SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.00330 · CVPR · 2023

Efficient On-device Training via Gradient Filtering

Guihong Li, Yuedong Yang, Radu Marculescu

arXiv · PDF · Open in the Atlas

Code that ran

None of the 3 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (3 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/2301.00330.json · badge: /api/ran/2301.00330.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
SLDGroup/GradientFilter-CVPR23 community
Papers with Code archive
0 ran · 3 no recorded run
FunctionStatusWhere it lives
Conv2dAvg Not yet run
unverified (harvested, no recorded run)
SLDGroup/GradientFilter-CVPR23/classification/custom_op/conv_avg.py
pointer only (licence: NOASSERTION) · get_code("785e93b7306920fe")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, SLDGroup/GradientFilter-CVPR23 (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.

Conv2dAvgOp Not yet run
unverified (harvested, no recorded run)
SLDGroup/GradientFilter-CVPR23/classification/custom_op/conv_avg.py
pointer only (licence: NOASSERTION) · get_code("48536c0bcffdcfb6")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, SLDGroup/GradientFilter-CVPR23 (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.

Conv2dDilatedOp Not yet run
unverified (harvested, no recorded run)
SLDGroup/GradientFilter-CVPR23/classification/custom_op/conv_avg.py
pointer only (licence: NOASSERTION) · get_code("0bea454a757905f7")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, SLDGroup/GradientFilter-CVPR23 (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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Despite its importance for federated learning, continuous learning and many other applications, on-device training remains an open problem for EdgeAI. The problem stems from the large number of operations (e.g., floating point multiplications and additions) and memory consumption required during training by the back-propagation algorithm. Consequently, in this paper, we propose a new gradient filtering approach which enables on-device CNN model training. More precisely, our approach creates a special structure with fewer unique elements in the gradient map, thus significantly reducing the computational complexity and memory consumption of back propagation during training. Extensive experiments on image classification and semantic segmentation with multiple CNN models (e.g., MobileNet, DeepLabV3, UPerNet) and devices (e.g., Raspberry Pi and Jetson Nano) demonstrate the effectiveness and wide applicability of our approach. For example, compared to SOTA, we achieve up to 19× speedup and 77.1% memory savings on ImageNet classification with only 0.1% accuracy loss. Finally, our method is easy to implement and deploy; over 20× speedup and 90% energy savings have been observed compared to highly optimized baselines in MKLDNN and CUDNN on NVIDIA Jetson Nano. Consequently, our approach opens up a new direction of research with a huge potential for on-device training. 1

For agents

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

get_harvested_code_for_paper("2301.00330")
get_code_for_paper("2301.00330")
have("2301.00330")

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

curl https://syntology.ai/api/ran/2301.00330.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.00330.svg)](https://syntology.ai/paper/2301.00330)

Connect an agent — have() is free.