SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.00067 · 2026

Modality as Heterogeneity: Node Splitting and Graph Rewiring for Multimodal Graph Learning

Ercan Kuruoglu, Yihan Zhang, Coleman Weathermaster

arXiv · PDF · Open in the Atlas

Code that ran

8 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 1 failure of our instrument; 2 no recorded run), measured 2026-11-22; 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/2602.00067.json · badge: /api/ran/2602.00067.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
zyh23-chn/NSG-MoE community
Papers with Code archive
8 ran · 2 no recorded run
FunctionStatusWhere it lives
BaseNSG Ran
ran on a synthesized input · constructed an object; no result was computed
zyh23-chn/NSG-MoE/src/ud_models/nsg.py
pointer only (licence: NONE) · get_code("29c43a186116779e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zyh23-chn/NSG-MoE 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.

GAT_h Ran
ran on a synthesized input · constructed an object; no result was computed
zyh23-chn/NSG-MoE/src/ud_models/nsg.py
pointer only (licence: NONE) · get_code("6701df08b2830421")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zyh23-chn/NSG-MoE 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.

HAN Ran
ran on a synthesized input · constructed an object; no result was computed
zyh23-chn/NSG-MoE/src/ud_models/nsg.py
pointer only (licence: NONE) · get_code("0ce5866f03880121")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zyh23-chn/NSG-MoE 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.

HGT Ran
ran on a synthesized input · constructed an object; no result was computed
zyh23-chn/NSG-MoE/src/ud_models/nsg.py
pointer only (licence: NONE) · get_code("9d69e1508e783636")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zyh23-chn/NSG-MoE 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.

SAGE_h Ran
ran on a synthesized input · constructed an object; no result was computed
zyh23-chn/NSG-MoE/src/ud_models/nsg.py
pointer only (licence: NONE) · get_code("c2c1b589e00d8191")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zyh23-chn/NSG-MoE 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.

maximum_spanning_tree Ran
ran, honoured the contract we drafted
zyh23-chn/NSG-MoE/src/ud_models/nsg.py
pointer only (licence: NONE) · get_code("f794a29c5858961a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zyh23-chn/NSG-MoE 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.

pairwise_cos_sim Ran
ran, honoured the contract we drafted
zyh23-chn/NSG-MoE/src/ud_models/nsg.py
pointer only (licence: NONE) · get_code("f3365a2dbe75c14a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zyh23-chn/NSG-MoE 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.

tup2str Ran
ran; our contract draft was wrong, not the code
zyh23-chn/NSG-MoE/src/ud_models/nsg.py
pointer only (licence: NONE) · get_code("8b1cfbfa6f5f6e71")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zyh23-chn/NSG-MoE 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.

NSG_MOE Not yet run
unverified (harvested, no recorded run)
zyh23-chn/NSG-MoE/src/ud_models/nsg.py
pointer only (licence: NONE) · get_code("dfc1a9a567e75cd3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zyh23-chn/NSG-MoE 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.

save_with_pickle Not yet run
unverified (harvested, no recorded run)
zyh23-chn/NSG-MoE/src/ud_models/nsg.py
pointer only (licence: NONE) · get_code("8207e6abfbd40d95")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zyh23-chn/NSG-MoE 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 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 10 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.

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

Multimodal graphs are gaining increasing attention due to their rich representational power and wide applicability, yet they introduce substantial challenges arising from severe modality confusion. To address this issue, we propose NSG (Node Splitting Graph)-MoE, a multimodal graph learning framework that integrates a node-splitting and graph-rewiring mechanism with a structured Mixture-of-Experts (MoE) architecture. It explicitly decomposes each node into modality-specific components and assigns relation-aware experts to process heterogeneous message flows, thereby preserving structural information and multimodal semantics while mitigating the undesirable mixing effects commonly observed in general-purpose GNNs. Extensive experiments on three multimodal benchmarks demonstrate that NSG-MoE consistently surpasses strong baselines. Despite incorporating MoE-which is typically computationally heavy-our method achieves competitive training efficiency. Beyond empirical results, we provide a spectral analysis revealing that NSG performs adaptive filtering over modality-specific subspaces, thus explaining its disentangling behavior. Furthermore, an information-theoretic analysis shows that the architectural constraints imposed by NSG reduces mutual information between data and parameters and improving generalization capability.

For agents

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

get_harvested_code_for_paper("2602.00067")
get_code_for_paper("2602.00067")
have("2602.00067")

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

curl https://syntology.ai/api/ran/2602.00067.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.00067.svg)](https://syntology.ai/paper/2602.00067)

Connect an agent — have() is free.