Kernelized Hypergraph Neural Networks

Hypergraph Neural Networks (HGNNs) have attracted much attention for high-order structural data learning. Existing methods mainly focus on simple mean-based aggregation or manually combining multiple aggregations to capture multiple information on hypergraphs. However, those methods inherently lack...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 47(2025), 10 vom: 01. Sept., Seite 8938-8954
1. Verfasser: Feng, Yifan (VerfasserIn)
Weitere Verfasser: Zhang, Yifan, Ying, Shihui, Du, Shaoyi, Gao, Yue
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2025
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000caa a22002652c 4500
001 NLM392372584
003 DE-627
005 20250914232045.0
007 cr uuu---uuuuu
008 250912s2025 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2025.3585179  |2 doi 
028 5 2 |a pubmed25n1566.xml 
035 |a (DE-627)NLM392372584 
035 |a (NLM)40601442 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Feng, Yifan  |e verfasserin  |4 aut 
245 1 0 |a Kernelized Hypergraph Neural Networks 
264 1 |c 2025 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 12.09.2025 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Hypergraph Neural Networks (HGNNs) have attracted much attention for high-order structural data learning. Existing methods mainly focus on simple mean-based aggregation or manually combining multiple aggregations to capture multiple information on hypergraphs. However, those methods inherently lack continuous non-linear modeling ability and are sensitive to varied distributions. Although some kernel-based aggregations on GNNs and CNNs can capture non-linear patterns to some degree, those methods are restricted in the low-order correlation and may cause unstable computation in training. In this work, we introduce Kernelized Hypergraph Neural Networks (KHGNN) and its variant, Half-Kernelized Hypergraph Neural Networks (H-KHGNN), which synergize mean-based and max-based aggregation functions to enhance representation learning on hypergraphs. KHGNN's kernelized aggregation strategy adaptively captures both semantic and structural information via learnable parameters, offering a mathematically grounded blend of kernelized aggregation approaches for comprehensive feature extraction. H-KHGNN addresses the challenge of overfitting in less intricate hypergraphs by employing non-linear aggregation selectively in the vertex-to-hyperedge message-passing process, thus reducing model complexity. Our theoretical contributions reveal a bounded gradient for kernelized aggregation, ensuring stability during training and inference. Empirical results demonstrate that KHGNN and H-KHGNN outperform state-of-the-art models across 10 graph/hypergraph datasets, with ablation studies demonstrating the effectiveness and computational stability of our method 
650 4 |a Journal Article 
700 1 |a Zhang, Yifan  |e verfasserin  |4 aut 
700 1 |a Ying, Shihui  |e verfasserin  |4 aut 
700 1 |a Du, Shaoyi  |e verfasserin  |4 aut 
700 1 |a Gao, Yue  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 47(2025), 10 vom: 01. Sept., Seite 8938-8954  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnas 
773 1 8 |g volume:47  |g year:2025  |g number:10  |g day:01  |g month:09  |g pages:8938-8954 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2025.3585179  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 47  |j 2025  |e 10  |b 01  |c 09  |h 8938-8954