English
Related papers

Related papers: Riemannian Patch Assignment Gradient Flows

200 papers

Graphs are pervasive in the real-world, such as social network analysis, bioinformatics, and knowledge graphs. Graph neural networks (GNNs) have great ability in node classification, a fundamental task on graphs. Unfortunately, conventional…

Machine Learning · Computer Science 2024-09-05 Quan Li , Tianxiang Zhao , Lingwei Chen , Junjie Xu , Suhang Wang

We study the possibility of using multilevel algorithms for the computation of correlation functions of gradient flow observables. For each point in the correlation function an approximate flow is defined which depends only on links in a…

High Energy Physics - Lattice · Physics 2016-04-13 Miguel García Vera , Stefan Schaefer

In this paper we study dynamic averaging load balancing on general graphs. We consider infinite time and dynamic processes, where in every step new load items are assigned to randomly chosen nodes. A matching is chosen, and the load is…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-02-24 Petra Berenbrink , Lukas Hintze , Hamed Hosseinpour , Dominik Kaaser , Malin Rau

Paper proposes a model of large networks based on a random preferential attachment graph with addition of complete subgraphs (cliques). The proposed model refers to models of random graphs following the nonlinear preferential attachment…

Social and Information Networks · Computer Science 2019-04-05 E. B. Yudin

Reservoir computing has been successfully applied to graphs as a preprocessing method to improve the training efficiency of Graph Neural Networks (GNNs). However, a common issue that arises when repeatedly applying layer operators on graphs…

Machine Learning · Computer Science 2025-09-29 Anna Bison , Alessandro Sperduti

We study graph-based Laplacian semi-supervised learning at low labeling rates. Laplacian learning uses harmonic extension on a graph to propagate labels. At very low label rates, Laplacian learning becomes degenerate and the solution is…

Statistics Theory · Mathematics 2020-06-05 Jeff Calder , Dejan Slepčev , Matthew Thorpe

This paper analyzes the problem of assigning weights to edges incrementally in a dynamic complete bipartite graph consisting of producer and consumer nodes. The objective is to minimize the overall cost while satisfying certain constraints.…

Distributed, Parallel, and Cluster Computing · Computer Science 2011-05-03 Ankur Sahai

Graph neural networks (GNNs) and label propagation represent two interrelated modeling strategies designed to exploit graph structure in tasks such as node property prediction. The former is typically based on stacked message-passing layers…

Machine Learning · Computer Science 2021-10-15 Yangkun Wang , Jiarui Jin , Weinan Zhang , Yongyi Yang , Jiuhai Chen , Quan Gan , Yong Yu , Zheng Zhang , Zengfeng Huang , David Wipf

The random dot product graph (RDPG) is an independent-edge random graph that is analytically tractable and, simultaneously, either encompasses or can successfully approximate a wide range of random graphs, from relatively simple stochastic…

We present a unified framework, with quantitative estimates, for deterministic interacting particle systems whose pairwise interactions may depend on heterogeneous labels. Heterogeneity is kept at every level by adding a frozen label…

Analysis of PDEs · Mathematics 2026-05-21 Thierry Paul , Emmanuel Trélat

Statistical inference for spatial processes from partially realized or scattered data has seen voluminous developments in diverse areas ranging from environmental sciences to business and economics. Inference on the associated rates of…

Statistics Theory · Mathematics 2026-01-06 Didong Li , Aritra Halder , Sudipto Banerjee

In this paper we study a gradient flow approach to the problem of quantization of measures in one dimension. By embedding our problem in $L^2$, we find a continuous version of it that corresponds to the limit as the number of particles…

Analysis of PDEs · Mathematics 2016-01-26 Emanuele Caglioti , François Golse , Mikaela Iacobelli

Graphs are ubiquitous, and learning on graphs has become a cornerstone in artificial intelligence and data mining communities. Unlike pixel grids in images or sequential structures in language, graphs exhibit a typical non-Euclidean…

Machine Learning · Computer Science 2026-02-12 Li Sun , Qiqi Wan , Suyang Zhou , Zhenhao Huang , Philip S. Yu

One of the cornerstones of the field of signal processing on graphs are graph filters, direct analogues of classical filters, but intended for signals defined on graphs. This work brings forth new insights on the distributed graph filtering…

Machine Learning · Computer Science 2017-09-18 Elvin Isufi , Andreas Loukas , Andrea Simonetto , Geert Leus

Graphs are nowadays ubiquitous in the fields of signal processing and machine learning. As a tool used to express relationships between objects, graphs can be deployed to various ends: I) clustering of vertices, II) semi-supervised…

Machine Learning · Computer Science 2020-07-17 Carlos Lassance , Vincent Gripon , Gonzalo Mateos

We consider an explicitly solvable model (formulated in the Riemannian geometry terms) for a stationary wave process in a specific thin domain with the Dirichlet boundary conditions on the boundary of the domain. The transition from the…

Mathematical Physics · Physics 2016-04-04 S. Molchanov , B. Vainberg

This paper focus on investigating the distributed Riemannian stochastic optimization problem on the Stiefel manifold for multi-agent systems, where all the agents work collaboratively to optimize a function modeled by the average of their…

Optimization and Control · Mathematics 2025-01-17 Jishu Zhao , Xi Wang , Jinlong Lei

Flow and diffusion models produce high-quality samples, but adapting them to user preferences or constraints post-training remains costly and brittle, a challenge commonly called reward alignment. We argue that efficient reward alignment…

Volume entropy is an important invariant of metric graphs as well as Riemannian manifolds. In this note, we calculate the change of volume entropy when an edge is added to a metric graph. Using the first result, we investigate the change of…

Dynamical Systems · Mathematics 2018-09-24 Wooyeon Kim , Seonhee Lim

Local dependence random graph models are a class of block models for network data which allow for dependence among edges under a local dependence assumption defined around the block structure of the network. Since being introduced by…

Statistics Theory · Mathematics 2025-01-06 Jonathan R. Stewart