SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.14566 · IJCAI · 2020

TRP: Trained Rank Pruning for Efficient Deep Neural Networks

Yiran Chen, Weiyao Lin, Shuai Zhang, Hongkai Xiong, Yuhui Xu, Wei Wen, Yuxi Li, Botao Wang, Yingyong Qi

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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; 2 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/2004.14566.json · badge: /api/ran/2004.14566.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
yuhuixu1993/Trained-Rank-Pruning community
Papers with Code archive
2 ran · 2 no recorded run
FunctionStatusWhere it lives
MultiPathConv Ran
ran on a synthesized input
yuhuixu1993/Trained-Rank-Pruning/decompose.py
pointer only (licence: NONE) · get_code("d1b8a0724e607c78")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yuhuixu1993/Trained-Rank-Pruning 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.

pd_conv Ran
ran; our contract draft was wrong, not the code
yuhuixu1993/Trained-Rank-Pruning/decompose.py
pointer only (licence: NONE) · get_code("b8c55d7ef22663ad")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yuhuixu1993/Trained-Rank-Pruning 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.

_set_model_attr Not yet run
unverified (harvested, no recorded run)
yuhuixu1993/Trained-Rank-Pruning/decompose.py
pointer only (licence: NONE) · get_code("8e94c3ab598d601d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yuhuixu1993/Trained-Rank-Pruning 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. No invocation recorded.

network_decouple Not yet run
unverified (harvested, no recorded run)
yuhuixu1993/Trained-Rank-Pruning/decompose.py
pointer only (licence: NONE) · get_code("0a1b4ae9f13aec4f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yuhuixu1993/Trained-Rank-Pruning 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. No invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 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.

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

To enable DNNs on edge devices like mobile phones, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attempted to directly approximate a pretrained model by low-rank decomposition; however, small approximation errors in parameters can ripple over a large prediction loss. As a result, performance usually drops significantly and a sophisticated effort on fine-tuning is required to recover accuracy. Apparently, it is not optimal to separate low-rank approximation from training. Unlike previous works, this paper integrates low rank approximation and regularization into the training process. We propose Trained Rank Pruning (TRP), which alternates between low rank approximation and training. TRP maintains the capacity of the original network while imposing low-rank constraints during training. A nuclear regularization optimized by stochastic sub-gradient descent is utilized to further promote low rank in TRP. The TRP trained network inherently has a low-rank structure, and is approximated with negligible performance loss, thus eliminating the fine-tuning process after low rank decomposition. The proposed method is comprehensively evaluated on CIFAR-10 and Ima-geNet, outperforming previous compression methods using low rank approximation.

For agents

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

get_harvested_code_for_paper("2004.14566")
get_code_for_paper("2004.14566")
have("2004.14566")

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

curl https://syntology.ai/api/ran/2004.14566.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.14566.svg)](https://syntology.ai/paper/2004.14566)

Connect an agent — have() is free.