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 technique normalizes nodes within groups to improve GNN performance.
This paper tests the multivariate normality of node degrees in Erdős-Rényi graphs.
From a sequence of similarity networks, with edges representing certain similarity measures between nodes, we are interested in detecting a change-point which changes the statistical property of the networks. After the change, a subset of anomalous nodes which compares dissimilarly with the normal nodes. We study a sim…
ULES embeds dynamic networks with stability guarantees.
Graph representation learning aims at transforming graph data into meaningful low-dimensional vectors to facilitate the employment of machine learning and data mining algorithms designed for general data. Most current graph representation learning approaches are transductive, which means that they require all the nodes…
Improves performance of deep GCNs by controlling node feature variance.
The graph Laplacian plays key roles in information processing of relational data, and has analogies with the Laplacian in differential geometry. In this paper, we generalize the analogy between graph Laplacian and differential geometry to the hypergraph setting, and propose a novel hypergraph -Laplacian. Unlike the …
New graph embedding method improves link prediction and node classification.
CUQ-GNN adapts uncertainty quantification for graph data, improving on GPN.
The autoencoder is an artificial neural network model that learns hidden representations of unlabeled data. With a linear transfer function it is similar to the principal component analysis (PCA). While both methods use weight vectors for linear transformations, the autoencoder does not come with any indication similar…
Gene expression profiles have been widely used to characterize patterns of cellular responses to diseases. As data becomes available, scalable learning toolkits become essential to processing large datasets using deep learning models to model complex biological processes. We present an autoencoder to capture nonlinear …
Improved bipartite link prediction using 2-hop paths.
Simplifies GNN models by selecting important features for node classification.
Bi-directional Curriculum Learning improves graph anomaly detection by considering both homogeneity and heterogeneity.
Lipschitz normalization boosts deep attention models, especially for graph neural networks.
The study applies spatial density models to mobile node movements using Möbius distributions.
We present a novel spectral embedding of graphs that incorporates weights assigned to the nodes, quantifying their relative importance. This spectral embedding is based on the first eigenvectors of some properly normalized version of the Laplacian. We prove that these eigenvectors correspond to the configurations of lo…
Normalizing flows are shown to be equivalent to Bayesian networks, revealing new insights.
In this paper we show that if the minimal good resolution graph of a normal surface singularity contains at least two nodes (i.e. vertex with valency at least 3) then the singularity does not admit a smoothing with Milnor fiber having rational homology equal to the rational homology of the 4-disk (called a ration…
Enhances graph neural networks by considering feature similarities in node aggregation.
Networks or graphs can easily represent a diverse set of data sources that are characterized by interacting units or actors. Social networks, representing people who communicate with each other, are one example. Communities or clusters of highly connected actors form an essential feature in the structure of several emp…
Improved graph neural networks by separating feature aggregation and depth.
Method identifies root causes of anomalies in causal processes.
Steerable neural ODEs on homogeneous spaces for equivariant feature dynamics.
The ubiquitous proliferation of online social networks has led to the widescale emergence of relational graphs expressing unique patterns in link formation and descriptive user node features. Matrix Factorization and Completion have become popular methods for Link Prediction due to the low rank nature of mutual node fr…
The paper proposes a new model to analyze directed networks and accurately estimate community memberships.
This paper explores GNN functions on random graphs, highlighting the importance of node Positional Encodings.
Novel GNN method for semi-supervised clustering of signed networks.
Spectral clustering is widely used to partition graphs into distinct modules or communities. Existing methods for spectral clustering use the eigenvalues and eigenvectors of the graph Laplacian, an operator that is closely associated with random walks on graphs. We propose a new spectral partitioning method that exploi…
Graphical normalizing flows use Bayesian networks to improve normalizing flows' interpretability and performance.
RLF uses Riemann-Lebesgue cutting for better regression.
Method detects anomalies on attributed graphs with few labeled instances.
The paper examines how well node similarities are preserved by random projections in graph embeddings.
The paper uses transformed ANOVA to identify important fire detection variables.
Paper introduces Categorical Normalizing Flows for better handling of categorical data.
Meta-graph is currently the most powerful tool for similarity search on heterogeneous information networks,where a meta-graph is a composition of meta-paths that captures the complex structural information. However, current relevance computing based on meta-graph only considers the complex structural information, but i…
Graph Neural Networks (graph NNs) are a promising deep learning approach for analyzing graph-structured data. However, it is known that they do not improve (or sometimes worsen) their predictive performance as we pile up many layers and add non-lineality. To tackle this problem, we investigate the expressive power of g…
This paper models how features influence event triggers in high-dimensional networks.
Proposes BN layers for neural networks on complex domains, improving training stability and accuracy.
GHNet improves graph learning by balancing homogeneity and heterogeneity.
A variety of graph neural networks (GNNs) frameworks for representation learning on graphs have been recently developed. These frameworks rely on aggregation and iteration scheme to learn the representation of nodes. However, information between nodes is inevitably lost in the scheme during learning. In order to reduce…
The paper studies matrix normalization and graph balancing using a new functional and gradient descent.
Deep learning models have achieved huge success in numerous fields, such as computer vision and natural language processing. However, unlike such fields, it is hard to apply traditional deep learning models on the graph data due to the 'node-orderless' property. Normally, adjacency matrices will cast an artificial and …
We consider a graphical model where a multivariate normal vector is associated with each node of the underlying graph and estimate the graphical structure. We minimize a loss function obtained by regressing the vector at each node on those at the remaining ones under a group penalty. We show that the proposed estimator…
Intrusion detection systems (IDSs) generate valuable knowledge about network security, but an abundance of false alarms and a lack of methods to capture the interdependence among alerts hampers their utility for network defense. Here, we explore a graph-based approach for fusing alerts generated by multiple IDSs (e.g.,…
Spectral clustering is sensitive to how graphs are constructed from data particularly when proximal and imbalanced clusters are present. We show that Ratio-Cut (RCut) or normalized cut (NCut) objectives are not tailored to imbalanced data since they tend to emphasize cut sizes over cut values. We propose a graph partit…
The performance of graph neural nets (GNNs) is known to gradually decrease with increasing number of layers. This decay is partly attributed to oversmoothing, where repeated graph convolutions eventually make node embeddings indistinguishable. We take a closer look at two different interpretations, aiming to quantify o…
Adaptive framework predicts stock prices better during volatile periods.