arXiv research

Paper proposes an algorithm to reconstruct optimal model structure from graph adjacency matrix.

Auto-encoders have emerged as a successful framework for unsupervised learning. However, conventional auto-encoders are incapable of utilizing explicit relations in structured data. To take advantage of relations in graph-structured data, several graph auto-encoders have recently been proposed, but they neglect to reco…

EggNet reconstructs particle tracks from hits using evolving graph attention networks.

DefenseVGAE defends graph neural networks against adversarial attacks.

This paper reconstructs complex graph signals using kernel methods on manifolds.

This paper is first-line research expanding GANs into graph topology analysis. By leveraging the hierarchical connectivity structure of a graph, we have demonstrated that generative adversarial networks (GANs) can successfully capture topological features of any arbitrary graph, and rank edge sets by different stages a…

GUIDE detects anomalies in attributed networks by reconstructing node attributes and higher-order structures.

Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the laten…

Method reconstructs financial networks from aggregate data, revealing critical link density.

Study reconstructs causal graph from latent variables using mixture oracles.

COSMO learns DAG structure without acyclicity constraints.

Graph auto-encoder predicts unobserved node features from biological networks and omics data.

A novel approach is put forth that utilizes data similarity, quantified on a graph, to improve upon the reconstruction performance of principal component analysis. The tasks of data dimensionality reduction and reconstruction are formulated as graph filtering operations, that enable the exploitation of data node connec…

Graph embedding leaks sensitive graph properties and subgraphs.

Graph auto-encoders predict stock market instability by measuring graph structure changes.

The paper introduces heterogeneous manifolds for better graph embeddings.

In this paper, we investigate a relation between finite graphs, simplicial flag complexes and right-angled Coxeter groups, and we provide a class of reconstructible finite graphs. We show that if $Γ$ is a finite graph which is the 1-skeleton of some simplicial flag complex $L$ which is a homology manifold of dimension …

A challenging problem in complex networks is the network reconstruction problem from data. This work deals with a class of networks denoted as conserved networks, in which a flow associated with every edge and the flows are conserved at all non-source and non-sink nodes. We propose a novel polynomial time algorithm to …

Hierarchical graph clustering is a common technique to reveal the multi-scale structure of complex networks. We propose a novel metric for assessing the quality of a hierarchical clustering. This metric reflects the ability to reconstruct the graph from the dendrogram, which encodes the hierarchy. The optimal represent…

Single-particle electron cryomicroscopy is an essential tool for high-resolution 3D reconstruction of proteins and other biological macromolecules. An important challenge in cryo-EM is the reconstruction of non-rigid molecules with parts that move and deform. Traditional reconstruction methods fail in these cases, resu…

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…

New method separates graph structure from node attributes to recover lost signal.

A key problem in statistics and machine learning is the determination of network structure from data. We consider the case where the structure of the graph to be reconstructed is known to be scale-free. We show that in such cases it is natural to formulate structured sparsity inducing priors using submodular functions,…

Algorithm reconstructs vertex positions in random geometric graphs with improved accuracy.

Graph embedding aims to transfer a graph into vectors to facilitate subsequent graph analytics tasks like link prediction and graph clustering. Most approaches on graph embedding focus on preserving the graph structure or minimizing the reconstruction errors for graph data. They have mostly overlooked the embedding dis…

Network structures in various backgrounds play important roles in social, technological, and biological systems. However, the observable network structures in real cases are often incomplete or unavailable due to measurement errors or private protection issues. Therefore, inferring the complete network structure is use…

Fine-tunes GNNs by preserving generative patterns to improve transferability.

Sharp threshold found for aligning Gaussian-weighted graphs.

We study the problem of sampling k-bandlimited signals on graphs. We propose two sampling strategies that consist in selecting a small subset of nodes at random. The first strategy is non-adaptive, i.e., independent of the graph structure, and its performance depends on a parameter called the graph coherence. On the co…

This paper resolves the all-or-nothing phase transition in graph matching.

A number of applications in engineering, social sciences, physics, and biology involve inference over networks. In this context, graph signals are widely encountered as descriptors of vertex attributes or features in graph-structured data. Estimating such signals in all vertices given noisy observations of their values…

CASTLE learns causal DAG to improve model generalization.

Paper proposes a method to improve DAG structure reconstruction using auxiliary DAGs.

Develops GNNs for incomplete graphs, improving learning from missing node attributes.

Graphs derived from cohomology help reconstruct defining graphs of Artin groups.

The (variational) graph auto-encoder and its variants have been popularly used for representation learning on graph-structured data. While the encoder is often a powerful graph convolutional network, the decoder reconstructs the graph structure by only considering two nodes at a time, thus ignoring possible interaction…

Researchers reconstruct algebraic maps onto curves based on prescribed Reeb graphs.

CCHM algorithm learns BN structure with latent variables, improving causal effect measurement.

Recently, data augmentation in the semi-supervised regime, where unlabeled data vastly outnumbers labeled data, has received a considerable attention. In this paper, we describe an efficient technique for this task, exploiting a recent framework we proposed for missing data imputation called graph imputation neural net…

MLPF uses graph neural networks to improve particle-flow reconstruction in high-pileup conditions.

Self-Organizing Maps (SOM) are popular unsupervised artificial neural network used to reduce dimensions and visualize data. Visual interpretation from Self-Organizing Maps (SOM) has been limited due to grid approach of data representation, which makes inter-scenario analysis impossible. The paper proposes a new way to …

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…

DAPDAG learns DAG structure to adapt predictions across domains.

A fast spectral algorithm detects community structure in evolving graphs.

Graph neural networks (GNNs) are shown to be successful in modeling applications with graph structures. However, training an accurate GNN model requires a large collection of labeled data and expressive features, which might be inaccessible for some applications. To tackle this problem, we propose a pre-training framew…

IGNNK uses GNN for spatiotemporal kriging, improving scalability and transferability.

Improved particle-flow event reconstruction for future colliders using scalable neural networks.

CMS uses machine learning to improve particle flow reconstruction.