Voltage graph
View article
Adversarially Regularized Graph Autoencoder for Graph Embedding Open
Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction erro…
View article
Adaptive Graph Convolutional Neural Networks Open
Graph Convolutional Neural Networks (Graph CNNs) are generalizations of classical CNNs to handle graph data such as molecular data, point could and social networks. Current filters in graph CNNs are built for fixed and shared graph structu…
View article
Learning Laplacian Matrix in Smooth Graph Signal Representations Open
The construction of a meaningful graph plays a crucial role in the success of many graph-based representations and algorithms for handling structured data, especially in the emerging field of graph signal processing. However, a meaningful …
View article
Attributed Graph Clustering: A Deep Attentional Embedding Approach Open
Graph clustering is a fundamental task which discovers communities or groups in networks. Recent studies have mostly focused on developing deep learning approaches to learn a compact graph embedding, upon which classic clustering methods l…
View article
Graph Neural Networks with Convolutional ARMA Filters Open
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, c…
View article
A Generalization of Transformer Networks to Graphs Open
We propose a generalization of transformer neural network architecture for arbitrary graphs. The original transformer was designed for Natural Language Processing (NLP), which operates on fully connected graphs representing all connections…
View article
Graph Classification using Structural Attention Open
Graph classification is a problem with practical applications in many different domains. To solve this problem, one usually calculates certain graph statistics (i.e., graph features) that help discriminate between graphs of different class…
View article
Heterogeneous Graph Structure Learning for Graph Neural Networks Open
Heterogeneous Graph Neural Networks (HGNNs) have drawn increasing attention in recent years and achieved outstanding performance in many tasks. The success of the existing HGNNs relies on one fundamental assumption, i.e., the original hete…
View article
Autoregressive Moving Average Graph Filtering Open
One of the cornerstones of the field of signal processing on graphs are graph filters, direct analogues of classical filters, but intended for signals defined on graphs. This work brings forth new insights on the distributed graph filterin…
View article
Topology Adaptive Graph Convolutional Networks Open
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 (T…
View article
Stability Properties of Graph Neural Networks Open
Graph neural networks (GNNs) have emerged as a powerful tool for nonlinear processing of graph signals, exhibiting success in recommender systems, power outage prediction, and motion planning, among others. GNNs consists of a cascade of la…
View article
Gated Graph Recurrent Neural Networks Open
Graph processes exhibit a temporal structure determined by the sequence index and and a spatial structure determined by the graph support. To learn from graph processes, an information processing architecture must then be able to exploit b…
View article
A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications Open
Graph is an important data representation which appears in a wide diversity of real-world scenarios. Effective graph analytics provides users a deeper understanding of what is behind the data, and thus can benefit a lot of useful applicati…
View article
Composition-based Multi-Relational Graph Convolutional Networks Open
Graph Convolutional Networks (GCNs) have recently been shown to be quite successful in modeling graph-structured data. However, the primary focus has been on handling simple undirected graphs. Multi-relational graphs are a more general and…
View article
A Restricted Black-Box Adversarial Framework Towards Attacking Graph Embedding Models Open
With the great success of graph embedding model on both academic and industry area, the robustness of graph embedding against adversarial attack inevitably becomes a central problem in graph learning domain. Regardless of the fruitful prog…
View article
Single valued neutrosophic graphs: Degree, order and size Open
The single valued neutrosophic graph is a new version of graph theory presented recently as a generalization of fuzzy graph and intuitionistic fuzzy graph. The single valued neutrosophic graph (SVN-graph) is used when the relation between …
View article
Advances in Distributed Graph Filtering Open
Graph filters are one of the core tools in graph signal processing. A central aspect of them is their direct distributed implementation. However, the filtering performance is often traded with distributed communication and computational sa…
View article
Gaussian boson sampling for perfect matchings of arbitrary graphs Open
A famously hard graph problem with a broad range of applications is computing\nthe number of perfect matchings, that is the number of unique and complete\npairings of the vertices of a graph. We propose a method to estimate the number\nof …
View article
Reconstruction of Graph Signals Through Percolation from Seeding Nodes Open
New schemes to recover signals defined in the nodes of a graph are proposed.\nOur focus is on reconstructing bandlimited graph signals, which are signals\nthat admit a sparse representation in a frequency domain related to the\nstructure o…
View article
Filtering Random Graph Processes Over Random Time-Varying Graphs Open
Graph filters play a key role in processing the graph spectra of signals\nsupported on the vertices of a graph. However, despite their widespread use,\ngraph filters have been analyzed only in the deterministic setting, ignoring\nthe impac…
View article
Edge Contraction Pooling for Graph Neural Networks Open
Graph Neural Network (GNN) research has concentrated on improving convolutional layers, with little attention paid to developing graph pooling layers. Yet pooling layers can enable GNNs to reason over abstracted groups of nodes instead of …
View article
Theoretically Efficient Parallel Graph Algorithms Can Be Fast and Scalable Open
There has been significant recent interest in parallel graph processing due\nto the need to quickly analyze the large graphs available today. Many graph\ncodes have been designed for distributed memory or external memory. However,\ntoday e…
View article
Adaptive Graph Convolutional Neural Networks Open
Graph Convolutional Neural Networks (Graph CNNs) are generalizations of classical CNNs to handle graph data such as molecular data, point could and social networks. Current filters in graph CNNs are built for fixed and shared graph structu…
View article
Graph Transformer Networks: Learning meta-path graphs to improve GNNs Open
Graph Neural Networks (GNNs) have been widely applied to various fields due to their powerful representations of graph-structured data. Despite the success of GNNs, most existing GNNs are designed to learn node representations on the fixed…
View article
Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding Open
Distance-based knowledge graph embeddings have shown substantial improvement on the knowledge graph link prediction task, from TransE to the latest state-of-the-art RotatE. However, complex relations such as N-to-1, 1-to-N and N-to-N still…
View article
Pseudoinverse of the Laplacian and best spreader node in a network Open
Determining a set of "important" nodes in a network constitutes a basic endeavor in network science. Inspired by electrical flows in a resistor network, we propose the best conducting node j in a graph G as the minimizer of the diagonal el…
View article
Learning Graph-Level Representation for Drug Discovery Open
Predicating macroscopic influences of drugs on human body, like efficacy and toxicity, is a central problem of small-molecule based drug discovery. Molecules can be represented as an undirected graph, and we can utilize graph convolution n…
View article
Graph Wavelet Neural Network Open
We present graph wavelet neural network (GWNN), a novel graph convolutional neural network (CNN), leveraging graph wavelet transform to address the shortcomings of previous spectral graph CNN methods that depend on graph Fourier transform.…
View article
Learning-Based Efficient Graph Similarity Computation via Multi-Scale Convolutional Set Matching Open
Graph similarity computation is one of the core operations in many graph-based applications, such as graph similarity search, graph database analysis, graph clustering, etc. Since computing the exact distance/similarity between two graphs …
View article
Incremental Graph Computations Open
The incremental problem for a class Q of graph queries aims to compute, given a query Q 2 Q, graph G, output Q(G) and updates G to G as input, changes O to Q(G) such that Q(GG) = Q(G)O. It is called bounded if its cost can be expressed as …