Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

113226339452 · Jun 202019922001200920182026
48 results for local graph

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

problem Understanding the convergence of global GNNs and connecting local and global approaches.
method Categorization of GNNs into local and global, study of Invariant Graph Networks, connecting local and global approaches, and using local MPNN for graph coarsening.
result Established a connection between local and global GNN approaches.

The paper classifies dense conjugacy classes in mapping class groups of locally finite graphs.

problem Identifying which mapping class groups have dense conjugacy classes.
method Developed flux homomorphisms and combinatorial criteria for stability.
result A complete classification for self-similar locally finite graphs and a criterion for stability.

Develops graph uncertainty principles for signals, improving signal reconstruction and analysis.

problem Limits on the concentration of graph signals under dictionary transforms.
method Generalizes Lieb's methods to graph signals, incorporating local structure.
result Local uncertainty principles improve random sampling of graph signals.

Proposes methods for local clustering in attributed graphs.

problem Finding a single cluster concentrated on a specific region in a graph.
method Introduces Graph Unimodality (GU) and Attribute Unimodality (AU) measures, and LOCLU algorithm to optimize Compactness score.
result Local cluster detected by LOCLU concentrates on the region of interest and exhibits unimodal data distribution.

The paper investigates why GNNs struggle to generalize from small to large graphs.

problem Challenges in graph neural networks' ability to generalize across different graph sizes.
method Identified and studied the effect of local structure on size generalization; proposed a novel SSL task.
result GNNs can converge to non-generalizing solutions when there is a discrepancy in local structure.

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

problem Generalizing local-to-global property to graph products of infinite groups.
method Generalizing maximization procedure for relatively hierarchically hyperbolic groups and showing stable embeddings.
result Graph products of infinite Morse local-to-global groups have the Morse local-to-global property.

Spatial graph representation improves GNN performance.

problem GNNs struggle with distinguishing similar local structures in different graph locations.
method Proposes a spatial graph representation method to distinguish local structures and simplify graph downsampling.
result Proposed graph pooling method achieves competitive results.

New methods identify local clusters in graphs with few labels.

problem Identifying specific substructures in large graphs without additional structural information.
method Random sampling, diffusion, and overlap analysis of local clusters.
result Proves the correctness of the proposed methods and achieves state-of-the-art results.

It is shown that for any locally knotted edge of a 3-connected graph in S3S^3, there is a ball that contains all of the local knots of that edge and is unique up to an isotopy setwise fixing the graph. This result is applied to the study of topological symmetry groups of graphs embedded in S3S^3.

2010-10-04abs ↗pdf ↗

New research limits what GNNs can compute and generalizes their performance.

problem Limits of GNNs in computing graph properties and generalization bounds.
method Novel graph-theoretic formalism and data-dependent generalization bounds.
result Proves GNNs can't compute certain graph properties and provides tighter generalization bounds.

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.

Proposes robust local scaling using conditional quantiles of graph similarities.

problem Spectral analysis sensitivity to parameters and noise.
method Auto-encoding neural network for inferring conditional quantiles of similarity functions.
result Proposed approach outperforms existing methods in spectral clustering and single-example label propagation.

Sharp bounds on diameter and eigenvalues for amply regular graphs.

problem Finding bounds for amply regular graphs' diameter and eigenvalues.
method New ideas relating discrete Ricci curvature to local matching properties, including a novel construction of a regular bipartite graph.
result Sharp diameter and eigenvalue bounds for amply regular graphs.

The study proves sampling-based GNNs can approximate training on full graphs with small subgraphs.

problem Training Graph Neural Networks (GNNs) on large graphs is computationally expensive.
method Theoretical framework using graph local limits to prove approximation of GNN training on small samples.
result Parameters learned from sampling-based GNNs on small subgraphs are close to those on full graphs.

A framework for federated graph classification over non-IID graphs.

problem Training graph mining models collaboratively across different domains with non-IID graphs.
method Graph Clusters Federated Learning (GCFL) framework, dynamically finding clusters based on GNN gradients, and a gradient sequence-based clustering mechanism (GCFL+).
result Demonstrated effectiveness of GCFL+ in reducing structure and feature heterogeneity among graphs.

In this paper we study the gradient estimate for positive solutions of Schrodinger equations on locally finite graph. Then we derive Harnack's inequality for positive solutions of the Schrodinger equations. We also set up some results about Green functions of the Laplacian equation on locally finite graph. Interesting …

2013-10-31abs ↗pdf ↗

GNNs may be limited by graph topology, affecting their learning outcomes.

problem Understanding how graph topology influences GNN behavior and performance.
method Investigating the interaction between local topological features and GNN message-passing schemes.
result Locally similar neighborhoods can lead to consistent node representations, affecting GNN performance.

Graph neural network framework learns graph representations from node features and local structures.

problem Lack of hierarchical pooling to preserve graph structure in graph neural networks.
method Introduces a pooling operator based on graph Fourier transform to combine node features and local structures.
result Framework $\m$ improves graph classification performance on 6 benchmarks.

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

problem Graphs lack a straightforward way to perform non-local feature aggregation like images and texts.
method Utilizes Latent Fixed Data Structure (LFDS) to aggregate feature vectors from local extraction.
result Proposed methods achieve competitive or better results with linear computational complexity.

This work investigates how GCNs should handle local structure discrepancies in testing nodes.

problem GCNs assume homophily but real graphs often have discrepancies in local structure.
method Using causal graph analysis, the study intervenes the graph structure to assess the local structure's impact on predictions.
result The method effectively enhances GCN predictions by eliminating local structure discrepancies.

The paper characterizes chordal graphs via edge deletions and finds a local minimum spanning tree algorithm.

problem Characterizing chordal graphs and finding efficient minimum spanning trees.
method Focus on exposed edges, characterize chordal graphs via deletions, and use local properties to modify Kruskal's algorithm.
result A modified Kruskal's algorithm for weighted chordal graphs is local and efficient.

In this paper, we consider three typical problems on a locally finite connected graph. The first one is to study the Bochner formula for the Laplacian operator on a locally finite connected graph. We use the Bochner formula to derive the Bernstein type estimate of the heat equation. The second is to derive the Reilly t…

2013-04-01abs ↗pdf ↗