Abstract
Graph-based semi-supervised learning (SSL) assigns labels to initially unlabelled vertices in a graph. Graph neural networks (GNNs), esp. graph convolutional networks (GCNs), are at the core of the current-state-of-the art models for graph-based SSL problems. GCNs have recently been extended to undirected hypergraphs in which relationships go beyond pairwise associations. There is a need to extend GCNs to directed hypergraphs which represent more expressively many real-world data sets such as co-authorship networks and recommendation networks. Furthermore, labels of interest in these applications are most naturally represented by probability distributions. Motivated by these needs, in this paper, we propose a novel GNN-based method for directed hypergraphs, called Directed Hypergraph Network (DHN) for semi-supervised learning of probability distributions (Soft SSL). A key contribution of this paper is to establish generalisation error bounds for GNN-based soft SSL. In fact, our theoretical analysis is quite general and has straightforward applicability to DHN as well as to existing hypergraph methods. We demonstrate the effectiveness of our method through detailed experimentation on real-world datasets. We have made the code available.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bai, S., Zhang, F., Torr, P.H.S.: Hypergraph convolution and hypergraph attention. Pattern Recogn. 110, 107637 (2021)
Chan, T.H., Liang, Z.: Generalizing the hypergraph laplacian via a diffusion process with mediators. In: COCOON (2018)
Chen, Y., Ye, J., Li, J.: A distance for HMMs based on aggregated wasserstein metric and state registration. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 451–466. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46466-4_27
Corduneanu, A., Jaakkola, T.S.: Distributed information regularization on graphs. In: NIPS, pp. 297–304. MIT Press (2005)
Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. In: NIPS. Curran Associates, Inc. (2013)
Dong, Y., Sawin, W., Bengio, Y.: HNHN: hypergraph networks with hyperedge neurons. arXiv preprint arXiv:2006.12278 (2020)
Feng, Y., You, H., Zhang, Z., Ji, R., Gao, Y.: Hypergraph neural networks. In: AAAI (2019)
Frogner, C., Mirzazadeh, F., Solomon, J.: Learning entropic wasserstein embeddings. In: ICLR (2019)
Gallo, G., Longo, G., Pallottino, S., Nguyen, S.: Directed hypergraphs and applications. Discrete Appl. Math. 42(2–3), 177–201 (1993)
Gao, T., Asoodeh, S., Huang, Y., Evans, J.: Wasserstein soft label propagation on hypergraphs: algorithm and generalization error bounds. In: AAAI (2019)
Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: ICML (2017)
Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: NIPS. Curran Associates, Inc. (2017)
Hamilton, W.L.: Graph representation learning. Synth. Lect. Artif. Intell. Mach. Learn. 14(3), 1–159 (2020)
Han, J., Cheng, B., Wang, X.: Two-phase hypergraph based reasoning with dynamic relations for multi-hop KBQA. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI), pp. 3615–3621 (2020)
Hein, M., Setzer, S., Jost, L., Rangapuram, S.S.: The total variation on hypergraphs - learning on hypergraphs revisited. In: NIPS. Curran Associates, Inc. (2013)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)
Liao, R., Zhao, Z., Urtasun, R., Zemel, R.S.: Lanczosnet: multi-scale deep graph convolutional networks. In: ICLR (2019)
Ma, Y., Tang, J.: Deep learning on graphs. Cambridge University Press (2020)
Muzellec, B., Cuturi, M.: Generalizing point embeddings using the wasserstein space of elliptical distributions. In: NeurIPS. Curran Associates, Inc. (2018)
Solomon, J., Rustamov, R., Guibas, L., Butscher, A.: Wasserstein propagation for semi-supervised learning. In: ICML (2014)
Subramanya, A., Bilmes, J.: Semi-supervised learning with measure propagation. J. Mach. Learn. Res. 12, 3311–3370 (2011)
Subramanya, A., Talukdar, P.P.: Graph-based semi-supervised learning. Synth. Lect. Artif. Intell. Mach. Learn. 8(4), 1–125 (2014)
Tsuda, K.: Propagating distributions on a hypergraph by dual information regularization. In: ICML (2005)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: ICLR (2018)
Verma, S., Zhang, Z.L.: Stability and generalization of graph convolutional neural networks. In: KDD (2019)
Villani, C.: Topics in Optimal Transportation Theory (2003)
Villani, C.: Optimal Transport - Old and New. vol. 338. Springer-Verlag (2008)
Wu, F., Souza, A., Zhang, T., Fifty, C., Yu, T., Weinberger, K.: Simplifying graph convolutional networks. In: ICML (2019)
Yadati, N., Nimishakavi, M., Yadav, P., Nitin, V., Louis, A., Talukdar, P.: HyperGCN: a new method of training graph convolutional networks on hypergraphs. In: NeurIPS. Curran Associates, Inc. (2019)
Zhang, C., Hu, S., Tang, Z.G., Chan, T.H.H.: Re-revisiting learning on hypergraphs: confidence interval and subgradient method. In: ICML (2017)
Zhang, R., Zou, Y., Ma, J.: Hyper-sagnn: a self-attention based graph neural network for hypergraphs. In: International Conference on Learning Representations (ICLR) (2020)
Zhou, D., Huang, J., Schölkopf, B.: Learning with hypergraphs: clustering, classification, and embedding. In: Schölkopf, B., Platt, J.C., Hoffman, T. (eds.) NIPS. MIT Press (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Yadati, N., Gao, T., Asoodeh, S., Talukdar, P., Louis, A. (2021). Graph Neural Networks for Soft Semi-Supervised Learning on Hypergraphs. In: Karlapalem, K., et al. Advances in Knowledge Discovery and Data Mining. PAKDD 2021. Lecture Notes in Computer Science(), vol 12712. Springer, Cham. https://doi.org/10.1007/978-3-030-75762-5_36
Download citation
DOI: https://doi.org/10.1007/978-3-030-75762-5_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-75761-8
Online ISBN: 978-3-030-75762-5
eBook Packages: Computer ScienceComputer Science (R0)