Top Research Papers on Graph Theory

This book provides an extensive set of tools for applying fuzzy mathematics and graph theory to real-life problems. Balancing the basics and latest developments in fuzzy graph theory, this book starts with existing fundamental theories such as connectivity, isomorphism, products of fuzzy graphs, and different types of paths and arcs in fuzzy graphs to focus on advanced concepts such as planarity in fuzzy graphs, fuzzy competition graphs, fuzzy threshold graphs, fuzzy tolerance graphs, fuzzy trees, coloring in fuzzy graphs, bipolar fuzzy graphs, intuitionistic fuzzy graphs, m-polar fuzzy graphs...

The study of sampling signals on graphs with the goal of building an analog of sampling for standard signals in the time and spatial domains is reviewed, focusing on theory and potential applications.

Spectral clustering converts the data clustering problem to the graph cut problem. It is based on graph theory. Due to the reliable theoretical basis and good clustering performance, spectral clustering has been successfully applied in many fields. Although spectral clustering has many advantages, it faces the challenges of high time and space complexity when dealing with large scale complex data. Firstly, this paper introduces the basic concept of graph theory, reviews the properties of Laplacian matrix and the traditional graph cuts method. Then, it focuses on four aspects of the realization...

It is proved that GNNs achieve near-optimal performance in wireless networks with much fewer training samples than traditional neural architectures and proposed design guidelines are proposed, which includes graph modeling, neural architecture design, and theory-guided performance enhancement.

This article discusses the basic graph theory concepts and the various graph types, as well as the available data structures for storing and reading graphs, and describes several network properties.

This update describes new features and enhancements introduced over many new versions from 2015 to 2022 of Cytoscape.js, an open-source JavaScript-based graph library used to render interactive graphs in a web browser.

The current review illustrated changed global network organization of structural and functional brain connectomes in MDD compared to HC and were varied according to the onset age and medication status.

The mean phase coherence method, based on the “phase-locking value,” was the most frequently used functional estimation technique in the reviewed studies and the unweighted functional brain network has received substantially more attention in the literature than the weighted network.

Our analysis may provide new insights into developing biomarkers for depression detection based on brain networks.

A new model, known as Graph Transformer, is proposed that uses explicit relation encoding and allows direct communication between two distant nodes and provides a more efficient way for global graph structure modeling.

The role of graph convolutional filters in GNNs is discussed and it is shown that any architecture built with such filters has the fundamental properties of permutation equivariance and stability to changes in the topology.

This work proposes ROLAND, an effective graph representation learning framework for real-world dynamic graphs that can help researchers easily repurpose any static GNN to dynamic graphs and proposes a scalable and efficient training approach for dynamic GNNs via incremental training and meta-learning.

Experimental results show that AGE consistently outperforms state-of-the-art graph embedding methods considerably on node clustering and link prediction tasks, and the proposed Adaptive Graph Encoder employs an adaptive encoder that iteratively strengthens the filtered features for better node embeddings.

This paper systematically reviews graph-based analysis methods of Graph Signal Processing, Graph Neural Networks and graph topology inference, and their applications to biological data, and covers the Graph Fourier Transform and the graph filter developed in GSP.

This article proposes a graph-in-graph (GiG) model and a related GiG convolutional network (GiGCN) for HSI classification from a superpixel viewpoint and is the first to propose the GiG framework from the superpixel point and the GiGCN scheme for H SI classification.

This work makes the first attempt towards learning an optimal heterogeneous graph structure for HGNNs and proposes a novel framework HGSL, which jointly performs Heterogeneous Graph Structure Learning and GNN parameters learning for classification task.

This paper makes the first attempt to employ deep learning technique for attributed multi-view graph clustering, and proposes a novel task-guided One2Multi graph autoencoder clustering framework that can jointly optimize the cluster label assignments and embeddings suitable forgraph clustering.

This approach integrates the processing of missing features and graph learning within the same neural network architecture and demonstrates through extensive experiments that this approach significantly outperforms the imputation based methods in node classification and link prediction tasks.

A new way to implement multiscale extraction via constructing Haar-type graph framelets with desired properties of permutation equivariance, efficiency, and sparsity, for deep learning tasks on graphs is developed.

This study is aimed at providing a broad, complete as well as comprehensive overview of GNN-based technologies for solving four different KG tasks, including link prediction, knowledge graph alignment, knowledge graphs reasoning, and node classification.

A general framework Pro-GNN is proposed, which can jointly learn a structural graph and a robust graph neural network model from the perturbed graph guided by these properties, and achieves significantly better performance compared with the state-of-the-art defense methods, even when the graph is heavily perturbed.

We present the Open Graph Benchmark (OGB), a diverse set of challenging and realistic benchmark datasets to facilitate scalable, robust, and reproducible graph machine learning (ML) research. OGB datasets are large-scale, encompass multiple important graph ML tasks, and cover a diverse range of domains, ranging from social and information networks to biological networks, molecular graphs, source code ASTs, and knowledge graphs. For each dataset, we provide a unified evaluation protocol using meaningful application-specific data splits and evaluation metrics. In addition to building the dataset...

Self-supervised learning of graph neural networks (GNN) is in great need because of the widespread label scarcity issue in real-world graph/network data. Graph contrastive learning (GCL), by training GNNs to maximize the correspondence between the representations of the same graph in its different augmented forms, may yield robust and transferable GNNs even without using labels. However, GNNs trained by traditional GCL often risk capturing redundant graph features and thus may be brittle and provide sub-par performance in downstream tasks. Here, we propose a novel principle, termed adversarial...

Differentiable Graph Module is introduced, a learnable function predicting the edge probability in the graph relevant for the task, that can be combined with convolutional graph neural network layers and trained in an end-to-end fashion and achieves state-of-the-art results.

Tracking the historical events that lead to the interweaving of data and knowledge.

This book provides a comprehensive and accessible introduction to knowledge graphs, which have recently garnered notable attention from both industry and academia. Knowledge graphs are founded on the

This article provides a comprehensive introduction to knowledge graphs, which have recently garnered significant attention from both industry and academia in scenarios that require exploiting diverse, dynamic, large-scale collections of data.

This book describes methods and tools that empower information providers to build and maintain knowledge graphs. The approaches presented cover the entire life-cycle from knowledge graph construction and implementation to validation, error correction and further enrichments.

This book provides a comprehensive and accessible introduction to knowledge
\ngraphs, which have recently garnered notable attention from both industry and
\nacademia. Knowledge graphs are founded on the principle of applying a graph-based
\nabstraction to data, and are now broadly deployed in scenarios that require integrating
\nand extracting value from multiple, diverse sources of data at large scale.
\nThe book is divided into ten chapters. The rst chapter provides a general introduction
\nto the area, de nes the concept of a “knowledge graph”, and provides
\na ...

Pangenome graphs stand to become a ubiquitous tool in genomics, and it is unclear whether they will replace linear reference genomes, but their ability to harmoniously relate multiple sequence and coordinate systems will make them useful irrespective of which pangenomic models become most common in the future.

This paper proposes a novel recommendation framework, named Contextualized Graph Attention Network (CGAT), which can explicitly exploit both local and non-local graph context information of an entity in KG, and compares it with state-of-the-art KG-based recommendation methods on real datasets.

The proposed indicator can effectively reduce the heterophily degree of the graph, thus boosting the overall GAD performance and showing that prediction errors are less likely to affect the identification process.

This survey covers a new rapidly growing family of automated graph feature engineering techniques, presents an in-depth analysis of models based on network types, and overviews a wide range of applications to machine learning problems on graphs.

This paper introduces a new graph neural network, namely GRAPH-BERT (Graph based BERT), solely based on the attention mechanism without any graph convolution or aggregation operators, which can out-perform the existing GNNs in both the learning effectiveness and efficiency.

This work seeks to extend previous imbalanced learning techniques for i.i.d data to the imbalanced node classification task to facilitate GNN classifiers, and chooses to adopt synthetic minority over-sampling algorithms, as they are found to be the most effective and stable.

The long short-term memory (LSTM) is utilized to update the weight parameters of GCN for capturing the global structure information across all time steps of dynamic graphs, and a new Dice similarity is proposed to overcome the problem that the influence of directed neighbors is unnoticeable.

It is argued that the road alignment (both road centerline and junctions) should be firstly guaranteed, then the connectivity will make sense, because the connectivity without precise alignment is of non-sense.

This work proposes a new model named Metapath Aggregated Graph Neural Network (MAGNN), which achieves more accurate prediction results than state-of-the-art baselines and employs three major components, i.e., the node content transformation to encapsulate input node attributes, the intra-metapath aggregation to incorporate intermediate semantic nodes, and the inter-metal aggregation to combine messages from multiple metapaths.

A novel self-supervised representation learning method via Sub-graph Contrast, namely Subg-Con, is proposed by utilizing the strong correlation between central nodes and their sampled subgraphs to capture regional structure information and has prominent performance advantages in weaker supervision requirements, model learning scalability, and parallelization.

This paper is the first to use the learning-based video motion magnification method to extract the features of shape representations from the intermediate layer while magnifying MEs, and is also thefirst to use deep learning to automatically train the graph representation for MEs.