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.
Study shows how leveraging hierarchical similarity graphs improves matrix completion in recommender systems.
Proposes SimPool for graph pooling using structural similarity features.
Recently, graph neural networks have been adopted in a wide variety of applications ranging from relational representations to modeling irregular data domains such as point clouds and social graphs. However, the space of graph neural network architectures remains highly fragmented impeding the development of optimized …
We propose a robust, scalable, integrated methodology for community detection and community comparison in graphs. In our procedure, we first embed a graph into an appropriate Euclidean space to obtain a low-dimensional representation, and then cluster the vertices into communities. We next employ nonparametric graph in…
Proposes a graph pooling method leveraging node proximity for hierarchical graph representation learning.
Algorithm refines matrix ratings using hierarchical graph clustering.
DHGAK aligns substructures for better graph kernel performance.
We present a novel clustering approach for moving object trajectories that are constrained by an underlying road network. The approach builds a similarity graph based on these trajectories then uses modularity-optimization hiearchical graph clustering to regroup trajectories with similar profiles. Our experimental stud…
PSimGNN partitions graphs into subgraphs for efficient graph similarity computation.
Convex clustering is a recent stable alternative to hierarchical clustering. It formulates the recovery of progressively coalescing clusters as a regularized convex problem. While convex clustering was originally designed for handling Euclidean distances between data points, in a growing number of applications, the dat…
We introduce agents that use object-oriented reasoning to consider alternate states of the world in order to more quickly find solutions to problems. Specifically, a hierarchical controller directs a low-level agent to behave as if objects in the scene were added, deleted, or modified. The actions taken by the controll…
HGNN learns augmented features for deep multi-task learning.
Sum-Product Networks (SPNs) are a class of expressive yet tractable hierarchical graphical models. LearnSPN is a structure learning algorithm for SPNs that uses hierarchical co-clustering to simultaneously identifying similar entities and similar features. The original LearnSPN algorithm assumes that all the variables …
CNNs, RNNs, GCNs, and CapsNets have shown significant insights in representation learning and are widely used in various text mining tasks such as large-scale multi-label text classification. However, most existing deep models for multi-label text classification consider either the non-consecutive and long-distance sem…
Unsupervised method learns hierarchical graph representations without labels.
Graph convolutional networks (GCNs) have been successfully applied in node classification tasks of network mining. However, most of these models based on neighborhood aggregation are usually shallow and lack the "graph pooling" mechanism, which prevents the model from obtaining adequate global information. In order to …
New approach reduces particle simulation complexity to linear time and space.
Hierarchical clustering based on pairwise similarities is a common tool used in a broad range of scientific applications. However, in many problems it may be expensive to obtain or compute similarities between the items to be clustered. This paper investigates the hierarchical clustering of N items based on a small sub…
The paper develops a decision support system for hierarchical text classification of conference proceedings.
Can we identify node labels from graph labels?
The problem of hierarchical clustering items from pairwise similarities is found across various scientific disciplines, from biology to networking. Often, applications of clustering techniques are limited by the cost of obtaining similarities between pairs of items. While prior work has been developed to reconstruct cl…
A large collection of daily time series for 60 world currencies' exchange rates is considered. The correlation matrices are calculated and the corresponding Minimal Spanning Tree (MST) graphs are constructed for each of those currencies used as reference for the remaining ones. It is shown that multiplicity of the MST …
A new method generates graphs with hierarchical structures.
Novel graph network learns hierarchical network structure.
MolHF generates complex molecules with hierarchical flow-based model.
Proposes HypCSE for enhanced hierarchical clustering.
New graphs show hierarchical hyperbolic properties, extending previous work.
A new method for efficient portfolio optimization using graph structures.
The study shows that certain curve graphs are hierarchically hyperbolic but not Gromov hyperbolic.
HGNet improves GNNs' ability to handle long-range interactions in graphs.
Proposes cone embedding for better graph hierarchical structure representation.
Representation learning has become an invaluable approach for learning from symbolic data such as text and graphs. However, while complex symbolic datasets often exhibit a latent hierarchical structure, state-of-the-art methods typically learn embeddings in Euclidean vector spaces, which do not account for this propert…
This paper explores vulnerabilities in hierarchical graph pooling neural networks for graph classification.
MxPool learns graph features from diverse graphs using a hierarchical structure.
Graph Neural Networks (GNNs), which generalize deep neural networks to graph-structured data, have drawn considerable attention and achieved state-of-the-art performance in numerous graph related tasks. However, existing GNN models mainly focus on designing graph convolution operations. The graph pooling (or downsampli…
Proposes a new model for clustering passenger trajectories with graphs.
Slow feature analysis (SFA) is an unsupervised-learning algorithm that extracts slowly varying features from a multi-dimensional time series. A supervised extension to SFA for classification and regression is graph-based SFA (GSFA). GSFA is based on the preservation of similarities, which are specified by a graph struc…
Unified framework for modeling hierarchical spaces in design problems.
Multiresolution Matrix Factorization (MMF) was recently introduced as an alternative to the dominant low-rank paradigm in order to capture structure in matrices at multiple different scales. Using ideas from multiresolution analysis (MRA), MMF teased out hierarchical structure in symmetric matrices by constructing a se…
Proposes HBGNN for better recommendation systems using graph neural networks.
Despite being very successful within the pattern recognition and machine learning community, graph-based methods are often unusable because of the lack of mathematical operations defined in graph domain. Graph embedding, which maps graphs to a vectorial space, has been proposed as a way to tackle these difficulties ena…
We show that many graphs naturally associated to a connected, compact, orientable surface are hierarchically hyperbolic spaces in the sense of Behrstock, Hagen and Sisto. They also automatically have the coarse median property defined by Bowditch. Consequences for such graphs include a distance formula analogous to Mas…
A new method for linear regression using feature graphs and hierarchical shrinkage.
A new method for efficient structural node embeddings using Von Neumann entropy.
HC-GNN tackles long-range graph information and high-order neighbourhoods.
Paper uses HGNN to predict stock types from relationships and temporal data.
Introduces hierarchical hyperbolic spaces for non-experts.
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…