arXiv Machine Learning July 20, 2026 By Zhiheng Zhou, Mengyao Zhou, Yancheng Chen, Dengyi Zhao, Xingqin Qi, Guiying Yan

From Diffusion to Reaction-Diffusion: A Dynamical-Systems View of Oversmoothing in Hypergraph Neural Networks

Read the original on arXiv Machine Learning →

arXiv:2607. 15773v1 Announce Type: new Abstract: Higher-order couplings enhance the expressive power of hypergraph neural networks (HGNNs), but they also intensify representation collapse in deep propagation due to strong multi-way feature mixing.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 9

Hypergraph Neural Stochastic Diffusion: An SDE Framework for Uncertainty Estimation

arXiv:2607. 07330v1 Announce Type: cross Abstract: Hypergraph neural networks have shown powerful capability in modeling higher-order relations, yet their predictive uncertainty remains underexplored.

By Zhiheng Zhou, Mengyao Zhou, Dengyi Zhao, Xingqin Qi, Guiying Yan

diffusion benchmarks

arXiv AI

Aug 10

Fluid-DiT: Graph-Free Diffusion Transformers for Fluid Flow Simulations Learning

arXiv:2608. 07161v1 Announce Type: cross Abstract: Simulating complex fluid flows requires capturing full equilibrium distributions rather than just mean trajectories, yet high-fidelity solvers remain computationally prohibitive.

By Shentong Mo, Guolin Ke

llms diffusion benchmarks

arXiv Machine Learning

Jun 9

Bulk-boundary decomposition of neural networks

arXiv:2511. 02003v2 Announce Type: replace Abstract: We present the bulk--boundary decomposition as a new framework for understanding the training dynamics of deep neural networks.

By Donghee Lee, Hye-Sung Lee, Jaeok Yi

arXiv Machine Learning

Jun 9

Beyond Convolution: Advancing Hypergraph Neural Networks with Hypergraph U-Nets

arXiv:2606. 09051v1 Announce Type: new Abstract: Convolutions have successfully transitioned from image processing to the complex realm of non-Euclidean higher-order domains, particularly in hypergraphs.

By Fuli Wang, Wei Qian, Daniel L. Lau, Gonzalo R. Arce

benchmarks

arXiv Machine Learning

Jul 30

HYVINT: Intensity-Driven Hypergraph Generation with Variational Embeddings

arXiv:2605. 16836v2 Announce Type: replace-cross Abstract: Hypergraphs provide a principled framework for modeling polyadic interactions, with applications in recommendation systems, social networks, and molecular modeling.

By Xinyi Hong, Shuntuo Xu, Zhou Yu

rag

arXiv Machine Learning

Jul 31

Persistent Gaussian Perturbations Prevent Oversmoothing in Recurrent Graph Neural Networks

arXiv:2607. 28185v1 Announce Type: new Abstract: Oversmoothing is a fundamental limitation of deep graph neural networks (GNNs), where repeated message passing causes node representations to become increasingly similar, eventually collapsing toward a low-dimensional subspace.

By Mostafa Haghir Chehreghani

Related stories

Hypergraph Neural Stochastic Diffusion: An SDE Framework for Uncertainty Estimation

Fluid-DiT: Graph-Free Diffusion Transformers for Fluid Flow Simulations Learning

Bulk-boundary decomposition of neural networks

Beyond Convolution: Advancing Hypergraph Neural Networks with Hypergraph U-Nets

HYVINT: Intensity-Driven Hypergraph Generation with Variational Embeddings

Persistent Gaussian Perturbations Prevent Oversmoothing in Recurrent Graph Neural Networks