Hypergraph Structure Learning for Hypergraph Neural Networks

Abstract

Anomaly detection in graphs has attracted considerable interests in both academia and industry due to its wide applications in numerous domains ranging from finance to biology. Meanwhile, graph neural networks (GNNs) is emerging as a powerful tool for modeling graph data. A natural and fundamental question that arises here is: can abnormality be detected by graph neural networks? In this paper, we aim to answer this question, which is nontrivial. As many existing works have explored, graph neural networks can be seen as filters for graph signals, with the favor of low frequency in graphs. In other words, GNN will smooth the signals of adjacent nodes. However, abnormality in a graph intuitively has the characteristic that it tends to be dissimilar to its neighbors, which are mostly normal samples. It thereby conflicts with the general assumption with traditional GNNs. To solve this, we propose a novel Adaptive Multi-frequency Graph Neural Network (AMNet), aiming to capture both low-frequency and high-frequency signals, and adaptively combine signals of different frequencies. Experimental results on real-world datasets demonstrate that our model achieves a significant improvement comparing with several state-of-the-art baseline methods.

Enhancing Language Representation with Constructional Information for Natural Language Understanding

“…Hypergraph neural networks. Recent research has extended conventional graph to hypergraph (Feng et al, 2019;Ding et al, 2020a;Cai et al, 2022), which can model high-order data correlation. However, when the networks ignore the representation of hyperedges, the capability of capturing higher-order relationships between nodes can be inhibited (Fan et al, 2021).…”