SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.14459 · 2024

PolyFormer: Scalable Node-wise Filters via Polynomial Graph Transformer

arXiv · PDF · Open in the Atlas

Code that ran

10 of 14 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 9 failures of our instrument; 4 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/2407.14459.json · badge: /api/ran/2407.14459.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
air029/polyformer canonical (classifier label)
classifier basis: census
10 ran · 4 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; our contract draft was wrong, not the code
air029/polyformer/node_classification_large_graph/training_batch.py
pointer only (licence: NONE) · get_code("5842468b7170d5c1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, air029/polyformer 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.

cheby Ran
ran, honoured the contract we drafted
air029/polyformer/node_classification/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from ivam-he/chebnetii, is pointer only (licence: NONE) · get_code("d7653b0093307e2d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, air029/polyformer 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.

even_quantile_labels Ran
ran; our contract draft was wrong, not the code
air029/polyformer/node_classification_large_graph/dataloader/LINKX_dataset.py
pointer only (licence: NONE) · get_code("60fa16c14dfd02f0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, air029/polyformer 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.

index_to_mask Ran
ran; our contract draft was wrong, not the code
air029/polyformer/node_classification/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from xwangxshi/FSpecGNN, is pointer only (licence: NONE) · get_code("015b48620e1b8319")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, air029/polyformer 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.

load_twitch Ran
ran; our contract draft was wrong, not the code
air029/polyformer/node_classification_large_graph/dataloader/LINKX_dataset.py
pointer only (licence: NONE) · get_code("8e507f8a537044ad")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, air029/polyformer 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.

load_twitch_gamer Ran
ran; our contract draft was wrong, not the code
air029/polyformer/node_classification_large_graph/dataloader/LINKX_dataset.py
pointer only (licence: NONE); the stored copy get_code serves, from jlinki/jdr, is pointer only (licence: NONE) · get_code("d4e6fd9f6cd8a3ad")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, air029/polyformer 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.

sparse_mx_to_torch_sparse_tensor Ran
ran; our contract draft was wrong, not the code
air029/polyformer/node_classification_large_graph/processing_dataset.py
pointer only (licence: NONE) · get_code("c97b99c4e8201a97")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, air029/polyformer 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.

sys_normalized_adjacency Ran
ran; our contract draft was wrong, not the code
air029/polyformer/node_classification_large_graph/processing_dataset.py
pointer only (licence: NONE) · get_code("adcee8aadfbcc909")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, air029/polyformer 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.

sys_normalized_adjacency_i Ran
ran; our contract draft was wrong, not the code
air029/polyformer/node_classification_large_graph/processing_dataset.py
pointer only (licence: NONE) · get_code("b6d88af9096c2c9a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, air029/polyformer 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.

take_rest Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
air029/polyformer/node_classification/utils.py
pointer only (licence: NONE) · get_code("54cc1bc4ace00fb7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, air029/polyformer 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.

DataLoader Not yet run
unverified (harvested, no recorded run)
air029/polyformer/node_classification/dataloader/dataset_loader.py
pointer only (licence: NONE) · get_code("f36c10b62c48e05e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, air029/polyformer 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.

DataLoader Not yet run
unverified (harvested, no recorded run)
air029/polyformer/node_classification_large_graph/dataloader/dataset_loader.py
pointer only (licence: NONE) · get_code("3e9e130cf0f52cb4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, air029/polyformer 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.

create_batch Not yet run
unverified (harvested, no recorded run)
air029/polyformer/node_classification_large_graph/training_batch.py
pointer only (licence: NONE) · get_code("c92a4ce1dc31074e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, air029/polyformer 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.

train Not yet run
unverified (harvested, no recorded run)
air029/polyformer/node_classification_large_graph/training_batch.py
pointer only (licence: NONE) · get_code("b756e3430fe59b3a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, air029/polyformer 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 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 1 the same month, 5 later) and 9 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
sparse_mx_to_torch_sparse_tensor 32 other papers
27 dated earlier, 2 the same month, 2 later, 1 same year, order not determinable · 4 only as an assembly brick
1806.09055 (2018-06)
DARTS: Differentiable Architecture Search
1902.07153 (2019-02)
Simplifying Graph Convolutional Networks
2002.01633 (2020-02)
Structural Deep Clustering Network
and 29 more not named here
load_twitch_gamer 8 other papers
4 dated earlier, 4 later
2210.07606 (2022-10)
Revisiting Heterophily For Graph Neural Networks
2302.01524 (2023-02)
Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing
2310.09202 (2023-10)
Graph Distillation with Eigenbasis Matching
and 5 more not named here
cheby 4 other papers
3 dated earlier, 1 later · 1 only as an assembly brick
2110.14446 (2021-10)
Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
2202.03580 (2022-02)
Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited
2405.19121 (2024-05)
Spatio-Spectral Graph Neural Networks
and 1 more not named here
index_to_mask 4 other papers
2 dated earlier, 2 later
2310.01892 (2023-10)
FiGURe: Simple and Efficient Unsupervised Node Representations with Filter Augmentations
2312.14438 (2023-12)
PC-Conv: Unifying Homophily and Heterophily with Two-fold Filtering
2507.16347 (2025-07)
Leveraging Personalized PageRank and Higher-Order Topological Structures for Heterophily Mitigation in Graph Neural Networks
and 1 more not named here
even_quantile_labels 3 other papers
2 dated earlier, 1 later
2305.10498 (2023-05)
Edge Directionality Improves Learning on Heterophilic Graphs
2310.02232 (2023-10)
HoloNets: Spectral Convolutions do extend to Directed Graphs
2606.07475 (2026-06)
Graph Neural Network leveraging Higher-order Class Label Connectivity for Heterophilous Graphs

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

Spectral Graph Neural Networks have demonstrated superior performance in graph representation learning. However, many current methods focus on employing shared polynomial coefficients for all nodes, i.e., learning node-unified filters, which limits the filters' flexibility for node-level tasks. The recent DSF attempts to overcome this limitation by learning node-wise coefficients based on positional encoding. However, the initialization and updating process of the positional encoding are burdensome, hindering scalability on large-scale graphs. In this work, we propose a scalable node-wise filter, PolyAttn. Leveraging the attention mechanism, PolyAttn can directly learn node-wise filters in an efficient manner, offering powerful representation capabilities. Building on PolyAttn, we introduce the whole model, named PolyFormer. In the lens of Graph Transformer models, PolyFormer, which calculates attention scores within nodes, shows great scalability. Moreover, the model captures spectral information, enhancing expressiveness while maintaining efficiency. With these advantages, PolyFormer offers a desirable balance between scalability and expressiveness for node-level tasks. Extensive experiments demonstrate that our proposed methods excel at learning arbitrary node-wise filters, showing superior performance on both homophilic and heterophilic graphs, and handling graphs containing up to 100 million nodes. The code is available at https://github.com/air029/PolyFormer.

For agents

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

get_harvested_code_for_paper("2407.14459")
get_code_for_paper("2407.14459")
have("2407.14459")

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

curl https://syntology.ai/api/ran/2407.14459.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.14459.svg)](https://syntology.ai/paper/2407.14459)

Connect an agent — have() is free.