Papers
Topics
Authors
Recent
Detailed Answer
Quick Answer
Concise responses based on abstracts only
Detailed Answer
Well-researched responses based on abstracts and relevant paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses
Gemini 2.5 Flash
Gemini 2.5 Flash 79 tok/s
Gemini 2.5 Pro 49 tok/s Pro
GPT-5 Medium 15 tok/s Pro
GPT-5 High 15 tok/s Pro
GPT-4o 100 tok/s Pro
Kimi K2 186 tok/s Pro
GPT OSS 120B 445 tok/s Pro
Claude Sonnet 4 36 tok/s Pro
2000 character limit reached

Visual Analytics of Multivariate Networks with Representation Learning and Composite Variable Construction (2303.09590v3)

Published 16 Mar 2023 in cs.SI, cs.HC, and cs.LG

Abstract: Multivariate networks are commonly found in real-world data-driven applications. Uncovering and understanding the relations of interest in multivariate networks is not a trivial task. This paper presents a visual analytics workflow for studying multivariate networks to extract associations between different structural and semantic characteristics of the networks (e.g., what are the combinations of attributes largely relating to the density of a social network?). The workflow consists of a neural-network-based learning phase to classify the data based on the chosen input and output attributes, a dimensionality reduction and optimization phase to produce a simplified set of results for examination, and finally an interpreting phase conducted by the user through an interactive visualization interface. A key part of our design is a composite variable construction step that remodels nonlinear features obtained by neural networks into linear features that are intuitive to interpret. We demonstrate the capabilities of this workflow with multiple case studies on networks derived from social media usage and also evaluate the workflow with qualitative feedback from experts.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (82)
  1. https://github.com/hylu1994/Network-CV.
  2. J. Albert. Sabermetrics: The past, the present, and the future. In J. A. Gallian, ed., Mathematics and Sports, p. 3–14. Mathematical Association of America, 2010. doi: 10 . 5948/UPO9781614442004 . 002
  3. Mining communities and their descriptions on attributed graphs: A survey. Data Min Knowl Disc, 35(3):661–687, 2021. doi: 10 . 1007/s10618-021-00741-z
  4. Time Curves: Folding time to visualize patterns of temporal evolution in data. IEEE Trans Vis Comput Graph, 22(1):559–568, 2016. doi: 10 . 1109/TVCG . 2015 . 2467851
  5. A taxonomy and survey of dynamic graph visualization. Comput Graph Forum, 36(1):133–159, 2017. doi: 10 . 1111/cgf . 12791
  6. D33{}^{3}start_FLOATSUPERSCRIPT 3 end_FLOATSUPERSCRIPT data-driven documents. IEEE Trans Vis Comput Graph, 17(12):2301–2309, 2011. doi: 10 . 1109/TVCG . 2011 . 185
  7. Uncovering sociological effect heterogeneity using tree-based machine learning. Sociol Methodol, 51(2):189–223, 2021. doi: 10 . 1177/0081175021993503
  8. M. Cavallo and Ç. Demiralp. A visual interaction framework for dimensionality reduction based data exploration. In Proc. CHI, pp. 1–13, 2018. doi: 10 . 1145/3173574 . 3174209
  9. Social media and network boundaries among college students: Reconstructing companions, conversations, and contact circles. Taiwanese Sociology, 37:1–46, 2019. Written in Chinese. doi: 10 . 6676/TS . 201906_(37) . 02
  10. The state of the art in enhancing trust in machine learning models with the use of visualizations. Comput Graph Forum, 39(3):713–756, 2020. doi: 10 . 1111/cgf . 14034
  11. t-viSNE: Interactive assessment and interpretation of t-SNE projections. IEEE Trans Vis Comput Graph, 26(8):2696–2714, 2020. doi: 10 . 1109/tvcg . 2020 . 2986996
  12. Calliope-Net: Automatic generation of graph data facts via annotated node-link diagrams. IEEE Trans Vis Comput Graph, 2023 (forthcoming). doi: 10 . 48550/arXiv . 2308 . 06441
  13. Social capital I: Measurement and associations with economic mobility. Nature, 608:108–121, 2022. doi: 10 . 3386/w30313
  14. Visualization techniques for categorical analysis of social networks with multiple edge sets. Soc Networks, 37:56–64, 2014. doi: 10 . 1016/j . socnet . 2013 . 12 . 002
  15. J. P. Cunningham and Z. Ghahramani. Linear dimensionality reduction: Survey, insights, and generalizations. J. Mach. Learn. Res., 16(1):2859–2900, 2015. doi: 10 . 48550/arXiv . 1406 . 0873
  16. Dimensionality reduction for large-scale neural recordings. Nat Neurosci, 17(11):1500–1509, 2014. doi: 10 . 1038/nn . 3776
  17. C. P. Dancey and J. Reidy. Statistics without maths for psychology. Pearson London, 2017.
  18. DimReader: Axis lines that explain non-linear projections. IEEE Trans Vis Comput Graph, 25(1):481–490, 2018. doi: 10 . 1109/tvcg . 2018 . 2865194
  19. ManyNets: An interface for multiple network analysis and visualization. In Proc. CHI, pp. 213–222, 2010. doi: 10 . 1145/1753326 . 1753358
  20. A visual analytics system for brain functional connectivity comparison across individuals, groups, and time points. In Proc. PacificVis, pp. 250–259, 2017. doi: 10 . 1109/pacificvis . 2017 . 8031601
  21. Supporting analysis of dimensionality reduction results with contrastive learning. IEEE Trans Vis Comput Graph, 26(1):45–55, 2020. doi: 10 . 1109/tvcg . 2019 . 2934251
  22. Interactive dimensionality reduction for comparative analysis. IEEE Trans Vis Comput Graph, 28(1):758–768, 2022. doi: 10 . 1109/tvcg . 2021 . 3114807
  23. A visual analytics framework for contrastive network analysis. In Proc. VAST, pp. 48–59, 2020. doi: 10 . 1109/vast50239 . 2020 . 00010
  24. Network comparison with interpretable contrastive network representation learning. J Data Sci Stat Vis, 2(5), 2022. doi: 10 . 52933/jdssv . v2i5 . 56
  25. M. Gleicher. Explainers: Expert explorations with crafted projections. IEEE Trans Vis Comput Graph, 19(12):2042–2051, 2013. doi: 10 . 1109/tvcg . 2013 . 157
  26. R. Gove. Gragnostics: Fast, interpretable features for comparing graphs. In Proc. IV, pp. 201–209, 2019. doi: 10 . 1109/iv . 2019 . 00042
  27. A. Grover and J. Leskovec. node2vec: Scalable feature learning for networks. In Proc. KDD, pp. 855–864, 2016. doi: 10 . 1145/2939672 . 2939754
  28. Regularized linear discriminant analysis and its application in microarrays. Biostat, 8(1):86–100, 2007. doi: 10 . 1093/biostatistics/kxj035
  29. Inductive representation learning on large graphs. In Proc. NIPS, pp. 1024–1034, 2017. doi: 10 . 48550/arXiv . 1706 . 02216
  30. Robustness and explainability of artificial intelligence. Technical Report KJ-NA-30040-EN-N (online), Publications Office of the European Union, 2020. doi: doi:10 . 2760/57493
  31. EgoNav: Exploring networks through egocentric spatializations. In Proc. AVI, pp. 563–570, 2012. doi: 10 . 1145/2254556 . 2254661
  32. Y. Hu. Efficient, high-quality force-directed graph drawing. Math J, 10(1):37–71, 2005.
  33. VA + embeddings STAR: A state-of-the-art report on the use of embeddings in visual analytics. Comput Graph Forum, 42(3):539–571, 2023. doi: 10 . 1111/cgf . 14859
  34. A declarative rendering model for multiclass density maps. IEEE Trans Vis Comput Graph, 25(1):470–480, 2018. doi: 10 . 1109/tvcg . 2018 . 2865141
  35. Uncovering representative groups in multidimensional projections. Comput Graph Forum, 34(3):281–290, 2015. doi: 10 . 1111/cgf . 12640
  36. Multivariate Network Visualization, vol. 8380 of Lect Notes Comput Sci. Springer, 2014. doi: 10 . 1007/978-3-319-06793-3
  37. T. N. Kipf and M. Welling. Semi-supervised classification with graph convolutional networks. In Proc. ICLR, pp. 1–10, 2017. doi: 10 . 48550/arXiv . 1609 . 02907
  38. Visual neural decomposition to explain multivariate data sets. IEEE Trans Vis Comput Graph, 27(2):1374–1384, 2020. doi: 10 . 1109/tvcg . 2020 . 3030420
  39. Clustervision: Visual supervision of unsupervised clustering. IEEE Trans Vis Comput Graph, 24(1):142–151, 2018. doi: 10 . 1109/tvcg . 2017 . 2745085
  40. What would a graph look like in this layout? A machine learning approach to large graph visualization. IEEE Trans Vis Comput Graph, 24(1):478–488, 2018. doi: 10 . 1109/tvcg . 2017 . 2743858
  41. From indirect to direct contacts on Facebook: A big-data approach to the making of triadic network closure. Can Rev Sociol, 59(2):207–227, 2022. doi: 10 . 1111/cars . 12375
  42. S. Lespinats and M. Aupetit. CheckViz: Sanity check and topological clues for linear and non-linear mappings. Comput Graph Forum, 30(1):113–125, 2011. doi: 10 . 1111/j . 1467-8659 . 2010 . 01835 . x
  43. A visual analytics system for water distribution system optimization. In Proc. VIS, pp. 126–130, 2021. doi: 10 . 1109/vis49827 . 2021 . 9623272
  44. Winglets: Visualizing association with uncertainty in multi-class scatterplots. IEEE Trans Vis Comput Graph, 26(1):770–779, 2020. doi: 10 . 1109/tvcg . 2019 . 2934811
  45. S. M. Lundberg. SHAP (SHapley Additive exPlanations). https://github.com/slundberg/shap, 2018. Accessed: 2022-12-28.
  46. A unified approach to interpreting model predictions. In Proc. NIPS, vol. 30, 2017. doi: 10 . 48550/arXiv . 1705 . 07874
  47. A further comparison of simplification methods for decision-tree induction. In D. Fisher and H.-J. Lenz, eds., Learning from Data: Artificial Intelligence and Statistics V, pp. 365–374. Springer New York, 1996. doi: 10 . 1007/978-1-4612-2404-4_35
  48. Multidimensional projections for visual analysis of social networks. J Comput Sci Technol, 27(4):791–810, 2012. doi: 10 . 1007/s11390-012-1265-5
  49. MVN-Reduce: Dimensionality reduction for the visual analysis of multivariate networks. In Proc. EuroVis, pp. 13–17, 2017. doi: 10 . 2312/eurovisshort . 20171126
  50. A. Mayorga and M. Gleicher. Splatterplots: Overcoming overdraw in scatter plots. IEEE Trans Vis Comput Graph, 19(9):1526–1538, 2013. doi: 10 . 1109/tvcg . 2013 . 65
  51. The state of the art in multilayer network visualization. Comput Graph Forum, 38(6):125–149, 2019. doi: 10 . 1111/cgf . 13610
  52. I. Muse. ColorAide. https://facelessuser.github.io/coloraide/, 2020. Accessed: 2022-12-29.
  53. Multivariate data explanation by jumping emerging patterns visualization. arXiv:2106.11112, 2021. doi: 10 . 48550/arXiv . 2106 . 11112
  54. M. Newman. Networks. Oxford University Press, 2018.
  55. The state of the art in visualizing multivariate networks. Comput Graph Forum, 38(3):807–832, 2019. doi: 10 . 1111/cgf . 13728
  56. PyTorch: An imperative style, high-performance deep learning library. In Proc. NeurIPS, pp. 8024–8035, 2019. doi: 10 . 48550/arXiv . 1912 . 01703
  57. Scikit-learn: Machine learning in Python. J Mach Learn Res, 12:2825–2830, 2011. doi: 10 . 48550/arXiv . 1201 . 0490
  58. T. P. Peixoto. The graph-tool python library. figshare, 2014. http://figshare.com/articles/graph_tool/1164194.
  59. M. J. Powell. Direct search algorithms for optimization calculations. Acta Numerica, 7:287–336, 1998. doi: 10 . 1017/s0962492900002841
  60. N. Pržulj. Biological network comparison using graphlet degree distribution. Bioinformatics, 23(2):e177–e183, 2007. doi: 10 . 1093/bioinformatics/btq091
  61. Measuring dependence powerfully and equitably. J Mach Learn Res, 17(1):7406–7468, 2016. doi: 10 . 48550/arXiv . 1505 . 02213
  62. Deep inductive graph representation learning. IEEE Trans Knowl Data Eng, 32(3):438–452, 2018. doi: 10 . 1109/TKDE . 2018 . 2878247
  63. A. Sarikaya and M. Gleicher. Scatterplots: Tasks, data, and designs. IEEE Trans Vis Comput Graph, 24(1):402–412, 2018. doi: 10 . 1109/tvcg . 2017 . 2744184
  64. Interactive visual pattern search on graph data via graph representation learning. IEEE Trans Vis Comput Graph, 28(1):335–345, 2022. doi: 10 . 1109/tvcg . 2021 . 3114857
  65. Composite variables: When and how. Nurs Res, 62(1):45, 2013. doi: 10 . 1097/nnr . 0b013e3182741948
  66. The Matplotlib development team. Choosing colormaps in matplotlib. https://matplotlib.org/stable/users/explain/colors/colormaps.html, 2023. Accessed: 2023-09-25.
  67. Representative factor generation for the interactive visual analysis of high-dimensional data. IEEE Trans Vis Comput Graph, 18(12):2621–2630, 2012. doi: 10 . 1109/tvcg . 2012 . 256
  68. Reducing snapshots to points: A visual analytics approach to dynamic network exploration. IEEE Trans Vis Comput Graph, 22(1):1–10, 2016. doi: 10 . 1109/TVCG . 2015 . 2468078
  69. Out of the plane: Flower vs. star glyphs to support high-dimensional exploration in two-dimensional embeddings. IEEE Trans Vis Comput Graph, pp. 1–15, 2022 (early access). doi: 10 . 1109/TVCG . 2022 . 3216919
  70. SciPy 1.0: Fundamental algorithms for scientific computing in Python. Nat Methods, 17:261–272, 2020. doi: 10 . 1038/s41592-020-0772-5
  71. Visual analysis of graphs with multiple connected components. In Proc. VAST, pp. 155–162, 2009. doi: 10 . 1109/vast . 2009 . 5333893
  72. Quantifying hierarchy and dynamics in US faculty hiring and retention. Nature, 610(7930):120–127, 2022. doi: 10 . 1038/s41586-022-05222-x
  73. M. Waskom. seaborn.swarmplot. https://seaborn.pydata.org/generated/seaborn.swarmplot.html, 2016. Accessed: 2022-12-27.
  74. M. L. Waskom. seaborn: statistical data visualization. J Open Source Softw, 6(60):3021, 2021. doi: 10 . 21105/joss . 03021
  75. A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learn Syst, 32(1):4–24, 2021. doi: 10 . 1109/tnnls . 2020 . 2978386
  76. Do transformers really perform badly for graph representation? In Proc. NeurIPS, vol. 34, pp. 28877–28888, 2021. doi: 10 . 48550/arXiv . 2106 . 05234
  77. EVNet: An explainable deep network for dimension reduction. IEEE Trans Vis Comput Graph, pp. 1–18, 2022 (early access). doi: 10 . 1109/TVCG . 2022 . 3223399
  78. Network representation learning: A survey. IEEE Trans Big Data, 6(1):3–28, 2018. doi: 10 . 1109/TBDATA . 2018 . 2850013
  79. Dimension reconstruction for visual exploration of subspace clusters in high-dimensional data. In Proc. PacificVis, pp. 128–135, 2016. doi: 10 . 1109/pacificvis . 2016 . 7465260
  80. H. Zou and T. Hastie. Regularization and variable selection via the elastic net. J R Stat Soc Series B Stat Methodol, 67(2):301–320, 2005. doi: 10 . 1111/j . 1467-9868 . 2005 . 00503 . x
  81. Sparse principal component analysis. J Comput Graph Stat, 15(2):265–286, 2006. doi: 10 . 1198/106186006X113430
  82. Contrastive learning using spectral methods. Proc. NIPS, 26, 2013.
Citations (3)
View on Semantic Scholar
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up

Summary

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

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

Follow-Up Questions

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
Youtube Logo Streamline Icon: https://streamlinehq.com

YouTube