Papers › Structure-Preserving Transformers for Sequences of SPD Matrices

Structure-Preserving Transformers for Sequences of SPD Matrices

14 Sep 2023arXiv:2309.07579archive 2025-07-28

Mathieu Seraphim, Alexis Lechervy, Florian Yger, Luc Brun, Olivier Etard

In recent years, Transformer-based auto-attention mechanisms have been successfully applied to the analysis of a variety of context-reliant data types, from texts to images and beyond, including data from non-Euclidean geometries. In this paper, we present such a mechanism, designed to classify sequences of Symmetric Positive Definite matrices while preserving their Riemannian geometry throughout the analysis. We apply our method to automatic sleep staging on timeseries of EEG-derived covariance matrices from a standard dataset, obtaining high levels of stage-wise performance.

PaperPDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

mathieuseraphim/spdtransnet officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
MathieuSeraphim/SPDTransNet_plus mentioned on GitHubpytorchSyntology: not harvested 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

EEGEEG based sleep stagingSleep Stage DetectionSleep Staging

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sleep Stage Detection MASS SS3 SPDTransNet Macro-F1 0.8124 #6 of 6 Archive leaderboard report
Sleep Stage Detection MASS SS3 SPDTransNet Macro-averaged Accuracy 84.40% #6 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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