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.
SpaPool combines dense and sparse techniques for efficient graph pooling.
Graph embedding techniques convert graph data into vectors to preserve graph properties.
Graph matching is a challenging problem with very important applications in a wide range of fields, from image and video analysis to biological and biomedical problems. We propose a robust graph matching algorithm inspired in sparsity-related techniques. We cast the problem, resembling group or collaborative sparsity f…
GraphGen generates large labeled graphs efficiently and accurately.
We present GraphTSNE, a novel visualization technique for graph-structured data based on t-SNE. The growing interest in graph-structured data increases the importance of gaining human insight into such datasets by means of visualization. Among the most popular visualization techniques, classical t-SNE is not suitable o…
This work aims at recovering signals that are sparse on graphs. Compressed sensing offers techniques for signal recovery from a few linear measurements and graph Fourier analysis provides a signal representation on graph. In this paper, we leverage these two frameworks to introduce a new Lasso recovery algorithm on gra…
Proposes Isometric Graph Neural Networks to preserve graph distances.
A new method boosts graph neural networks by preventing over-smoothing and over-squashing.
This paper tackles credit card fraud detection using graph-based learning methods.
This paper proposes a web-based visual graph analytics platform for interactive graph mining, visualization, and real-time exploration of networks. GraphVis is fast, intuitive, and flexible, combining interactive visualizations with analytic techniques to reveal important patterns and insights for sense making, reasoni…
Improves interpretability of graph representation learning models.
The paper tackles scalability issues in Graph Representation Learning.
Matrix completion models are among the most common formulations of recommender systems. Recent works have showed a boost of performance of these techniques when introducing the pairwise relationships between users/items in the form of graphs, and imposing smoothness priors on these graphs. However, such techniques do n…
Paper proposes a new method for population-wise matching of sulcal graphs.
DAOR efficiently embeds graphs without tuning, improving speed and interpretability.
Improved graph-based connectivity estimation using heat modelling.
A natural approach to analyze interaction data of form "what-connects-to-what-when" is to create a time-series (or rather a sequence) of graphs through temporal discretization (bandwidth selection) and spatial discretization (vertex contraction). Such discretization together with non-negative factorization techniques c…
Parallelizes graph embedding for large graphs.
Graph Networks are used to make decisions in potentially complex scenarios but it is usually not obvious how or why they made them. In this work, we study the explainability of Graph Network decisions using two main classes of techniques, gradient-based and decomposition-based, on a toy dataset and a chemistry task. Ou…
Optimizes graph spectral density learning for large networks.
Graph embeddings have become a key and widely used technique within the field of graph mining, proving to be successful across a broad range of domains including social, citation, transportation and biological. Graph embedding techniques aim to automatically create a low-dimensional representation of a given graph, whi…
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…
Graphs with fat minors have a limited large-scale structure.
Neural networks that compute over graph structures are a natural fit for problems in a variety of domains, including natural language (parse trees) and cheminformatics (molecular graphs). However, since the computation graph has a different shape and size for every input, such networks do not directly support batched t…
Study uses graph techniques to understand meromorphic quadratic differential strata.
Attack graphs provide compact representations of the attack paths that an attacker can follow to compromise network resources by analysing network vulnerabilities and topology. These representations are a powerful tool for security risk assessment. Bayesian inference on attack graphs enables the estimation of the risk …
Graph pooling method uses GNN to cluster graphs efficiently.
This study bridges the gap between spatial and spectral GNNs.
In this paper, we compute the graph skein algebra of the punctured disk with two holes. Then, we apply the graph skein techniques developed here to establish necessary conditions for a spatial graph to have a symmetry of order , where is a prime. The obstruction criteria introduced here extend some results obtai…
Graph machine learning lacks a balanced theory, focusing on expressive power and optimization.
Graph-structured data such as social networks, functional brain networks, gene regulatory networks, communications networks have brought the interest in generalizing deep learning techniques to graph domains. In this paper, we are interested to design neural networks for graphs with variable length in order to solve le…
Graph-structured data appears frequently in domains including chemistry, natural language semantics, social networks, and knowledge bases. In this work, we study feature learning techniques for graph-structured inputs. Our starting point is previous work on Graph Neural Networks (Scarselli et al., 2009), which we modif…
Classifies graph configuration spaces homeomorphic to manifolds.
New method calculates bridge indices of spatial graphs using diagram colorings and Wirtinger number.
Paper rigorously defines Feynman graph integrals on Kähler manifolds.
Attack graphs are a powerful tool for security risk assessment by analysing network vulnerabilities and the paths attackers can use to compromise network resources. The uncertainty about the attacker's behaviour makes Bayesian networks suitable to model attack graphs to perform static and dynamic analysis. Previous app…
We describe a computationally efficient, stochastic graph-regularization technique that can be utilized for the semi-supervised training of deep neural networks in a parallel or distributed setting. We utilize a technique, first described in [13] for the construction of mini-batches for stochastic gradient descent (SGD…
Graph kernels have become an established and widely-used technique for solving classification tasks on graphs. This survey gives a comprehensive overview of techniques for kernel-based graph classification developed in the past 15 years. We describe and categorize graph kernels based on properties inherent to their des…
This research improves graph embeddings by optimizing node sampling with centrality weights.
ShapeVis visualizes high-dimensional data efficiently.
GraphSAINT improves GCN training efficiency and accuracy with graph sampling.
MatchGNet detects malware by learning program behavior graphs.
GRM uses graph neural networks to score process activity relevance.
New sampling technique improves KGC model performance.
Deep learning approximates shortest path distances in large graphs.
New deep learning method solves TSP faster and more efficiently.
Improved graph clustering with modularity and coarsening for attributes and communities.
Paper introduces graph-based transforms for video compression.