mlsanityData to 7 Oct 2026

A graph representation based on fluid diffusion model for data analysis: theoretical aspects and enhanced community detection

arXiv 2112.04388 ↗First posted 7 Dec 2021cs.SI cs.LGcited by 1

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Representing data by means of graph structures identifies one of the most valid approach to extract information in several data analysis applications. This is especially true when multimodal datasets are investigated, as records collected by means of diverse sensing strategies are taken into account and explored. Nevertheless, classic graph signal processing is based on a model for information propagation that is configured according to heat diffusion mechanism. This system provides several constraints and assumptions on the data properties that might be not valid for multimodal data analysis, especially when large scale datasets collected from heterogeneous sources are considered, so that the accuracy and robustness of the outcomes might be severely jeopardized. In this paper, we introduce a novel model for graph definition based on fluid diffusion. The proposed approach improves the ability of graph-based data analysis to take into account several issues of modern data analysis in operational scenarios, so to provide a platform for precise, versatile, and efficient understanding of the phenomena underlying the records under exam, and to fully exploit the potential provided by the diversity of the records in obtaining a thorough characterization of the data and their significance. In this work, we focus our attention to using this fluid diffusion model to drive a community detection scheme, i.e., to divide multimodal datasets into many groups according to similarity among nodes in an unsupervised fashion. Experimental results achieved by testing real multimodal datasets in diverse application scenarios show that our method is able to strongly outperform state-of-the-art schemes for community detection in multimodal data analysis.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 45 of its 140 references that are in the map. First posted on arXiv 7 Dec 2021.

Builds on

45 of 140 references.

References · 45

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  6. 2019Simplifying Graph Convolutional Networkscited by 1,470
  7. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  8. 2017Multimodal Machine Learning: A Survey and Taxonomycited by 1,004
  9. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 624
  10. 2018Deep Learning on Graphs: A Surveycited by 393
  11. 2020SIGN: Scalable Inception Graph Neural Networkscited by 283
  12. 2020Generalization and Representational Limits of Graph Neural Networkscited by 217
33 more
  1. 2016How to learn a graph from smooth signalscited by 146
  2. 2021Graph Learning: A Surveycited by 140
  3. 2018SpectralNet: Spectral Clustering using Deep Neural Networkscited by 94
  4. 2021Graph-based Semi-supervised Learning: A Comprehensive Reviewcited by 79
  5. 2020Graph signal processing for machine learning: A review and new perspectivescited by 73
  6. 2015A Review of Feature Selection Methods Based on Mutual Informationcited by 67
  7. 2020Deep Learning for Community Detection: Progress, Challenges and Opportunitiescited by 42
  8. 2017Attributed Social Network Embeddingcited by 34
  9. 2014Covariate-assisted spectral clusteringcited by 29
  10. 2015Random Walks, Markov Processes and the Multiscale Modular Organization of Complex Networkscited by 24
  11. 2014Learning Latent Block Structure in Weighted Networkscited by 22
  12. 2018Analysis of spectral clustering algorithms for community detection: the general bipartite settingcited by 20
  13. 2017Community detection, link prediction, and layer interdependence in multilayer networkscited by 17
  14. 2019Learnable Manifold Alignment (LeMA) : A Semi-supervised Cross-modality Learning Framework for Land Cover and Land Use Classificationcited by 17
  15. 2017Fluid Communities: A Competitive, Scalable and Diverse Community Detection Algorithmcited by 16
  16. 2020Kernel-based Graph Learning from Smooth Signals: A Functional Viewpointcited by 12
  17. 2015Community Detection in Networks with Node Featurescited by 10
  18. 2018Forman-Ricci Curvature for Hypergraphscited by 9
  19. 2019Deep Network Embedding for Graph Representation Learning in Signed Networkscited by 9
  20. 2018Multiscale dynamical embeddings of complex networkscited by 8
  21. 2019Optimal Laplacian regularization for sparse spectral community detectioncited by 5
  22. 2020Hierarchical community structure in networkscited by 5
  23. 2018Segmentation of Scanning Tunneling Microscopy Images Using Variational Methods and Empirical Waveletscited by 4
  24. 2018Beyond Pham's algorithm for joint diagonalizationcited by 4
  25. 2013Generalized Measures for the Evaluation of Community Detection Methodscited by 3
  26. 2013Community detection and graph partitioningcited by 3
  27. 2016Additive Approximation Algorithms for Modularity Maximizationcited by 3
  28. 2019Cross-domain Network Representationscited by 3
  29. 2021Enhancing ensemble learning and transfer learning in multimodal data analysis by adaptive dimensionality reductioncited by 2
  30. 2016Community detection in networks using self-avoiding random walkscited by 1
  31. 2016Multiple-View Spectral Clustering for Group-wise Functional Community Detectioncited by 1
  32. 2017Multimodal Clustering for Community Detectioncited by 1
  33. 2020Community detection based on first passage probabilitiescited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Improving embedding of graphs with missing data by soft manifoldscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Towards understanding Diffusion Models (on Graphs)
  2. 2026Graph Residual Conjugate Diffusion: SNR-Equalized Heat Flow for Graph Signals
  3. 2025DiffGraph: Heterogeneous Graph Diffusion Model
  4. 2024Advancing Graph Generation through Beta Diffusion
  5. 2025Graph Representation Learning with Diffusion Generative Models
  6. 2025Graph-Aware Diffusion for Signal Generation
  7. 2026Discrete Diffusion for Large Graph Generation via Structural Candidate Restriction
  8. 2026Graph Representation via Elements of Discrete Morse and Cobordism Theories