arXiv research

Paper models graph edge dependencies using latent variables for community detection.

HGT models heterogeneous graphs with dedicated node and edge representations.

Graph neural networks improve with edge similarity constraints in RNA structure analysis.

FoSR adds edges to graphs to prevent oversquashing and oversmoothing in GNNs.

Traffic forecasting is of great importance to transportation management and public safety, and very challenging due to the complicated spatial-temporal dependency and essential uncertainty brought about by the road network and traffic conditions. Latest studies mainly focus on modeling the spatial dependency by utilizi…

We show that if X is a minimal length carrier graph in a hyperbolic 3-manifold, M, then if X contains a sufficiently short edge, it must contain a short circuit, as well. The meaning of "short" depends only on the rank of the fundamental group of M. We also expand the class of manifolds which are known to have minimal …

In this paper, we present a novel way to summarize the structure of large graphs, based on non-parametric estimation of edge density in directed multigraphs. Following coclustering approach, we use a clustering of the vertices, with a piecewise constant estimation of the density of the edges across the clusters, and ad…

The Mutual Information (MI) is an often used measure of dependency between two random variables utilized in information theory, statistics and machine learning. Recently several MI estimators have been proposed that can achieve parametric MSE convergence rate. However, most of the previously proposed estimators have th…

We propose a method for non-projective dependency parsing by incrementally predicting a set of edges. Since the edges do not have a pre-specified order, we propose a set-based learning method. Our method blends graph, transition, and easy-first parsing, including a prior state of the parser as a special case. The propo…

This paper tackles graph translation challenges by predicting both node and edge attributes simultaneously.

The paper controls false discovery rate in link prediction using conformal inference.

Paper explores exact recovery of communities in weighted graphs using Gaussian and exponential distributions.

Graph matching in noisy environments with Markovian errors.

Hypergraphs are used in machine learning to model higher-order relationships in data. While spectral methods for graphs are well-established, spectral theory for hypergraphs remains an active area of research. In this paper, we use random walks to develop a spectral theory for hypergraphs with edge-dependent vertex wei…

GTEA learns node representations in temporal interaction graphs.

New model captures time series dependence across and within blocks.

Study reveals limits of detecting local geometry in random graphs.

This work analyzes the stability of graph filters under large perturbations.

New method controls false edge detections in Gaussian graphical models.

We consider the task of causal structure learning over measurement dependence inducing latent (MeDIL) causal models. We show that this task can be framed in terms of the graph theoretic problem of finding edge clique covers,resulting in an algorithm for returning minimal MeDIL causal models (minMCMs). This algorithm is…

Constructs Lie algebras from labeled directed graphs and identifies properties of these algebras.

New research finds six bipartite intrinsically knotted graphs with 23 edges.

Edge augmentation connects disconnected graphs by elevating eigenvalues.

Graph kernels for metric graphs using tropical algebra.

Study on planar graph braid groups' second homology.

Johnson, Kidwell, and Michael showed that intrinsically knotted graphs have at least 21 edges. Also it is known that K7 and the thirteen graphs obtained from K7 by rY moves are intrinsically knotted graphs with 21 edges. We prove that these 14 graphs are the only intrinsically knotted graphs with 21 edges.

CoMGNN models heterogeneous graphs with evolving nodes and edges.

Stable topological summary captures evolving dependency structure in dynamic Bayesian networks.

The maximum number of maximum cliques in a graph is determined for graphs with at least 15 vertices.

Framework for universal graph function approximators outperforms existing methods.

Every infinitely edge-connected graph has a minor of Farey graph or $T_{\aleph_0}\ast t$.

Edge features contain important information about graphs. However, current state-of-the-art neural network models designed for graph learning, e.g. graph convolutional networks (GCN) and graph attention networks (GAT), adequately utilize edge features, especially multi-dimensional edge features. In this paper, we build…

Two complete graphs are connected by adding some edges. The obtained graph is called the gluing graph. The more we add edges, the larger the Ricci curvature on it becomes. We calculate the Ricci curvature of each edge on the gluing graph and obtain the least number of edges that result in the gluing graph having positi…

We prove several results about chordal graphs and weighted chordal graphs by focusing on exposed edges. These are edges that are properly contained in a single maximal complete subgraph. This leads to a characterization of chordal graphs via deletions of a sequence of exposed edges from a complete graph. Most interesti…

This study examines how removing edges from complete graphs affects Ollivier Ricci curvature.

Proposes a novel approach using vector cross product to preserve directional edges in directed graphs.

A known failing of many popular random graph models is that the Aldous-Hoover Theorem guarantees these graphs are dense with probability one; that is, the number of edges grows quadratically with the number of nodes. This behavior is considered unrealistic in observed graphs. We define a notion of edge exchangeability …

New graph types help identify complex relationships.

This paper proposes a method to learn graph representations by partitioning edges into communities.

Conventional sequential learning methods such as Recurrent Neural Networks (RNNs) focus on interactions between consecutive inputs, i.e. first-order Markovian dependency. However, most of sequential data, as seen with videos, have complex temporal dependencies that imply variable-length semantic flows and their composi…

A maximally linkless graph is a graph that can be embedded in $\mathbb{R}^3$ without any links, but cannot be embedded in such a way if any other edge is added to the graph. Recently, a family of maximally linkless graphs was found with $m=3n-3$ edges. We improve upon this by demonstrating a new family of maximally lin…

Maximal knotless graphs have at least 74% of their vertices' edges.

Grid homology properties for MOY graphs studied.

A graph is 2-apex if it is planar after the deletion of at most two vertices. Such graphs are not intrinsically knotted, IK. We investigate the converse, does not IK imply 2-apex? We determine the simplest possible counterexample, a graph on nine vertices and 21 edges that is neither IK nor 2-apex. In the process, we s…

Study detects edge correlation between unlabeled random graphs.

We propose {graphical sure screening}, or GRASS, a very simple and computationally-efficient screening procedure for recovering the structure of a Gaussian graphical model in the high-dimensional setting. The GRASS estimate of the conditional dependence graph is obtained by thresholding the elements of the sample covar…

Bundling of graph edges (node-to-node connections) is a common technique to enhance visibility of overall trends in the edge structure of a large graph layout, and a large variety of bundling algorithms have been proposed. However, with strong bundling, it becomes hard to identify origins and destinations of individual…

ES-MLP combines Graph-MLP with edge splitting for node classification on both homophilic and heterophilic graphs.