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 sense stationarity to signals defined over the vertices of arbitrary weighted undirected graphs. We show that stationarity is expressed through the graph localization operator reminiscent of translation. We prove that stationary graph signals are characterized by a well-defined Power Spectral Density that can be efficiently estimated even for large graphs. We leverage this new concept to derive Wiener-type estimation procedures of noisy and partially observed signals and illustrate the performance of this new model for denoising and regression.
Convolutional Neural Networks (CNNs) are a cornerstone of the Deep Learning toolbox and have led to many breakthroughs in Artificial Intelligence. So far, these neural networks (NNs) have mostly been developed for regular Euclidean domains such as those supporting images, audio, or video. Because of their success, CNN-based methods are becoming increasingly popular in Cosmology. Cosmological data often comes as spherical maps, which make the use of the traditional CNNs more complicated. The commonly used pixelization scheme for spherical maps is the Hierarchical Equal Area isoLatitude Pixelisation (HEALPix). We present a spherical CNN for analysis of full and partial HEALPix maps, which we call DeepSphere. The spherical CNN is constructed by representing the sphere as a graph. Graphs are versatile data structures that can represent pairwise relationships between objects or act as a discrete representation of a continuous manifold. Using the graph-based representation, we define many of the standard CNN operations, such as convolution and pooling. With filters restricted to being radial, our convolutions are equivariant to rotation on the sphere, and DeepSphere can be made invariant or equivariant to rotation. This way, DeepSphere is a special case of a graph CNN, tailored to the HEALPix sampling of the sphere. This approach is computationally more efficient than using spherical harmonics to perform convolutions. We demonstrate the method on a classification problem of weak lensing mass maps from two cosmological models and compare its performance with that of three baseline classifiers, two based on the power spectrum and pixel density histogram, and a classical 2D CNN. Our experimental results show that the performance of DeepSphere is always superior or equal to the baselines. For high noise levels and for data covering only a smaller fraction of the sphere, DeepSphere achieves typically 10% better classification accuracy than the baselines. Finally, we show how learned filters can be visualized to introspect the NN.Code and examples are available at https://github.com/SwissDataScienceCenter/DeepSphere.
Abstract-An emerging way to deal with highdimensional non-euclidean data is to assume that the underlying structure can be captured by a graph. Recently, ideas have begun to emerge related to the analysis of time-varying graph signals. This work aims to elevate the notion of joint harmonic analysis to a full-fledged framework denoted as Time-Vertex Signal Processing, that links together the time-domain signal processing techniques with the new tools of graph signal processing. This entails three main contributions: (a) We provide a formal motivation for harmonic time-vertex analysis as an analysis tool for the state evolution of simple Partial Differential Equations on graphs. (b) We improve the accuracy of joint filtering operators by up-to two orders of magnitude. (c) Using our joint filters, we construct time-vertex dictionaries analyzing the different scales and the local time-frequency content of a signal. The utility of our tools is illustrated in numerous applications and datasets, such as dynamic mesh denoising and classification, still-video inpainting, and source localization in seismic events. Our results suggest that joint analysis of time-vertex signals can bring benefits to regression and learning.
Mining useful clusters from high dimensional data has received significant attention of the computer vision and pattern recognition community in the recent years. Linear and non-linear dimensionality reduction has played an important role to overcome the curse of dimensionality. However, often such methods are accompanied with three different problems: high computational complexity (usually associated with the nuclear norm minimization), non-convexity (for matrix factorization methods) and susceptibility to gross corruptions in the data. In this paper we propose a principal component analysis (PCA) based solution that overcomes these three issues and approximates a low-rank recovery method for high dimensional datasets. We target the low-rank recovery by enforcing two types of graph smoothness assumptions, one on the data samples and the other on the features by designing a convex optimization problem. The resulting algorithm is fast, efficient and scalable for huge datasets with O(nlog(n)) computational complexity in the number of data samples. It is also robust to gross corruptions in the dataset as well as to the model parameters. Clustering experiments on 7 benchmark datasets with different types of corruptions and background separation experiments on 3 video datasets show that our proposed model outperforms 10 state-of-the-art dimensionality reduction models. Our theoretical analysis proves that the proposed model is able to recover approximate low-rank representations with a bounded error for clusterable data
In this paper, we present a new algorithm to estimate a signal from its short-time Fourier transform modulus (STFTM). This algorithm is computationally simple and is obtained by an acceleration of the well-known Griffin-Lim algorithm (GLA). Before deriving the algorithm, we will give a new interpretation of the GLA and formulate the phase recovery problem in an optimization form. We then present some experimental results where the new algorithm is tested on various signals. It shows not only significant improvement in speed of convergence but it does as well recover the signals with a smaller error than the traditional GLA.
Graph-based techniques emerged as a choice to deal with the dimensionality issues in modeling multivariate time series. However, there is yet no complete understanding of how the underlying structure could be exploited to ease this task. This work provides contributions in this direction by considering the forecasting of a process evolving over a graph. We make use of the (approximate) time-vertex stationarity assumption, i.e., timevarying graph signals whose first and second order statistical moments are invariant over time and correlated to a known graph topology. The latter is combined with VAR and VARMA models to tackle the dimensionality issues present in predicting the temporal evolution of multivariate time series.We find out that by projecting the data to the graph spectral domain: (i) the multivariate model estimation reduces to that of fitting a number of uncorrelated univariate ARMA models and (ii) an optimal low-rank data representation can be exploited so as to further reduce the estimation costs. In the case that the multivariate process can be observed at a subset of nodes, the proposed models extend naturally to Kalman filtering on graphs allowing for optimal tracking. Numerical experiments with both synthetic and real data validate the proposed approach and highlight its benefits over state-of-the-art alternatives.
The goal of this paper is to improve learning for multivariate processes whose structure is dependent on some known graph topology; especially when the number of available samples is much smaller than the number of variables. Typically, the graph information is incorporated into the learning process via a smoothness assumption postulating that the values supported on well-connected vertices exhibit small variations. We argue that smoothness is not enough. To capture the behavior of complex interconnected systems, such as transportation and biological networks, it is important to train expressive models, being able to reproduce a wide range of graph and temporal behaviors.Motivated by this need, this paper puts forth a novel definition of time-vertex wide-sense stationarity, or joint stationarity for short. We believe that the proposed definition is natural, at it intimately relates to existing definitions of stationarity in the time and vertex domains. We use joint stationarity to regularize learning and to reduce computational complexity in both estimation and recovery tasks. In particular, we show that for any jointly stationary process: (a) one can learn the covariance structure from O(1) samples, and (b) can solve MMSE recovery problems, such as interpolation, denoising, forecasting, in complexity that is linear to the edges and timesteps. Experiments with three datasets suggest that joint stationarity can yield significant accuracy improvements in the reconstruction effort of under-sampled problems, even when the graph is only approximately known or the process is only close to stationary.Proof of Theorem 1. By construction of the JFT basis, X[0, 0] captures the DC-offset of a signal, and condition (a) is equivalent to stating that E[x] = c1 N T . Moreover, if the graph is connected and (a) holds, at least one of E X [n 1 , τ 1 ]and E X [n 2 , τ 2 ] must be zero when n 1 = n 2 or τ 1 = τ 2 and E X [n 1 , τ 1 ]X[n 2 , τ 2 ] = E X [n 1 , τ 1 ]X[n 2 , τ 2 ] − E X [n 1 , τ 1 ] E X [n 2 , τ 2 ] = (U * J ΣU J )[(τ 1 − 1)N + n 1 , (τ 2 − 1)N + n 2 ]. Therefore, condition (b) is equivalent to stating that Σ = U J DU * J for some diagonal matrix D. In addition, (c) asserts that D[(τ −1)N +n, (τ −1)N +n] = h(λ n , ω τ ) for every n, τ .Thus taken together, (b) and (c) state that Σ = U J DU * J = U J h(Λ G , Λ T )U * J = h(L G , L T ), which is the second moment condition of a JWSS process.
We studied the ability of deep neural networks (DNNs) to restore missing audio content based on its context, a process usually referred to as audio inpainting. We focused on gaps in the range of tens of milliseconds, a condition which has not received much attention yet. The proposed DNN structure was trained on audio signals containing music and musical instruments, separately, with 64-ms long gaps. The input to the DNN was the context, i.e., the signal surrounding the gap, transformed into time-frequency (TF) coefficients. Two networks were analyzed, a DNN with complex-valued TF coefficient output and another one producing magnitude TF coefficient output, both based on the same network architecture. We found significant differences in the inpainting results between the two DNNs. In particular, we discuss the observation that the complexvalued DNN fails to produce reliable results outside the low frequency range. Further, our results were compared to those obtained from a reference method based on linear predictive coding (LPC). For instruments, our DNNs were not able to match the performance of reference method, although the magnitude network provided good results as well. For music, however, our magnitude DNN significantly outperformed the reference method, demonstrating a generally good usability of the proposed DNN structure for inpainting complex audio signals like music. This paves the road towards future, more sophisticated audio inpainting approaches based on DNNs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
334 Leonard St
Brooklyn, NY 11211
Copyright © 2023 scite Inc. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.