第一篇 Edge Representation Learning with Hypergraphs Abstract 图神经网络最近在表示图结构数据方面取得了显著的成功,在节点嵌入和图的池化方法方面都取得了迅速的进展。考虑到节点的连通性,过往的工作主要关注于从节点中获取信息,而在edge的representation方面没有做太多工作,这是图的基本
Edge Representation Learning with Hypergraphs是一种创新的图神经网络框架，旨在解决传统GNN在边缘表示学习上的不足。以下为该框架的核心要点：双超图变换：DHT是一种将图的边缘转换为超图节点的方法。通过这种方式，可以利用已有的节点级表示学习技术来处理边缘，从而更精确地捕捉边缘信息。这对于图的精确重构...
在图神经网络（GNN）取得显著进展的同时，对于边缘（edge）的表示学习却相对较少关注。传统的GNN主要集中在节点的表示学习上，而边缘在图重构和生成等任务中的关键作用并未充分挖掘。为此，我们提出了一种创新的边缘表示学习框架，称为双超图变换（DHT）的边缘超图神经网络（EHGNN）。DHT将图的边缘转换为...
Official Code Repository for the paper "Edge Representation Learning with Hypergraphs" (NeurIPS 2021): https://arxiv.org/abs/2106.15845. In this repository, we implement the Dual Hypergraph Transformation (DHT) and two edge pooling methods HyperDrop and HyperCluster. Contribution We introduce a nove...
We propose a new formulation called hyperedge expansion (HE) for hypergraph learning. The HE expansion transforms the hypergraph into a directed graph on the hyperedge level. Compared to the existing works (e.g. star expansion or normalized hypergraph cu
They incorporate hyperedge features into model learning and design diverse objective functions for optimization to obtain embeddings of candidate hyperedges. These methods do not consider the influence of different hyperedges related to nodes. Hence, attention mechanisms are introduced into hypergraphs (...
Hypergraphs provide a natural representation for many real world datasets. We propose a novel framework, HNHN, for hypergraph representation learning. HNHN is a hypergraph convolution network with nonlinear activation functions applied to both hypernodes and hyperedges, combined with a normalization ...
Moreover, we give conditions under which random walks on such hypergraphs are equivalent to random walks on graphs. As a corollary, we show that current machine learning methods that rely on Laplacians derived from random walks on hypergraphs with edge-independent vertex weights do not utilize ...
In this work, we present HEAT, a neural model capable of representing typed and qualified hypergraphs, where each hyperedge explicitly qualifies how participating nodes contribute. It can be viewed as a generalization of both message passing neural networks and Transformers. We evaluate HEAT on knowl...
Learning with hypergraphs: Clustering, classification and embedding. In Proceedings of the 19th International Conference on Neural Information Processing Systems, Vancouver, Canada, 4–7 December 2006; pp. 1601–1608. [Google Scholar] Sharma, K.K.; Seal, A.; Herrera-Viedma, E.; Krejcar, O. ...