Papers › Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention

Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention

9 Oct 2024arXiv:2410.06746archive 2025-07-28

Siyuan Huang, Yunchong Song, Jiayue Zhou, Zhouhan Lin

In the realm of graph learning, there is a category of methods that conceptualize graphs as hierarchical structures, utilizing node clustering to capture broader structural information. While generally effective, these methods often rely on a fixed graph coarsening routine, leading to overly homogeneous cluster representations and loss of node-level information. In this paper, we envision the graph as a network of interconnected node sets without compressing each cluster into a single embedding. To enable effective information transfer among these node sets, we propose the Node-to-Cluster Attention (N2C-Attn) mechanism. N2C-Attn incorporates techniques from Multiple Kernel Learning into the kernelized attention framework, effectively capturing information at both node and cluster levels. We then devise an efficient form for N2C-Attn using the cluster-wise message-passing framework, achieving linear time complexity. We further analyze how N2C-Attn combines bi-level feature maps of queries and keys, demonstrating its capability to merge dual-granularity information. The resulting architecture, Cluster-wise Graph Transformer (Cluster-GT), which uses node clusters as tokens and employs our proposed N2C-Attn module, shows superior performance on various graph-level tasks. Code is available at https://github.com/LUMIA-Group/Cluster-wise-Graph-Transformer.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2410.06746")

Code

Syntology Ran 13 of 14 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 2 ran · honoured contract; 3 ran · our draft was wrong; 8 ran with no contract checked.

By repository: official repository: 14 samples from 1 repository, 13 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

lumia-group/cluster-wise-graph-transformer officialmentioned in papermentioned on GitHubpytorch 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

14 samples harvested; 13 ran; 2 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
3ran · our draft was wrong
8ran
1unverified

Licence: 14 of the 14 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 LUMIA-Group/Cluster-wise-Graph-Transformer. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

GetRunTime LUMIA-Group/Cluster-wise-Graph-Transformer/wandb_script/sweep.py official repository ran · our draft was wrong no licence file found · pointer only · 54bb0b404bebbde0 · report
LapPE LUMIA-Group/Cluster-wise-Graph-Transformer/pe.py official repository ran no licence file found · pointer only · 2be5d5ffa7c2b792 · report
RWSE LUMIA-Group/Cluster-wise-Graph-Transformer/pe.py official repository ran no licence file found · pointer only · e63f8bb61e55a99d · report
cal_coarsen_adj LUMIA-Group/Cluster-wise-Graph-Transformer/graph_partition.py official repository ran fingerprinted no licence file found · pointer only · 586551d992664067 · report
combine_subgraphs LUMIA-Group/Cluster-wise-Graph-Transformer/graph_partition.py official repository ran · our draft was wrong no licence file found · pointer only · 6466f9f70510811c · report
count_sweep LUMIA-Group/Cluster-wise-Graph-Transformer/wandb_script/sweep.py official repository ran no licence file found · pointer only · 2044980e3c503153 · report
get_classifier LUMIA-Group/Cluster-wise-Graph-Transformer/Cluster_GT_N2C_L.py official repository ran no licence file found · pointer only · 97e6235979044fb2 · report
get_configs_from_file lumia-group/cluster-wise-graph-transformer/wandb_script/sweep.py official repository ran · our draft was wrong no licence file found · pointer only · c71a615c5a546070 · report
get_hash LUMIA-Group/Cluster-wise-Graph-Transformer/wandb_script/wandb_main.py official repository ran no licence file found · pointer only · 52890b345835d534 · report
get_input_transform LUMIA-Group/Cluster-wise-Graph-Transformer/Cluster_GT_N2C_L.py official repository ran no licence file found · pointer only · ed5fbe19001b6e38 · report
num_graphs LUMIA-Group/Cluster-wise-Graph-Transformer/data.py official repository ran · honoured contract no licence file found · pointer only · 9da87b0b1605a660 · report
random_walk LUMIA-Group/Cluster-wise-Graph-Transformer/pe.py official repository ran fingerprinted no licence file found · pointer only · 2d2ee0ffa615ecaf · report
to_sparse LUMIA-Group/Cluster-wise-Graph-Transformer/graph_partition.py official repository ran · honoured contract no licence file found · pointer only · 8039d4f24f678f0b · report
get_convs LUMIA-Group/Cluster-wise-Graph-Transformer/Cluster_GT_N2C_L.py official repository unverified no licence file found · pointer only · 2408224d33c2b803 · report

Tasks

Graph LearningNode Clustering

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutGraph TransformerLabel SmoothingLapEigenLaplacian PELayer 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