Papers › Towards Better Multi-head Attention via Channel-wise Sample Permutation

Towards Better Multi-head Attention via Channel-wise Sample Permutation

14 Oct 2024arXiv:2410.10914archive 2025-07-28

Shen Yuan, Hongteng Xu

Transformer plays a central role in many fundamental deep learning models, e.g., the ViT in computer vision and the BERT and GPT in natural language processing, whose effectiveness is mainly attributed to its multi-head attention (MHA) mechanism. In this study, we propose a simple and novel channel-wise sample permutation (CSP) operator, achieving a new structured MHA with fewer parameters and lower complexity. Given an input matrix, CSP circularly shifts the samples of different channels with various steps and then sorts grouped samples of each channel. This operator is equivalent to implicitly implementing cross-channel attention maps as permutation matrices, which achieves linear complexity and suppresses the risk of rank collapse when representing data. We replace the MHA of some representative models with CSP and test the CSP-based models in several discriminative tasks, including image classification and long sequence analysis. Experiments show that the CSP-based models achieve comparable or better performance with fewer parameters and lower computational costs than the classic Transformer and its state-of-the-art variants. The code is available at https://github.com/DaShenZi721/CSP.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2410.10914")

Code

Syntology Ran 4 of 7 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 4 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

dashenzi721/csp officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

7 samples harvested; 4 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4ran
3unverified

Licence: 7 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from dashenzi721/csp. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

distributed_init dashenzi721/csp/lra/mega_csp/fairseq/distributed_utils.py official repository ran no licence file found · pointer only · 07969f7041022050 · report
is_master dashenzi721/csp/lra/mega_csp/fairseq/distributed_utils.py official repository ran no licence file found · pointer only · 90b79fe15491de83 · report
safe_readline dashenzi721/csp/lra/mega_csp/fairseq/binarizer.py official repository ran no licence file found · pointer only · 82bdf940665aeeb4 · report
url_to_filename dashenzi721/csp/lra/mega_csp/fairseq/file_utils.py official repository ran fingerprinted no licence file found · pointer only · 9418b43048e4e4ec · report
all_reduce dashenzi721/csp/lra/mega_csp/fairseq/distributed_utils.py official repository unverified no licence file found · pointer only · 199e96db5edd0edd · report
filename_to_url dashenzi721/csp/lra/mega_csp/fairseq/file_utils.py official repository unverified no licence file found · pointer only · b1a033619f614e17 · report
load_archive_file dashenzi721/csp/lra/mega_csp/fairseq/file_utils.py official repository unverified no licence file found · pointer only · bd3fe80662b28bc7 · report

Tasks

Image Classificationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionAttention DropoutBERTBPECosine AnnealingDense ConnectionsDiscriminative Fine-TuningDropoutGPTLabel SmoothingLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingLinear Warmup With Linear DecayMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections