Arya Devanshu, Gupta Deepak K, Rudinac Stevan, Worring Marcel
IEEE Trans Pattern Anal Mach Intell. 2025 Jan;47(1):19-31. doi: 10.1109/TPAMI.2024.3434483. Epub 2024 Dec 4.
Graphs are the most ubiquitous data structures for representing relational datasets and performing inferences in them. They model, however, only pairwise relations between nodes and are not designed for encoding the higher-order relations. This drawback is mitigated by hypergraphs, in which an edge can connect an arbitrary number of nodes. Most hypergraph learning approaches convert the hypergraph structure to that of a graph and then deploy existing geometric deep learning methods. This transformation leads to information loss, and sub-optimal exploitation of the hypergraph's expressive power. We present HyperMSG, a novel hypergraph learning framework that uses a modular two-level neural message passing strategy to accurately and efficiently propagate information within each hyperedge and across the hyperedges. HyperMSG adapts to the data and task by learning an attention weight associated with each node's degree centrality. Such a mechanism quantifies both local and global importance of a node, capturing the structural properties of a hypergraph. HyperMSG is inductive, allowing inference on previously unseen nodes. Further, it is robust and outperforms state-of-the-art hypergraph learning methods on a wide range of tasks and datasets. Finally, we demonstrate the effectiveness of HyperMSG in learning multimodal relations through detailed experimentation on a challenging multimedia dataset.
图是表示关系数据集并在其中进行推理的最普遍的数据结构。然而，它们仅对节点之间的成对关系进行建模，并非为编码高阶关系而设计。超图缓解了这一缺点，在超图中，一条边可以连接任意数量的节点。大多数超图学习方法将超图结构转换为图结构，然后部署现有的几何深度学习方法。这种转换会导致信息丢失，并且无法充分利用超图的表达能力。我们提出了HyperMSG，这是一种新颖的超图学习框架，它使用模块化的两级神经消息传递策略在每个超边内以及跨超边准确而高效地传播信息。HyperMSG通过学习与每个节点的度中心性相关的注意力权重来适应数据和任务。这种机制量化了节点的局部和全局重要性，捕捉了超图的结构属性。HyperMSG是归纳性的，允许对以前未见过的节点进行推理。此外，它具有鲁棒性，在广泛的任务和数据集上优于现有的超图学习方法。最后，我们通过在具有挑战性的多媒体数据集上进行详细实验，证明了HyperMSG在学习多模态关系方面的有效性。
