Preventing Over-Smoothing for Hypergraph Neural Networks
- URL: http://arxiv.org/abs/2203.17159v1
- Date: Thu, 31 Mar 2022 16:33:31 GMT
- Title: Preventing Over-Smoothing for Hypergraph Neural Networks
- Authors: Guanzi Chen, Jiying Zhang
- Abstract summary: We show that the performance of hypergraph neural networks does not improve as the number of layers increases.
We develop a new deep hypergraph convolutional network called Deep-HGCN, which can maintain node representation in deep layers.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In recent years, hypergraph learning has attracted great attention due to its
capacity in representing complex and high-order relationships. However, current
neural network approaches designed for hypergraphs are mostly shallow, thus
limiting their ability to extract information from high-order neighbors. In
this paper, we show both theoretically and empirically, that the performance of
hypergraph neural networks does not improve as the number of layers increases,
which is known as the over-smoothing problem. To tackle this issue, we develop
a new deep hypergraph convolutional network called Deep-HGCN, which can
maintain the heterogeneity of node representation in deep layers. Specifically,
we prove that a $k$-layer Deep-HGCN simulates a polynomial filter of order $k$
with arbitrary coefficients, which can relieve the problem of over-smoothing.
Experimental results on various datasets demonstrate the superior performance
of the proposed model comparing to the state-of-the-art hypergraph learning
approaches.
Related papers
- From Hypergraph Energy Functions to Hypergraph Neural Networks [94.88564151540459]
We present an expressive family of parameterized, hypergraph-regularized energy functions.
We then demonstrate how minimizers of these energies effectively serve as node embeddings.
We draw parallels between the proposed bilevel hypergraph optimization, and existing GNN architectures in common use.
arXiv Detail & Related papers (2023-06-16T04:40:59Z) - Tensorized Hypergraph Neural Networks [69.65385474777031]
We propose a novel adjacency-tensor-based textbfTensorized textbfHypergraph textbfNeural textbfNetwork (THNN)
THNN is faithful hypergraph modeling framework through high-order outer product feature passing message.
Results from experiments on two widely used hypergraph datasets for 3-D visual object classification show the model's promising performance.
arXiv Detail & Related papers (2023-06-05T03:26:06Z) - Deep Graph Neural Networks via Flexible Subgraph Aggregation [50.034313206471694]
Graph neural networks (GNNs) can learn from graph-structured data and learn the representation of nodes through aggregating neighborhood information.
In this paper, we evaluate the expressive power of GNNs from the perspective of subgraph aggregation.
We propose a sampling-based node-level residual module (SNR) that can achieve a more flexible utilization of different hops of subgraph aggregation.
arXiv Detail & Related papers (2023-05-09T12:03:42Z) - Equivariant Hypergraph Diffusion Neural Operators [81.32770440890303]
Hypergraph neural networks (HNNs) using neural networks to encode hypergraphs provide a promising way to model higher-order relations in data.
This work proposes a new HNN architecture named ED-HNN, which provably represents any continuous equivariant hypergraph diffusion operators.
We evaluate ED-HNN for node classification on nine real-world hypergraph datasets.
arXiv Detail & Related papers (2022-07-14T06:17:00Z) - Hypergraph Convolutional Networks via Equivalency between Hypergraphs
and Undirected Graphs [59.71134113268709]
We present General Hypergraph Spectral Convolution(GHSC), a general learning framework that can handle EDVW and EIVW hypergraphs.
In this paper, we show that the proposed framework can achieve state-of-the-art performance.
Experiments from various domains including social network analysis, visual objective classification, protein learning demonstrate that the proposed framework can achieve state-of-the-art performance.
arXiv Detail & Related papers (2022-03-31T10:46:47Z) - Learnable Hypergraph Laplacian for Hypergraph Learning [34.28748027233654]
HyperGraph Convolutional Neural Networks (HGCNNs) have demonstrated their potential in modeling high-order relations preserved in graph structured data.
We propose the first learning-based method tailored for constructing adaptive hypergraph structure, termed HypERgrAph Laplacian aDaptor (HERALD)
HERALD adaptively optimize the adjacency relationship between hypernodes and hyperedges in an end-to-end manner and thus the task-aware hypergraph is learned.
arXiv Detail & Related papers (2021-06-12T02:07:07Z) - Residual Enhanced Multi-Hypergraph Neural Network [26.42547421121713]
HyperGraph Neural Network (HGNN) is the de-facto method for hypergraph representation learning.
We propose the Residual enhanced Multi-Hypergraph Neural Network, which can fuse multi-modal information from each hypergraph effectively.
arXiv Detail & Related papers (2021-05-02T14:53:32Z) - Towards Deeper Graph Neural Networks [63.46470695525957]
Graph convolutions perform neighborhood aggregation and represent one of the most important graph operations.
Several recent studies attribute this performance deterioration to the over-smoothing issue.
We propose Deep Adaptive Graph Neural Network (DAGNN) to adaptively incorporate information from large receptive fields.
arXiv Detail & Related papers (2020-07-18T01:11:14Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.