arXiv research

L-GCNs learn from complex multigraphs, improving node classification performance.

Develops methods for clustering hypergraphs with categorical edge labels.

This master thesis focuses on practical application of Convolutional Neural Network models on the task of road labeling with bike attractivity score. We start with an abstraction of real world locations into nodes and scored edges in partially annotated dataset. We enhance information available about each edge with pho…

Practically, we are often in the dilemma that the labeled data at hand are inadequate to train a reliable classifier, and more seriously, some of these labeled data may be mistakenly labeled due to the various human factors. Therefore, this paper proposes a novel semi-supervised learning paradigm that can handle both l…

Study abelian factors in Lie algebras from graph edge labels.

VFGNN tackles privacy-preserving node classification with federated GNN.

Paper proposes scalable multi-label classification for edge devices using CNN.

Semantic boundary and edge detection aims at simultaneously detecting object edge pixels in images and assigning class labels to them. Systematic training of predictors for this task requires the labeling of edges in images which is a particularly tedious task. We propose a novel strategy for solving this task, when pi…

Given a 2-crossing minimal chart $Γ$, a minimal chart with two crossings, set $α=\min\{~i~|~$there exists an edge of label $i$ containing a white vertex$\}$, and $β=\max\{~i~|~$there exists an edge of label $i$ containing a white vertex$\}$. In this paper we study the structure of a neighbourhood of $Γ_α\cupΓ_β$, and p…

CCVAE captures label characteristics in VAEs for better representation learning.

We present a graph-based semi-supervised learning (SSL) method for learning edge flows defined on a graph. Specifically, given flow measurements on a subset of edges, we want to predict the flows on the remaining edges. To this end, we develop a computational framework that imposes certain constraints on the overall fl…

Gaussian processes classify graphs using vertex and edge features.

New method constructs tilings of the plane using directed edges and alignments.

Proposes a method to improve graph neural networks on heterogeneous graphs using meta-paths.

VEC-SBM detects communities using side information like texts and images.

A labeled oriented tree is called injective if each generator occurs at most once as an edge label. We show that injective labeled oriented trees are aspherical. The proof relies on a new relative asphericity test based on a lemma of Stallings.

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

The classical setting of community detection consists of networks exhibiting a clustered structure. To more accurately model real systems we consider a class of networks (i) whose edges may carry labels and (ii) which may lack a clustered structure. Specifically we assume that nodes possess latent attributes drawn from…

Unified model combines GCN and LPA for better node classification.

No minimal chart of type (7) exists.

Geometric Graph Alignment enhances IoT intrusion detection using NID data.

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…

We introduce a new approach to unsupervised estimation of feature-rich semantic role labeling models. Our model consists of two components: (1) an encoding component: a semantic role labeling model which predicts roles given a rich set of syntactic and lexical features; (2) a reconstruction component: a tensor factoriz…

Researchers develop a method to interpret GNNs by identifying unnecessary edges in NLP models.

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…

Improved prediction accuracy in matrix factorization using graph-based priors.

FLAME auto-labels mobile data efficiently on diverse processors.

Paper introduces new techniques for real-time sensor data labelling.

No minimal chart of type (2,3,2) exists.

Edge augmentation connects disconnected graphs by elevating eigenvalues.

A labeled oriented graph (LOG) is an oriented graph with a labeling function from the edge set into the vertex set. The complexity of a LOG is the minimal cardinality of an initial set $S$ of vertices such that every vertex can be reached successively from $S$ only using edges with labels in $S$ or already visited vert…

Complex textual information extraction tasks are often posed as sequence labeling or \emph{shallow parsing}, where fields are extracted using local labels made consistent through probabilistic inference in a graphical model with constrained transitions. Recently, it has become common to locally parametrize these models…

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

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

LoCEC classifies user relationships in large social networks, addressing sparsity issues.

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 …

Convolutional neural network improves assertion detection in multi-label clinical text.

GRAPE uses graph representation to handle missing data in feature imputation and label prediction.

Enhances GNNs by improving input data quality from topology and labels.

Data de-duplication is the task of detecting multiple records that correspond to the same real-world entity in a database. In this work, we view de-duplication as a clustering problem where the goal is to put records corresponding to the same physical entity in the same cluster and putting records corresponding to diff…

New method quantifies network cycles to enhance community detection.

We present formulae for computing the Yamada polynomial of spatial graphs obtained by replacing edges of plane graphs, such as cycle-graphs, theta-graphs, and bouquet-graphs, by spatial parts. As a corollary, it is shown that zeros of Yamada polynomials of some series of spatial graphs are dense in a certain region in …

Paper tackles medical image diagnosis with unsupervised domain adaptation.

The labeled stochastic block model is a random graph model representing networks with community structure and interactions of multiple types. In its simplest form, it consists of two communities of approximately equal size, and the edges are drawn and labeled at random with probability depending on whether their two en…

GTEA learns node representations in temporal interaction graphs.

A {\em word labeled oriented graph} (WLOG) is an oriented graph $\cal G$ on vertices $X=\{ x_1,\ldots ,x_k\}$, where each oriented edge is labeled by a word in $X^{\pm1}$. WLOGs give rise to presentations which generalize Wirtinger presentations of knots. WLOG presentations, where the underlying graph is a tree are of …

This paper presents a proof-of-concept demonstration of triaxial strain tomography from Bragg-edge neutron imaging within a three-dimensional sample. Bragg-edge neutron transmission can provide high-resolution images of the average through thickness strain within a polycrystalline material. This poses an associated ric…

Structured prediction can be thought of as a simultaneous prediction of multiple labels. This is often done by maximizing a score function on the space of labels, which decomposes as a sum of pairwise and unary potentials. The above is naturally modeled with a graph, where edges and vertices are related to pairwise and…