SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.05026 · NeurIPS · 2023

Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts

Wenwu Zhu, Xin Wang, Ziwei Zhang, Zeyang Zhang, Haoyang Li, Hui Xue, Zhou Qin, Weigao Wen

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2403.05026.json · badge: /api/ran/2403.05026.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
wondergo2017/sild canonical (classifier label)
classifier basis: census
7 ran · 1 no recorded run
FunctionStatusWhere it lives
convert_size Ran
ran; our contract draft was wrong, not the code
wondergo2017/sild/sild/utils/misc.py
pointer only (licence: NONE) · get_code("5bae103b0fece156")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wondergo2017/sild 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.

convert_time Ran
ran; our contract draft was wrong, not the code
wondergo2017/sild/sild/utils/misc.py
pointer only (licence: NONE) · get_code("af00f5a224563094")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wondergo2017/sild 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.

mkdirs Ran
ran; our contract draft was wrong, not the code
wondergo2017/sild/sild/utils/data_util.py
pointer only (licence: NONE) · get_code("520dfca725ed1118")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wondergo2017/sild 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.

prepare_dir Ran
ran; our contract draft was wrong, not the code
wondergo2017/sild/sild/utils/data_util.py
pointer only (licence: NONE) · get_code("060b44f5278742c2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wondergo2017/sild 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.

select_by_field Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
wondergo2017/sild/DIDA/DIDA/utils/data_util.py
pointer only (licence: NONE) · get_code("7187eb430177392f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wondergo2017/sild 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.

timing Ran
ran; our contract draft was wrong, not the code
wondergo2017/sild/sild/utils/misc.py
pointer only (licence: NONE) · get_code("5e4e8d3f54d33bac")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wondergo2017/sild 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.

xavier_init Ran
ran; our contract draft was wrong, not the code
wondergo2017/sild/DIDA/DIDA/utils/inits.py
pointer only (licence: NONE) · get_code("072c717f02e44012")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wondergo2017/sild 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.

mp_exec Not yet run
unverified (harvested, no recorded run)
wondergo2017/sild/DIDA/DIDA/utils/mp.py
pointer only (licence: NONE) · get_code("8fca4741f029cd21")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wondergo2017/sild 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 1 later) and 3 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.

FunctionAlso present inEarliest-datedOthers named
mkdirs 2 other papers
1 dated earlier, 1 later
2311.11114 (2023-11)
Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization
2406.10426 (2024-06)
MiNT: Multi-Network Training for Transfer Learning on Temporal Graphs
mp_exec 1 other paper
1 dated earlier
2311.11114 (2023-11)
Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization
prepare_dir 1 other paper
1 dated earlier
2311.11114 (2023-11)
Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization
select_by_field 1 other paper
1 dated earlier
2311.11114 (2023-11)
Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization
xavier_init 1 other paper
1 dated earlier
2311.11114 (2023-11)
Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization

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

Dynamic graph neural networks (DyGNNs) currently struggle with handling distribution shifts that are inherent in dynamic graphs. Existing work on DyGNNs with out-of-distribution settings only focuses on the time domain, failing to handle cases involving distribution shifts in the spectral domain. In this paper, we discover that there exist cases with distribution shifts unobservable in the time domain while observable in the spectral domain, and propose to study distribution shifts on dynamic graphs in the spectral domain for the first time. However, this investigation poses two key challenges: i) it is non-trivial to capture different graph patterns that are driven by various frequency components entangled in the spectral domain; and ii) it remains unclear how to handle distribution shifts with the discovered spectral patterns. To address these challenges, we propose Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts (SILD), which can handle distribution shifts on dynamic graphs by capturing and utilizing invariant and variant spectral patterns. Specifically, we first design a DyGNN with Fourier transform to obtain the ego-graph trajectory spectrums, allowing the mixed dynamic graph patterns to be transformed into separate frequency components. We then develop a disentangled spectrum mask to filter graph dynamics from various frequency components and discover the invariant and variant spectral patterns. Finally, we propose invariant spectral filtering, which encourages the model to rely on invariant patterns for generalization under distribution shifts. Experimental results on synthetic and real-world dynamic graph datasets demonstrate the superiority of our method for both node classification and link prediction tasks under distribution shifts.

For agents

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

get_harvested_code_for_paper("2403.05026")
get_code_for_paper("2403.05026")
have("2403.05026")

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

curl https://syntology.ai/api/ran/2403.05026.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.05026.svg)](https://syntology.ai/paper/2403.05026)

Connect an agent — have() is free.