Hybrid Low-Order and Higher-Order Graph Convolutional Networks

  title={Hybrid Low-Order and Higher-Order Graph Convolutional Networks},
  author={Fangyuan Lei and Xun Liu and Qingyun Dai and Bingo Wing-Kuen Ling and Huimin Zhao and Yan Liu},
  journal={Computational Intelligence and Neuroscience},
With the higher-order neighborhood information of a graph network, the accuracy of graph representation learning classification can be significantly improved. However, the current higher-order graph convolutional networks have a large number of parameters and high computational complexity. Therefore, we propose a hybrid lower-order and higher-order graph convolutional network (HLHG) learning model, which uses a weight sharing mechanism to reduce the number of network parameters. To reduce the… 

Figures and Tables from this paper

MulStepNET: stronger multi-step graph convolutional networks via multi-power adjacency matrix combination

This work proposes MulStepNET, a stronger multi-step graph convolutional network architecture that can capture more global information, by simultaneously combining multi- step neighborhoods information, and achieves better performance in terms of accuracy and stability compared to other baselines.

Multihop Neighbor Information Fusion Graph Convolutional Network for Text Classification

This paper adopts the weight-sharing mechanism to design different order graph convolutions for avoiding the potential concerns of overfitting and designs a new multihop neighbor information fusion (MIF) operator which mixes different neighbor features from 1-hop to k-hops.

AdjMix: simplifying and attending graph convolutional networks

AdjMix is proposed, a simple and attentional graph convolutional model that is scalable to wider structure and captures more nodes features information, by simultaneously mixing the adjacency matrices of different powers.

Stacked Mixed-Order Graph Convolutional Networks for Collaborative Filtering

This paper proposes SMOG-CF (Stacked Mixed-Order Graph Convolutional Networks for Collaborative Filtering), a GCN-based framework that can directly capture high-order connectivity among nodes and facilitates ‘path-level’ information propagation between neighboring nodes at any order.

Hop-Aware Dimension Optimization for Graph Neural Networks

A simple yet effective ladder-style GNN architecture, namely LADDER-GNN, that separate messages from different hops and assign different dimensions for them before concatenating them to obtain the node representation.

Ladder-GNN: Hop-Aware Representation Learning for Graph Neural Networks

A simple yet effective hopaware aggregation scheme is proposed, resulting in a ladder-style GNN architecture, namely Ladder-GNN, which verifies the proposed LadderGNN on seven semi-supervised node classification datasets, including both homogeneous and heterogeneous graphs.

Relational Graph Neural Network Design via Progressive Neural Architecture Search

We propose a novel solution to addressing a longstanding dilemma in the representation learning of graph neural networks (GNNs): how to effectively capture and represent useful information embedded

Multihop Neighbor Information Fusion Graph Convolutional Network for Text Classification

Guangdong Key Provincial Laboratory of Intellectual Property & Big Data, Guangdong Polytechnic Normal University, Guangzhou 510665, China School of Electronic and Information, Guangdong Polytechnic

Research on autonomous underwater vehicle wall following based on reinforcement learning and multi-sonar weighted round robin mode

A novel work mode with weighted polling which can independently identify the environment, dynamically establish the environmental model, and switch the operating frequency of the sonar is proposed and the tank test verified the effectiveness of the algorithm.



Higher-order Graph Convolutional Networks

This work proposes a motif-based graph attention model, called Motif Convolutional Networks (MCNs), which generalizes past approaches by using weighted multi-hop motif adjacency matrices to capture higher-order neighborhoods.

A Higher-Order Graph Convolutional Layer

This work proposes a new Graph Convolutional layer which mixes multiple powers of the adjacency matrix, allowing it to learn delta operators, and illustrates the strength of the proposed layer on both synthetic graph datasets, and on several real-world citation graphs.

Similarity Learning with Higher-Order Graph Convolutions for Brain Network Analysis

This work proposes an end-to-end similarity learning framework called Higher-order Siamese GCN for multi-subject fMRI data analysis that performs higher-order convolutions by incorporating higher- order proximity in graph convolutional networks to characterize and learn the community structure in brain connectivity networks.

Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning

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.

CayleyNets: Graph Convolutional Neural Networks With Complex Rational Spectral Filters

A new spectral domain convolutional architecture for deep learning on graphs with a new class of parametric rational complex functions (Cayley polynomials) allowing to efficiently compute spectral filters on graphs that specialize on frequency bands of interest.

MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing

This work proposes a new model, MixHop, that can learn a general class of neighborhood mixing relationships by repeatedly mixing feature representations of neighbors at various distances, and proposes sparsity regularization that allows to visualize how the network prioritizes neighborhood information across different graph datasets.

Semi-Supervised Classification with Graph Convolutional Networks

A scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs which outperforms related methods by a significant margin.

How Powerful are Graph Neural Networks?

This work characterize the discriminative power of popular GNN variants, such as Graph Convolutional Networks and GraphSAGE, and show that they cannot learn to distinguish certain simple graph structures, and develops a simple architecture that is provably the most expressive among the class of GNNs.

Deep Convolutional Networks on Graph-Structured Data

This paper develops an extension of Spectral Networks which incorporates a Graph Estimation procedure, that is test on large-scale classification problems, matching or improving over Dropout Networks with far less parameters to estimate.

GraRep: Learning Graph Representations with Global Structural Information

A novel model for learning vertex representations of weighted graphs that integrates global structural information of the graph into the learning process and significantly outperforms other state-of-the-art methods in such tasks.