SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.01642 · NeurIPS · 2022

Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively

Jia Li, Ge Li, Zhi Jin, Haojie Zhang, Zhongjin Zhang, Yuqi Zhu

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 (1 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; 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/2211.01642.json · badge: /api/ran/2211.01642.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
zhanghaojie077/dps canonical (classifier label)
classifier basis: classifier_2025
3 ran · 1 no recorded run
FunctionStatusWhere it lives
DPSDense Ran
ran on a synthesized input · constructed an object; no result was computed
zhanghaojie077/dps/transformers/DPSDense/moudle.py
pointer only (licence: NONE) · get_code("6dc2be3dcd179daf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhanghaojie077/dps 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.

grads_ops Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhanghaojie077/dps/transformers/DPSDense/grads_ops.py
pointer only (licence: NONE) · get_code("cc085a876a8faad0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhanghaojie077/dps 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.

grads_ops Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhanghaojie077/dps/transformers/DPSDense/moudle.py
pointer only (licence: NONE) · get_code("db2632aaaf76ff8e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhanghaojie077/dps 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.

Grads_Ops Not yet run
unverified (harvested, no recorded run)
zhanghaojie077/dps/transformers/DPSDense/moudle.py
pointer only (licence: NONE) · get_code("3322371b4a0a62ab")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhanghaojie077/dps 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 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

Large-scale pre-trained language models have achieved impressive results on a wide range of downstream tasks recently. However, fine-tuning an extremely large-scale pre-trained language model on limited target datasets is often plagued by overfitting and representation degradation. In this paper, we propose a Dynamic Parameter Selection (DPS) algorithm for the large-scale pre-trained models during fine-tuning, which adaptively selects a more promising subnetwork to perform staging updates based on gradients of back-propagation. Experiments on the GLUE benchmark show that DPS outperforms previous fine-tuning methods in terms of overall performance and stability, and consistently achieves better results with variable pre-trained language models. In addition, DPS brings a large magnitude of improvement in out-of-domain transferring experiments and low-resource scenarios, which shows that it can maintain stable general contextual features and reduce the representation collapse. We release our code at https://github.com/ZhangHaojie077/DPS.

For agents

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

get_harvested_code_for_paper("2211.01642")
get_code_for_paper("2211.01642")
have("2211.01642")

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

curl https://syntology.ai/api/ran/2211.01642.json

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

[![Syntology run record](https://syntology.ai/api/ran/2211.01642.svg)](https://syntology.ai/paper/2211.01642)

Connect an agent — have() is free.