Dynamic Hypergraph Neural Networks

By Jianwen Jiang, Yuxuan Wei, Yifan Feng, Jingxuan Cao, Yue Gao. International Joint Conference on Artificial Intelligence, 2019

429 citations recorded by the source corpus.

In recent years, graph/hypergraph-based deep learning methods have attracted much attention from researchers. These deep learning methods take graph/hypergraph structure as prior knowledge in the model. However, hidden and important relations are not directly represented in the inherent structure. To tackle this issue, we propose a dynamic hypergraph neural networks framework (DHGNN), which is composed of the stacked layers of two modules: dynamic hypergraph construction (DHG) and hypergrpah convolution (HGC). Considering initially constructed hypergraph is probably not a suitable representation for data, the DHG module dynamically updates hypergraph structure on each layer. Then hypergraph convolution is introduced to encode high-order data relations in a hypergraph structure. The HGC module includes two phases: vertex convolution and hyperedge convolution, which are designed to aggregate feature among vertices and hyperedges, respectively. We have evaluated our method on standard datasets, the Cora citation network and Microblog dataset. Our method outperforms state-of-the-art methods. More experiments are conducted to demonstrate the effectiveness and robustness of our method to diverse data distributions.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c0a96cb13fa9c427315e57e990678de19d5813c0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Hongzhi Yin
2. Xin Xia
3. Junliang Yu
4. Li-zhen Cui
5. Davide Bacciu
6. Federico Errica
7. Marco Podda
8. Chao Huang

In Computer Vision and Pattern Recognition

1. Li-zhen Cui
2. Lianghao Xia
3. Xin Xia
4. Qinyong Wang
5. Chao Huang
6. Partha P. Talukdar
7. Hongzhi Yin
8. Junliang Yu

Citations in the corpus

• A Gentle Introduction to Deep Learning for Graphs (2019, background): “Some works on learning from hypergraph have recently been published [146, 145, 38, 67], and the most recent ones take inspiration from local and iterative processing of graphs.”
• Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation (2020, background): “(Jiang et al. 2019) proposed a dynamic hypergraph neural network and (Bandyopadhyay, Das, and Murty 2020) developed the line hypergraph convolutional networks.”
• Hypergraph Contrastive Collaborative Filtering (2022, methodology): “Toadap-tively learn hypergraph-based dependent structures across users and items, we propose to paramerterize hypergraph dependency matrices H ( 𝑢 ) , H ( 𝑣 ) which are jointly optimized along with the GNN-based CF architecture.”
• HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs (2018, methodology): “Hypergraph neural networks [17] and their variants [23, 24] use the clique expansion to extend GCNs for hypergraphs.”