SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.03214 · ICML · 2022

Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning

Sixing Yu, Arya Mazaheri, Ali Jannesari

arXiv · PDF · Open in the Atlas

Code that ran

3 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 1 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/2102.03214.json · badge: /api/ran/2102.03214.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
yusx-swapp/gnn-rl-model-compression canonical (classifier label)
classifier basis: classifier_2025
3 ran · 1 no recorded run
FunctionStatusWhere it lives
add_self_loops Ran
ran; our contract draft was wrong, not the code
yusx-swapp/gnn-rl-model-compression/gnnrl/models/multi_stage_gcn.py
pointer only (licence: NONE) · get_code("42cca7024fd92bd2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yusx-swapp/gnn-rl-model-compression 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.

adjust_learning_rate Ran
ran, honoured the contract we drafted
yusx-swapp/gnn-rl-model-compression/gnnrl/fine_tune.py
pointer only (licence: NONE) · get_code("53fba30b1d44a663")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yusx-swapp/gnn-rl-model-compression 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.

real_pruning Ran
ran; our contract draft was wrong, not the code
yusx-swapp/gnn-rl-model-compression/gnnrl/fine_tune.py
pointer only (licence: NONE) · get_code("5daa9d84ca37aacb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yusx-swapp/gnn-rl-model-compression 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.

multi_stage_conv Not yet run
unverified (harvested, no recorded run)
yusx-swapp/gnn-rl-model-compression/gnnrl/models/multi_stage_gcn.py
pointer only (licence: NONE) · get_code("b4cb3415e0a1d565")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yusx-swapp/gnn-rl-model-compression 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, 1 are also present in other papers whose code we hold (1 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.

FunctionAlso present inEarliest-datedOthers named
adjust_learning_rate 1 other paper
1 dated earlier
1802.03494 (2018-02)
AMC: AutoML for Model Compression and Acceleration on Mobile Devices

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

Model compression is an essential technique for deploying deep neural networks (DNNs) on power and memory-constrained resources. However, existing model-compression methods often rely on human expertise and focus on parameters' local importance, ignoring the rich topology information within DNNs. In this paper, we propose a novel multi-stage graph embedding technique based on graph neural networks (GNNs) to identify DNN topologies and use reinforcement learning (RL) to find a suitable compression policy. We performed resource-constrained (i.e., FLOPs) channel pruning and compared our approach with state-of-the-art model compression methods. We evaluated our method on various models from typical to mobile-friendly networks, such as ResNet family, VGG-16, MobileNet-v1/v2, and Shuf-fleNet. Results show that our method can achieve higher compression ratios with a minimal finetuning cost yet yields outstanding and competitive performance. The code is open-sourced at https://github.com/yusx-swapp/ GNN-RL-Model-Compression.

For agents

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

get_harvested_code_for_paper("2102.03214")
get_code_for_paper("2102.03214")
have("2102.03214")

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

curl https://syntology.ai/api/ran/2102.03214.json

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

[![Syntology run record](https://syntology.ai/api/ran/2102.03214.svg)](https://syntology.ai/paper/2102.03214)

Connect an agent — have() is free.