Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 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

A Unified View on Neural Message Passing with Opinion Dynamics for Social Networks (2310.01272v2)

Published 2 Oct 2023 in cs.SI, cs.AI, and q-bio.QM

Abstract: Social networks represent a common form of interconnected data frequently depicted as graphs within the domain of deep learning-based inference. These communities inherently form dynamic systems, achieving stability through continuous internal communications and opinion exchanges among social actors along their social ties. In contrast, neural message passing in deep learning provides a clear and intuitive mathematical framework for understanding information propagation and aggregation among connected nodes in graphs. Node representations are dynamically updated by considering both the connectivity and status of neighboring nodes. This research harmonizes concepts from sociometry and neural message passing to analyze and infer the behavior of dynamic systems. Drawing inspiration from opinion dynamics in sociology, we propose ODNet, a novel message passing scheme incorporating bounded confidence, to refine the influence weight of local nodes for message propagation. We adjust the similarity cutoffs of bounded confidence and influence weights of ODNet and define opinion exchange rules that align with the characteristics of social network graphs. We show that ODNet enhances prediction performance across various graph types and alleviates oversmoothing issues. Furthermore, our approach surpasses conventional baselines in graph representation learning and proves its practical significance in analyzing real-world co-occurrence networks of metabolic genes. Remarkably, our method simplifies complex social network graphs solely by leveraging knowledge of interaction frequencies among entities within the system. It accurately identifies internal communities and the roles of genes in different metabolic pathways, including opinion leaders, bridge communicators, and isolators.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (71)
  1. Hypergraph convolution and hypergraph attention. Pattern Recognition, 110:107637, 2021.
  2. Relational inductive biases, deep learning, and graph networks. CoRR, abs/1806.01261, 2018.
  3. Microbial community composition, co-occurrence network pattern and nitrogen transformation genera response to biochar addition in cattle manure-maize straw composting. Science of the Total Environment, 721:137759, 2020.
  4. Geometric and physical quantities improve e (3) equivariant message passing. In International Conference on Learning Representations, 2021.
  5. Distributed control of robotic networks: a mathematical approach to motion coordination algorithms, volume 27. Princeton University Press, 2009.
  6. A note on over-smoothing for graph neural networks. arXiv:2006.13318, 2020.
  7. From radial symmetry to fractal behavior of aggregation equilibria for repulsive–attractive potentials. Calculus of Variations and Partial Differential Equations, 62(1):28, 2023.
  8. Particle, kinetic, and hydrodynamic models of swarming. Mathematical modeling of collective behavior in socio-economic and life sciences, pp.  297–336, 2010a.
  9. Self-propelled interacting particle systems with roosting force. Mathematical Models and Methods in Applied Sciences, 20(supp01):1533–1552, 2010b.
  10. GRAND: Graph neural diffusion. In ICML, 2021. URL https://openreview.net/forum?id=_1fu_cjsaRE.
  11. Simple and deep graph convolutional networks. In ICML, pp.  1725–1735. PMLR, 2020.
  12. Neural ordinary differential equations. In NeurIPS, volume 31, 2018.
  13. Adaptive universal generalized pagerank graph neural network. In ICLR, 2021. URL https://openreview.net/forum?id=n6jl7fLxrP.
  14. You are allset: A multiset function framework for hypergraph neural networks. In International Conference on Learning Representations, 2022.
  15. Towards the biogeography of prokaryotic genes. Nature, 601(7892):252–256, 2022.
  16. Emergent behavior in flocks. IEEE Transactions on Automatic Control, 52(5):852–862, 2007.
  17. Morris H. DeGroot. Reaching a consensus. Journal of the American Statistical Association, 69(345):118–121, 1974. ISSN 01621459. URL http://www.jstor.org/stable/2285509.
  18. Hnhn: Hypergraph networks with hyperedge neurons. arXiv:2006.12278, 2020.
  19. Self-propelled particles with soft-core interactions: patterns, stability, and collapse. Physical review letters, 96(10):104302, 2006.
  20. Emergent behaviors of the Cucker-Smale ensemble under attractive-repulsive couplings and rayleigh frictions. Mathematical Models and Methods in Applied Sciences, 29(07):1349–1385, 2019.
  21. Hypergraph neural networks. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pp.  3558–3565, 2019.
  22. Fast graph representation learning with PyTorch Geometric. In ICLR Workshop on Representation Learning on Graphs and Manifolds, 2019.
  23. John RP French Jr. A formal theory of social power. Psychological review, 63(3):181, 1956.
  24. Hypergraph Learning: Methods and Practices. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(5), May 2022. ISSN 1939-3539.
  25. Using fuzzy logic to leverage html markup for web page representation. IEEE Transactions on Fuzzy Systems, 25(4):919–933, 2016.
  26. Neural message passing for quantum chemistry. In ICML, 2017.
  27. Algebraic graph theory, volume 207. Springer Science & Business Media, 2001.
  28. William L Hamilton. Graph representation learning. Synthesis Lectures on Artifical Intelligence and Machine Learning, 14(3):1–159, 2020.
  29. Inductive representation learning on large graphs. In NeurIPS, 2017.
  30. Frank Harary. A criterion for unanimity in french’s theory of social power. 1959.
  31. Dirk Helbing. Quantitative sociodynamics: stochastic methods and models of social interaction processes. Springer Science & Business Media, 2010.
  32. Formation of clumps and patches in self-aggregation of finite-size particles. Physica D: Nonlinear Phenomena, 220(2):183–196, 2006.
  33. Unignn: a unified framework for graph and hypergraph neural networks. arXiv:2105.00956, 2021.
  34. Collective Dynamics of Opposing Groups with Stochastic Communication. Vietnam Journal of Mathematics, 49(3):619–636, September 2021. ISSN 2305-221X, 2305-2228. doi: 10.1007/s10013-020-00430-2. URL https://link.springer.com/10.1007/s10013-020-00430-2.
  35. Semi-supervised classification with graph convolutional networks. In ICLR, 2017.
  36. Stability of ring patterns arising from two-dimensional particle interactions. Physical Review E, 84(1):015203, 2011.
  37. Emergent behaviour in multi-particle systems with non-local interactions, 2013.
  38. Metabolic modeling of species interaction in the human microbiome elucidates community-level assembly rules. Proceedings of the National Academy of Sciences, 110(31):12804–12809, 2013.
  39. Insights into the ecology, evolution, and metabolism of the widespread woesearchaeotal lineages. Microbiome, 6:1–16, 2018.
  40. Framelet message passing. arXiv:2302.14806, 2023.
  41. Comparison of prokaryotes between mount everest and the mariana trench. Microbiome, 10(1):215, 2022.
  42. Function and functional redundancy in microbial systems. Nature ecology & evolution, 2(6):936–943, 2018.
  43. Automating the construction of internet portals with machine learning. Information Retrieval, 3(2):127–163, 2000.
  44. Geometric deep learning on graphs and manifolds using mixture model CNNs. In CVPR, pp.  5115–5124, 2017.
  45. Jacob L Moreno. Sociometry, experimental method and the science of society. Lulu. com, 2012.
  46. Jacob Levy Moreno. Who shall survive?: A new approach to the problem of human interrelations. 1934.
  47. Heterophilious dynamics enhances consensus. SIAM Review, 56(4):577–621, 2014.
  48. Query-driven active surveying for collective classification. In 10th International Workshop on Mining and Learning with Graphs, volume 8, pp.  1, 2012.
  49. Robert Z Norman et al. Structural models: An introduction to the theory of directed graphs. 1965.
  50. Revisiting graph neural networks: All we have is low-pass filters. arXiv:1905.09550, 2019.
  51. Graph neural networks exponentially lose expressive power for node classification. In ICLR, 2019.
  52. Geom-GCN: geometric graph convolutional networks. In ICLR, 2020. URL https://openreview.net/forum?id=S1e2agrFvS.
  53. Graph neural ordinary differential equations. In AAAI Workshop on Deep Learning on Graphs: Methodologies and Applications, 2020.
  54. A tutorial on modeling and analysis of dynamic social networks. part i. Annual Reviews in Control, 43:65–79, 2017.
  55. Opinion dynamics and bounded confidence: models, analysis and simulation. 2002.
  56. Distributed consensus in multi-vehicle cooperative control, volume 27. Springer, 2008.
  57. Graph-coupled oscillator networks. In International Conference on Machine Learning, pp.  18888–18909. PMLR, 2022.
  58. Collective classification in network data. AI Magazine, 29(3):93–93, 2008.
  59. Pitfalls of graph neural network evaluation. arXiv:1811.05868, 2018.
  60. Microbial diversity in extreme environments. Nature Reviews Microbiology, 20(4):219–235, 2022.
  61. Nonlinear higher-order label spreading. In Proceedings of the Web Conference 2021, pp.  2402–2413, 2021.
  62. Graph attention networks. In ICLR, 2018.
  63. Equivariant hypergraph diffusion neural operators. arXiv:2207.06680, 2022.
  64. ACMP: Allen-cahn message passing with attractive and repulsive forces for graph neural networks. In ICLR, 2023. URL https://openreview.net/forum?id=4fZc_79Lrqs.
  65. Wolfgang Weidlich. Sociodynamics: A systematic approach to mathematical modelling in the social sciences. Courier Corporation, 2006.
  66. Norbert Wiener. The human use of human beings: Cybernetics and society. Number 320. Da capo press, 1988.
  67. Continuous graph neural networks. In ICML, pp.  10432–10441, 2020.
  68. Hypergcn: A new method for training graph convolutional networks on hypergraphs. Advances in neural information processing systems, 32, 2019.
  69. Mengbin Ye. Opinion dynamics and the evolution of social power in social networks. Springer, 2019.
  70. PairNorm: Tackling oversmoothing in GNNs. In ICLR, 2020. URL https://openreview.net/forum?id=rkecl1rtwB.
  71. Beyond homophily in graph neural networks: Current limitations and effective designs. In NeurIPS, volume 33, pp.  7793–7804, 2020.
Citations (1)

Summary

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