SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.17682 · ACL · 2023

One Network, Many Masks: Towards More Parameter-Efficient Transfer Learning

Guangtao Zeng, Peiyuan Zhang, Wei Lu

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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; 1 failure 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/2305.17682.json · badge: /api/ran/2305.17682.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
chaoscodes/propetl marked official in Papers with Code
Papers with Code archive
1 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
ForwardContext Ran
ran on a synthesized input · constructed an object; no result was computed
chaoscodes/propetl/propetl-roberta/src/transformers/adapters/modeling.py
code served (permissive licence) · get_code("be9db1b1fddfe2d8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, ForwardContext: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import functools
import threading

torch.manual_seed(0)

# Create a minimal model class with the required attributes and methods
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.config = type('Config', (), {
            'adapters': {'adapter1': True}  # Non-None to trigger context wrapping
        })()
        self.linear = nn.Linear(4, 3)
    
    def forward_context(self, context, *args, **kwargs):
        """Called by ForwardContext.__init__ if model has this method"""
        # Set up context attributes if they're requested via output_* kwargs
        if kwargs.get('output_adapter_gating_scores', False):
            context.output_adapter_gating_scores = True
            context.adapter_gating_scores = {}
        if kwargs.get('output_adapter_fusion_attentions', False):
            context.output_adapter_fusion_attentions = True
            context.adapter_fusion_attentions = {}
        if kwargs.get('output_adapter_input_parallelized', False):
            context.output_adapter_input_parallelized = True
            context.adapter_input_parallelized = {}

# Create model instance
model = MinimalModel()

# Create minimal arguments
# The __init__ takes: model, *args, **kwargs
# args can be anything passed through
# kwargs should include the model and potentially output_* flags

ARGS = {
    'model': model,
    'args': (torch.randn(2, 4),),  # Small dummy tensor arg
    'kwargs': {
        'output_adapter_gating_scores': False,
        'output_adapter_fusion_attentions': False,
        'output_adapter_input_parallelized': False,
    }
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ForwardContext — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ForwardContext output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
kronecker_product Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from lins-lab/capaboost
pointer only · get_code("54fa343f001c7cff")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

PHMLayer Not yet run
unverified (harvested, no recorded run)
chaoscodes/propetl/propetl-roberta/src/transformers/adapters/modeling.py
code served (permissive licence) · get_code("658bd7adfbfc0a67")
How it ran

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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 2 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
kronecker_product
brick of this paper's assembly: helper
5 other papers
2 dated earlier, 3 later
2106.04647 (2021-06)
Efficient Low-Rank Hypercomplex Adapter Layers
2301.12132 (2023-01)
AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning
2310.20150 (2023-10)
Unlearn What You Want to Forget: Efficient Unlearning for LLMs
and 2 more not named here

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

Fine-tuning pre-trained language models for multiple tasks tends to be expensive in terms of storage. To mitigate this, parameter-efficient transfer learning (PETL) methods have been proposed to address this issue, but they still require a significant number of parameters and storage when being applied to broader ranges of tasks. To achieve even greater storage reduction, we propose PROPETL, a novel method that enables efficient sharing of a single PETL module which we call prototype network (e.g., adapter, LoRA, and prefix-tuning) across layers and tasks. We then learn binary masks to select different sub-networks from the shared prototype network and apply them as PETL modules into different layers. We find that the binary masks can determine crucial information from the network, which is often ignored in previous studies. Our work can also be seen as a type of pruning method, where we find that overparameterization also exists in the seemingly small PETL modules. We evaluate PROPETL on various downstream tasks and show that it can outperform other PETL methods with approximately 10% of the parameter storage required by the latter. 1

For agents

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

get_harvested_code_for_paper("2305.17682")
get_code_for_paper("2305.17682")
have("2305.17682")

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

curl https://syntology.ai/api/ran/2305.17682.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.17682.svg)](https://syntology.ai/paper/2305.17682)

Connect an agent — have() is free.