The field of graph neural networks and hypergraph learning is rapidly advancing, with a focus on developing more efficient and effective methods for learning from complex relational data. Recent developments have highlighted the importance of capturing long-range dependencies and higher-order interactions in graph-structured data, with techniques such as graph diffusion and hypergraph neural networks showing promise. Notable papers in this area include Graph Neural Diffusion via Generalized Opinion Dynamics, which proposes a novel framework for graph neural diffusion, and Implicit Hypergraph Neural Network, which introduces a new approach for learning long-range dependencies in hypergraphs. Other noteworthy papers include A Remedy for Over-Squashing in Graph Learning via Forman-Ricci Curvature based Graph-to-Hypergraph Structural Lifting, which addresses the issue of over-squashing in graph learning, and DHG-Bench, which provides a comprehensive benchmark for deep hypergraph learning.
Advances in Graph Neural Networks and Hypergraph Learning
Sources
Graph Neural Diffusion via Generalized Opinion Dynamics
A Remedy for Over-Squashing in Graph Learning via Forman-Ricci Curvature based Graph-to-Hypergraph Structural Lifting
DHG-Bench: A Comprehensive Benchmark on Deep Hypergraph Learning
Constructing Invariant and Equivariant Operations by Symmetric Tensor Network
Influence Prediction in Collaboration Networks: An Empirical Study on arXiv
Deep Graph Neural Point Process For Learning Temporal Interactive Networks
Non-Dissipative Graph Propagation for Non-Local Community Detection
Implicit Hypergraph Neural Network
On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks
A Non-Asymptotic Convergent Analysis for Scored-Based Graph Generative Model via a System of Stochastic Differential Equations
SBGD: Improving Graph Diffusion Generative Model via Stochastic Block Diffusion
Graph Structure Learning with Temporal Graph Information Bottleneck for Inductive Representation Learning
HIP: Model-Agnostic Hypergraph Influence Prediction via Distance-Centrality Fusion and Neural ODEs