arXiv research

This thesis explores GNNs, categorizing them into local and global approaches.

Graph products inherit Morse local-to-global property from their components.

Graph kernels are widely used for measuring the similarity between graphs. Many existing graph kernels, which focus on local patterns within graphs rather than their global properties, suffer from significant structure information loss when representing graphs. Some recent global graph kernels, which utilizes the align…

Model forecasts global stock market volatility using dynamic graphs and all trading days.

Global graph structure improves GNN performance.

Graph Signal Processing improves stock market volatility forecasting.

Graph neural networks (GNNs) have shown great power in learning on attributed graphs. However, it is still a challenge for GNNs to utilize information faraway from the source node. Moreover, general GNNs require graph attributes as input, so they cannot be appled to plain graphs. In the paper, we propose new models nam…

COMRECGC finds common recourse for global counterfactual explanations in GNNs.

The monitoring of large dynamic networks is a major chal- lenge for a wide range of application. The complexity stems from properties of the underlying graphs, in which slight local changes can lead to sizable variations of global prop- erties, e.g., under certain conditions, a single link cut that may be overlooked du…

Poisson learning doesn't solve graph semi-supervised learning issues.

Deep learning predicts drug prescriptions across global health records.

We introduce and study the conical curvature-dimension condition, $CCD(K,N)$, for graphs. We show that $CCD(K,N)$ provides necessary and sufficient conditions for the underlying graph to satisfy a sharp global Poincaré inequality which in turn translates to a sharp lower bound for the first eigenvalues of these graphs.…

Most state-of-the-art graph kernels only take local graph properties into account, i.e., the kernel is computed with regard to properties of the neighborhood of vertices or other small substructures. On the other hand, kernels that do take global graph propertiesinto account may not scale well to large graph databases.…

In this paper, we unify the Markov theory of a variety of different types of graphs used in graphical Markov models by introducing the class of loopless mixed graphs, and show that all independence models induced by $m$-separation on such graphs are compositional graphoids. We focus in particular on the subclass of rib…

Continuing our previous work (arXiv:1509.07981v1), we derive another global gradient estimate for positive functions, particularly for positive solutions to the heat equation on finite or locally finite graphs. In general, the gradient estimate in the present paper is independent of our previous one. As applications, i…

We give a description of local and global moves on a class of locally planar trivalent graphs and we show that it contains $λ$-Scale calculus, therefore in particular untyped lambda calculus. Surprisingly, the beta reduction rule comes from a local "sewing" transformation of trivalent locally planar graphs.

Paper proposes G-CRD to improve GNNs by preserving global graph topology.

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…

We present an equivalent criterion for the global existence of Euler's multiplier for an integrable one-form taking into account the corresponding codim-1-foliation. In particular, the impact of inseparable leaves is considered. Here, we suppose that the foliation can be reduced to a graph; we also discuss obstructions…

Quantum computing improves graph neural network aggregation.

Graph cuts find global optima for Potts models in slight perturbations.

Paper presents a novel approach for global feature aggregation in Graph Neural Networks.

To take full advantage of fast-growing unlabeled networked data, this paper introduces a novel self-supervised strategy for graph representation learning by exploiting natural supervision provided by the data itself. Inspired by human social behavior, we assume that the global context of each node is composed of all no…

Study shows how discrete graph curvature relates to manifold curvature.

We propose a novel node embedding of directed graphs to statistical manifolds, which is based on a global minimization of pairwise relative entropy and graph geodesics in a non-linear way. Each node is encoded with a probability density function over a measurable space. Furthermore, we analyze the connection between th…

Study neural architectures on learned latent graphs using Schrödinger dynamics.

Rigidity is the property of a structure that does not flex. It is well studied in discrete geometry and mechanics, and has applications in material science, engineering and biological sciences. A bar-and-joint framework is a pair $(G,p)$ of graph $G$ together with a map $p$ of the vertices of $G$ into the Euclidean pla…

This paper improves GNNs' generalization by adding a Low-Rank Global Attention module.

Graph embedding method captures both local and global network structure.

Graph neural networks help assess how global changes affect plant-pollinator networks.

Study detects anomalies in financial markets using GNN and nonextensive entropy.

Structure inference is an important task for network data processing and analysis in data science. In recent years, quite a few approaches have been developed to learn the graph structure underlying a set of observations captured in a data space. Although real-world data is often acquired in settings where relationship…

We investigate 3-dimensional globally hyperbolic AdS manifolds containing "particles", i.e., cone singularities of angles less than $2π$ along a time-like graph $Γ$. To each such space we associate a graph and a finite family of pairs of hyperbolic surfaces with cone singularities. We show that this data is sufficient …

We propose a number of techniques for obtaining a global ranking from data that may be incomplete and imbalanced -- characteristics almost universal to modern datasets coming from e-commerce and internet applications. We are primarily interested in score or rating-based cardinal data. From raw ranking data, we construc…

A new method detects financial fraud using graph transformers.

CTGCN learns dynamic graph embeddings preserving both local and global graph structure.

GNNRank uses neural networks to learn global rankings from competition match data.

A new framework for knowledge graph embedding using sheaves.

We describe two locally finite graphs naturally associated to each knot type K, called Reidemeister graphs. We determine several local and global properties of these graphs and prove that in one case the graph-isomorphism type is a complete knot invariant up to mirroring. Lastly, we introduce another object, relating t…

We study two global structural properties of a graph $Γ$, denoted AS and CFS, which arise in a natural way from geometric group theory. We study these properties in the Erdös--Rényi random graph model G(n,p), proving a sharp threshold for a random graph to have the AS property asymptotically almost surely, and giving f…

Semi-supervised learning on graph structured data has received significant attention with the recent introduction of Graph Convolution Networks (GCN). While traditional methods have focused on optimizing a loss augmented with Laplacian regularization framework, GCNs perform an implicit Laplacian type regularization to …

MaGNet integrates local and global graph information for interpretable results.

The paper investigates how Global Self-attention improves GCNs.

New research shows hyperbolic embeddings are useful for global consistency tasks in graphs.

The paper solves curvature problems on graphs using a special flow.

Develops a novel global pooling framework using optimal transport.

Graphs can be used to represent and reason about systems and a variety of metrics have been devised to quantify their global characteristics. However, little is currently known about how to construct a graph or improve an existing one given a target objective. In this work, we formulate the construction of a graph as a…

Proposes MGMN for end-to-end graph similarity learning.