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.
CoMGNN models heterogeneous graphs with evolving nodes and edges.
VEC-SBM detects communities using side information like texts and images.
Kernel networks' stability edge linked to Fisher Information singularity.
In matrix factorization, available graph side-information may not be well suited for the matrix completion problem, having edges that disagree with the latent-feature relations learnt from the incomplete data matrix. We show that removing these edges improves prediction accuracy and scalability. We…
NEAR improves graph classification by aggregating edge information.
Recovering edge activities from node activity data in temporal networks.
The Mutual Information (MI) is an often used measure of dependency between two random variables utilized in information theory, statistics and machine learning. Recently several MI estimators have been proposed that can achieve parametric MSE convergence rate. However, most of the previously proposed estimators have th…
This paper proposes a discrimination technique for vertices in a weighted network. We assume that the edge weights and adjacencies in the network are conditionally independent and that both sources of information encode class membership information. In particular, we introduce a edge weight distribution matrix to the s…
Spectral embedding improves with edge weight transformations.
Edge features contain important information about graphs. However, current state-of-the-art neural network models designed for graph learning, e.g. graph convolutional networks (GCN) and graph attention networks (GAT), adequately utilize edge features, especially multi-dimensional edge features. In this paper, we build…
The edge of chaos optimizes machine learning models.
Study suggests using information flow measures to target interventions in neural networks.
Functional connections in the brain are frequently represented by weighted networks, with nodes representing locations in the brain, and edges representing the strength of connectivity between these locations. One challenge in analyzing such data is that inference at the individual edge level is not particularly biolog…
New graph learning model can approximate any function and handle edge values.
We study the problem of end-to-end learning from complex multigraphs with potentially very large numbers of edges between two vertices, each edge labeled with rich information. Examples range from communication networks to flights between airports or financial transaction graphs. We propose Latent-Graph Convolutional N…
To accommodate heterogeneous tasks in Internet of Things (IoT), a new communication and computing paradigm termed mobile edge computing emerges that extends computing services from the cloud to edge, but at the same time exposes new challenges on security. The present paper studies online security-aware edge computing …
We propose a new method for embedding graphs while preserving directed edge information. Learning such continuous-space vector representations (or embeddings) of nodes in a graph is an important first step for using network information (from social networks, user-item graphs, knowledge bases, etc.) in many machine lear…
We study Einstein metrics on smooth compact 4-manifolds with an edge-cone singularity of specified cone angle along an embedded 2-manifold. To do so, we first derive modified versions of the Gauss-Bonnet and signature theorems for arbitrary Riemannian 4-manifolds with edge-cone singularities, and then show that these y…
Study reveals limits of detecting local geometry in random graphs.
Study sets limits for detecting a subhypergraph in uniform hypergraphs.
The paper analyzes deep neural networks' expressivity and training, revealing critical expressivity issues.
Efficiently searches ancestral graphs using multivariate information.
Polynomial-time algorithm estimates edge density of random graphs with privacy and robustness.
Graph neural networks improve with edge similarity constraints in RNA structure analysis.
Summarizing large-scaled directed graphs into small-scale representations is a useful but less studied problem setting. Conventional clustering approaches, which based on "Min-Cut"-style criteria, compress both the vertices and edges of the graph into the communities, that lead to a loss of directed edge information. O…
This work surveys attacks and defenses on edge neural networks.
New method recovers graph latent positions under edge differential privacy.
We consider the problem of model selection in Gaussian Markov fields in the sample deficient scenario. The benchmark information-theoretic results in the case of d-regular graphs require the number of samples to be at least proportional to the logarithm of the number of vertices to allow consistent graph recovery. When…
The paper proposes a novel Kernelized image segmentation scheme for noisy images that utilizes the concept of Smallest Univalue Segment Assimilating Nucleus (SUSAN) and incorporates spatial constraints by computing circular colour map induced weights. Fuzzy damping coefficients are obtained for each nucleus or center p…
Bayesian optimization improved for nanophotonic device design.
This paper presents a new Graph Neural Network (GNN) type using feature-wise linear modulation (FiLM). Many standard GNN variants propagate information along the edges of a graph by computing "messages" based only on the representation of the source of each edge. In GNN-FiLM, the representation of the target node of an…
Researchers develop a method to interpret GNNs by identifying unnecessary edges in NLP models.
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…
Paper presents privacy-preserving techniques for HD computing.
This paper tackles task offloading in edge computing systems with dynamic interactions.
IIC decouples causal identification into two phases, significantly reducing the HTC gap in linear SEMs.
SGATs learn sparse attention coefficients to improve graph learning tasks on large, noisy graphs.
GRCN improves GCNs by predicting missing edges and revising weights.
EEGNN improves graph neural networks by enhancing graph structure.
We introduce a novel type of stabilization map on the configuration spaces of a graph, which increases the number of particles occupying an edge. There is an induced action on homology by the polynomial ring generated by the set of edges, and we show that this homology module is finitely generated. An analogue of class…
Graph pruning improves neural network performance by addressing squashing and smoothing issues.
New method for online learning IC models with node-level feedback.
New method solves group synchronization with cycle-edge message passing.
Statistical inference on graphs is a burgeoning field in the applied and theoretical statistics communities, as well as throughout the wider world of science, engineering, business, etc. In many applications, we are faced with the reality of errorfully observed graphs. That is, the existence of an edge between two vert…
Predicting the occurrence of links is a fundamental problem in networks. In the link prediction problem we are given a snapshot of a network and would like to infer which interactions among existing members are likely to occur in the near future or which existing interactions are we missing. Although this problem has b…
FoSR adds edges to graphs to prevent oversquashing and oversmoothing in GNNs.
With the recent popularity of graphical clustering methods, there has been an increased focus on the information between samples. We show how learning cluster structure using edge features naturally and simultaneously determines the most likely number of clusters and addresses data scale issues. These results are parti…
Investor flows in Korean equity market transmit shared information, not private signals.