Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
166 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Influential Simplices Mining via Simplicial Convolutional Network (2307.05841v1)

Published 11 Jul 2023 in cs.SI, cs.AI, and physics.soc-ph

Abstract: Simplicial complexes have recently been in the limelight of higher-order network analysis, where a minority of simplices play crucial roles in structures and functions due to network heterogeneity. We find a significant inconsistency between identifying influential nodes and simplices. Therefore, it remains elusive how to characterize simplices' influence and identify influential simplices, despite the relative maturity of research on influential nodes (0-simplices) identification. Meanwhile, graph neural networks (GNNs) are potent tools that can exploit network topology and node features simultaneously, but they struggle to tackle higher-order tasks. In this paper, we propose a higher-order graph learning model, named influential simplices mining neural network (ISMnet), to identify vital h-simplices in simplicial complexes. It can tackle higher-order tasks by leveraging novel higher-order presentations: hierarchical bipartite graphs and higher-order hierarchical (HoH) Laplacians, where targeted simplices are grouped into a hub set and can interact with other simplices. Furthermore, ISMnet employs learnable graph convolutional operators in each HoH Laplacian domain to capture interactions among simplices, and it can identify influential simplices of arbitrary order by changing the hub set. Empirical results demonstrate that ISMnet significantly outperforms existing methods in ranking 0-simplices (nodes) and 2-simplices. In general, this novel framework excels in identifying influential simplices and promises to serve as a potent tool in higher-order network analysis.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (45)
  1. F. Battiston, G. Cencetti, I. Iacopini, V. Latora, M. Lucas, A. Patania, J.-G. Young, and G. Petri, “Networks beyond pairwise interactions: Structure and dynamics,” Physics Reports, vol. 874, pp. 1–92, 2020.
  2. J. Grilli, G. Barabás, M. J. Michalska-Smith, and S. Allesina, “Higher-order interactions stabilize dynamics in competitive network models,” Nature, vol. 548, no. 7666, pp. 210–213, 2017.
  3. D. Centola, “The spread of behavior in an online social network experiment,” Science, vol. 329, no. 5996, pp. 1194–1197, 2010.
  4. E. Ganmor, R. Segev, and E. Schneidman, “Sparse low-order interaction network underlies a highly correlated and learnable neural population code,” Proceedings of the National Academy of Sciences, vol. 108, pp. 9679 – 9684, 2011.
  5. F. Battiston, E. Amico, A. Barrat, G. Bianconi, G. Ferraz de Arruda, B. Franceschiello, I. Iacopini, S. Kéfi, V. Latora, and Y. Moreno, “The physics of higher-order interactions in complex systems,” Nature Physics, vol. 17, no. 10, pp. 1093–1098, 2021.
  6. Y. Zeng, Y. Huang, X.-L. Ren, and L. Lü, “Identifying vital nodes through augmented random walks on higher-order networks,” arXiv preprint arXiv:2305.06898, 2023.
  7. R. Pastor-Satorras, C. Castellano, P. Van Mieghem, and A. Vespignani, “Epidemic processes in complex networks,” Reviews of modern physics, vol. 87, no. 3, p. 925, 2015.
  8. A. Braunstein, L. Dall’Asta, G. Semerjian, and L. Zdeborová, “Network dismantling,” Proceedings of the National Academy of Sciences, vol. 113, no. 44, pp. 12 368–12 373, 2016.
  9. O. T. Courtney and G. Bianconi, “Generalized network structures: The configuration model and the canonical ensemble of simplicial complexes,” Physical Review E, vol. 93, no. 6, p. 062311, 2016.
  10. L. Lü, D. Chen, X.-L. Ren, Q.-M. Zhang, Y.-C. Zhang, and T. Zhou, “Vital nodes identification in complex networks,” Physics Reports, vol. 650, pp. 1–63, 2016.
  11. X.-L. Ren, N. Gleinig, D. Helbing, and N. Antulov-Fantulin, “Generalized network dismantling,” Proceedings of the National Academy of Sciences, vol. 116, pp. 6554 – 6559, 2019.
  12. G. Zhao, P. Jia, A. Zhou, and B. Zhang, “Infgcn: Identifying influential nodes in complex networks with graph convolutional networks,” Neurocomputing, vol. 414, pp. 18–26, 2020.
  13. S. Kumar, A. Mallik, A. Khetarpal, and B. Panda, “Influence maximization in social networks using graph embedding and graph neural network,” Information Sciences, vol. 607, pp. 1617–1636, 2022.
  14. T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” in International Conference on Learning Representations (ICLR), 2017.
  15. L. Lü, Y.-C. Zhang, C. H. Yeung, and T. Zhou, “Leaders in social networks, the delicious case,” PloS One, vol. 6, no. 6, p. e21202, 2011.
  16. J. E. Hirsch, “An index to quantify an individual’s scientific research output,” Proceedings of the National academy of Sciences, vol. 102, no. 46, pp. 16 569–16 572, 2005.
  17. M. Kitsak, L. K. Gallos, S. Havlin, F. Liljeros, L. Muchnik, H. E. Stanley, and H. A. Makse, “Identification of influential spreaders in complex networks,” Nature physics, vol. 6, no. 11, pp. 888–893, 2010.
  18. L. C. Freeman et al., “Centrality in social networks: Conceptual clarification,” Social network: critical concepts in sociology. Londres: Routledge, vol. 1, pp. 238–263, 2002.
  19. L. C. Freeman, “A set of measures of centrality based on betweenness,” Sociometry, pp. 35–41, 1977.
  20. P. Bonacich, “Some unique properties of eigenvector centrality,” Social networks, vol. 29, no. 4, pp. 555–564, 2007.
  21. S. Brin and L. Page, “The anatomy of a large-scale hypertextual web search engine,” Computer networks and ISDN systems, vol. 30, no. 1-7, pp. 107–117, 1998.
  22. Z. Qu, Y. Huang, and M. Zheng, “A novel coherence-based quantum steganalysis protocol,” Quantum Information Processing, vol. 19, p. 362, 2020.
  23. A. Ghavasieh, M. Stella, J. D. Biamonte, and M. D. Domenico, “Unraveling the effects of multiscale network entanglement on empirical systems,” Communications Physics, vol. 4, pp. 1–10, 2021.
  24. M. Curado, L. Tortosa, and J. F. Vicent, “A novel measure to identify influential nodes: Return random walk gravity centrality,” Information Sciences, 2023.
  25. D. I. Shuman, S. K. Narang, P. Frossard, A. Ortega, and P. Vandergheynst, “The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains,” IEEE Signal Processing Magazine, vol. 30, no. 3, pp. 83–98, 2013.
  26. J. Bruna, W. Zaremba, A. Szlam, and Y. LeCun, “Spectral networks and deep locally connected networks on graphs,” in 2nd International Conference on Learning Representations, ICLR 2014, 2014.
  27. M. Defferrard, X. Bresson, and P. Vandergheynst, “Convolutional neural networks on graphs with fast localized spectral filtering,” Advances in neural information processing systems, vol. 29, pp. 3838–3845, 2016.
  28. E.-Y. Yu, Y.-P. Wang, Y. Fu, D.-B. Chen, and M. Xie, “Identifying critical nodes in complex networks via graph convolutional networks,” Knowledge-Based Systems, vol. 198, p. 105893, 2020.
  29. S. Munikoti, L. Das, and B. Natarajan, “Scalable graph neural network-based framework for identifying critical nodes and links in complex networks,” Neurocomputing, vol. 468, pp. 211–221, 2022.
  30. Y. Ou, Q. Guo, J.-L. Xing, and J.-G. Liu, “Identification of spreading influence nodes via multi-level structural attributes based on the graph convolutional network,” Expert Systems with Applications, p. 117515, 2022.
  31. C. Bodnar, F. Frasca, Y. Wang, N. Otter, G. F. Montufar, P. Lio, and M. Bronstein, “Weisfeiler and lehman go topological: Message passing simplicial networks,” in International Conference on Machine Learning (ICML), 2021, pp. 1026–1037.
  32. M. Balcilar, R. Guillaume, P. Héroux, B. Gaüzère, S. Adam, and P. Honeine, “Analyzing the expressive power of graph neural networks in a spectral perspective,” in Proceedings of the International Conference on Learning Representations (ICLR), 2021.
  33. M. He, Z. Wei, and J.-R. Wen, “Convolutional neural networks on graphs with chebyshev approximation, revisited,” in Advances in Neural Information Processing Systems, 2022.
  34. E. Chien, J. Peng, P. Li, and O. Milenkovic, “Adaptive universal generalized pagerank graph neural network,” in International Conference on Learning Representations, 2020.
  35. M. He, Z. Wei, H. Xu et al., “Bernnet: Learning arbitrary graph spectral filters via bernstein approximation,” Advances in Neural Information Processing Systems, vol. 34, pp. 14 239–14 251, 2021.
  36. X. Wang and M. Zhang, “How powerful are spectral graph neural networks,” in International Conference on Machine Learning.   PMLR, 2022, pp. 23 341–23 362.
  37. A. L. Lloyd and R. M. May, “How viruses spread among computers and people,” Science, vol. 292, no. 5520, pp. 1316–1317, 2001.
  38. I. Iacopini, G. Petri, A. Barrat, and V. Latora, “Simplicial models of social contagion,” Nature communications, vol. 10, no. 1, pp. 1–9, 2019.
  39. C. Castellano and R. Pastor-Satorras, “Thresholds for epidemic spreading in networks,” Physical Review Letters, vol. 105, no. 21, p. 218701, 2010.
  40. A. R. Benson, R. Abebe, M. T. Schaub, A. Jadbabaie, and J. Kleinberg, “Simplicial closure and higher-order link prediction,” Proceedings of the National Academy of Sciences, vol. 115, no. 48, pp. E11 221–E11 230, 2018.
  41. R. M. Ewing, P. Chu, F. Elisma, H. Li, P. Taylor, S. Climie, L. McBroom-Cerajewski, M. D. Robinson, L. O’Connor, M. Li et al., “Large-scale mapping of human protein–protein interactions by mass spectrometry,” Molecular systems biology, vol. 3, no. 1, p. 89, 2007.
  42. J. Leskovec, J. Kleinberg, and C. Faloutsos, “Graph evolution: Densification and shrinking diameters,” ACM transactions on Knowledge Discovery from Data (TKDD), vol. 1, no. 1, pp. 2–es, 2007.
  43. S. Aref, D. Friggens, and S. Hendy, “Analysing scientific collaborations of new zealand institutions using scopus bibliometric data,” in Proceedings of the Australasian Computer Science Week Multiconference, 2018, pp. 1–10.
  44. L. E. Rocha, F. Liljeros, and P. Holme, “Simulated epidemics in an empirical spatiotemporal network of 50,185 sexual contacts,” PLoS computational biology, vol. 7, no. 3, p. e1001109, 2011.
  45. J.-F. Rual, K. Venkatesan, T. Hao, T. Hirozane-Kishikawa, A. Dricot, N. Li, G. F. Berriz, F. D. Gibbons, M. Dreze, N. Ayivi-Guedehoussou et al., “Towards a proteome-scale map of the human protein–protein interaction network,” Nature, vol. 437, no. 7062, pp. 1173–1178, 2005.
Citations (5)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now