33 citations · 84 across the 11 of their papers we have counts for
8 papers · 1 filter
ProtoGuide: Prototype-Driven Guidance for Class-Conditional Graph Generation
Salvatore Romano, Marco Grassia, Pietro Liò +1
Discrete diffusion models are a prominent family for graph generation, but standard class-conditional mechanisms embed the class signal in the denoiser during training, tying the c…
How Particle System Theory Enhances Hypergraph Message Passing
Yixuan Ma, Kai Yi, Pietro Lio +2
Hypergraphs effectively model higher-order relationships in natural phenomena, capturing complex interactions beyond pairwise connections. We introduce a novel hypergraph message p…
How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashing
Keke Huang, Yu Guang Wang, Ming Li +1
Spectral Graph Neural Networks (GNNs), alternatively known as graph filters, have gained increasing prevalence for heterophily graphs. Optimal graph filters rely on Laplacian eigen…
Dirichlet Energy Enhancement of Graph Neural Networks by Framelet Augmentation
Jialin Chen, Yuelin Wang, Cristian Bodnar +3
Graph convolutions have been a pivotal element in learning graph representations. However, recursively aggregating neighboring information with graph convolutions leads to indistin…
An Effective Universal Polynomial Basis for Spectral Graph Neural Networks
Keke Huang, Pietro Liò
Spectral Graph Neural Networks (GNNs), also referred to as graph filters have gained increasing prevalence for heterophily graphs. Optimal graph filters rely on Laplacian eigendeco…
Spectral Transform Forms Scalable Transformer
Bingxin Zhou, Xinliang Liu, Yuehua Liu +3
Many real-world relational systems, such as social networks and biological systems, contain dynamic interactions. When learning dynamic graph representation, it is essential to emp…
How Framelets Enhance Graph Neural Networks
Xuebin Zheng, Bingxin Zhou, Junbin Gao +4
This paper presents a new approach for assembling graph neural networks based on framelet transforms. The latter provides a multi-scale representation for graph-structured data. We…
Path Integral Based Convolution and Pooling for Graph Neural Networks
Zheng Ma, Junyu Xuan, Yu Guang Wang +2
Graph neural networks (GNNs) extends the functionality of traditional neural networks to graph-structured data. Similar to CNNs, an optimized design of graph convolution and poolin…