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.
This paper explains GNNs using graph signal denoising.
Unified view of GNNs as graph signal denoising.
Paper proposes JDR to denoise graph features and rewire graphs for better node classification.
New analysis improves denoising of modulo signals on graphs.
We propose a new framework for manifold denoising based on processing in the graph Fourier frequency domain, derived from the spectral decomposition of the discrete graph Laplacian. Our approach uses the Spectral Graph Wavelet transform in order to per- form non-iterative denoising directly in the graph frequency domai…
Proposes GIB for recognizing informative subgraphs in graphs.
STARK improves denoising of low-depth spatial transcriptomics images.
The original contributions of this paper are twofold: a new understanding of the influence of noise on the eigenvectors of the graph Laplacian of a set of image patches, and an algorithm to estimate a denoised set of patches from a noisy image. The algorithm relies on the following two observations: (1) the low-index e…
New method denoises graph signals using wavelets, scalable for large graphs.
This work studies the denoising of piecewise smooth graph signals that exhibit inhomogeneous levels of smoothness over a graph, where the value at each node can be vector-valued. We extend the graph trend filtering framework to denoising vector-valued graph signals with a family of non-convex regularizers, which exhibi…
This study uses deep learning to improve the accuracy of raw data denoising in ProtoDUNE experiments.
We study an extention of total variation denoising over images to over Cartesian power graphs and its applications to estimating non-parametric network models. The power graph fused lasso (PGFL) segments a matrix by exploiting a known graphical structure, , over the rows and columns. Our main results shows that for …
Proposes DeGLIF to denoise graph data for label noise robustness.
The paper analyzes oversmoothing in GNNs and quantifies the effects of mixing and denoising.
Detects graph topology changes from noisy signals using prior spectral information.
Privacy-preserving GNNs for graph data with sensitive node data.
Deep GNNs and self-supervision boost graph learning at scale.
Discrete noise improves graph generation quality and speed.
AdarGCN tackles noisy web images in few-shot learning.
Problems in machine learning (ML) can involve noisy input data, and ML classification methods have reached limiting accuracies when based on standard ML data sets consisting of feature vectors and their classes. Greater accuracy will require incorporation of prior structural information on data into learning. We study …
Graph neural networks have become one of the most important techniques to solve machine learning problems on graph-structured data. Recent work on vertex classification proposed deep and distributed learning models to achieve high performance and scalability. However, we find that the feature vectors of benchmark datas…
Neighbor Mixture Model captures node correlations in graphs.
New method for faster graph parameter inference from large random Kronecker graphs.
Modern methods for learning over graph input data have shown the fruitfulness of accounting for relationships among elements in a collection. However, most methods that learn over set input data use only rudimentary approaches to exploit intra-collection relationships. In this work we introduce Deep Message Passing on …
Graph representation learning, aiming to learn low-dimensional representations which capture the geometric dependencies between nodes in the original graph, has gained increasing popularity in a variety of graph analysis tasks, including node classification and link prediction. Existing representation learning methods …
Efficiently learns deep factor graphs using Gaussian belief propagation.
DISTANA predicts and denoises spatial wave dynamics.
We consider the problem of estimating a low-rank matrix from a noisy observed matrix. Previous work has shown that the optimal method depends crucially on the choice of loss function. In this paper, we use a family of weighted loss functions, which arise naturally for problems such as submatrix denoising, denoising wit…
While it is believed that denoising is not always necessary in many big data applications, we show in this paper that denoising is helpful in urban traffic analysis by applying the method of bounded total variation denoising to the urban road traffic prediction and clustering problem. We propose two easy-to-implement m…
DDCD uses diffusion models to learn causal structures from noisy data.
Exact posterior score estimation for solving linear inverse problems
A new model designs molecular latent vectors for drug discovery.
Laplacian Eigenvectors of the graph constructed from a data set are used in many spectral manifold learning algorithms such as diffusion maps and spectral clustering. Given a graph constructed from a random sample of a -dimensional compact submanifold in , we establish the spectral convergence rate…
Dantzig Selector (DS) is widely used in compressed sensing and sparse learning for feature selection and sparse signal recovery. Since the DS formulation is essentially a linear programming optimization, many existing linear programming solvers can be simply applied for scaling up. The DS formulation can be explained a…
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 problem. We design a family of autoregressive moving average (ARMA) recursions,…
GDiff tackles blind denoising with Gibbs sampling and Monte Carlo inference.
Unified method for simultaneous denoising and clustering.
Nonparametric empirical Bayes denoising on Riemannian manifolds
SNORE applies denoiser only on images with noise of adequate level for image restoration.
A new approach to denoising using optimal transport theory.
Recovering a high-quality image from noisy indirect measurements is an important problem with many applications. For such inverse problems, supervised deep convolutional neural network (CNN)-based denoising methods have shown strong results, but the success of these supervised methods critically depends on the availabi…
Graph neural networks (GNNs) are shown to be successful in modeling applications with graph structures. However, training an accurate GNN model requires a large collection of labeled data and expressive features, which might be inaccessible for some applications. To tackle this problem, we propose a pre-training framew…
Paper analyzes self-supervised image denoising with denatured data.
This paper considers regression tasks involving high-dimensional multivariate processes whose structure is dependent on some {known} graph topology. We put forth a new definition of time-vertex wide-sense stationarity, or joint stationarity for short, that goes beyond product graphs. Joint stationarity helps by reducin…
Geometric approach clusters intersecting manifolds with high probability.
Nyström approximation for scalable operator learning
Deep neural networks are often used to implement powerful generative models for real-world data. Notable applications include image denoising, as well as other classical inverse problems like compressed sensing and super-resolution. To provide a rigorous but simplified analysis of generative models, in this work, we in…
Graphs are a central tool in machine learning and information processing as they allow to conveniently capture the structure of complex datasets. In this context, it is of high importance to develop flexible models of signals defined over graphs or networks. In this paper, we generalize the traditional concept of wide …