mlsanityData to 7 Oct 2026

Graph signal processing for machine learning: A review and new perspectives

arXiv 2007.16061 ↗First posted 31 Jul 2020cs.LG cs.SI eess.SPcited by 73

Not on the map. Why?

Abstract (arXiv)

The effective representation, processing, analysis, and visualization of large-scale structured data, especially those related to complex domains such as networks and graphs, are one of the key questions in modern machine learning. Graph signal processing (GSP), a vibrant branch of signal processing models and algorithms that aims at handling data supported on graphs, opens new paths of research to address this challenge. In this article, we review a few important contributions made by GSP concepts and tools, such as graph filters and transforms, to the development of novel machine learning algorithms. In particular, our discussion focuses on the following three aspects: exploiting data structure and relational priors, improving data and computational efficiency, and enhancing model interpretability. Furthermore, we provide new perspectives on future development of GSP techniques that may serve as a bridge between applied mathematics and signal processing on one side, and machine learning and network science on the other. Cross-fertilization across these different disciplines may help unlock the numerous challenges of complex data analysis in the modern age.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 10; 2023: 18; 2024: 18; 2025: 13; 2026: 5.

73 papers.

Sort:

By area:

  1. 2023Specformer: Spectral Graph Neural Networks Meet Transformerscited by 102
  2. 2021Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patternscited by 95
  3. 2022Graph Filters for Signal Processing and Machine Learning on Graphscited by 53
  4. 2021How Powerful is Graph Convolution for Recommendation?cited by 50
  5. 2021Interpretable Stability Bounds for Spectral Graph Filterscited by 28
  6. 2023A Survey on Spectral Graph Neural Networkscited by 26
  7. 2021Graph Structural Attack by Perturbing Spectral Distancecited by 16
  8. 2023Combinatorial Complexes: Bridging the Gap Between Cell Complexes and Hypergraphscited by 15
  9. 2021Modeling Ideological Salience and Framing in Polarized Online Groups with Graph Neural Networks and Structured Sparsitycited by 9
  10. 2023On Manipulating Signals of User-Item Graph: A Jacobi Polynomial-based Graph Collaborative Filteringcited by 9
  11. 2023Fairness-Aware Graph Filter Designcited by 8
  12. 2024Redesigning graph filter-based GNNs to relax the homophily assumptioncited by 8
38 more
  1. 2023Bures-Wasserstein Means of Graphscited by 6
  2. 2024Convolutional Learning on Directed Acyclic Graphscited by 6
  3. 2024A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectivenesscited by 6
  4. 2025Learning Sheaf Laplacian Optimizing Restriction Mapscited by 6
  5. 2021On the Stability of Low Pass Graph Filter With a Large Number of Edge Rewirescited by 5
  6. 2023Representing Edge Flows on Graphs via Sparse Cell Complexescited by 5
  7. 2021Laplacian Constrained Precision Matrix Estimation: Existence and High Dimensional Consistencycited by 4
  8. 2021Graph Neural Networks with Parallel Neighborhood Aggregations for Graph Classificationcited by 4
  9. 2022Graph Normalized-LMP Algorithm for Signal Estimation Under Impulsive Noisecited by 4
  10. 2022Complex-Value Spatio-temporal Graph Convolutional Neural Networks and its Applications to Electric Power Systems AIcited by 4
  11. 2022Graph Federated Learning for CIoT Devices in Smart Home Applicationscited by 4
  12. 2023Graph Classification Gaussian Processes via Spectral Featurescited by 4
  13. 2023TabGSL: Graph Structure Learning for Tabular Data Predictioncited by 3
  14. 2024Frequency-aware Graph Signal Processing for Collaborative Filteringcited by 3
  15. 2024Spectral GNN via Two-dimensional (2-D) Graph Convolutioncited by 3
  16. 2024LLM Online Spatial-temporal Signal Reconstruction Under Noisecited by 3
  17. 2025A Few Moments Please: Scalable Graphon Learning via Moment Matchingcited by 3
  18. 2025DoFlow: Flow-based Generative Models for Interventional and Counterfactual Forecasting on Time Seriescited by 3
  19. 2026Spatiotemporal Imputation with Graph-Informed Flow Matchingcited by 3
  20. 2022Towards Understanding Graph Neural Networks: An Algorithm Unrolling Perspectivecited by 2
  21. 2023Fairness-aware Optimal Graph Filter Designcited by 2
  22. 2024Optimizing k in kNN Graphs with Graph Learning Perspectivecited by 2
  23. 2024Through the Dual-Prism: A Spectral Perspective on Graph Data Augmentation for Graph Classificationcited by 2
  24. 2024Network Topology Inference from Smooth Signals Under Partial Observabilitycited by 2
  25. 2025Heterogeneous Graph Structure Learning through the Lens of Data-generating Processescited by 2
  26. 2025Partition-wise Graph Filtering: A Unified Perspective Through the Lens of Graph Coarseningcited by 2
  27. 2021A graph representation based on fluid diffusion model for data analysis: theoretical aspects and enhanced community detectioncited by 1
  28. 2022Graph Convolutional Neural Networks Sensitivity under Probabilistic Error Modelcited by 1
  29. 2023Barron Space for Graph Convolution Neural Networkscited by 1
  30. 2023Improving embedding of graphs with missing data by soft manifoldscited by 1
  31. 2024Adaptive Least Mean Squares Graph Neural Networks and Online Graph Signal Estimationcited by 1
  32. 2024Bayesian Optimization of Functions over Node Subsets in Graphscited by 1
  33. 2024Low Rank Multi-Dictionary Selection at Scalecited by 1
  34. 2024Online Graph Filtering Over Expanding Graphscited by 1
  35. 2024Learning signals defined on graphs with optimal transport and Gaussian process regressioncited by 1
  36. 2024Learning Graph Filters for Structure-Function Coupling based Hub Node Identificationcited by 1
  37. 2024Graph Signal Adaptive Message Passingcited by 1
  38. 2025Leveraging Low-rank Factorizations of Conditional Correlation Matrices in Graph Learningcited by 1

50 most cited of 73 All 73 (JSON)