Abstract
Node classification is one of the core tasks on attributed graphs, but successful graph learning solutions require sufficiently labeled data. To keep annotation costs low, active graph learning focuses on selecting the most qualitative subset of nodes that maximizes label efficiency. However, deciding which heuristic is best suited for an unlabeled graph to increase label efficiency is a persistent challenge. Existing solutions either neglect aligning the learned model and the sampling method or focus only on limited selection aspects. They are thus sometimes worse or only equally good as random sampling. In this work, we introduce a novel active graph learning approach called DiffusAL, showing significant robustness in diverse settings. Toward better transferability between different graph structures, we combine three independent scoring functions to identify the most informative node samples for labeling in a parameter-free way: i) Model Uncertainty, ii) Diversity Component, and iii) Node Importance computed via graph diffusion heuristics. Most of our calculations for acquisition and training can be pre-processed, making DiffusAL more efficient compared to approaches combining diverse selection criteria and similarly fast as simpler heuristics. Our experiments on various benchmark datasets show that, unlike previous methods, our approach significantly outperforms random selection in 100% of all datasets and labeling budgets tested.
S. Gilhuber and J. Busch—Equal contribution
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
- 2.
On Physics, Degree underperformed considerably and is therefore omitted for better presentation.
References
Ash, J.T., Zhang, C., Krishnamurthy, A., Langford, J., Agarwal, A.: Deep batch active learning by diverse, uncertain gradient lower bounds. In: ICLR (2020)
Battaglia, P.W., et al.: Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261 (2018)
Bilgic, M., Mihalkova, L., Getoor, L.: Active learning for networked data. In: Proceedings of the 27th International Conference on Machine Learning (ICML 2010), pp. 79–86 (2010)
Borutta, F., Busch, J., Faerman, E., Klink, A., Schubert, M.: Structural graph representations based on multiscale local network topologies. In: WI-IAT (2019)
Bronstein, M.M., Bruna, J., LeCun, Y., Szlam, A., Vandergheynst, P.: Geometric deep learning: going beyond euclidean data. IEEE SPM 34(4), 18–42 (2017)
Busch, J., Kocheturov, A., Tresp, V., Seidl, T.: Nf-gnn: network flow graph neural networks for malware detection and classification. In: SSDBM (2021)
Busch, J., Pi, J., Seidl, T.: Pushnet: efficient and adaptive neural message passing. In: ECAI (2020)
Cai, H., Zheng, V.W., Chang, K.C.C.: Active learning for graph embedding. arXiv preprint arXiv:1705.05085 (2017)
Chandra, A.L., Desai, S.V., Devaguptapu, C., Balasubramanian, V.N.: On initial pools for deep active learning. In: NeurIPS 2020 Workshop on Pre-registration in Machine Learning, pp. 14–32. PMLR (2021)
Contardo, G., Denoyer, L., Artières, T.: A meta-learning approach to one-step active-learning. In: AutoML@PKDD/ECML (2017)
Faerman, E., Borutta, F., Busch, J., Schubert, M.: Semi-supervised learning on graphs based on local label distributions. In: MLG (2018)
Faerman, E., Borutta, F., Busch, J., Schubert, M.: Ada-lld: adaptive node similarity using multi-scale local label distributions. In: WI-IAT (2020)
Fey, M., Lenssen, J.E.: Fast graph representation learning with PyTorch Geometric. In: ICLR Workshop on Representation Learning on Graphs and Manifolds (2019)
Frey, C.M.M., Ma, Y., Schubert, M.: Sea: graph shell attention in graph neural networks. In: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (2022)
Gao, L., Yang, H., Zhou, C., Wu, J., Pan, S., Hu, Y.: Active discriminative network representation learning. In: IJCAI (2018)
Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: ICML, pp. 1263–1272. PMLR (2017)
Hamilton, W.L.: Graph representation learning. Synth. Lect. Artifi. Intell. Mach. Learn. 14(3), 1–159 (2020)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)
Klicpera, J., Bojchevski, A., Günnemann, S.: Predict then propagate: graph neural networks meet personalized pagerank. In: ICLR (2019)
Klicpera, J., Weißenberger, S., Günnemann, S.: Diffusion improves graph learning. Adv. Neural. Inf. Process. Syst. 32, 13354–13366 (2019)
Lee, J.B., Rossi, R., Kong, X.: Graph classification using structural attention. In: KDD, pp. 1666–1674 (2018)
Li, Q., Han, Z., Wu, X.M.: Deeper insights into graph convolutional networks for semi-supervised learning. In: AAAI (2018)
Liu, J., Wang, Y., Hooi, B., Yang, R., Xiao, X.: Lscale: latent space clustering-based active learning for node classification. In: Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2022, Grenoble, France, 19–23 September 2022, Proceedings, Part I, pp. 55–70. Springer (2023). https://doi.org/10.1007/978-3-031-26387-3_4
Moore, C., Yan, X., Zhu, Y., Rouquier, J.B., Lane, T.: Active learning for node classification in assortative and disassortative networks. In: Proceedings of the 17th ACM SIGKDD international Conference on Knowledge Discovery and Data Mining, pp. 841–849 (2011)
Namata, G.M., London, B., Getoor, L., Huang, B.: Query-driven active surveying for collective classification. In: MLG (2012)
Ogawa, Y., Maekawa, S., Sasaki, Y., Fujiwara, Y., Onizuka, M.: Adaptive node embedding propagation for semi-supervised classification. In: Oliver, N., Pérez-Cruz, F., Kramer, S., Read, J., Lozano, J.A. (eds.) ECML PKDD 2021. LNCS (LNAI), vol. 12976, pp. 417–433. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86520-7_26
Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems 32, pp. 8024–8035. Curran Associates, Inc. (2019)
Regol, F., Pal, S., Zhang, Y., Coates, M.: Active learning on attributed graphs via graph cognizant logistic regression and preemptive query generation. In: ICML, pp. 8041–8050. PMLR (2020)
Regol, F., Pal, S., Zhang, Y., Coates, M.: Active learning on attributed graphs via graph cognizant logistic regression and preemptive query generation. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020, JMLR.org (2020)
Sen, P., Namata, G., Bilgic, M., Getoor, L., Galligher, B., Eliassi-Rad, T.: Collective classification in network data. AI Mag. 29(3), 93 (2008)
Sener, O., Savarese, S.: Active learning for convolutional neural networks: a core-set approach. In: ICLR (2018)
Settles, B.: Active learning literature survey. Computer Sciences Technical Report 1648, University of Wisconsin-Madison (2009)
Seung, H.S., Opper, M., Sompolinsky, H.: Query by committee. In: Proceedings of the Fifth Annual Workshop on Computational Learning Theory, COLT 1992, pp. 287–294. Association for Computing Machinery, New York (1992)
Shchur, O., Mumme, M., Bojchevski, A., Günnemann, S.: Pitfalls of graph neural network evaluation. In: NeurIPS Relational Representation Learning Workshop (2018)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. In: ICLR (2018)
Veličković, P., Fedus, W., Hamilton, W.L., Lió, P., Bengio, Y., Hjelm, R.D.: Deep graph infomax. In: ICLR (2018)
Wu, Y., Xu, Y., Singh, A., Yang, Y., Dubrawski, A.: Active learning for graph neural networks via node feature propagation. arXiv preprint arXiv:1910.07567 (2019)
Wu, Y., Xu, Y., Singh, A., Yang, Y., Dubrawski, A.: Active learning for graph neural networks via node feature propagation. CoRR abs/ arXiv: 1910.07567 (2019)
Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks?. In: ICLR (2019)
Xu, K., Li, C., Tian, Y., Sonobe, T., Kawarabayashi, K.i., Jegelka, S.: Representation learning on graphs with jumping knowledge networks. In: ICML, pp. 5453–5462. PMLR (2018)
Zhang, M., Chen, Y.: Link prediction based on graph neural networks. In: Advances in Neural Information Processing Systems 31 (2018)
Zhang, W., Shen, Y., Li, Y., Chen, L., Yang, Z., Cui, B.: Alg: fast and accurate active learning framework for graph convolutional networks. In: SIGMOD, pp. 2366–2374 (2021)
Zhang, W., et al.: Grain: Improving data efficiency of graph neural networks via diversified influence maximization. Proc. VLDB Endow. 14(11), 2473–2482 (2021)
Zhao, L., et al.: T-gcn: a temporal graph convolutional network for traffic prediction. IEEE Trans. Intell. Transp. Syst. 21(9), 3848–3858 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gilhuber, S., Busch, J., Rotthues, D., Frey, C.M.M., Seidl, T. (2023). DiffusAL: Coupling Active Learning with Graph Diffusion for Label-Efficient Node Classification. 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 14169. Springer, Cham. https://doi.org/10.1007/978-3-031-43412-9_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-43412-9_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43411-2
Online ISBN: 978-3-031-43412-9
eBook Packages: Computer ScienceComputer Science (R0)