The paper introduces an unsupervised hypergraph neural network designed to detect anomalous hyperedges—higher-order associations that deviate from typical patterns. Unlike conventional graph methods that capture only pairwise relationships, this approach leverages hypergraphs to model associations among any number of entities. Experiments on real-life datasets show the model effectively identifies unusual hyperedges without requiring labeled data.
By Md. Tanvir Alam, Md. Mahmudur Rahman, Md. Fahim Arefin, Chowdhury Farhan Ahmed, Zisan Mahmud, Md. Sadman Sakib, Carson K. Leung
arXiv:2607. 05017v1 Announce Type: cross Abstract: The performance of deep learning models crucially depends on the settings of hyperparameters like learning rate, initialization scale, and weight decay.
By Gage DeZoort, Boris Hanin
arXiv:2608. 02128v1 Announce Type: new Abstract: Training Graph Neural Networks on large graphs is challenged by the memory cost of storing all node representations across layers.
By Antonin Joly, Nicolas Keriven, Aline Roumy
HyPE-GT introduces a framework that generates learnable hyperbolic positional encodings for Graph Transformers, enabling the capture of complex hierarchical relationships in graph-structured data. Unlike traditional Euclidean encodings, HyPE’s hyperbolic encodings can be selected to suit specific downstream tasks and help mitigate oversmoothing in deep Graph Neural Networks. Experiments on molecular benchmarks and large-scale Open Graph Benchmark datasets demonstrate improved performance, while additional tests on Coauthor and Copurchase networks confirm HyPE’s effectiveness in controlling oversmoothing.
By Kushal Bose, Swagatam Das
arXiv:2511. 11046v3 Announce Type: replace-cross Abstract: Graph neural networks (GNNs) have become an indispensable tool for analyzing relational data.
By Brian Godwin Lim, Galvin Brice Lim, Renzo Roel Tan, Irwin King, Kazushi Ikeda
The paper introduces MGHRL, a framework for hypergraph representation learning that adapts hyperedge granularity through a granular-ball splitting strategy. It constructs hyperedges at multiple levels of detail, capturing high-order relationships tailored to the graph’s topology. A multi-granularity hypergraph network then processes these hyperedges with sub-networks and hierarchical reversible connections, achieving superior performance on benchmark datasets.
By Sen Zhao, Yifan Guan, Jinyuan Ni, Gaojie Xu, Zhang Xu, Xiaoyu Lian, Yi Liu, Yi Wang, Wei Wang