Abstract
Hypergraphs recently have emerged as a new promising alternative to describe complex dependencies in spatio-temporal processes, resulting in the newest trend in multivariate time series forecasting, based semi-supervised learning of spatio-temporal data with Hypergraph Convolutional Networks. Nevertheless, such recent approaches are often limited in their capability to accurately describe higher-order interactions among spatio-temporal entities and to learn hidden interrelations among network substructures. Motivated by the emerging results on simplicial convolution, we introduce the concepts of Hodge theory and Hodge Laplacians, that is, a higher-order generalization of the graph Laplacian, to hypergraph learning. Furthermore, we develop a novel framework for hyper-simplex-graph representation learning which describes complex relationships among both graph and hyper-simplex-graph simplices and, as a result, simultaneously extracts latent higher-order spatio-temporal dependencies. We provide theoretical foundations behind the proposed hyper-simplex-graph representation learning and validate our new Hodge-style Hyper-simplex-graph Neural Networks (H\(^2\)-Nets) on 7 real world spatio-temporal benchmark datasets. Our experimental results indicate that H\(^2\)-Nets outperforms the state-of-the-art methods by a significant margin, while demonstrating lower computational costs.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Agarwal, S., Branson, K., Belongie, S.: Higher order learning with graphs. In: Proceedings of the International Conference on Machine Learning, pp. 17–24 (2006)
Arya, D., Gupta, D.K., Rudinac, S., Worring, M.: Hypersage: generalizing inductive representation learning on hypergraphs. arXiv preprint arXiv:2010.04558 (2020)
Atwood, J., Towsley, D.: Diffusion-convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 29. Curran Associates, Inc. (2016)
Bai, L., Yao, L., Li, C., Wang, X., Wang, C.: Adaptive graph convolutional recurrent network for traffic forecasting. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 17804–17815. Curran Associates, Inc. (2020)
Bai, S., Kolter, J.Z., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 (2018)
Barbarossa, S., Sardellitti, S., Ceci, E.: Learning from signals defined over simplicial complexes. In: IEEE Data Science Workshop. IEEE (2018)
Benson, A.R., Abebe, R., Schaub, M.T., Jadbabaie, A., Kleinberg, J.: Simplicial closure and higher-order link prediction. Proc. Natl. Acad. Sci. USA 115(48), E11221–E11230 (2018)
Bilal, U., Jemmott, J.B., Schnake-Mahl, A., Murphy, K., Momplaisir, F.: Racial/ethnic and neighbourhood social vulnerability disparities in COVID-19 testing positivity, hospitalization, and in-hospital mortality in a large hospital system in Pennsylvania: a prospective study of electronic health records. Lancet Reg. Health-Am. 10, 100220 (2022)
Bodnar, C., et al.: Weisfeiler and lehman go topological: message passing simplicial networks. In: ICLR 2021 Workshop on Geometrical and Topological Representation Learning (2021)
Bolla, M.: Spectra, euclidean representations and clusterings of hypergraphs. Discret. Math. 117(1–3), 19–39 (1993)
Bronstein, M.M., Bruna, J., Cohen, T., Veličković, P.: Geometric deep learning: grids, groups, graphs, geodesics, and gauges (2021)
Bunch, E., You, Q., Fung, G., Singh, V.: Simplicial 2-complex convolutional neural networks. In: NeurIPS 2020 Workshop on Topological Data Analysis and Beyond (2020)
Cao, D., et al.: Spectral temporal graph neural network for multivariate time-series forecasting. In: Advances in Neural Information Processing Systems (2020)
Chen, Y., Jiang, T., Heleno, M., Moreira, A., Gel, Y.R.: Evaluating distribution system reliability with hyperstructures graph convolutional nets. In: IEEE International Conference on Big Data, pp. 1793–1800 (2022)
Chen, Y., Batsakis, S., Poor, H.V.: Higher-order spatio-temporal neural networks for COVID-19 forecasting. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1–5. IEEE (2023)
Chen, Y., Gel, Y., Poor, H.V.: Time-conditioned dances with simplicial complexes: zigzag filtration curve based supra-hodge convolution networks for time-series forecasting. Adv. Neural. Inf. Process. Syst. 35, 8940–8953 (2022)
Chen, Y., Gel, Y.R., Poor, H.V.: BScNets: block simplicial complex neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence (2022)
Chen, Y., Heleno, M., Moreira, A., Gel, Y.R.: Topological graph convolutional networks solutions for power distribution grid planning. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp. 123–134 (2023)
Chen, Y., Jacob, R.A., Gel, Y.R., Zhang, J., Poor, H.V.: Learning power grid outages with higher-order topological neural networks. IEEE Trans. Power Syst. (2023)
Chen, Y., Segovia, I., Gel, Y.R.: Z-GCNETs: time zigzags at graph convolutional networks for time series forecasting. In: Proceedings of the International Conference on Machine Learning, pp. 1684–1694 (2021)
Chen, Y., Segovia-Dominguez, I., Coskunuzer, B., Gel, Y.: Tamp-s2gcnets: coupling time-aware multipersistence knowledge representation with spatio-supra graph convolutional networks for time-series forecasting. In: International Conference on Learning Representations (2022)
Ebli, S., Defferrard, M., Spreemann, G.: Simplicial neural networks. In: Topological Data Analysis and Beyond workshop at Advances in Neural Information Processing Systems (2020)
Feng, Y., You, H., Zhang, Z., Ji, R., Gao, Y.: Hypergraph neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 3558–3565 (2019)
Geng, X., et al.: Spatiotemporal multi-graph convolution network for ride-hailing demand forecasting. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 3656–3663 (2019)
Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 70, pp. 1263–1272. PMLR (2017)
Guo, S., Lin, Y., Feng, N., Song, C., Wan, H.: Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 922–929 (2019)
Hajij, M., Istvan, K., Zamzmi, G.: Cell complex neural networks. In: NeurIPS 2020 Workshop on Topological Data Analysis and Beyond (2020)
Hamilton, W.L., Ying, R., Leskovec, J.: Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems (2017)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Hsiao, W.Y., Liu, J.Y., Yeh, Y.C., Yang, Y.H.: Compound word transformer: learning to compose full-song music over dynamic directed hypergraphs. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 4503–4511 (2021)
Huang, J., Yang, J.: UniGNN: a unified framework for graph and hypergraph neural networks. In: Proceedings of the International Joint Conference on Artificial Intelligence (2021)
Jiang, J., Wei, Y., Feng, Y., Cao, J., Gao, Y.: Dynamic hypergraph neural networks. In: Proceedings of the International Joint Conference on Artificial Intelligence (2019)
Karimi, A.M., Wu, Y., Koyuturk, M., French, R.H.: Spatiotemporal graph neural network for performance prediction of photovoltaic power systems. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 15323–15330 (2021)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: Proceedings of the International Conference on Learning Representations (2017)
Lai, G., Chang, W.C., Yang, Y., Liu, H.: Modeling long-and short-term temporal patterns with deep neural networks. In: ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 95–104 (2018)
Li, Y., Yu, R., Shahabi, C., Liu, Y.: Diffusion convolutional recurrent neural network: data-driven traffic forecasting. In: Proceedings of the International Conference on Learning Representations (2018)
Liang, Y., et al.: UrbanFM: inferring fine-grained urban flows. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM (2019)
Lim, L.H.: Hodge laplacians on graphs. SIAM Rev. 62(3), 685–715 (2020)
Oreshkin, B.N., Carpov, D., Chapados, N., Bengio, Y.: N-beats: neural basis expansion analysis for interpretable time series forecasting. In: Proceedings of the International Conference on Learning Representations (2019)
Pan, Z., Liang, Y., Wang, W., Yu, Y., Zheng, Y., Zhang, J.: Urban traffic prediction from spatio-temporal data using deep meta learning. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM (2019)
Rangapuram, S.S., Seeger, M.W., Gasthaus, J., Stella, L., Wang, Y., Januschowski, T.: Deep state space models for time series forecasting. In: Advances in Neural Information Processing Systems, vol. 31 (2018)
Reitsma, M.B., et al.: Racial/ethnic disparities in COVID-19 exposure risk, testing, and cases at the subcounty level in California: study examines racial/ethnic disparities in COVID-19 risk, testing, and cases. Health Aff. 40(6), 870–878 (2021)
Roddenberry, T.M., Glaze, N., Segarra, S.: Principled simplicial neural networks for trajectory prediction. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 9020–9029. PMLR (2021)
Roddenberry, T.M., Segarra, S.: HodgeNet: graph neural networks for edge data. In: The 53rd Asilomar Conference on Signals, Systems, and Computers. IEEE (2019)
Sawhney, R., Agarwal, S., Wadhwa, A., Derr, T., Shah, R.R.: Stock selection via spatiotemporal hypergraph attention network: a learning to rank approach. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 497–504 (2021)
Schaub, M.T., Benson, A.R., Horn, P., Lippner, G., Jadbabaie, A.: Random walks on simplicial complexes and the normalized hodge 1-laplacian. SIAM Rev. 62(2), 353–391 (2020)
Schaub, M.T., Zhu, Y., Seby, J.B., Roddenberry, T.M., Segarra, S.: Signal processing on higher-order networks: livin’on the edge... and beyond. Signal Process. 187, 108149 (2021)
Sen, R., Yu, H.F., Dhillon, I.S.: Think globally, act locally: a deep neural network approach to high-dimensional time series forecasting. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Song, C., Lin, Y., Guo, S., Wan, H.: Spatial-temporal synchronous graph convolutional networks: A new framework for spatial-temporal network data forecasting. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 01, pp. 914–921 (2020)
Srinivasan, D., Chan, C.W., Balaji, P.: Computational intelligence-based congestion prediction for a dynamic urban street network. Neurocomputing 72(10–12), 2710–2716 (2009)
Sun, X., et al.: Heterogeneous hypergraph embedding for graph classification. In: Proceedings of the ACM International Conference on Web Search and Data Mining, pp. 725–733 (2021)
Tran, A., Mathews, A., Ong, C.S., Xie, L.: Radflow: a recurrent, aggregated, and decomposable model for networks of time series. In: Proceedings of the International World Wide Web Conference, pp. 730–742 (2021)
Wang, J., Zhang, Y., Wei, Y., Hu, Y., Piao, X., Yin, B.: Metro passenger flow prediction via dynamic hypergraph convolution networks. IEEE Trans. Intell. Transp. Syst. 22(12), 7891–7903 (2021)
Wu, S., Rizoiu, M.A., Xie, L.: Estimating attention flow in online video networks. Proc. ACM Hum.-Comput. Interact. 3, 1–25 (2019)
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., Yu, P.S.: A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 32(1), 4–24 (2021)
Wu, Z., Pan, S., Long, G., Jiang, J., Zhang, C.: Graph WaveNet for deep spatial-temporal graph modeling. In: Proceedings of the International Joint Conference on Artificial Intelligence. International Joint Conferences on Artificial Intelligence Organization (2019)
Xia, L., Huang, C., Xu, Y., Dai, P., Bo, L., Zhang, X., Chen, T.: Spatial-temporal sequential hypergraph network for crime prediction with dynamic multiplex relation learning. In: Proceedings of the International Joint Conference on Artificial Intelligence (2021)
Yadati, N., Nimishakavi, M., Yadav, P., Nitin, V., Louis, A., Talukdar, P.: Hypergcn: a new method of training graph convolutional networks on hypergraphs. In: Advances in Neural Information Processing Systems, pp. 1511–1522 (2019)
Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence (2018)
Yao, H., Tang, X., Wei, H., Zheng, G., Li, Z.: Revisiting spatial-temporal similarity: a deep learning framework for traffic prediction. In: Proceedings of the AAAI Conference on Artificial Intelligence (2019)
Yao, H., et al.: Deep multi-view spatial-temporal network for taxi demand prediction. In: Proceedings of the AAAI Conference on Artificial Intelligence (2018)
Yi, J., Park, J.: Hypergraph convolutional recurrent neural network. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining August 2020. ACM (2020)
Yin, H., Benson, A.R., Leskovec, J.: Higher-order clustering in networks. Phys. Rev. E 97(5), 052306 (2018)
Yin, N., et al.: Dynamic hypergraph convolutional network. In: IEEE International Conference on Data Engineering (2022)
Yu, B., Yin, H., Zhu, Z.: Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. In: Proceedings of the International Joint Conference on Artificial Intelligence. International Joint Conferences on Artificial Intelligence Organization (2018)
Zhang, J., Zheng, Y., Qi, D.: Deep spatio-temporal residual networks for citywide crowd flows prediction. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 1655–1661 (2017)
Zhang, J., Zheng, Y., Qi, D., Li, R., Yi, X.: DNN-based prediction model for spatio-temporal data. In: Proceedings of the ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. ACM (2016)
Zheng, W., Yan, L., Gou, C., Wang, F.Y.: Two heads are better than one: hypergraph-enhanced graph reasoning for visual event ratiocination. In: Proceedings of the International Conference on Machine Learning, vol. 139, pp. 12747–12760 (2021)
Acknowledgements
This work was supported by the NASA grant # 21-AIST21_2-0059 and the ONR grant # N00014-21-1-2530. The views expressed in the article do not necessarily represent the views of the NASA and ONR.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Ethical Statement
The H\(^2\)-Nets approach and, more generally, the ideas of Hodge theory open a new pathway for learning the key multi-node interactions in many domains associated with spatio-temporal data analysis where such critical higher-order interactions are typically neglected. Such applications range from wildfire plume tracking in complex terrains to bio-threat surveillance to human mobility monitoring. While we do not anticipate any negative societal impacts of the proposed H\(^2\)-Nets ideas and the concepts of the Hodge theory, it is important to emphasise that we currently lack any formal inferential tools to quantify the uncertainties associated with learning high-order interactions, which limits our abilities in risk quantification as well as interpretability and explainability.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, Y., Jiang, T., Gel, Y.R. (2023). H\(^2\)-Nets: Hyper-hodge Convolutional Neural Networks for Time-Series Forecasting. In: Koutra, D., Plant, C., Gomez Rodriguez, M., Baralis, E., Bonchi, F. (eds) Machine Learning and Knowledge Discovery in Databases: Research Track. ECML PKDD 2023. Lecture Notes in Computer Science(), vol 14173. Springer, Cham. https://doi.org/10.1007/978-3-031-43424-2_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-43424-2_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43423-5
Online ISBN: 978-3-031-43424-2
eBook Packages: Computer ScienceComputer Science (R0)