SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.04662 · CVPR · 2022

DiSparse: Disentangled Sparsification for Multitask Model Compression

Zhangyang Wang, Gao Huang, Xinglong Sun, Humphrey Shi, Ali Hassani

arXiv · PDF · Open in the Atlas

Code that ran

2 of 6 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 0 have no contract verdict; 2 failures of our instrument; 4 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/2206.04662.json · badge: /api/ran/2206.04662.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
SHI-Labs/DiSparse-Multitask-Model-Compression community
Papers with Code archive
2 ran · 4 no recorded run
FunctionStatusWhere it lives
get_pruned_init Ran
ran; our contract draft was wrong, not the code
SHI-Labs/DiSparse-Multitask-Model-Compression/dynamic_prune.py
pointer only (licence: NONE) · get_code("85b11b5ac1824b27")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SHI-Labs/DiSparse-Multitask-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.

get_sparsity_dict Ran
ran; our contract draft was wrong, not the code
SHI-Labs/DiSparse-Multitask-Model-Compression/dynamic_prune.py
pointer only (licence: NONE) · get_code("698e8939c8e2bde6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SHI-Labs/DiSparse-Multitask-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.

deepcopy_pruned_net Not yet run
unverified (harvested, no recorded run)
SHI-Labs/DiSparse-Multitask-Model-Compression/dynamic_prune.py
pointer only (licence: NONE) · get_code("d753c50cd4fedd5b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SHI-Labs/DiSparse-Multitask-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.

deepcopy_pruned_net_v2 Not yet run
unverified (harvested, no recorded run)
SHI-Labs/DiSparse-Multitask-Model-Compression/dynamic_prune.py
pointer only (licence: NONE) · get_code("a1947097cace01b4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SHI-Labs/DiSparse-Multitask-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.

dynamic_disparse Not yet run
unverified (harvested, no recorded run)
SHI-Labs/DiSparse-Multitask-Model-Compression/dynamic_prune.py
pointer only (licence: NONE) · get_code("0b70bdfc84ab571f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SHI-Labs/DiSparse-Multitask-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.

pseudo_forward Not yet run
unverified (harvested, no recorded run)
SHI-Labs/DiSparse-Multitask-Model-Compression/dynamic_prune.py
pointer only (licence: NONE) · get_code("c9c7d2f187b2b92e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SHI-Labs/DiSparse-Multitask-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 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, 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 6 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 the popularity of Model Compression and Multitask Learning, how to effectively compress a multitask model has been less thoroughly analyzed due to the challenging entanglement of tasks in the parameter space. In this paper, we propose DiSparse, a simple, effective, and first-of-its-kind multitask pruning and sparse training scheme. We consider each task independently by disentangling the importance measurement and take the unanimous decisions among all tasks when performing parameter pruning and selection. Our experimental results demonstrate superior performance on various configurations and settings compared to popular sparse training and pruning methods. Besides the effectiveness in compression, DiSparse also provides a powerful tool to the multitask learning community. Surprisingly, we even observed better performance than some dedicated multitask learning methods in several cases despite the high model sparsity enforced by DiSparse. We analyzed the pruning masks generated with DiSparse and observed strikingly similar sparse network architecture identified by each task even before the training starts. We also observe the existence of a "watershed" layer where the task relatedness sharply drops, implying no benefits in continued parameters sharing. Our code and models will be available at: https://github.com/SHI-Labs/DiSparse-Multitask-Model-Compression.

For agents

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

get_harvested_code_for_paper("2206.04662")
get_code_for_paper("2206.04662")
have("2206.04662")

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

curl https://syntology.ai/api/ran/2206.04662.json

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

[![Syntology run record](https://syntology.ai/api/ran/2206.04662.svg)](https://syntology.ai/paper/2206.04662)

Connect an agent — have() is free.