, and our shrunk models can also obtain a 3.09% accuracy improvement on average, with almost no extra training overhead. The related codes and data will be available at https://github.com/ntuliuteam/Collate.

For agents

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

get_harvested_code_for_paper("2607.08013")
get_code_for_paper("2607.08013")
have("2607.08013")

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

curl https://syntology.ai/api/ran/2607.08013.json

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

[![Syntology run record](https://syntology.ai/api/ran/2607.08013.svg)](https://syntology.ai/paper/2607.08013)

Connect an agent — have() is free.