Holomorphic analogs of Feynman integrals are shown to be finite.
problem Finite evaluation of holomorphic Feynman integrals.
method Compactification of graph moduli space with metrics.
result Holomorphic Feynman integrals are ultraviolet finite.
Paper rigorously defines Feynman graph integrals on Kähler manifolds.
problem Establishing convergence of Feynman graph integrals on Kähler manifolds.
method Using Getzler's rescaling technique, graph integrands are extended to forms with divisorial-type singularities in the compactification of configuration spaces.
result Feynman graph integrals are rigorously defined as Cauchy principal value integrals.
Paper addresses hidden faces in configuration space integrals for embeddings.
problem Understanding hidden faces in configuration space integrals for long embeddings.
method Modified configuration space integrals incorporating acyclic bar complex of a dg algebra.
result Cochain map from new graph complex to de Rham complex of embeddings modulo immersions.
PAN uses path integrals for graph convolution and pooling, improving GNN performance.
problem Designing efficient graph convolution and pooling for graph neural networks.
method Path integral based graph convolution and pooling using learnable weights for path lengths.
result PAN achieves state-of-the-art performance on various graph classification/regression tasks.
In this work we study the geodesic flow on nilmanifolds associated to graphs. We are interested in the construction of first integrals to show complete integrability on some compact quotients. Also examples of integrable geodesic flows and of non-integrable ones are shown.
Convolution operations designed for graph-structured data usually utilize the graph Laplacian, which can be seen as message passing between the adjacent neighbors through a generic random walk. In this paper, we propose PAN, a new graph convolution framework that involves every path linking the message sender and recei…
We introduce a "minimal" Kontsevich integral that generates the original Kontsevich integral while at the same time producing ribbons whose boundaries are the braids on which the minimal Kontsevich integral is evaluated. We generalize the definition of the Kontsevich integral to that of graphs in R^3 and study the beha…
A new method integrates forms on Riemann surfaces, leading to modular forms.
problem Integrating differential forms with poles on Riemann surfaces.
method Simple procedure to integrate differential forms with arbitrary holomorphic poles, establishing an analytic theory for integrals over configuration spaces.
result Regularized graph integrals on elliptic curves are almost-holomorphic modular forms.
New curvature measure for graphs improves diameter and eigenvalue estimates.
problem Estimating properties of graphs using Ricci curvature.
method Introduced integral Ricci curvature Iκ0 for graphs. result Uniform estimates for diameter, number of vertices, and eigenvalue.
We construct an extension of the Kontsevich integral of knots to knotted trivalent graphs, which commutes with orientation switches, edge deletions, edge unzips, and connected sums. In 1997 Murakami and Ohtsuki [MO] first constructed such an extension, building on Drinfel'd's theory of associators. We construct a step …
Graph manifolds are manifolds that decompose along tori into pieces with a tame S1-structure. In this paper, we prove that the simplicial volume of graph manifolds (which is known to be zero) can be approximated by integral simplicial volumes of their finite coverings. This gives a uniform proof of the vanishing of …
Integrates singular subalgebroids using diffeological groupoids.
problem Integration of singular subalgebroids.
method Definition of integration via diffeological groupoids with specific properties.
result Holonomy groupoids correspond to singular subalgebroids with submersive property.
New theory defines invariants for framed 3-manifolds using trivalent graphs with self-loops.
problem Defining invariants for framed 3-manifolds with semi-simple Lie groups.
method Constructing graph complexes and cocycles, including self-loops, to define invariants.
result Higher-loop invariants can be defined by graph cocycles with or without self-loops.
MOTGNN integrates multi-omics data for disease classification with improved accuracy and interpretability.
problem Challenges in integrating multi-omics data due to high dimensionality, heterogeneity, and lack of reliable interaction networks.
method MOTGNN uses XGBoost for graph construction, modality-specific GNNs for representation learning, and a deep feedforward network for cross-omics integration.
result MOTGNN outperforms state-of-the-art baselines by 5-10% in accuracy, ROC-AUC, and F1-score across three real-world disease datasets.
DGRCL integrates dynamic and static graph relations for financial market prediction.
problem Capturing the evolving nature of stock markets while considering both temporal changes and static relational structures.
method Dynamic Graph Representation with Contrastive Learning (DGRCL) framework, including Embedding Enhancement (EE) and Contrastive Constrained Training (CCT) modules.
result DGRCL significantly outperforms state-of-the-art TGL baselines on NASDAQ and NYSE datasets.
Two graph homologies help compute embedding space.
problem Computing the rational homotopy group of long embeddings.
method Invented two graph homologies and constructed a map between them.
result A monomorphism from top hairy graph homology to top BCR graph homology.
This is a substantially revised version. The Kontsevich integral of a knot is a graph-valued invariant which (when graded by the Vassiliev degree of graphs) is characterized by a universal property; namely it is a universal Vassiliev invariant of knots. We introduce a second grading of the Kontsevich integral, the Eule…
Paper detects non-trivial cycles in embedding spaces using graph integrals.
problem Detecting non-trivial cycles in embedding spaces.
method Construct cycles from chord diagrams, use modified configuration space integrals, and pair arguments.
result Non-trivial cycles in embedding spaces are detected.
We define integral odd Khovanov homology of principally unimodular bipartite graph-links.
A new neural network layer integrates graph learning into classification tasks.
problem Lack of relational information in standard deep learning architectures for label predictions.
method Derives backpropagation equations for a differentiable graph learning layer.
result Smooth label transitions, improved generalization, and robustness to adversarial attacks.
We introduce and study so-called self-indexed graphs. These are (oriented) finite graphs endowed with a map from the set of edges to the set of vertices. Such graphs naturally arise from classical knot and link diagrams. In fact, the graphs resulting from link diagrams have an additional structure, an integral flow. We…
Assessing world-wide financial integration constitutes a recurrent challenge in macroeconometrics, often addressed by visual inspections searching for data patterns. Econophysics literature enables us to build complementary, data-driven measures of financial integration using graphs. The present contribution investigat…
We solve Euler equations on graph manifolds, classifying steady flows with Morse-Bott Bernoulli functions.
problem Classifying steady Euler flows with Morse-Bott Bernoulli functions.
method Constructing non-vanishing steady solutions using integrable systems and topology.
result Steady Euler flows with Morse-Bott Bernoulli functions exist only on graph three-manifolds.
Paper presents voxel graph operators for vector data models.
problem Efficient conversion and analysis of geometric models.
method Topological voxelization, graph construction, differential operator derivation.
result Discrete differential and integral operators from voxel complexes.
Graph Neural Networks (GNNs), which generalize deep neural networks to graph-structured data, have drawn considerable attention and achieved state-of-the-art performance in numerous graph related tasks. However, existing GNN models mainly focus on designing graph convolution operations. The graph pooling (or downsampli…
This study explores complex structures on Lie algebras from graph perspectives.
problem Existence and characterization of complex structures on 2-step nilpotent Lie algebras.
method Introducing adapted complex structures and analyzing integrability conditions.
result Characterization of graphs that admit abelian adapted complex structures and unique invariant subgraphs.
New graph representation learning network improves scalability and feature integration.
problem Scalability and feature integration in graph neural networks for large, dense graphs.
method Adaptive sampling of neighbours based on weighted multi-step transition probabilities.
result Comparable or better results on various graph benchmarks.
XIMP improves molecular property prediction by integrating multiple graph representations.
problem Graph neural networks struggle in data-scarce regimes and fail to surpass traditional methods.
method Cross-graph inter-message passing with multiple graph abstractions.
result XIMP outperforms state-of-the-art baselines across diverse molecular property tasks.
Paper proposes DMGD for integrating outlier and community detection in graph embedding.
problem Outlier nodes affect graph embedding of regular nodes, especially in networks with multiple communities.
method DMGD integrates outlier and community detection with node embedding using multiclass graph description.
result DMGD detects outliers relative to their communities and achieves better node embedding compared to state-of-the-arts.
We give a generalization of Fukaya's Morse homotopy theoretic approach for 2-loop Chern--Simons perturbation theory to 3-valent graphs with arbitrary number of loops at least 2. We construct a sequence of invariants of integral homology 3-spheres with values in a space of 3-valent graphs (Jacobi diagrams or Feynman dia…
This work proposes an unsupervised neural network framework for solving combinatorial optimization problems on graphs.
problem Challenges in neural networks solving combinatorial optimization problems without labeled instances.
method Inspired by Erdos' probabilistic method, a neural network parametrizes a probability distribution over sets, optimizing it to find low-cost integral solutions.
result The method provides valid solutions to the maximum clique problem and local graph clustering, achieving competitive results.
We define invariants for colored oriented spatial graphs by generalizing CM invariants, which were defined via non-integral highest weight representations of Uq(sl2). We apply the same method to define Yokota's invariants, and we call these invariants Yokota type invariants. Then we propose a volume conjecture of t…
Low-dimensional embeddings of knowledge graphs and behavior graphs have proved remarkably powerful in varieties of tasks, from predicting unobserved edges between entities to content recommendation. The two types of graphs can contain distinct and complementary information for the same entities/nodes. However, previous…
Graph database outperforms in filtering ESG stocks efficiently.
problem Efficiently filtering ESG stocks from large lists of equities.
method Compared SQL, No-SQL, and graph databases; used Python for database interactions; collected data from stock price and financial news.
result Graph database is more efficient for ESG stock filtering.
MaGNet integrates local and global graph information for interpretable results.
problem Lack of interpretability and inability to learn varying-order representations in GNNs.
method Model-agnostic Graph Neural Network (MaGNet) framework integrating estimation and interpretation models.
result MaGNet effectively integrates information of various orders and provides meaningful, interpretable results.
We consider complete asymptotically flat Riemannian manifolds that are the graphs of smooth functions over Rn. By recognizing the scalar curvature of such manifolds as a divergence, we express the ADM mass as an integral of the product of the scalar curvature and a nonnegative potential function, thus provin…
Novel method combines physics priors for energy-conserving dynamics.
problem Learning long-term dynamics of complex physical systems from noisy data.
method Variational Integrator Graph Networks integrating energy constraint, high-order symplectic integrators, and graph neural networks.
result Improves predictive performance across single and many-body problems.
Graph auto-encoder predicts unobserved node features from biological networks and omics data.
problem Integrating biological networks and continuous node features for better prediction.
method Graph neural networks and feature auto-encoders trained on feature reconstruction.
result Graph feature auto-encoder outperforms auto-encoders trained on graph reconstruction for predicting unobserved node features.
We introduce vine computational graphs for efficient ML integration of vine copulas.
problem Integrating vine copulas into modern machine learning pipelines.
method Developed vine computational graphs and algorithms for conditional sampling, scheduling, and structure construction.
result Gradient flow through vine copulas improves performance in machine learning models.
Improved graph clustering with modularity and coarsening for attributes and communities.
problem Inaccurate community detection and computational inefficiency in graph clustering.
method Integrates coarsening and modularity maximization, using a loss function with log-determinant, smoothness, and modularity components.
result Superior clustering outcomes, proven consistent under DC-SBM, and efficient algorithm integration with GNNs and VGAEs.
Paper classifies minimal graph transformations into new families of surfaces.
problem Classifying minimal graph transformations into new families of surfaces.
method Formulated and solved a coupled system of partial differential equations, reduced to solving an ordinary differential equation.
result Established rigorous equivalence to a modified problem for a harmonic function, yielding new families of minimal surfaces.
CopulaGNN integrates graph representational and correlational roles for better node-level predictions.
problem Graphs encode diverse roles in node-level prediction tasks, but GNNs struggle with correlational information.
method Copula theory to describe multivariate dependence, integrating representational and correlational graph information.
result CopulaGNN improves GNN performance on regression tasks by leveraging both types of graph information.
Minimal graphs grow slowly on curved spaces, proving constant solutions.
problem Characterizing minimal graphs with sublinear growth on manifolds.
method New technique to get gradient bounds by integral estimates, no further geometric assumptions.
result Entire solutions are constant when negative part grows like r/logr. In this note we prove that every two-dimensional entire Willmore graph in R3 with square integrable mean curvature is a plane.
The paper extends game theory using Hodge theory on graphs.
problem Generalizing Shapley's value allocation formula for cooperative games on graphs.
method Connecting stochastic path integrals to Hodge-theoretic Poisson's equations on graphs.
result The value allocation operator is the solution to Poisson's equation in combinatorial Hodge theory.
Study of mapping class groups on infinite graphs, focusing on their large-scale geometry.
problem Understanding the large-scale geometry of mapping class groups on infinite graphs.
method Using coarse geometry techniques, classify coarsely bounded groups and compute asymptotic dimension.
result Identify conditions for global and local coarsely bounded pure mapping class groups of infinite rank graphs.
Aims to integrate AI and modelling for patient health forecasting.
problem Personalized, precise treatment plans for patients.
method Graph neural network (GNNs) and generative adversarial network (GANs) for probabilistic simulations.
result Demonstrated integration of molecular data for predicting physiological state evolution.
Paper uses HGNN to predict stock types from relationships and temporal data.
problem Predicting stock types from complex market data.
method Integrates stock relationships and temporal data using HGNN.
result Effective prediction of stock types with HGNN model.