Papers › Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attention

Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attention

27 May 2021NeurIPS 2021 12arXiv:2105.13495archive 2025-07-28

Byung-Hoon Kim, Jong Chul Ye, Jae-Jin Kim

Functional connectivity (FC) between regions of the brain can be assessed by the degree of temporal correlation measured with functional neuroimaging modalities. Based on the fact that these connectivities build a network, graph-based approaches for analyzing the brain connectome have provided insights into the functions of the human brain. The development of graph neural networks (GNNs) capable of learning representation from graph structured data has led to increased interest in learning the graph representation of the brain connectome. Although recent attempts to apply GNN to the FC network have shown promising results, there is still a common limitation that they usually do not incorporate the dynamic characteristics of the FC network which fluctuates over time. In addition, a few studies that have attempted to use dynamic FC as an input for the GNN reported a reduction in performance compared to static FC methods, and did not provide temporal explainability. Here, we propose STAGIN, a method for learning dynamic graph representation of the brain connectome with spatio-temporal attention. Specifically, a temporal sequence of brain graphs is input to the STAGIN to obtain the dynamic graph representation, while novel READOUT functions and the Transformer encoder provide spatial and temporal explainability with attention, respectively. Experiments on the HCP-Rest and the HCP-Task datasets demonstrate exceptional performance of our proposed method. Analysis of the spatio-temporal attention also provide concurrent interpretation with the neuroscientific knowledge, which further validates our method. Code is available at https://github.com/egyptdj/stagin

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 15 code samples harvested from 2 repositories linked to this paper: 13 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 4 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 11 samples from 1 repository, 10 ran (10 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 13 samples that ran has no recorded date.

egyptdj/stagin officialmentioned in papermentioned on GitHubpytorchSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
summerwings/cdgin mentioned on GitHubpytorchSyntology: 11 samples, 10 ran (0 instrument-failed) · 1 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

15 samples harvested: 13 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 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.

1ran · honoured contract
12ran
2unverified

Licence: 15 of the 15 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”. For 6 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

egyptdj/stagin official repository 4 samples, 3 ran (0 instrument-failed) · 1 unverified
ModuleTimestamping model.py ran GPL-3.0 (copyleft) · pointer only · 84a3e8003fcb5340 · report fixture: returned ModuleTimestamping · level recorded 2026-09-22
ModuleTransformer model.py ran GPL-3.0 (copyleft) · pointer only · 430499354e73b4a5 · report fixture: returned ModuleTransformer · level recorded 2026-09-22
count_parameters in 278 papers model.py ran · honoured contract GPL-3.0 (copyleft) · pointer only · 8f101e1712844130 · report fixture: signature model:callable/0/? · returned int · level recorded, date not recorded
ModelSTAGIN model.py unverified GPL-3.0 (copyleft) · pointer only · 1a6ed53e10fc4d86 · report
summerwings/cdgin community (archive-listed) 11 samples, 10 ran (0 instrument-failed) · 1 unverified
CL_MLP net/CDGIN.py ran no licence file found · pointer only · c7794a32fc398023 · report fixture: returned CL_MLP · level recorded 2026-09-22
LayerGIN net/CDGIN.py ran no licence file found · pointer only · 44ecc65021788153 · report fixture: returned LayerGIN · level recorded 2026-09-22
ModuleFusion net/CDGIN.py ran no licence file found · pointer only · fc5fbcce16d4f1f6 · report fixture: returned ModuleFusion · level recorded 2026-09-22
ModuleGARO net/CDGIN.py ran no licence file found · pointer only · af27625e1c1da111 · report fixture: returned ModuleGARO · level recorded 2026-09-22
ModuleMeanReadout net/CDGIN.py ran fingerprinted no licence file found · pointer only · 8852ed5fb37bb4ba · report fixture: returned ModuleMeanReadout · level recorded 2026-09-22
ModuleSERO net/CDGIN.py ran no licence file found · pointer only · 61c36fd5f2765068 · report fixture: returned ModuleSERO · level recorded 2026-09-22
ModuleSumReadout net/CDGIN.py ran fingerprinted no licence file found · pointer only · fd1f1a2352953434 · report fixture: returned ModuleSumReadout · level recorded 2026-09-22
ModuleTimestamping net/CDGIN.py ran no licence file found · pointer only · 5b36578d41bd3a30 · report fixture: returned ModuleTimestamping · level recorded 2026-09-22
ModuleTransformer net/CDGIN.py ran fingerprinted no licence file found · pointer only · a2b5e9d3759d13f5 · report fixture: returned ModuleTransformer · level recorded 2026-09-22
Percentile net/CDGIN.py ran fingerprinted no licence file found · pointer only · fea2fca6373c48d7 · report fixture: signature input:Tensor/2/float, percentiles:list/1/int · returned Tensor · level recorded 2026-09-24
ModelCDGIN net/CDGIN.py unverified no licence file found · pointer only · 007776ff55ed978a · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for STAGIN (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for STAGIN (graph method: STAGIN). 11 bricks; individually on a fixture: 10 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. ModelCDGIN entry · level 0 · unverified · 007776ff55ed978a
  2. CL_MLP helper · level 1 · ran · c7794a32fc398023
  3. LayerGIN model · level 1 · ran · 44ecc65021788153
  4. ModuleFusion model · level 1 · ran · fc5fbcce16d4f1f6
  5. ModuleGARO model · level 1 · ran · af27625e1c1da111
  6. ModuleMeanReadout model · level 1 · ran · 8852ed5fb37bb4ba
  7. ModuleSERO model · level 1 · ran · 61c36fd5f2765068
  8. ModuleSumReadout model · level 1 · ran · fd1f1a2352953434
  9. ModuleTimestamping helper · level 1 · ran · 5b36578d41bd3a30
  10. ModuleTransformer model · level 1 · ran · a2b5e9d3759d13f5
  11. Percentile helper · level 1 · ran · fea2fca6373c48d7

harvested Assembly for STAGIN (graph method: STAGIN). 8 bricks; individually on a fixture: 7 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. ModelSTAGIN entry · level 0 · unverified · 1a6ed53e10fc4d86
  2. LayerGIN model · level 1 · ran · 44ecc65021788153
  3. ModuleGARO model · level 1 · ran · af27625e1c1da111
  4. ModuleMeanReadout model · level 1 · ran · 8852ed5fb37bb4ba
  5. ModuleSERO model · level 1 · ran · 61c36fd5f2765068
  6. ModuleTimestamping model · level 1 · ran · 84a3e8003fcb5340
  7. ModuleTransformer model · level 1 · ran · 430499354e73b4a5
  8. Percentile helper · level 1 · ran · fea2fca6373c48d7

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2105.13495") returns these assemblies with each brick's role and wiring (how to connect).

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