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 of graphs interpolating curve and pants graphs, providing formulae and geometry classifications.
Deep GNNs and self-supervision boost graph learning at scale.
Augments graph node features to improve GNN performance.
Method analyzes large-scale network data to detect communication pattern shifts.
We focus on developing a novel scalable graph-based semi-supervised learning (SSL) method for a small number of labeled data and a large amount of unlabeled data. Due to the lack of labeled data and the availability of large-scale unlabeled data, existing SSL methods usually encounter either suboptimal performance beca…
Study large-scale geometry of graph braid groups via cubical structures.
Efficiently attacks large-scale graphs without using the whole graph.
A plethora of multi-view subspace clustering (MVSC) methods have been proposed over the past few years. Researchers manage to boost clustering accuracy from different points of view. However, many state-of-the-art MVSC algorithms, typically have a quadratic or even cubic complexity, are inefficient and inherently diffi…
Study of mapping class groups on infinite graphs, focusing on their large-scale geometry.
Bipartite graphs have been used to represent data relationships in many data-mining applications such as in E-commerce recommendation systems. Since learning in graph space is more complicated than in Euclidian space, recent studies have extensively utilized neural nets to effectively and efficiently embed a graph's no…
New method infers causal factors from large-scale data without full graph reconstruction.
We propose a nonparametric approach to link prediction in large-scale dynamic networks. Our model uses graph-based features of pairs of nodes as well as those of their local neighborhoods to predict whether those nodes will be linked at each time step. The model allows for different types of evolution in different part…
A scalable method to learn causal graphs from large data.
Graph neural networks improve El Niño forecasts.
Graph embedding methods transform high-dimensional and complex graph contents into low-dimensional representations. They are useful for a wide range of graph analysis tasks including link prediction, node classification, recommendation and visualization. Most existing approaches represent graph nodes as point vectors i…
The -NN graph has played a central role in increasingly popular data-driven techniques for various learning and vision tasks; yet, finding an efficient and effective way to construct -NN graphs remains a challenge, especially for large-scale high-dimensional data. In this paper, we propose a new approach to const…
Under the framework of spectral clustering, the key of subspace clustering is building a similarity graph which describes the neighborhood relations among data points. Some recent works build the graph using sparse, low-rank, and -norm-based representation, and have achieved state-of-the-art performance. Howeve…
Graph neural networks improve network localization accuracy and efficiency.
Graphs on surfaces have a 2-dimensional large scale structure.
Graph Neural Networks (GNNs) have been emerging as a promising method for relational representation including recommender systems. However, various challenging issues of social graphs hinder the practical usage of GNNs for social recommendation, such as their complex noisy connections and high heterogeneity. The oversm…
A diversified portfolio is created by solving the MIS problem in large market graphs, outperforming conventional methods.
Study shows SNN graph Laplacians converge to k-NN graph Laplacians under large scale asymptotics.
This paper proposes a new method for learning covers of geometric datasets to improve topological inference and visualization.
New method discovers causal relationships in large-scale data.
We consider the sparse inverse covariance regularization problem or graphical lasso with regularization parameter . Suppose the co- variance graph formed by thresholding the entries of the sample covariance matrix at is decomposed into connected components. We show that the vertex-partition induced by the thresh…
We propose a scalable Gromov-Wasserstein learning (S-GWL) method and establish a novel and theoretically-supported paradigm for large-scale graph analysis. The proposed method is based on the fact that Gromov-Wasserstein discrepancy is a pseudometric on graphs. Given two graphs, the optimal transport associated with th…
DeeperGCN tackles deep GCNs by overcoming vanishing gradient and over-smoothing issues.
OGB provides diverse graph datasets for robust ML research.
This paper studies large-scale dynamical networks where the current state of the system is a linear transformation of the previous state, contaminated by a multivariate Gaussian noise. Examples include stock markets, human brains and gene regulatory networks. We introduce a transition matrix to describe the evolution, …
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…
CoSimGNN improves graph similarity computation for large graphs.
CHILI datasets tackle inorganic nanomaterials, advancing graph machine learning.
InfDetect detects e-commerce insurance fraud using graph analysis.
This work improves GNN training efficiency by maximizing ego-graph information.
New non-homophilous graph datasets and methods for scalable learning.
The monitoring of large dynamic networks is a major chal- lenge for a wide range of application. The complexity stems from properties of the underlying graphs, in which slight local changes can lead to sizable variations of global prop- erties, e.g., under certain conditions, a single link cut that may be overlooked du…
PPRGo uses approximate PageRank to speed up GNNs on large graphs.
We present a structural clustering algorithm for large-scale datasets of small labeled graphs, utilizing a frequent subgraph sampling strategy. A set of representatives provides an intuitive description of each cluster, supports the clustering process, and helps to interpret the clustering results. The projection-based…
Large GNNs trained with Graph Parallelism improve atomic simulation accuracy.
Generative models for graphs have been typically committed to strong prior assumptions concerning the form of the modeled distributions. Moreover, the vast majority of currently available models are either only suitable for characterizing some particular network properties (such as degree distribution or clustering coe…
Graphs with fat minors have a limited large-scale structure.
BGRL learns graph representations without costly negative examples.
A graph-based sampling and consensus (GraphSAC) approach is introduced to effectively detect anomalous nodes in large-scale graphs. Existing approaches rely on connectivity and attributes of all nodes to assign an anomaly score per node. However, nodal attributes and network links might be compromised by adversaries, r…
While the harmonic function solution performs well in many semi-supervised learning (SSL) tasks, it is known to scale poorly with the number of samples. Recent successful and scalable methods, such as the eigenfunction method focus on efficiently approximating the whole spectrum of the graph Laplacian constructed from …
Convolutional neural networks (CNNs) have achieved great success on grid-like data such as images, but face tremendous challenges in learning from more generic data such as graphs. In CNNs, the trainable local filters enable the automatic extraction of high-level features. The computation with filters requires a fixed …
Study the geometry of graph product extension graphs.
Let G be a finitely presented group, and G' its commutator subgroup. Let C be the Cayley graph of G' with all commutators in G as generators. Then C is large scale simply connected. Furthermore, if G is a torsion-free nonelementary word-hyperbolic group, C is one-ended. Hence (in this case), the asymptotic dimension of…
This paper improves GNN efficiency for large-scale graph applications.