Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
162 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

An Evolution Kernel Method for Graph Classification through Heat Diffusion Dynamics (2306.14688v1)

Published 26 Jun 2023 in cs.LG

Abstract: Autonomous individuals establish a structural complex system through pairwise connections and interactions. Notably, the evolution reflects the dynamic nature of each complex system since it recodes a series of temporal changes from the past, the present into the future. Different systems follow distinct evolutionary trajectories, which can serve as distinguishing traits for system classification. However, modeling a complex system's evolution is challenging for the graph model because the graph is typically a snapshot of the static status of a system, and thereby hard to manifest the long-term evolutionary traits of a system entirely. To address this challenge, we suggest utilizing a heat-driven method to generate temporal graph augmentation. This approach incorporates the physics-based heat kernel and DropNode technique to transform each static graph into a sequence of temporal ones. This approach effectively describes the evolutional behaviours of the system, including the retention or disappearance of elements at each time point based on the distributed heat on each node. Additionally, we propose a dynamic time-wrapping distance GDTW to quantitatively measure the distance between pairwise evolutionary systems through optimal matching. The resulting approach, called the Evolution Kernel method, has been successfully applied to classification problems in real-world structural graph datasets. The results yield significant improvements in supervised classification accuracy over a series of baseline methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (38)
  1. Animal social networks: an introduction for complex systems scientists. Journal of Complex Networks, 9(2):cnab001, 2021. doi:\colorblue10.1093/comnet/cnab001.
  2. Male aggression varies with consortship rate and habitat in a dolphin social network. Behavioral Ecology and Sociobiology, 73:1–7, 2019. doi:\colorblue10.1007/s00265-019-2753-1.
  3. Opinion attractiveness and its effect in opinion formation models. Physica A: Statistical Mechanics and its Applications, 559:125017, 2020. doi:\colorblue10.1016/j.physa.2020.125017.
  4. Data preparation for mining world wide web browsing patterns. Knowledge and information systems, 1(1):5–32, 1999. doi:\colorblue10.1007/BF03325089.
  5. An ensemble feature selection algorithm based on pagerank centrality and fuzzy logic. Knowledge-Based Systems, 233:107538, 2021. doi:\colorblue10.1016/j.knosys.2021.107538.
  6. Learning subtree pattern importance for weisfeiler-lehman based graph kernels. Machine Learning, 110(7):1585–1607, 2021. doi:\colorblue10.1007/s10994-021-05991-y.
  7. Feature selection and learning for graphlet kernel. Pattern Recognition Letters, 136:63–70, 2020. doi:\colorblue10.1016/j.patrec.2020.05.023.
  8. Deep graph kernels. In Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining, pages 1365–1374, 2015. doi:\colorblue10.1145/2783258.2783417.
  9. Persistence fisher kernel: A riemannian manifold kernel for persistence diagrams. Advances in Neural Information Processing Systems, 31, 2018. doi:\colorblue10.48550/arXiv.1802.03569.
  10. Qi Zhao and Yusu Wang. Learning metrics for persistence-based summaries and applications for graph classification. Advances in Neural Information Processing Systems, 32, 2019. doi:\colorblue10.48550/arXiv.1904.12189.
  11. Exploiting the flexibility inside park-level commercial buildings considering heat transfer time delay: A memory-augmented deep reinforcement learning approach. IEEE Transactions on Sustainable Energy, 13(1):207–219, 2022. doi:\colorblue10.1109/TSTE.2021.3107439.
  12. Heat kernel based community detection. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 1386–1395, 2014. doi:\colorblue10.1145/2623330.2623706.
  13. Diffusionrank: a possible penicillin for web spamming. In Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval, pages 431–438, 2007. doi:\colorblue10.1145/1277741.1277815.
  14. Spectral graph theory. Number 92. American Mathematical Soc., 1997.
  15. Semi-supervised classification with graph convolutional networks. In Proceedings International Conference on Learning Representations, 2017. doi:\colorblue10.48550/arXiv.1609.02907.
  16. Fast polynomial approximation of heat kernel convolution on manifolds and its application to brain sulcal and gyral graph pattern analysis. IEEE transactions on medical imaging, 39(6):2201–2212, 2020. doi:\colorblue10.1109/TMI.2020.2967451.
  17. Diffusion kernels on graphs and other discrete structures. In Proceedings of the 19th international conference on machine learning, volume 2002, pages 315–322, 2002.
  18. A concise and provably informative multi-scale signature based on heat diffusion. In Computer graphics forum, volume 28, pages 1383–1392. Wiley Online Library, 2009. doi:\colorblue10.1111/j.1467-8659.2009.01515.x.
  19. Charles Van Loan. The sensitivity of the matrix exponential. SIAM Journal on Numerical Analysis, 14(6):971–981, 1977. doi:\colorblue10.1137/0714065.
  20. Miroslav Fiedler. A property of eigenvectors of nonnegative symmetric matrices and its application to graph theory. Czechoslovak mathematical journal, 25(4):619–633, 1975.
  21. Just slaq when you approximate: accurate spectral distances for web-scale graphs. In Proceedings of the Web Conference 2020, pages 2697–2703, 2020. doi:\colorblue10.1145/3366423.3380026.
  22. Restricted boltzmann machines in quantum physics. Nature Physics, 15:887–892, 2019. doi:\colorblue10.1038/s41567-019-0545-1.
  23. Fastgcn: fast learning with graph convolutional networks via importance sampling. In Proceedings International Conference on Learning Representations, 2018. doi:\colorblue10.48550/arXiv.1801.10247.
  24. Adaptively constrained dynamic time warping for time series classification and clustering. Information Sciences, 534:97–116, 2020. doi:\colorblue10.1016/j.ins.2020.04.009.
  25. Time-series averaging and local stability-weighted dynamic time warping for online signature verification. Pattern Recognition, 112:107699, 2021. doi:\colorblue10.1016/j.patcog.2020.107699.
  26. Adaptive dynamic programming for control: A survey and recent advances. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 51(1):142–160, 2020. doi:\colorblue10.1109/TSMC.2020.3042876.
  27. graph2vec: Learning distributed representations of graphs. arXiv preprint arXiv:1707.05005, 2017. doi:\colorblue10.48550/arXiv.1707.05005.
  28. Structure-activity relationship of mutagenic aromatic and heteroaromatic nitro compounds. correlation with molecular orbital energies and hydrophobicity. Journal of Medicinal Chemistry, 34(2):786–797, 1991. doi:\colorblue10.1021/jm00106a046.
  29. Distinguishing enzyme structures from non-enzymes without alignments. Journal of Molecular Biology, 330(4):771–783, 2003. doi:\colorblue10.1016/S0022-2836(03)00628-4.
  30. The predictive toxicology challenge 2000-2001. Bioinformatics, 17(1):107–108, 2001. doi:\colorblue10.1093/bioinformatics/17.1.107.
  31. Protein function prediction via graph kernels. Bioinformatics, 21(suppl_1):i47–i56, 2005. doi:\colorblue10.1093/bioinformatics/bti1007.
  32. Graph classification using structural attention. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 1666–1674, 2018. doi:\colorblue10.1145/3219819.3219980.
  33. Anonymous walk embeddings. In International conference on machine learning, pages 2186–2195. PMLR, 2018. doi:\colorblue10.48550/arXiv.1805.11921.
  34. Learning convolutional neural networks for graphs. In International conference on machine learning, pages 2014–2023. PMLR, 2016. doi:\colorblue10.48550/arXiv.1605.05273.
  35. Weisfeiler-lehman graph kernels. Journal of Machine Learning Research, 1(3):1–48, 2010. doi:\colorblue10.1016/j.websem.2011.06.001.
  36. Deep graph kernels. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 1365–1374, 2015. doi:\colorblue10.1145/2783258.2783417.
  37. Efficient graphlet kernels for large graph comparison. In Artificial Intelligence and Statistics, pages 488–495, 2009.
  38. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining, pages 855–864, 2016. doi:\colorblue10.1145/2939672.2939754.

Summary

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

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