Integrative analysis of patient health records and neuroimages using MemGCN.
problem Combining EHR and neuroimaging data for disease understanding.
method Memory-Based Graph Convolution Network (MemGCN) framework.
result Superior classification performance in Parkinson's Disease cases versus controls.
Efficient memory layer improves graph neural networks for graph classification and regression.
problem Efficiently learning node representations and graph coarsening for arbitrary graph topology.
method Introduces a memory layer for GNNs that learns node representations and graph coarsening, and two new networks: MemGNN and GMN.
result Proposed models achieve state-of-the-art results in graph classification and regression benchmarks.
MTRGL learns temporal correlations from multi-modal data for improved pair trading.
problem Discerning temporal correlations among financial entities.
method Combines time series data and discrete features into a temporal graph, using a memory-based temporal graph neural network.
result MTRGL outperforms traditional methods in temporal graph link prediction and pair trading.
BiGraphNet generalizes graph neural networks for more efficient operations.
problem Fragmented graph neural network architectures hinder optimization.
method Explicitly separates input and output nodes, enabling new efficient operations.
result BiGraphNet accelerates and scales computations in hierarchical networks.
Real time application of deep learning algorithms is often hindered by high computational complexity and frequent memory accesses. Network pruning is a promising technique to solve this problem. However, pruning usually results in irregular network connections that not only demand extra representation efforts but also …
Paper improves graph convolutional networks by adjusting filter size.
problem Improving predictive performance of graph convolutional networks.
method Introducing a hyper-parameter to influence filter size in graph convolutions.
result Improves predictive performance of Deep Graph Convolutional Networks.
Deep neural networks have excelled on a wide range of problems, from vision to language and game playing. Neural networks very gradually incorporate information into weights as they process data, requiring very low learning rates. If the training distribution shifts, the network is slow to adapt, and when it does adapt…
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…
Automates graph convolutional network design for semi-supervised node classification.
problem Designing optimal graph convolutional network architectures for semi-supervised node classification.
method An automatic process to define a problem-specific architecture based on graph structure.
result The proposed method outperforms existing methods in classification performance and network compactness.
Graph convolutional kernel networks generalize CNNs to graph data.
problem Representing graph-structured data for machine learning.
method Convolutional kernel networks applied to graph data.
result Competitive performance on graph classification benchmarks.
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…
Proposes a new QSGCNN model for graph classification.
problem Information loss and imprecise representation in existing GCN models.
method Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model.
result Demonstrates effectiveness on benchmark graph classification datasets.
AEGCN uses autoencoder constraints to improve graph node classification.
problem Node classification on graph domains with reduced information loss.
method Autoencoder-constrained graph convolutional network (AEGCN).
result Adding autoencoder constraints significantly improves graph convolutional network performance.
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…
Graph convolutional networks fail to use eigenvectors beyond the first, unlike spectral embedding.
problem Understanding when graph convolutional networks fail compared to spectral embedding.
method Presented a simple generative model to illustrate failure.
result Graph convolutional networks fail to use eigenvectors beyond the first in certain graphs.
Develops BASGCN for graph classification with improved feature learning.
problem Graph classification with information loss and imprecise representation.
method Transforms graphs into grid structures and defines a new spatial graph convolution operation.
result Reduces information loss and improves feature representation compared to existing models.
Improved graph convolutional networks using perturbed graph Laplacian.
problem Improving graph convolutional networks' generalization.
method Minimizing loss with perturbed graph Laplacian eigendecomposition.
result Consistent improvement on semi-supervised node classification tasks.
ARMA filters improve graph neural networks' flexibility and robustness.
problem Improving graph neural networks' performance and robustness.
method Proposes an ARMA-based graph convolutional layer for graph neural networks.
result ARMA filters outperform polynomial filters in various graph tasks.
AdaGCN uses AdaBoost to efficiently integrate high-order neighbor knowledge in graph neural networks.
problem Efficiently exploring and exploiting knowledge from different hops of neighbors in graph neural networks.
method Incorporates AdaBoost into graph convolutional networks to integrate knowledge from high-order neighbors.
result AdaGCN achieves state-of-the-art prediction performance across different graphs and label rates.
This paper introduces Haar convolution for GNNs to reduce computational cost.
problem High computational cost in GNNs for large graph sizes.
method Introduces Haar basis for graph convolution and Fast Haar Transforms.
result State-of-the-art results on graph-based regression and node classification tasks.
New schemes improve lifelong learning by balancing old and new tasks.
problem Catastrophic forgetting in deep neural networks when learning multiple tasks.
method Unified optimization perspective of episodic memory based approaches, introducing MEGA-I and MEGA-II schemes.
result Significant improvement in lifelong learning benchmarks, reducing error by up to 18%.
Graph convolutional Gaussian processes learn functions on graphs.
problem Learning translation-invariant relationships on non-Euclidean domains.
method Bayesian nonparametric method using graph convolutional neural networks.
result Graph convolutional Gaussian processes outperform existing methods on images and triangular meshes.
The paper bounds the complexity of GCNs using Rademacher complexity.
problem Understanding the sample complexity of GCNs.
method Derived tight upper and lower bounds of Rademacher complexity for GCN models.
result The derived bounds depend on the largest eigenvalue of the graph filter and the degree distribution.
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.
problem Limited application of GCNs to undirected graphs.
method Uses first- and second-order proximity to extend GCNs to directed graphs.
result DGCN outperforms state-of-the-art methods on citation and co-purchase datasets.
GCNs improve multi-layer network classification by expanding the distance between means.
problem Improving multi-layer network classification with graphical information.
method Theoretical and empirical study of graph convolutions in multi-layer networks.
result Graph convolutions expand the classification regime by a factor of 1 / E m d e g 4 1/\sqrt[4]{\mathbb{E}{
m deg}} 1/ 4 E m d e g . Adaptive graph convolution improves attributed graph clustering performance.
problem Joint modeling of graph structures and node attributes is challenging.
method Adaptive graph convolution that captures global cluster structure and selects appropriate order for different graphs.
result Empirical results show our method compares favorably with state-of-the-art methods.
BankGCN improves graph convolution networks by handling multi-channel signals with adaptive filter banks.
problem Handling multi-channel graph signals with limited architectures.
method BankGCN decomposes multi-channel signals into subspaces and uses adapted filters for each subspace.
result BankGCN achieves excellent performance in graph classification on benchmark datasets.
Graph Convolutional Gaussian Processes predict missing links.
problem Link prediction in large graphs.
method Simplified graph convolutions and variational inducing point method.
result Consistent improvements over existing models and competitive performance.
SWAG uses graph convolutions to recommend products.
problem Product recommendation using graph-structured data.
method Graph Convolutional Network (GCN) with weighted random walks and aggregations.
result Graph-based approach improves product recommendations.
The paper bridges spectral and spatial graph convolutions, improving model capacity and transferability.
problem Improving graph neural networks by bridging spectral and spatial design.
method Theoretical demonstration and general framework for spectral analysis, new spectral convolutions, and depthwise separable convolutions.
result General framework allows spectral analysis of ConvGNNs, showing their performance and limits, and proposing new spectral convolutions.
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 …
GCRNNs improve graph problem solving with fewer parameters.
problem Graph process problems like earthquake epicenter identification and weather prediction.
method GCRNNs use convolutional filter banks and time-gated variations of GCRNNs (Gated GCRNNs) to improve performance.
result GCRNNs significantly improve performance over GNNs and another graph recurrent architecture.
Graph Convolutional Networks improve performance on complex data.
problem Processing high-dimensional, graph-based data for automation.
method Enhanced existing Graph Convolutional Network models with four improvements.
result Significant performance improvements on four benchmark datasets.
Combines BERT and graph CNN for improved text classification.
problem Text classification problems
method Combining BERT embedding and graph convolutional neural network
result Graph CNN model performs better than classical models combined with BERT
Proposes SGCN for spatially structured data.
problem Lack of node neighbor ordering in GCNs.
method Uses spatial features to learn from graphs with spatial positions.
result Empirically outperforms state-of-the-art methods.
Improved GCNs for non-sparse graphs with low-rank filters.
problem Training and evaluation of GCNs on large non-sparse graphs is computationally expensive.
method Introduced low-rank filters and a reduced-order GCN architecture.
result Significant runtime acceleration and improved accuracy achieved.
Study explains Graph Convolutional Networks decisions.
problem Difficulty in understanding Graph Network decisions.
method Gradient-based and decomposition-based techniques.
result Sets groundwork for future explainability development.
PAN improves graph neural networks using path integrals.
problem Efficiency and performance of graph neural networks.
method PAN uses path integrals to generalize graph Laplacian, incorporating all paths between nodes.
result PAN achieves state-of-the-art performance on benchmark tasks.
New method uses CNNs to estimate graph means.
problem Estimating the mean of graph-valued data.
method Convolutional Neural Networks (CNNs) for graph morphology learning.
result CNNs reliably recover the sample Frechet mean.
Enhances GCNs to resist graph attacks.
problem Vulnerability of GCNs to topological attacks.
method Introduces a new robust convolution operator and training paradigm.
result Improves adversarial robustness and performance.
A new linear GCN model improves recommendation performance for large graphs.
problem Training difficulties and over-smoothing in GCN-based CF models.
method Proposes a linear residual graph convolutional network (LRGCCF) to address training difficulties and over-smoothing issues.
result The proposed model yields better efficiency and effectiveness on real datasets.
Scattering GCN improves graph neural networks by filtering oversmoothing.
problem Oversmoothing in GCNs limits their ability to distinguish graph nodes.
method Augmenting GCNs with geometric scattering transforms and residual convolutions.
result Scattering GCN outperforms GAT in semi-supervised node classification.
A distributed algorithm for training graph convolutional networks.
problem Training graph convolutional networks with sparse network topology and distributed agents.
method Formulate inference and optimization in a distributed scenario, propose a gradient descent procedure, and design communication topology.
result Convergence to stationary solutions of the GCN training problem under mild conditions.
LanczosNet uses Lanczos algorithm for efficient graph convolution.
problem Efficiently capturing multi-scale information in graph data.
method Lanczos algorithm for low-rank graph Laplacian approximation, learnable spectral filters.
result LanczosNet achieves state-of-the-art performance on citation networks and QM8.
DEMO-Net improves graph neural networks by focusing on node degree.
problem Limited analysis of graph convolution properties and lack of degree-specific graph structure.
method Proposes DEMO-Net, a degree-specific graph neural network that recursively identifies 1-hop neighborhood structures and uses multi-task learning for node representation learning.
result Demonstrates effectiveness and efficiency of DEMO-Net on node and graph classification benchmarks.
New hypergraph operators improve graph neural networks for higher-order relationships.
problem Learning deep embeddings on high-order graph-structured data.
method Introducing hypergraph convolution and hypergraph attention operators.
result Extensive experimental results show the effectiveness of hypergraph operators.
Proposes dynamic graph and node feature learning in GCNNs for better adaptability.
problem Fixed graphs for all GCNN layers limit adaptability to node feature structures.
method Dynamic graph and node feature learning using Mahalanobis distance metric.
result Superior performance in point clouds and citation networks.