UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks
This work addresses a bottleneck in machine learning for researchers and practitioners dealing with higher-order correlations in data, such as in social networks or citation networks, by providing a method to extend powerful GNN architectures to hypergraphs, though it is incremental in building upon existing GNN paradigms.
The paper tackles the challenge of adapting Graph Neural Networks (GNNs) to hypergraphs by proposing UniGNN, a unified framework that generalizes GNN models to hypergraphs, achieving state-of-the-art performance with an accuracy increase from 77.4% to 88.8% on the DBLP dataset for semi-supervised hypernode classification.
Hypergraph, an expressive structure with flexibility to model the higher-order correlations among entities, has recently attracted increasing attention from various research domains. Despite the success of Graph Neural Networks (GNNs) for graph representation learning, how to adapt the powerful GNN-variants directly into hypergraphs remains a challenging problem. In this paper, we propose UniGNN, a unified framework for interpreting the message passing process in graph and hypergraph neural networks, which can generalize general GNN models into hypergraphs. In this framework, meticulously-designed architectures aiming to deepen GNNs can also be incorporated into hypergraphs with the least effort. Extensive experiments have been conducted to demonstrate the effectiveness of UniGNN on multiple real-world datasets, which outperform the state-of-the-art approaches with a large margin. Especially for the DBLP dataset, we increase the accuracy from 77.4\% to 88.8\% in the semi-supervised hypernode classification task. We further prove that the proposed message-passing based UniGNN models are at most as powerful as the 1-dimensional Generalized Weisfeiler-Leman (1-GWL) algorithm in terms of distinguishing non-isomorphic hypergraphs. Our code is available at \url{https://github.com/OneForward/UniGNN}.