Corpus ID: 52175753

HyperGCN: Hypergraph Convolutional Networks for Semi-Supervised Classification

@article{Yadati2018HyperGCNHC,
  title={HyperGCN: Hypergraph Convolutional Networks for Semi-Supervised Classification},
  author={Naganand Yadati and Madhav Nimishakavi and Prateek Yadav and Anand Louis and Partha Pratim Talukdar},
  journal={ArXiv},
  year={2018},
  volume={abs/1809.02589}
}
Graph-based semi-supervised learning (SSL) is an important learning problem where the goal is to assign labels to initially unlabeled nodes in a graph. [...] Key Method In particular, we propose HyperGCN, an SSL method which uses a layer-wise propagation rule for convolutional neural networks operating directly on hypergraphs. To the best of our knowledge, this is the first principled adaptation of GCNs to hypergraphs. HyperGCN is able to encode both the hypergraph structure and hypernode features in an…Expand
HpLapGCN: Hypergraph p-Laplacian graph convolutional networks
TLDR
This paper simplifies and deduce a one-order approximation of spectral hypergraph p-Laplacian convolutions and proposes an effective variant of GCN, i.e. HpLapGCN, a more efficient layer-wise aggregate rule for graph convolutional networks. Expand
Semi-supervised Learning with Graph Convolutional Networks Based on Hypergraph
TLDR
This paper proposes a new graph learning method to output a high-quality graph structure, aiming at eventually improving classification performance for the downstream GCN model (HS-GCN). Expand
Hyper-SAGNN: a self-attention based graph neural network for hypergraphs
TLDR
This work develops a new self-attention based graph neural network called Hyper-SAGNN applicable to homogeneous and heterogeneous hypergraphs with variable hyperedge sizes that significantly outperforms the state-of-the-art methods on traditional tasks while also achieving great performance on a new task called outsider identification. Expand
Example-feature graph convolutional networks for semi-supervised classification
TLDR
The definition of the spectral example-feature graph (EFG) convolution that simultaneously utilizes the example graph Laplacian and feature graph LaPLacian to better preserve the local geometry distributions of data is introduced. Expand
Dynamic Graph Learning Convolutional Networks for Semi-supervised Classification
Over the past few years, graph representation learning (GRL) has received widespread attention on the feature representations of the non-Euclidean data. As a typical model of GRL, graph convolutionalExpand
HesGCN: Hessian graph convolutional networks for semi-supervised classification
TLDR
HesGCN can learn more efficient data features by fusing the original feature information with its structure information based on Hessian, and gets a more efficient convolution layer rule by optimizing the one-order spectral graph Hessian convolutions. Expand
Semi-Supervised Classification on Non-Sparse Graphs Using Low-Rank Graph Convolutional Networks
TLDR
By introducing low-rank filters in GCNs, this work gains significant runtime acceleration and simultaneously improved accuracy and proposes an architecture change mimicking techniques from Model Order Reduction in what is called a reduced-order GCN. Expand
Human activity recognition by manifold regularization based dynamic graph convolutional networks
TLDR
A manifold regularized dynamic graph convolutional network (MRDGCN) that automatically updates the structure information by manifold regularization until model fitting and builds an optimization convolution layer formulation to acquire the optimal structure information. Expand
Knowledge Hypergraphs: Extending Knowledge Graphs Beyond Binary Relations
TLDR
This work introduces HypE, a convolution-based embedding method for knowledge hypergraph completion, and develops public benchmarks and baselines to show experimentally that HypE is more effective than proposed baselines and existing methods. Expand
How Much and When Do We Need Higher-order Information in Hypergraphs? A Case Study on Hyperedge Prediction
TLDR
This work proposes a method of incrementally representing group interactions using a notion of n-projected graph whose accumulation contains information on up to n-way interactions, and quantifies the accuracy of solving a task as n grows for various datasets. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 64 REFERENCES
Confidence-based Graph Convolutional Networks for Semi-Supervised Learning
TLDR
ConfGCN is proposed, which estimates labels scores along with their confidences jointly in GCN-based setting and uses these estimated confidences to determine the influence of one node on another during neighborhood aggregation, thereby acquiring anisotropic capabilities. Expand
Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
TLDR
It is shown that the graph convolution of the GCN model is actually a special form of Laplacian smoothing, which is the key reason why GCNs work, but it also brings potential concerns of over-smoothing with many convolutional layers. Expand
Hypergraph Neural Networks
TLDR
A hypergraph neural networks framework for data representation learning, which can encode high-order data correlation in a hypergraph structure using a hyperedge convolution operation, which outperforms recent state-of-theart methods. Expand
Dual Graph Convolutional Networks for Graph-Based Semi-Supervised Classification
TLDR
This paper presents a simple and scalable semi-supervised learning method for graph-structured data in which only a very small portion of the training data are labeled, and introduces an unsupervised temporal loss function for the ensemble. Expand
Learning on Partial-Order Hypergraphs
TLDR
This work proposes a new data structure named Partial-Order Hypergraph, which specifically injects the partially ordering relations among vertices into a hyperedge and develops regularization-based learning theories for partial-order hypergraphs, generalizing conventional hypergraph learning by incorporating logical rules that encode the partial- order relations. Expand
Graph-Based Semi-Supervised Learning
TLDR
This synthesis lecture focuses on graph-based SSL algorithms (e.g., label propagation methods), which have been shown to outperform the state-of-the-art in many applications in speech processing, computer vision, natural language processing, and other areas of Artificial Intelligence. Expand
Extended Discriminative Random Walk: A Hypergraph Approach to Multi-View Multi-Relational Transductive Learning
TLDR
This work model multiway relations as hypergraphs and extend the discriminative random walk (DRW) framework for inference on multi-view, multi-relational data in a natural way, by representing attribute descriptions of the data also ashypergraphs. Expand
Learning with Hypergraphs: Clustering, Classification, and Embedding
TLDR
This paper generalizes the powerful methodology of spectral clustering which originally operates on undirected graphs to hypergraphs, and further develop algorithms for hypergraph embedding and transductive classification on the basis of the spectral hypergraph clustering approach. Expand
Graph Attention Networks
We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of priorExpand
Multi-Label Image Recognition With Graph Convolutional Networks
TLDR
This work proposes a multi-label classification model based on Graph Convolutional Network (GCN), and proposes a novel re-weighted scheme to create an effective label correlation matrix to guide information propagation among the nodes in GCN. Expand
...
1
2
3
4
5
...