Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Hypergraph Neural Diffusion: A PDE-Inspired Framework for Hypergraph Message Passing

About

Hypergraph neural networks (HGNNs) have shown remarkable potential in modeling high-order relationships that naturally arise in many real-world data domains. However, existing HGNNs often suffer from shallow propagation, oversmoothing, and limited adaptability to complex hypergraph structures. In this paper, we propose Hypergraph Neural Diffusion (HND), a novel framework that unifies nonlinear diffusion equations with neural message passing on hypergraphs. HND is grounded in a continuous-time hypergraph diffusion equation, formulated via hypergraph gradient and divergence operators, and modulated by a learnable, structure-aware coefficient matrix over hyperedge-node pairs. This partial differential equation (PDE) based formulation provides a physically interpretable view of hypergraph learning, where feature propagation is understood as an anisotropic diffusion process governed by local inconsistency and adaptive diffusion coefficient. From this perspective, neural message passing becomes a discretized gradient flow that progressively minimizes a diffusion energy functional. We derive rigorous theoretical guarantees, including energy dissipation, solution boundedness via a discrete maximum principle, and stability under explicit and implicit numerical schemes. The HND framework supports a variety of integration strategies such as non-adaptive-step (like Runge-Kutta) and adaptive-step solvers, enabling the construction of deep, stable, and interpretable architectures. Extensive experiments on benchmark datasets demonstrate that HND achieves competitive performance. Our results highlight the power of PDE-inspired design in enhancing the stability, expressivity, and interpretability of hypergraph learning.

Zhiheng Zhou, Mengyao Zhou, Xixun Lin, Xingqin Qi, Guiying Yan• 2026

Related benchmarks

TaskDatasetResultRank
Node ClassificationCora--
1215
Node ClassificationPubmed
Accuracy88.56
178
Node ClassificationCiteseer
Mean Accuracy75.8
90
Node ClassificationDBLP CA
Accuracy91.71
37
Node ClassificationCora CA
Mean Accuracy85.49
30
Hypergraph Node ClassificationModelNet40 (test)
Accuracy98.49
27
Hypergraph Node ClassificationNTU 2012 (test)
Accuracy93.32
27
Hypergraph Node ClassificationHouse (test)
Accuracy74.63
15
Hypergraph Node ClassificationSenate (test)
Accuracy70.97
14
Hypergraph Node ClassificationZoo (test)
Accuracy99.19
10
Showing 10 of 11 rows

Other info

Follow for update