SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.04647 · NeurIPS · 2021

Efficient Low-Rank Hypercomplex Adapter Layers

Sebastian Ruder, Rabeeh Karimi Mahabadi, James Henderson

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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; 5 failures of our instrument; 2 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/2106.04647.json · badge: /api/ran/2106.04647.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
rabeehk/compacter canonical (classifier label)
classifier basis: classifier_2025
4 ran · 2 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
glorot_normal Ran
ran; our contract draft was wrong, not the code
rabeehk/compacter/seq2seq/hypercomplex/layers.py
pointer only (licence: NONE) · get_code("7ecc9e97effd20b6")
How it ran

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

glorot_uniform Ran
ran; our contract draft was wrong, not the code
rabeehk/compacter/seq2seq/hypercomplex/layers.py
pointer only (licence: NONE) · get_code("b2ee26e229353a37")
How it ran

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

kronecker_product Ran
ran; our contract draft was wrong, not the code
rabeehk/compacter/seq2seq/hypercomplex/layers.py
pointer only (licence: NONE) · get_code("5540414829f19945")
How it ran

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

kronecker_product_einsum_batched Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from jkooy/Parameter-efficient-Fine-tuning-for-Vision-Transformers
pointer only; the stored copy get_code serves, from jkooy/Parameter-efficient-Fine-tuning-for-Vision-Transformers, is pointer only (licence: NONE) · get_code("59e2991d3f405758")
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.

run_command Ran
ran; our contract draft was wrong, not the code
rabeehk/compacter/seq2seq/run_seq2seq.py
pointer only (licence: NONE) · get_code("44e48dfbdecee3da")
How it ran

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

PHMLinear Not yet run
unverified (harvested, no recorded run)
rabeehk/compacter/seq2seq/hypercomplex/layers.py
pointer only (licence: NONE) · get_code("7979cb8ef8d378cf")
How it ran

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

matvec_product Not yet run
unverified (harvested, no recorded run)
rabeehk/compacter/seq2seq/hypercomplex/layers.py
pointer only (licence: NONE) · get_code("7dae3e67e6722206")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rabeehk/compacter 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 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 5 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 5 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
5 later
2301.12132 (2023-01)
AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning
2305.17682 (2023-05)
One Network, Many Masks: Towards More Parameter-Efficient Transfer Learning
2310.20150 (2023-10)
Unlearn What You Want to Forget: Efficient Unlearning for LLMs
and 2 more not named here
run_command 3 other papers
1 dated earlier, 2 later
2012.13255 (2020-12)
Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning
2302.03202 (2023-02)
Exploring the Benefits of Training Expert Language Models over Instruction Tuning
2606.24841 (2026-06)
Matching Tasks to Objectives: Fine-Tuning and Prompt-Tuning Strategies for Encoder-Decoder Pre-trained Language Models
kronecker_product_einsum_batched
brick of this paper's assembly: helper
2 other papers
2 later
2203.16329 (2022-03)
Parameter-efficient Model Adaptation for Vision Transformers
2204.08790 (2022-04)
ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models
glorot_uniform
brick of this paper's assembly: helper
1 other paper
1 later
2204.08790 (2022-04)
ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models
matvec_product
brick of this paper's assembly: helper
1 other paper
1 later
2311.05152 (2023-11)
Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks

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

Adapting large-scale pretrained language models to downstream tasks via fine-tuning is the standard method for achieving state-of-the-art performance on NLP benchmarks. However, fine-tuning all weights of models with millions or billions of parameters is sample-inefficient, unstable in low-resource settings, and wasteful as it requires storing a separate copy of the model for each task. Recent work has developed parameter-efficient fine-tuning methods, but these approaches either still require a relatively large number of parameters or underperform standard fine-tuning. In this work, we propose COMPACTER, a method for fine-tuning large-scale language models with a better trade-off between task performance and the number of trainable parameters than prior work. COMPACTER accomplishes this by building on top of ideas from adapters, low-rank optimization, and parameterized hypercomplex multiplication layers. Specifically, COMPACTER inserts task-specific weight matrices into a pretrained model's weights, which are computed efficiently as a sum of Kronecker products between shared "slow" weights and "fast" rank-one matrices defined per COMPACTER layer. By only training 0.047% of a pretrained model's parameters, COMPACTER performs on par with standard fine-tuning on GLUE and outperforms standard fine-tuning on SuperGLUE and low-resource settings. Our code is publicly available at https://github.com/rabeehk/compacter.

For agents

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

get_harvested_code_for_paper("2106.04647")
get_code_for_paper("2106.04647")
have("2106.04647")

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

curl https://syntology.ai/api/ran/2106.04647.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.04647.svg)](https://syntology.ai/paper/2106.04647)

Connect an agent — have() is free.