Abstract
The minimum cost multicut problem is the NP-hard/APX-hard combinatorial optimization problem of partitioning a real-valued edge-weighted graph such as to minimize the total cost of the partition. While graph convolutional neural networks (GNN) have proven to be promising in the context of combinatorial optimization, most of them are only tailored to or tested on positive-valued edge weights, i.e. they do not comply with the nature of the multicut problem. We therefore adapt various GNN architectures including Graph Convolutional Networks, Signed Graph Convolutional Networks and Graph Isomorphic Networks to facilitate the efficient encoding of real-valued edge costs. Moreover, we employ a reformulation of the multicut ILP constraints to a polynomial program as loss function that allows us to learn feasible multicut solutions in a scalable way. Thus, we provide the first approach towards end-to-end trainable multicuts. Our findings support that GNN approaches can produce good solutions in practice while providing lower computation times and largely improved scalability compared to LP solvers and optimized heuristics, especially when considering large instances. Our code is available at https://github.com/steffen-jung/GCN-Multicut.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Andres, B., Kappes, J.H., Beier, T., Köthe, U., Hamprecht, F.A.: Probabilistic image segmentation with closedness constraints. In: ICCV (2011)
Andres, B., et al.: Globally optimal closed-surface segmentation for connectomics. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7574, pp. 778–791. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33712-3_56
Arakelyan, E., Daza, D., Minervini, P., Cochez, M.: Complex query answering with neural link predictors (2021)
Arbeláez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. TPAMI 33(5), 898–916 (2011)
Bansal, N., Blum, A., Chawla, S.: Correlation clustering. Mach. Learn. 56(1–3), 89–113 (2004)
Beier, T., Andres, B., Köthe, U., Hamprecht, F.A.: An efficient fusion move algorithm for the minimum cost lifted multicut problem. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 715–730. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_44
Beier, T., Kroeger, T., Kappes, J., Köthe, U., Hamprecht, F.: Cut, glue, & cut: a fast, approximate solver for multicut partitioning. In: CVPR (2014)
Beier, T., et al.: Multicut brings automated neurite segmentation closer to human performance. Nat. Methods 14(2), 101–102 (2017)
Bello, I., Pham, H., Le, Q.V., Norouzi, M., Bengio, S.: Neural combinatorial optimization with reinforcement learning. In: ICLR Workshop (2017)
Chen, Y., Zhang, B.: Learning to solve network flow problems via neural decoding (2020)
Chopra, S., Rao, M.R.: The partition problem. Math. Program. 59(1), 87–115 (1993)
Dai, H., Khalil, E.B., Zhang, Y., Dilkina, B., Song, L.: Learning combinatorial optimization algorithms over graphs. In: NIPS (2017)
Demaine, E.D., Emanuel, D., Fiat, A., Immorlica, N.: Correlation clustering in general weighted graphs. Theor. Comput. Sci. 361(2–3), 172–187 (2006)
Derr, T., Ma, Y., Tang, J.: Signed graph convolutional networks. In: ICDM (2018)
Deza, M.M., Laurent, M.: Geometry of Cuts and Metrics. Springer, Heidelberg (1997)
Ding, J.Y., et al.: Accelerating primal solution findings for mixed integer programs based on solution prediction. In: AAAI, vol. 34, no. 02, pp. 1452–1459 (2020)
Fisher, R.A.: The use of multiple measurements in taxonomic problems. Ann. Eugen. 7(2), 179–188 (1936)
Gallier, J.: Spectral theory of unsigned and signed graphs. Applications to graph clustering: a survey (2016)
Gasse, M., Chételat, D., Ferroni, N., Charlin, L., Lodi, A.: Exact combinatorial optimization with graph convolutional neural networks. In: NeurIPS (2019)
Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: ICML (2017)
Gurobi Optimization L: Gurobi optimizer reference manual (2020). http://www.gurobi.com
Ho, K., Kardoost, A., Pfreundt, F.-J., Keuper, J., Keuper, M.: A two-stage minimum cost multicut approach to self-supervised multiple person tracking. In: Ishikawa, H., Liu, C.-L., Pajdla, T., Shi, J. (eds.) ACCV 2020. LNCS, vol. 12623, pp. 539–557. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-69532-3_33
Hou, Y.P.: Bounds for the least Laplacian eigenvalue of a signed graph. Acta Math. Sinica 21(4), 955–960 (2005)
Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., Schiele, B.: DeeperCut: a deeper, stronger, and faster multi-person pose estimation model. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 34–50. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46466-4_3
Joshi, C.K., Laurent, T., Bresson, X.: An efficient graph convolutional network technique for the travelling salesman problem (2019)
Jung, S., Ziegler, S., Kardoost, A., Keuper, M.: Optimizing edge detection for image segmentation with multicut penalties. CoRR abs/2112.05416 (2021)
Kappes, J.H., et al.: A comparative study of modern inference techniques for structured discrete energy minimization problems. Int. J. Comput. Vis. 115(2), 155–184 (2015). https://doi.org/10.1007/s11263-015-0809-x
Kappes, J.H., Speth, M., Andres, B., Reinelt, G., Schn, C.: Globally optimal image partitioning by multicuts. In: Boykov, Y., Kahl, F., Lempitsky, V., Schmidt, F.R. (eds.) EMMCVPR 2011. LNCS, vol. 6819, pp. 31–44. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-23094-3_3
Kardoost, A., Keuper, M.: Solving minimum cost lifted multicut problems by node agglomeration. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11364, pp. 74–89. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20870-7_5
Keuper, M., Andres, B., Brox, T.: Motion trajectory segmentation via minimum cost multicuts. In: ICCV (2015)
Keuper, M., Levinkov, E., Bonneel, N., Lavoué, G., Brox, T., Andres, B.: Efficient decomposition of image and mesh graphs by lifted multicuts. In: ICCV (2015)
Keuper, M., Tang, S., Andres, B., Brox, T., Schiele, B.: Motion segmentation multiple object tracking by correlation co-clustering. TPAMI 42(1), 140–153 (2020)
Keuper, M.: Higher-order minimum cost lifted multicuts for motion segmentation. In: ICCV (2017)
Kim, S., Nowozin, S., Kohli, P., Yoo, C.D.: Higher-order correlation clustering for image segmentation. In: NIPS (2011)
Kim, S., Yoo, C., Nowozin, S., Kohli, P.: Image segmentation using higher-order correlation clustering. TPAMI 36, 1761–1774 (2014)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)
Kool, W., Hoof, H.V., Welling, M.: Attention, learn to solve routing problems! In: ICLR (2019)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)
Kunegis, J., Schmidt, S., Lommatzsch, A., Lerner, J., Luca, E.W.D., Albayrak, S.: Spectral analysis of signed graphs for clustering, prediction and visualization. In: SDM (2010)
Li, Q., Han, Z., Wu, X.M.: Deeper insights into graph convolutional networks for semi-supervised learning. In: AAAI (2018)
Li, Z., Chen, Q., Koltun, V.: Combinatorial optimization with graph convolutional networks and guided tree search. In: NIPS (2018)
Ma, Q., Ge, S., He, D., Thaker, D., Drori, I.: Combinatorial optimization by graph pointer networks and hierarchical reinforcement learning. In: AAAI Workshop on Deep Learning on Graphs: Methodologies and Applications (2020)
Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: ICCV (2001)
Micheli, A.: Neural network for graphs: a contextual constructive approach. IEEE Trans. Neural Netw. 20(3), 498–511 (2009)
Nazari, M., Oroojlooy, A., Snyder, L., Takac, M.: Reinforcement learning for solving the vehicle routing problem. In: NIPS (2018)
Oulabi, Y., Bizer, C.: Extending cross-domain knowledge bases with long tail entities using web table data. In: Advances in Database Technology, pp. 385–396 (2019)
Prates, M.O.R., Avelar, P.H.C., Lemos, H., Lamb, L., Vardi, M.: Learning to solve NP-complete problems - a graph neural network for the decision TSP. In: AAAI (2019)
Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: The graph neural network model. IEEE Trans. Neural Netw. 20(1), 61–80 (2009)
Selsam, D., Lamm, M., Bünz, B., Liang, P., de Moura, L., Dill, D.L.: Learning a sat solver from single-bit supervision (2019)
Shi, J., Malik, J.: Normalized cuts and image segmentation. TPAMI 22(8), 888–905 (2000)
Shi, Y., Huang, Z., Wang, W., Zhong, H., Feng, S., Sun, Y.: Masked label prediction: unified message passing model for semi-supervised classification (2020)
Simonovsky, M., Komodakis, N.: Dynamic edge-conditioned filters in convolutional neural networks on graphs. In: CVPR (2017)
Song, J., Andres, B., Black, M., Hilliges, O., Tang, S.: End-to-end learning for graph decomposition. In: ICCV (2019)
Swoboda, P., Andres, B.: A message passing algorithm for the minimum cost multicut problem. In: CVPR (2017)
Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)
Vinyals, O., Fortunato, M., Jaitly, N.: Pointer networks. In: NIPS (2015)
Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks? In: ICLR (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Jung, S., Keuper, M. (2023). Learning to Solve Minimum Cost Multicuts Efficiently Using Edge-Weighted Graph Convolutional Neural Networks. In: Amini, MR., Canu, S., Fischer, A., Guns, T., Kralj Novak, P., Tsoumakas, G. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2022. Lecture Notes in Computer Science(), vol 13714. Springer, Cham. https://doi.org/10.1007/978-3-031-26390-3_28
Download citation
DOI: https://doi.org/10.1007/978-3-031-26390-3_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26389-7
Online ISBN: 978-3-031-26390-3
eBook Packages: Computer ScienceComputer Science (R0)
