arXiv research

Adaptive graph convolution improves attributed graph clustering performance.

Spectral graph convolutional neural networks (CNNs) require approximation to the convolution to alleviate the computational complexity, resulting in performance loss. This paper proposes the topology adaptive graph convolutional network (TAGCN), a novel graph convolutional network defined in the vertex domain. We provi…

Recently, many researchers have been focusing on the definition of neural networks for graphs. The basic component for many of these approaches remains the graph convolution idea proposed almost a decade ago. In this paper, we extend this basic component, following an intuition derived from the well-known convolutional…

This paper introduces Haar convolution for GNNs to reduce computational cost.

Graph convolutional kernel networks generalize CNNs to graph data.

Graph convolutional networks adapt the architecture of convolutional neural networks to learn rich representations of data supported on arbitrary graphs by replacing the convolution operations of convolutional neural networks with graph-dependent linear operations. However, these graph-dependent linear operations are d…

SWAG uses graph convolutions to recommend products.

Recently, graph neural networks have been adopted in a wide variety of applications ranging from relational representations to modeling irregular data domains such as point clouds and social graphs. However, the space of graph neural network architectures remains highly fragmented impeding the development of optimized …

This paper proposes a new Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes. Unlike state-of-the-art Graph Convolutional Neural Network (GCNN) models, the proposed QSGCNN model incorporates the process of identifying transit…

Traffic forecasting is a particularly challenging application of spatiotemporal forecasting, due to the time-varying traffic patterns and the complicated spatial dependencies on road networks. To address this challenge, we learn the traffic network as a graph and propose a novel deep learning framework, Traffic Graph C…

Automates graph convolutional network design for semi-supervised node classification.

Corrected graph convolutions improve node classification on graphs.

The paper bridges spectral and spatial graph convolutions, improving model capacity and transferability.

The paper bounds the complexity of GCNs using Rademacher complexity.

AEGCN uses autoencoder constraints to improve graph node classification.

GCN improved for large graphs with LCF to reduce complexity and noise.

Convolutional neural networks (CNNs) can be applied to graph similarity matching, in which case they are called graph CNNs. Graph CNNs are attracting increasing attention due to their effectiveness and efficiency. However, the existing convolution approaches focus only on regular data forms and require the transfer of …

Graph convolutional networks fail to use eigenvectors beyond the first, unlike spectral embedding.

Graph diffusion convolution improves graph learning by leveraging generalized graph diffusion.

Graph Convolutional Gaussian Processes predict missing links.

In this paper, we develop a novel Backtrackless Aligned-Spatial Graph Convolutional Network (BASGCN) model to learn effective features for graph classification. Our idea is to transform arbitrary-sized graphs into fixed-sized backtrackless aligned grid structures and define a new spatial graph convolution operation ass…

We present 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. We motivate the choice of our convolutional architecture via a localized first-order approximation of spectral graph convolutions.…

Extends GCNs to directed graphs for better performance.

New graph convolution captures local features on non-Euclidean grids.

Proposes a 2-WL-based graph convolution for improved graph classification.

Enhances GCNs to resist graph attacks.

DSGC improves graph representation learning by modeling object links and attribute relations.

BankGCN improves graph convolution networks by handling multi-channel signals with adaptive filter banks.

Molecular "fingerprints" encoding structural information are the workhorse of cheminformatics and machine learning in drug discovery applications. However, fingerprint representations necessarily emphasize particular aspects of the molecular structure while ignoring others, rather than allowing the model to make data-d…

GCNs improve regression tasks by aggregating neighbor signals.

CTGCN learns dynamic graph embeddings preserving both local and global graph structure.

Convolution Neural Network (CNN) has gained tremendous success in computer vision tasks with its outstanding ability to capture the local latent features. Recently, there has been an increasing interest in extending convolution operations to the non-Euclidean geometry. Although various types of convolution operations h…

GCN and GPCA are mathematically connected, leading to improved node classification performance.

Improved GCNs for non-sparse graphs with low-rank filters.

AdaGCN uses AdaBoost to efficiently integrate high-order neighbor knowledge in graph neural networks.

Learning representation on graph plays a crucial role in numerous tasks of pattern recognition. Different from grid-shaped images/videos, on which local convolution kernels can be lattices, however, graphs are fully coordinate-free on vertices and edges. In this work, we propose a Gaussian-induced convolution (GIC) fra…

A new linear GCN model improves recommendation performance for large graphs.

Indirect attacks can fool graph classifiers even with poisoned neighbors.

Proposes SGCN for spatially structured data.

GCNs improve multi-layer network classification by expanding the distance between means.

Popular graph neural networks implement convolution operations on graphs based on polynomial spectral filters. In this paper, we propose a novel graph convolutional layer inspired by the auto-regressive moving average (ARMA) filter that, compared to polynomial ones, provides a more flexible frequency response, is more …

Graph convolutions can enhance high frequencies, leading to over-sharpening.

We propose a novel Bayesian nonparametric method to learn translation-invariant relationships on non-Euclidean domains. The resulting graph convolutional Gaussian processes can be applied to problems in machine learning for which the input observations are functions with domains on general graphs. The structure of thes…

Combines BERT and graph CNN for improved text classification.

Paper proposes KE-GCN for better graph embedding.

In this paper, we develop a new aligned vertex convolutional network model to learn multi-scale local-level vertex features for graph classification. Our idea is to transform the graphs of arbitrary sizes into fixed-sized aligned vertex grid structures, and define a new vertex convolution operation by adopting a set of…

DEMO-Net improves graph neural networks by focusing on node degree.

We present our ongoing work on understanding the limitations of graph convolutional networks (GCNs) as well as our work on generalizations of graph convolutions for representing more complex node attribute dependencies. Based on an analysis of GCNs with the help of the corresponding computation graphs, we propose a gen…