SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.05296 · NeurIPS · 2023

Tailoring Self-Attention for Graph via Rooted Subtrees

Siyuan Huang, Yunchong Song, Zhouhan Lin, Jiayue Zhou

arXiv · PDF · Open in the Atlas

Code that ran

7 of 10 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; 6 failures of our instrument; 3 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/2310.05296.json · badge: /api/ran/2310.05296.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
LUMIA-Group/SubTree-Attention canonical (classifier label)
classifier basis: census
7 ran · 0 no recorded run
lumia-group/subtree-attention canonical (classifier label)
classifier basis: classifier_2025
0 ran · 3 no recorded run
FunctionStatusWhere it lives
GetRunTime Ran
ran; our contract draft was wrong, not the code
LUMIA-Group/SubTree-Attention/wandb_script/sweep.py
pointer only (licence: NONE) · get_code("54bb0b404bebbde0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LUMIA-Group/SubTree-Attention 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.

count_sweep Ran
ran, honoured the contract we drafted
LUMIA-Group/SubTree-Attention/wandb_script/sweep.py
pointer only (licence: NONE); the stored copy get_code serves, from LUMIA-Group/Cluster-wise-Graph-Transformer, is pointer only (licence: NONE) · get_code("2044980e3c503153")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LUMIA-Group/SubTree-Attention 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.

get_configs_from_file Ran
ran; our contract draft was wrong, not the code
LUMIA-Group/SubTree-Attention/wandb_script/sweep.py
pointer only (licence: NONE); the stored copy get_code serves, from lumia-group/cluster-wise-graph-transformer, is pointer only (licence: NONE) · get_code("c71a615c5a546070")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LUMIA-Group/SubTree-Attention 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.

get_hash Ran
ran; our contract draft was wrong, not the code
LUMIA-Group/SubTree-Attention/wandb_script/wandb_run.py
pointer only (licence: NONE); the stored copy get_code serves, from LUMIA-Group/Cluster-wise-Graph-Transformer, is pointer only (licence: NONE) · get_code("52890b345835d534")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LUMIA-Group/SubTree-Attention 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_fixed_splits Ran
ran; our contract draft was wrong, not the code
LUMIA-Group/SubTree-Attention/data_utils.py
pointer only (licence: NONE) · get_code("ef6b5e211f3c0418")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LUMIA-Group/SubTree-Attention 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.

rand_train_test_idx_502525 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
LUMIA-Group/SubTree-Attention/data_utils.py
pointer only (licence: NONE) · get_code("db1a5fc6a83c6a56")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LUMIA-Group/SubTree-Attention 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.

rand_train_test_idx_602020 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
LUMIA-Group/SubTree-Attention/data_utils.py
pointer only (licence: NONE) · get_code("0cc493296f804dee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LUMIA-Group/SubTree-Attention 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.

KeyProp_random_walk Not yet run
unverified (harvested, no recorded run)
lumia-group/subtree-attention/stagnn.py
pointer only (licence: NONE) · get_code("2bbdda01c3699b90")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lumia-group/subtree-attention 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.

MessageProp_random_walk Not yet run
unverified (harvested, no recorded run)
lumia-group/subtree-attention/stagnn.py
pointer only (licence: NONE) · get_code("8bb98a8a294dfa6e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lumia-group/subtree-attention 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.

STAGNN Not yet run
unverified (harvested, no recorded run)
lumia-group/subtree-attention/stagnn.py
pointer only (licence: NONE) · get_code("17a073c27378ac28")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lumia-group/subtree-attention 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, 5 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 5 later) and 5 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
load_fixed_splits 3 other papers
1 dated earlier, 2 later
2306.10759 (2023-06)
SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations
2403.15480 (2024-03)
SpikeGraphormer: A High-Performance Graph Transformer with Spiking Graph Attention
2407.01290 (2024-07)
Hypformer: Exploring Efficient Transformer Fully in Hyperbolic Space
GetRunTime 2 other papers
2 later
2402.14393 (2024-02)
Graph Parsing Networks
2410.06746 (2024-10)
Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention
count_sweep 1 other paper
1 later
2410.06746 (2024-10)
Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention
get_configs_from_file 1 other paper
1 later
2410.06746 (2024-10)
Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention
get_hash 1 other paper
1 later
2410.06746 (2024-10)
Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention

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

Attention mechanisms have made significant strides in graph learning, yet they still exhibit notable limitations: local attention faces challenges in capturing long-range information due to the inherent problems of the message-passing scheme, while global attention cannot reflect the hierarchical neighborhood structure and fails to capture fine-grained local information. In this paper, we propose a novel multihop graph attention mechanism, named Subtree Attention (STA), to address the aforementioned issues. STA seamlessly bridges the fully-attentional structure and the rooted subtree, with theoretical proof that STA approximates the global attention under extreme settings. By allowing direct computation of attention weights among multi-hop neighbors, STA mitigates the inherent problems in existing graph attention mechanisms. Further we devise an efficient form for STA by employing kernelized softmax, which yields a linear time complexity. Our resulting GNN architecture, the STAGNN, presents a simple yet performant STA-based graph neural network leveraging a hop-aware attention strategy. Comprehensive evaluations on ten node classification datasets demonstrate that STA-based models outperform existing graph transformers and mainstream GNNs. The code is available at https://github.com/LUMIA-Group/SubTree-Attention.

For agents

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

get_harvested_code_for_paper("2310.05296")
get_code_for_paper("2310.05296")
have("2310.05296")

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

curl https://syntology.ai/api/ran/2310.05296.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.05296.svg)](https://syntology.ai/paper/2310.05296)

Connect an agent — have() is free.