Papers › Recasting Self-Attention with Holographic Reduced Representations

Recasting Self-Attention with Holographic Reduced Representations

31 May 2023arXiv:2305.19534archive 2025-07-28

Mohammad Mahmudul Alam, Edward Raff, Stella Biderman, Tim Oates, James Holt

In recent years, self-attention has become the dominant paradigm for sequence modeling in a variety of domains. However, in domains with very long sequence lengths the 𝒪(T²) memory and 𝒪(T² H) compute costs can make using transformers infeasible. Motivated by problems in malware detection, where sequence lengths of T ≥100,000 are a roadblock to deep learning, we re-cast self-attention using the neuro-symbolic approach of Holographic Reduced Representations (HRR). In doing so we perform the same high-level strategy of the standard self-attention: a set of queries matching against a set of keys, and returning a weighted response of the values for each key. Implemented as a ``Hrrformer'' we obtain several benefits including 𝒪(T H logH) time complexity, 𝒪(T H) space complexity, and convergence in 10× fewer epochs. Nevertheless, the Hrrformer achieves near state-of-the-art accuracy on LRA benchmarks and we are able to learn with just a single layer. Combined, these benefits make our Hrrformer the first viable Transformer for such long malware classification sequences and up to 280× faster to train on the Long Range Arena benchmark. Code is available at https://github.com/NeuromorphicComputationResearchProgram/Hrrformer

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 11 code samples harvested from 2 repositories linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 8 samples from 1 repository, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed); community: 3 samples from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

neuromorphiccomputationresearchprogram/hrrformer officialmentioned in papermentioned on GitHubjaxApache-2.0Syntology: 8 samples, 4 ran (0 instrument-failed) · 4 unverified 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

11 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran
7unverified

Licence: 0 of the 11 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

neuromorphiccomputationresearchprogram/hrrformer official repository 8 samples, 4 ran (0 instrument-failed) · 4 unverified
cross_entropy_loss in 58 papers image/hrrformer_mgpu.py ran fingerprinted Apache-2.0 (permissive) · 11b73c012ece44e7 · report fixture: signature true:ArrayImpl/2/float, pred:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-26
evaluate in 514 papers image/hrrformer_mgpu.py ran fingerprinted Apache-2.0 (permissive) · f0b8db0a03177b1a · report fixture: signature true:ArrayImpl/2/float, pred:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-26
look_ahead_mask utils.py ran fingerprinted Apache-2.0 (permissive) · 387fdc05497309c2 · report fixture: signature x:ArrayImpl/3/float · returned ArrayImpl · level recorded 2026-09-26
pad_collate_func malware/binaryLoader.py ran Apache-2.0 (permissive) · 38dc6299f38b0c74 · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-26
initialize_model in 15 papers image/hrrformer_mgpu.py unverified Apache-2.0 (permissive) · 4f1a5274115568d4 · report
initialize_model in 15 papers retrieval/hrrformer_mgpu.py unverified Apache-2.0 (permissive) · c574416e3c30908b · report
merge in 85 papers utils.py unverified Apache-2.0 (permissive) · 9332d0930ef1d545 · report
split in 67 papers utils.py unverified Apache-2.0 (permissive) · aaa1f91613c8db28 · report
FutureComputing4AI/Hrrformer community 3 samples, 0 ran · 3 unverified
initialize_model in 15 papers malware/hrrformer_mgpu.py unverified Apache-2.0 (permissive) · a98da1a55cc51929 · report
predict in 126 papers malware/hrrformer_mgpu.py unverified Apache-2.0 (permissive) · a8de53c24dc4ea75 · report
train_step in 47 papers malware/hrrformer_mgpu.py unverified Apache-2.0 (permissive) · 73cf404c6a2e8e98 · report

Tasks

Malware ClassificationMalware Detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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