Graph-CNN for 3D point cloud classification tackles non-regular graph topology.
problem Classifying 3D point cloud data with non-regular graph topology.
method Developed PointGCN combining localized graph convolutions and graph downsampling.
result Achieves competitive performance on 3D object classification benchmark ModelNet.
GWNN uses graph wavelets for efficient graph CNNs.
problem Spectral graph CNNs' high computational cost and lack of interpretability.
method Graph wavelet transform for efficient graph convolution.
result GWNN significantly outperforms spectral graph CNNs.
Transform classical network structures to graph CNN for better graph recognition.
problem Transforming classical network structures to graph CNN for better graph recognition.
method Review and introduce ResNet, Inception, and DenseNet into graph CNN, constructing G_ResNet, G_Inception, G_DenseNet.
result Demonstrated how different network structures work on graph CNN in the graph recognition task.
Graph CNNs adapt to varying graph structures for better performance.
problem Fixed graph structures limit the performance of Graph CNNs on real data.
method Adaptive graph learning and distance metric learning for efficient graph construction.
result Adaptive Graph CNNs improve convergence speed and predictive accuracy on various graph datasets.
Paper revisits graph-CNNs using Laplace-Beltrami spectral filters and polynomials.
problem Improving spectral graph convolutional neural networks (graph-CNNs).
method Developed Laplace-Beltrami CNN (LB-CNN) by replacing graph Laplacian with LB operator and approximating spectral filters using Chebyshev, Laguerre, and Hermite polynomials.
result Classification accuracy of LB-CNN is not dependent on the type of polynomials or operators.
A grid layout method for graph classification using CNNs.
problem How to project graphs onto grids for CNNs to work effectively.
method Proposes a novel graph-preserving grid layout (GPGL) using integer programming to minimize topological loss, and solves it approximately with a regularized Kamada-Kawai algorithm.
result Demonstrates the success of the method for graph classification using multi-scale maxout CNNs.
DGCNN improves graph CNNs by handling irregular graphs.
problem Handling structural information loss and redundancy in graph CNNs.
method Proposes DGCNN using DGCL with mixed Gaussian model to handle irregular graphs.
result DGCNN outperforms state-of-the-art methods in graph classification and retrieval.
CNNs adapted for graphs match image CNNs without prior knowledge.
problem Matching CNN performance on graph-structured data without prior knowledge.
method Strided convolutions and data augmentation on graphs.
result Significant accuracy improvement on fMRI data.
New graph CNN layers improve accuracy on graph datasets.
problem Graph data relations are better represented as graphs, not grids.
method Proposed new graph CNN layers for vertex and edge features.
result Improved classification accuracy on graph datasets.
Ego-CNN detects critical structures in graphs efficiently.
problem Lack of precise detection of critical structures in existing graph embedding models.
method Ego-CNN uses ego-convolutions at each layer and stacks them in an ego-centric way.
result Ego-CNN achieves comparable task performance to state-of-the-art models and can incorporate scale-free priors.
Paper simplifies CNNs for irregular data using MIMO graph filters.
problem Challenges in applying CNNs to irregularly structured data.
method Introduces MIMO graph filters to CNNs, simplifying architectures.
result Proposed architectures reduce model complexity and computational cost.
TAGCN improves graph CNN performance without approximation.
problem Performance loss in spectral graph convolutional neural networks.
method Topology adaptive graph convolutional network (TAGCN) with adaptive filters.
result TAGCN outperforms existing spectral CNNs on various datasets.
Combines CNN and LSTM for spatio-temporal graph networks.
problem Improving spatio-temporal feature extraction.
method Proposes a new architecture combining CNN and LSTM temporal blocks.
result Empirical comparison shows our model outperforms existing models.
Graph-based CNN for spherical data with equivariance.
problem Efficiently learning from non-uniformly distributed spherical data.
method Discretized sphere as graph, graph convolutions, equivariance using Defferrard's graph neural network.
result Good performance on rotation-invariant learning problems.
GNNs generalize CNNs for graph data, showing equivariance and stability.
problem Processing signals on graphs.
method Graph convolutional filters, nonlinearities, stacked layers.
result GNNs converge to graphon neural networks under graph convergence.
Paper proposes a robust deep graph-based classifier for noisy labels.
problem Difficulty in feature learning with noisy training labels.
method Convolutional neural networks with graph Laplacian regularization (GLR).
result Proposed method outperforms state-of-the-art classifiers on noisy datasets.
Proposes a new CNN for meshes that can handle orientation.
problem Isotropic kernels in graph convolutions are insensitive to mesh geometry.
method Introduces gauge equivariant kernels and geometric message passing.
result Significantly improved expressivity over conventional GCNs.
DFNets uses feedback-looped filters for better graph CNN performance.
problem Improving CNN performance on graph structured data.
method DFNets incorporates feedback-looped spectral graph filters.
result DFNets outperforms state-of-the-art methods in document and entity classification tasks.
GCAPS-CNN improves GCNNs for graph classification.
problem Challenges in graph classification by current GCNN models.
method Integrates capsule idea into GCNNs for graph classification.
result Significantly outperforms state-of-the-art methods on benchmark datasets.
New method embeds entire graphs without supervision.
problem Representing entire graphs without supervision.
method Design anonymous walks and learn graph representations.
result Improved classification accuracy of CNN algorithms.
Graph-augmented CNN predicts drug interactions with high accuracy.
problem Predicting drug-drug interactions (DDIs) with high accuracy.
method Combining graph CNN with an attentive pooling network to extract structural relations between drug pairs.
result Desirable performance with ROC 0.988, F1-score 0.956, and AUPR 0.986.
In this work, we are interested in generalizing convolutional neural networks (CNNs) from low-dimensional regular grids, where image, video and speech are represented, to high-dimensional irregular domains, such as social networks, brain connectomes or words' embedding, represented by graphs. We present a formulation o…
A CNN model learns complex relationships in knowledge graphs.
problem Exploring complex relationships between entities and relationships in knowledge graphs.
method A Convolutional Neural Network (CNN) is used to learn entity and relationship representations in knowledge graphs.
result The proposed model outperforms state-of-the-art models on exploring unseen relationships.
LGCL uses learnable filters to apply CNNs on graphs.
problem Applying CNNs to generic graphs like networks.
method Learnable graph convolutional layer (LGCL) and sub-graph training.
result LGCL achieves better performance on various graph datasets.
A CNN on semi-regular meshes classifies brain diseases from MRI scans.
problem Classifying brain diseases from MRI scans.
method Developed a vertex-based graph CNN for semi-regular triangulated meshes.
result Vertex-based graph CNN outperformed spectral graph CNN in classifying MCI and AD.
GCNN research tackles graph data topology and prediction.
problem Graphs' irregularity and complexity make traditional CNN methods unsuitable.
method Review and categorization of GCNN techniques.
result TAGCN approach shows promise for improving graph data prediction.
Two graph neural network architectures improve CNN performance for graph signals.
problem Improving CNN performance for graph signals.
method Introducing two graph neural network architectures: selection GNN and aggregation GNN.
result Multinode aggregation GNNs consistently perform best in source localization and authorship attribution tasks.
Dual-Primal Graph CNN learns vertex and edge features on graphs.
problem Learning features on non-Euclidean structured data like graphs.
method Alternates graph convolutional operations on graph and its dual.
result State-of-the-art results on various graph benchmarks.
Proposes SimPool for graph pooling using structural similarity features.
problem Challenges in graph pooling due to lack of spatial locality.
method Integrates structural similarity features with a revised pooling layer to propose SimPool.
result SimPool produces node cluster assignments resembling CNN's locality preserving pooling.
DeepSphere improves spherical CNNs by balancing efficiency and rotation equivariance.
problem Designing efficient and rotation-equivariant convolutional layers for spherical data.
method Graph-based approach to represent spherical data, focusing on the number of vertices and neighbors.
result DeepSphere achieves state-of-the-art performance and demonstrates efficiency and flexibility.
Graph CNN method improves classification of irregular spatial data like building patterns.
problem Challenges in analyzing irregular spatial data with machine learning.
method Graph Fourier transform and convolution theorem to convert irregular spatial data into a learnable format.
result Significantly improved classification of building patterns compared to other methods.
Generalised SCNNs improve model prediction for non-lattice time series data.
problem Improving CNNs for non-regular graph topologies in time series data.
method Framework for graph-structured CNNs using adjacency matrices and scalable convolutional masks.
result Improvement in model prediction when graph structure is included.
PETNet improves AD diagnosis using graph-based CNN on PET images.
problem Early diagnosis of Alzheimer's Disease using PET imaging.
method PETNet, a graph-based CNN architecture for 3D PET image analysis.
result PETNet shows improved performance over deep learning and other methods on ADNI dataset.
Dual CNN for predicting links in graphs of graphs.
problem Link prediction in graphs of graphs.
method Dual Convolutional Neural Network (CNN) for combining external and internal graph structures.
result Effective link prediction on chemical network datasets.
MDGCN improves hyperspectral image classification by dynamically updating graphs.
problem Traditional CNNs struggle with irregular image regions and class boundaries.
method MDGCN uses dynamic graph convolution on hyperspectral images, adapting to local regions.
result MDGCN outperforms state-of-the-art methods on benchmark datasets.
Two KG-based methods explain transfer learning in CNN and ZSL.
problem Uninterpretable transfer learning for non-ML experts.
method Knowledge Graph-based explanation for transferability and model justification.
result Rich, human-understandable explanations for transfer learning.
DeepMap learns deep graph representations via CNNs, improving graph classification performance.
problem Quantifying graph similarities for tasks like classification.
method Proposes DeepMap framework extending CNNs to arbitrary graphs, learning dense low-dimensional vectors.
result DeepMap achieves state-of-the-art performance on graph classification benchmarks.
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.
This paper introduces a generalization of Convolutional Neural Networks (CNNs) from low-dimensional grid data, such as images, to graph-structured data. We propose a novel spatial convolution utilizing a random walk to uncover the relations within the input, analogous to the way the standard convolution uses the spatia…
UAG defends GNNs against adversarial attacks by quantifying and explaining uncertainties.
problem Lack of uncertainty quantification in GNNs makes them vulnerable to adversarial attacks.
method UAG uses Bayesian Uncertainty Technique (BUT) and Uncertainty-aware Attention Technique (UAT).
result UAG outperforms state-of-the-art solutions in defending adversarial attacks on GNNs.
Proposes a novel framework for multi-label text classification.
problem Lack of coherent consideration of non-consecutive and long-distance semantics and hierarchical relations among labels.
method Hierarchical taxonomy-aware and attentional graph capsule recurrent CNNs framework.
result Significantly improves multi-label text classification performance.
New CNNs for set functions using powerset shifts.
problem Classifying data indexed by the powerset of a finite set.
method Developed a novel class of CNNs with shift-equivariant convolutions.
result Demonstrated potential of powerset CNNs on synthetic and real-world datasets.
OCmst detects anomalies using CNN features and MSTs.
problem Novelty detection in data with no outliers.
method Uses CNN for feature extraction and MSTs for graph-based modeling.
result Achieved state-of-the-art results on CIFAR10 dataset.
Using predictive models to identify patterns that can act as biomarkers for different neuropathoglogical conditions is becoming highly prevalent. In this paper, we consider the problem of Autism Spectrum Disorder (ASD) classification where previous work has shown that it can be beneficial to incorporate a wide variety …
Unified geometric scattering model for measure spaces.
problem Improving CNNs for non-Euclidean data.
method Unified geometric scattering model for measure spaces.
result Unified model includes previous work and applies to more general settings.
GSimCNN predicts graph similarity using CNNs, outperforming existing methods.
problem Challenging pairwise graph similarity computation due to NP-hardness.
method Graph Edit Distance (GED) as core metric, GSimCNN (Convolutional Neural Networks).
result State-of-the-art performance on graph similarity search.
New network learns image features inductively for disease classification.
problem Pre-processing image features limits network optimization.
method Inductive end-to-end learning with CNN and graph filters trained jointly.
result Significantly improved classification scores and higher stability.
New protocol benchmarks deep learning methods' data efficiency.
problem Measuring data efficiency of deep learning methods.
method Proposed experimental protocol to benchmark CNNs and HiGSFA.
result HiGSFA outperforms CNNs on smaller datasets.