Kernel-based Reconstruction of Graph Signals
arXiv:1605.07174 · doi:10.1109/TSP.2016.2620116
Abstract
A number of applications in engineering, social sciences, physics, and biology involve inference over networks. In this context, graph signals are widely encountered as descriptors of vertex attributes or features in graph-structured data. Estimating such signals in all vertices given noisy observations of their values on a subset of vertices has been extensively analyzed in the literature of signal processing on graphs (SPoG). This paper advocates kernel regression as a framework generalizing popular SPoG modeling and reconstruction and expanding their capabilities. Formulating signal reconstruction as a regression task on reproducing kernel Hilbert spaces of graph signals permeates benefits from statistical learning, offers fresh insights, and allows for estimators to leverage richer forms of prior information than existing alternatives. A number of SPoG notions such as bandlimitedness, graph filters, and the graph Fourier transform are naturally accommodated in the kernel framework. Additionally, this paper capitalizes on the so-called representer theorem to devise simpler versions of existing Thikhonov regularized estimators, and offers a novel probabilistic interpretation of kernel methods on graphs based on graphical models. Motivated by the challenges of selecting the bandwidth parameter in SPoG estimators or the kernel map in kernel-based methods, the present paper further proposes two multi-kernel approaches with complementary strengths. Whereas the first enables estimation of the unknown bandwidth of bandlimited signals, the second allows for efficient graph filter selection. Numerical tests with synthetic as well as real data demonstrate the merits of the proposed methods relative to state-of-the-art alternatives.
Submitted May 2016
References in corpus (3)
Cited by in corpus (39)
- Graph Learning: A Survey
- Adaptive Graph Signal Processing: Algorithms and Optimal Sampling Strategies
- Adaptive Propagation Graph Convolutional Network
- Filtering Random Graph Processes Over Random Time-Varying Graphs
- Semi-Blind Inference of Topologies and Dynamical Processes over Graphs
- Reconstruction of Time-varying Graph Signals via Sobolev Smoothness
- Flow Smoothing and Denoising: Graph Signal Processing in the Edge-Space
- Online Graph-Adaptive Learning with Scalability and Privacy
- Inference of Spatio-Temporal Functions over Graphs via Multi-Kernel Kriged Kalman Filtering
- Vector-Valued Graph Trend Filtering with Non-Convex Penalties
- Canonical Correlation Analysis of Datasets with a Common Source Graph
- Distributed Training of Graph Convolutional Networks
- Sampling of graph signals via randomized local aggregations
- Gegenbauer Graph Neural Networks for Time-varying Signal Reconstruction
- Stochastic Local Interaction Model with Sparse Precision Matrix for Space-Time Interpolation
- Graph Signal Reconstruction Techniques for IoT Air Pollution Monitoring Platforms
- Matrix completion and extrapolation via kernel regression
- Reconstructing nodal pressures in water distribution systems with graph neural networks
- A Review of Graph-Powered Data Quality Applications for IoT Monitoring Sensor Networks
- Time-varying Signals Recovery via Graph Neural Networks
- Multiple Kernel Representation Learning on Networks
- Detecting Localized Categorical Attributes on Graphs
- Graph Learning for Spatiotemporal Signals with Long- and Short-Term Characterization
- Node-Adaptive Regularization for Graph Signal Reconstruction
- Hilbert Transform, Analytic Signal, and Modulation Analysis for Graph Signal Processing
- Gaussian Kernel Variance For an Adaptive Learning Method on Signals Over Graphs
- Supervised Linear Regression for Graph Learning from Graph Signals
- Semi-Supervised Learning on Graphs with Feature-Augmented Graph Basis Functions
- Folded Graph Signals: Sensing with Unlimited Dynamic Range
- Blind Community Detection from Low-rank Excitations of a Graph Filter
- Non-separable Spatio-temporal Graph Kernels via SPDEs
- Distributed Optimization of Graph Convolutional Network using Subgraph Variance
- Recursive Prediction of Graph Signals with Incoming Nodes
- Nonlinear Dimensionality Reduction on Graphs
- Fast Decentralized Linear Functions Over Edge Fluctuating Graphs
- Regularized Recovery by Multi-order Partial Hypergraph Total Variation
- Estimating Network Processes via Blind Identification of Multiple Graph Filters
- Enhancing Geometric Deep Learning via Graph Filter Deconvolution
- A Novel Scheme for Support Identification and Iterative Sampling of Bandlimited Graph Signals