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.
A new framework reduces data upload for image classification while protecting user privacy.
SWRLDA improves LDA for multi-class classification with edge classes.
Optimized neural networks for Edge TPU achieve high accuracy in real-time image classification.
The tilings of the 2-dimensional sphere by congruent triangles have been extensively studied, and the edge-to-edge tilings have been completely classified. However, not much is known about the tilings by other congruent polygons. In this paper, we classify the simplest case, which is the edge-to-edge tilings of the 2-d…
A hybrid neural network optimizes AI deployment on edge and cloud for energy efficiency.
This paper proposes a method to learn graph representations by partitioning edges into communities.
Optimized CNNs for AMC on edge devices reduce complexity without sacrificing accuracy.
Gaussian processes classify graphs using vertex and edge features.
Graph attention improves node classification by distinguishing important edges.
ES-MLP combines Graph-MLP with edge splitting for node classification on both homophilic and heterophilic graphs.
Graph data augmentation improves GNN performance in node classification.
New edge features improve GNN performance in biological datasets.
This paper proposes a discrimination technique for vertices in a weighted network. We assume that the edge weights and adjacencies in the network are conditionally independent and that both sources of information encode class membership information. In particular, we introduce a edge weight distribution matrix to the s…
LoCEC classifies user relationships in large social networks, addressing sparsity issues.
Method certifies edge predictions with cloud-level reliability.
While statistical analysis of a single network has received a lot of attention in recent years, with a focus on social networks, analysis of a sample of networks presents its own challenges which require a different set of analytic tools. Here we study the problem of classification of networks with labeled nodes, motiv…
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…
Graph Neural Networks (GNNs) have proved to be an effective representation learning framework for graph-structured data, and have achieved state-of-the-art performance on many practical predictive tasks, such as node classification, link prediction and graph classification. Among the variants of GNNs, Graph Attention N…
Spectral Graph Convolutional Networks (GCNs) are a generalization of convolutional networks to learning on graph-structured data. Applications of spectral GCNs have been successful, but limited to a few problems where the graph is fixed, such as shape correspondence and node classification. In this work, we address thi…
We propose a new graph kernel for graph classification and comparison using Ollivier Ricci curvature. The Ricci curvature of an edge in a graph describes the connectivity in the local neighborhood. An edge in a densely connected neighborhood has positive curvature and an edge serving as a local bridge has negative curv…
Statistical inference on graphs is a burgeoning field in the applied and theoretical statistics communities, as well as throughout the wider world of science, engineering, business, etc. In many applications, we are faced with the reality of errorfully observed graphs. That is, the existence of an edge between two vert…
ACERL embeds networks into a low-dimensional space preserving structural and semantic properties.
Enhances graph comparison by incorporating edge features using Fused Gromov-Wasserstein distance.
Graphs can be fooled by small edge changes, but this work protects them.
A new kernel measures brain network similarities, improving disease classification.
We study the problem of end-to-end learning from complex multigraphs with potentially very large numbers of edges between two vertices, each edge labeled with rich information. Examples range from communication networks to flights between airports or financial transaction graphs. We propose Latent-Graph Convolutional N…
ARGEW improves node embeddings for weighted homophilous graphs by emphasizing strong edge weights.
By means of color chord diagrams we establish a necessary and sufficient condition for -topological equivalence of functions with one essentially critical point on oriented surfaces with edge. We also calculate the number of -topologically non-equivalent functions with one essentially critical point on oriented s…
We present very efficient active learning algorithms for link classification in signed networks. Our algorithms are motivated by a stochastic model in which edge labels are obtained through perturbations of a initial sign assignment consistent with a two-clustering of the nodes. We provide a theoretical analysis within…
Improved DL models robust against adversarial attacks for wireless signal classification.
Graph Neural Networks (GNNs) have boosted the performance of many graph related tasks such as node classification and graph classification. Recent researches show that graph neural networks are vulnerable to adversarial attacks, which deliberately add carefully created unnoticeable perturbation to the graph structure. …
Given a clover link, we construct a bottom tangle by using a disk/band surface of the clover link. Since the Milnor number is already defined for a bottom tangle, we define the Milnor number for the clover link to be the Milnor number for the bottom tangle and show that for a clover link, if Milnor numbers of length k …
Unified model combines GCN and LPA for better node classification.
Graphs from features improve classification accuracy in tasks.
Biological and cellular systems are often modeled as graphs in which vertices represent objects of interest (genes, proteins, drugs) and edges represent relational ties among these objects (binds-to, interacts-with, regulates). This approach has been highly successful owing to the theory, methodology and software that …
In this paper we provide a principled approach to solve a transductive classification problem involving a similar graph (edges tend to connect nodes with same labels) and a dissimilar graph (edges tend to connect nodes with opposing labels). Most of the existing methods, e.g., Information Regularization (IR), Weighted …
The study classifies singularities in discrete improper affine spheres.
PageRank for Semi-Supervised Learning has shown to leverage data structures and limited tagged examples to yield meaningful classification. Despite successes, classification performance can still be improved, particularly in cases of fuzzy graphs or unbalanced labeled data. To address such limitations, a novel approach…
Convolution Neural Networks (CNN) have performed well in many applications such as object detection, pattern recognition, video surveillance and so on. CNN carryout feature extraction on labelled data to perform classification. Multi-label classification assigns more than one label to a particular data sample in a data…
Graph embedding is an important approach for graph analysis tasks such as node classification and link prediction. The goal of graph embedding is to find a low dimensional representation of graph nodes that preserves the graph information. Recent methods like Graph Convolutional Network (GCN) try to consider node attri…
This paper quantizes CapsNets for efficient edge deployment.
Learning graph-structured data with graph neural networks (GNNs) has been recently emerging as an important field because of its wide applicability in bioinformatics, chemoinformatics, social network analysis and data mining. Recent GNN algorithms are based on neural message passing, which enables GNNs to integrate loc…
FoSR adds edges to graphs to prevent oversquashing and oversmoothing in GNNs.
Enhances GNNs by improving input data quality from topology and labels.
Federated edge learning improves with CSIT-free model aggregation using RIS.
Automates design of lightweight neural networks for image classification.
Learning representation on graph plays a crucial role in numerous tasks of pattern recognition. Different from grid-shaped images/videos, on which local convolution kernels can be lattices, however, graphs are fully coordinate-free on vertices and edges. In this work, we propose a Gaussian-induced convolution (GIC) fra…
The paper controls false discovery rate in link prediction using conformal inference.