Skip to main content
SpringerLink
Log in

P\(^2\)CG: a privacy preserving collaborative graph neural network training framework

  • Regular Paper
  • Published:
The VLDB Journal Aims and scope Submit manuscript

Abstract

Graph neural networks (GNNs) and their variants have generalized deep learning methods into non-Euclidean graph data, bringing substantial improvement in many graph mining tasks. In practice, the large graph could be isolated by different databases. Recently, user privacy protection has become a crucial concern in practical machine learning, which motivates us to explore a GNN framework with data sharing and without violating user privacy leakage in the meanwhile. However, it is challenging to scale GNN training to edge partitioned distributed graph databases while preserving data privacy and model quality. In this paper, we propose a privacy preserving collaborative GNN training framework, P\(^2\)CG, aiming to obtain competitive model performance as the centralized setting. We present the clustering-based differential privacy algorithm to reduce the model degradation caused by the noisy edges generation. Moreover, we propose a novel interaction-based secure multi-layer graph convolution algorithm to alleviate the noise diffusion problem. Experimental results on the benchmark datasets and the production dataset in Tencent Inc. show that P\(^2\)CG can significantly increase the model performance and obtain competitive results as a centralized setting.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Notes

  1. https://docs.dgl.ai/en/0.4.x/api/python/data.html.

References

  1. Tencent Inc. Weshi (2021). https://weishi.qq.com

  2. Abu-El-Haija, S., Kapoor, A., Perozzi, B., Lee, J.: N-GCN: multi-scale graph convolution for semi-supervised node classification. In: UAI, p. 310 (2019)

  3. Abu-El-Haija, S., Perozzi, B., Kapoor, A., Alipourfard, N., Lerman, K., Harutyunyan, H., Steeg, G.V., Galstyan, A.: Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9–15 June 2019, Long Beach, California, USA, Proceedings of Machine Learning Research, vol. 97, pp. 21–29. PMLR (2019). http://proceedings.mlr.press/v97/abu-el-haija19a.html

  4. Albrecht, J.P.: How the GDPR will change the world. Eur. Data Prot. L. Rev. 2, 287 (2016)

    Article  Google Scholar 

  5. Aono, Y., Hayashi, T., Phong, L.T., Wang, L.: Scalable and secure logistic regression via homomorphic encryption. In: CODASPY, pp. 142–144 (2016). https://doi.org/10.1145/2857705.2857731

  6. Beigi, G., Mosallanezhad, A., Guo, R., Alvari, H., Nou, A., Liu, H.: Privacy-aware recommendation with private-attribute protection using adversarial learning. In: WSDM, pp. 34–42 (2020). https://doi.org/10.1145/3336191.3371832

  7. Bonchi, F., Gionis, A., Tassa, T.: Identity obfuscation in graphs through the information theoretic lens. In: ICDE (2011). https://doi.org/10.1109/ICDE.2011.5767905

  8. Bruna, J., Zaremba, W., Szlam, A., LeCun, Y.: Spectral networks and locally connected networks on graphs. In: ICLR (2014). arXiv:http://arxiv.org/abs/1312.6203

  9. Chaudhuri, K., Monteleoni, C.: Privacy-preserving logistic regression. In: NIPS, pp. 289–296 (2008). http://papers.nips.cc/paper/3486-privacy-preserving-logistic-regression

  10. Chen, M., Wei, Z., Ding, B., Li, Y., Yuan, Y., Du, X., Wen, J.: Scalable graph neural networks via bidirectional propagation. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6–12, 2020, Virtual (2020). https://proceedings.neurips.cc/paper/2020/hash/a7789ef88d599b8df86bbee632b2994d-Abstract.html

  11. Chen, X., Song, X., Ren, R., Zhu, L., Cheng, Z., Nie, L.: Fine-grained privacy detection with graph-regularized hierarchical attentive representation learning. TOIS 38(4), 37:1–37:26 (2020). https://doi.org/10.1145/3406109

  12. Cheng, K., Fan, T., Jin, Y., Liu, Y., Chen, T., Yang, Q.: Secureboost: a lossless federated learning framework. CoRR. arXiv:1901.08755 (2019)

  13. Cristofaro, E.D., Tsudik, G.: Practical private set intersection protocols with linear computational and bandwidth complexity. IACR Cryptol. ePrint Arch. 2009, 491 (2009). http://eprint.iacr.org/2009/491

  14. Dankar, F.K.: Privacy preserving linear regression on distributed databases. Trans. Data Priv. 8(1), 3–28 (2015). http://www.tdp.cat/issues11/tdp.a215a15.pdf

  15. Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: NeurIPS, pp. 3837–3845 (2016)

  16. Dev, H.: Privacy preserving social graphs for high precision community detection. In: SIGMOD, pp. 1615–1616 (2014). https://doi.org/10.1145/2588555.2612668

  17. Dong, C., Chen, L., Wen, Z.: When private set intersection meets big data: an efficient and scalable protocol. In: Sadeghi, A., Gligor, V.D., Yung, M. (eds.) 2013 ACM SIGSAC Conference on Computer and Communications Security, CCS’13, Berlin, Germany, November 4–8, 2013, pp. 789–800. ACM (2013). https://doi.org/10.1145/2508859.2516701

  18. Duong, C.T., Hoang, D., Yin, H., Weidlich, M., Nguyen, Q.V.H., Aberer, K.: Efficient streaming subgraph isomorphism with graph neural networks. Proc. VLDB Endow. 14(5), 730–742 (2021). http://www.vldb.org/pvldb/vol14/p730-duong.pdf

  19. Dwork, C.: Differential privacy: A survey of results. In: TAMC, pp. 1–19 (2008). https://doi.org/10.1007/978-3-540-79228-4_1

  20. Dwork, C., McSherry, F., Nissim, K., Smith, A.D.: Calibrating noise to sensitivity in private data analysis. In: TCC (2006). https://doi.org/10.1007/11681878_14

  21. Eliás, M., Kapralov, M., Kulkarni, J., Lee, Y.T.: Differentially private release of synthetic graphs. In: SODA, pp. 560–578 (2020). https://doi.org/10.1137/1.9781611975994.34

  22. Freedman, M.J., Nissim, K., Pinkas, B.: Efficient private matching and set intersection. In: Cachin, C., Camenisch, J. (eds.) Advances in Cryptology—EUROCRYPT 2004, International Conference on the Theory and Applications of Cryptographic Techniques, Interlaken, Switzerland, May 2–6, 2004, Proceedings, Lecture Notes in Computer Science, vol. 3027, pp. 1–19. Springer (2004). https://doi.org/10.1007/978-3-540-24676-3_1

  23. Friedman, A., Schuster, A.: Data mining with differential privacy. In: SIGKDD, pp. 493–502 (2010). https://doi.org/10.1145/1835804.1835868

  24. Fu, H., Zhang, A., Xie, X.: Effective social graph deanonymization based on graph structure and descriptive information. TIST 6(4), 49:1–49:29 (2015). https://doi.org/10.1145/2700836

  25. Gao, J., Chen, J., Li, Z., Zhang, J.: ICS-GNN: lightweight interactive community search via graph neural network. Proc. VLDB Endow. 14(6), 1006–1018 (2021). http://www.vldb.org/pvldb/vol14/p1006-gao.pdf

  26. Gao, T., Li, F.: Sharing social networks using a novel differentially private graph model. In: CCNC, pp. 1–4 (2019). https://doi.org/10.1109/CCNC.2019.8651689

  27. Gilad-Bachrach, R., Dowlin, N., Laine, K., Lauter, K.E., Naehrig, M., Wernsing, J.: Cryptonets: applying neural networks to encrypted data with high throughput and accuracy. In: ICML (2016)

  28. Gong, M., Pan, K., Xie, Y., Qin, A.K., Tang, Z.: Preserving differential privacy in deep neural networks with relevance-based adaptive noise imposition. Neural Netw. (2020). https://doi.org/10.1016/j.neunet.2020.02.001

  29. Hamilton, W.L., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: NeurIPS, pp. 1024–1034 (2017)

  30. Hanai, M., Suzumura, T., Tan, W.J., Liu, E.S., Theodoropoulos, G., Cai, W.: Distributed edge partitioning for trillion-edge graphs. PVLDB 12(13), 2379–2392 (2019). http://www.vldb.org/pvldb/vol12/p2379-hanai.pdf

  31. Harth, A., Umbrich, J., Hogan, A., Decker, S.: YARS2: a federated repository for querying graph structured data from the web. In: The Semantic Web, 6th International Semantic Web Conference, 2nd Asian Semantic Web Conference, ISWC 2007 + ASWC 2007, Busan, Korea, November 11–15, 2007, Lecture Notes in Computer Science, vol. 4825, pp. 211–224. Springer (2007). https://doi.org/10.1007/978-3-540-76298-0_16

  32. He, X., Deng, K., Wang, X., Li, Y., Zhang, Y., Wang, M.: Lightgcn: simplifying and powering graph convolution network for recommendation. In: SIGIR, pp. 639–648 (2020). https://doi.org/10.1145/3397271.3401063

  33. Hu, Y., Niu, D., Yang, J., Zhou, S.: FDML: A collaborative machine learning framework for distributed features. In: SIGKDD (2019). https://doi.org/10.1145/3292500.3330765

  34. Huang, J., Abadi, D.: LEOPARD: lightweight edge-oriented partitioning and replication for dynamic graphs. PVLDB 9(7), 540–551 (2016). https://doi.org/10.14778/2904483.2904486. http://www.vldb.org/pvldb/vol9/p540-huang.pdf

  35. Huang, J., Abadi, D.J., Ren, K.: Scalable SPARQL querying of large RDF graphs. Proc. VLDB Endow. 4(11), 1123–1134 (2011)

    Article  Google Scholar 

  36. Jin, B., Gao, C., He, X., Jin, D., Li, Y.: Multi-behavior recommendation with graph convolutional networks. In: SIGIR, pp. 659–668 (2020). https://doi.org/10.1145/3397271.3401072

  37. Jorgensen, Z., Yu, T., Cormode, G.: Publishing attributed social graphs with formal privacy guarantees. In: SIGMOD (2016). https://doi.org/10.1145/2882903.2915215

  38. Karypis, G., Kumar, V.: A fast and high quality multilevel scheme for partitioning irregular graphs. SIAM 20(1), 359–392 (1998). https://doi.org/10.1137/S1064827595287997

    Article  MathSciNet  MATH  Google Scholar 

  39. Khan, K., ur Rehman, S., Aziz, K., Fong, S., Sarasvady, S., Vishwa, A.: DBSCAN: past, present and future. In: The 5th International Conference on the Applications of Digital Information and Web Technologies, ICADIWT 2014, Chennai, India, February 17–19, 2014, pp. 232–238. IEEE (2014). https://doi.org/10.1109/ICADIWT.2014.6814687

  40. Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)

  41. Koren, Y., Bell, R.M., Volinsky, C.: Matrix factorization techniques for recommender systems. Computer 42(8), 30–37 (2009). https://doi.org/10.1109/MC.2009.263

    Article  Google Scholar 

  42. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)

  43. Lai, S., Yuan, X., Sun, S., Liu, J.K., Liu, Y., Liu, D.: Graphse\({^2}\): An encrypted graph database for privacy-preserving social search. In: Proceedings of the 2019 ACM Asia Conference on Computer and Communications Security, AsiaCCS 2019, Auckland, New Zealand, July 09–12, 2019, pp. 41–54. ACM (2019). https://doi.org/10.1145/3321705.3329803

  44. LeCun, Y., Boser, B.E., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W.E., Jackel, L.D.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989). https://doi.org/10.1162/neco.1989.1.4.541

    Article  Google Scholar 

  45. Li, K., Lu, G., Luo, G., Cai, Z.: Seed-free graph de-anonymiztiation with adversarial learning. In: CIKM, pp. 745–754 (2020). https://doi.org/10.1145/3340531.3411970

  46. Lieberman, M.D., Choudhury, S., Hughes, M., Patrone, D., Jr., R.T.H., Piatko, C.D., Chapman, M., Marple, J.P., Silberberg, D.: Parasol: An architecture for cross-cloud federated graph querying. In: Proceedings of the 3rd Workshop on Data analytics in the Cloud, DanaC 2014, June 22, 2014, Snowbird, Utah, USA, In Conjunction with ACM SIGMOD/PODS Conference, pp. 4:1–4:4. ACM (2014). https://doi.org/10.1145/2627770.2627771

  47. Lin, Y., Han, S., Mao, H., Wang, Y., Dally, B.: Deep gradient compression: reducing the communication bandwidth for distributed training. In: ICLR (2018)

  48. Liu, C., Liu, I., Yao, W., Li, J.: K-Anonymity against neighborhood attacks in weighted social networks. Secur Commun Netw 8(18), 3864–3882 (2015). https://doi.org/10.1002/sec.1306

    Article  Google Scholar 

  49. Liu, K., Terzi, E.: Towards identity anonymization on graphs. In: SIGMOD, pp. 93–106 (2008). https://doi.org/10.1145/1376616.1376629

  50. Liu, S., Ounis, I., Macdonald, C., Meng, Z.: A heterogeneous graph neural model for cold-start recommendation. In: SIGIR, pp. 2029–2032 (2020). https://doi.org/10.1145/3397271.3401252

  51. Mao, K., Xiao, X., Zhu, J., Lu, B., Tang, R., He, X.: Item tagging for information retrieval: a tripartite graph neural network based approach. In: SIGIR, pp. 2327–2336 (2020). https://doi.org/10.1145/3397271.3401438

  52. McMahan, B., Moore, E., Ramage, D., Hampson, S., y Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: AISTATS, vol. 54, pp. 1273–1282 (2017)

  53. McMahan, H.B., Moore, E., Ramage, D., y Arcas, B.A.: Federated learning of deep networks using model averaging. CoRR (2016). arXiv:http://arxiv.org/abs/1602.05629

  54. McSherry, F., Talwar, K.: Mechanism design via differential privacy. In: FOCS, pp. 94–103 (2007). https://doi.org/10.1109/FOCS.2007.41

  55. Mittal, P., Papamanthou, C., Song, D.X.: Preserving link privacy in social network based systems. In: NDSS (2013)

  56. Mohassel, P., Zhang, Y.: Secureml: a system for scalable privacy-preserving machine learning. In: SP, pp. 19–38 (2017). https://doi.org/10.1109/SP.2017.12

  57. Monti, F., Boscaini, D., Masci, J., Rodolà, E., Svoboda, J., Bronstein, M.M.: Geometric deep learning on graphs and manifolds using mixture model CNNs. In: CVPR, pp. 5425–5434 (2017). https://doi.org/10.1109/CVPR.2017.576

  58. Murtagh, F., Contreras, P.: Algorithms for hierarchical clustering: an overview. WIREs Data Mining Knowl. Discov. 2(1), 86–97 (2012). https://doi.org/10.1002/widm.53

    Article  Google Scholar 

  59. Ng, A.Y., Jordan, M.I., Weiss, Y.: On spectral clustering: Analysis and an algorithm. In: T.G. Dietterich, S. Becker, Z. Ghahramani (eds.) Advances in Neural Information Processing Systems 14 [Neural Information Processing Systems: Natural and Synthetic, NIPS 2001, December 3-8, 2001, Vancouver, BC, Canada], pp. 849–856. MIT Press (2001). https://proceedings.neurips.cc/paper/2001/hash/801272ee79cfde7fa5960571fee36b9b-Abstract.html

  60. Nguyen, H.H., Imine, A., Rusinowitch, M.: Network structure release under differential privacy. Trans. Data Priv. 9(3), 215–241 (2016). http://www.tdp.cat/issues16/abs.a248a16.php

  61. Paverd, A., Martin, A., Brown, I.: Modelling and automatically analysing privacy properties for honest-but-curious adversaries. Tech., Rep. (2014)

  62. Pei, H., Wei, B., Chang, K.C., Lei, Y., Yang, B.: Geom-gcn: geometric graph convolutional networks. In: ICLR (2020)

  63. Qin, Z., Bai, Y., Sun, Y.: Ghashing: semantic graph hashing for approximate similarity search in graph databases. In: Gupta, R., Liu, Y., Tang, J., Prakash, B.A. (eds.) KDD ’20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event, CA, USA, August 23–27, 2020, pp. 2062–2072. ACM (2020). https://doi.org/10.1145/3394486.3403257

  64. Qiu, R., Huang, Z., Li, J., Yin, H.: Exploiting cross-session information for session-based recommendation with graph neural networks. TOIS 38(3), 22:1–22:23 (2020). https://doi.org/10.1145/3382764

  65. Qiu, R., Yin, H., Huang, Z., Chen, T.: GAG: global attributed graph neural network for streaming session-based recommendation. In: SIGIR, pp. 669–678 (2020). https://doi.org/10.1145/3397271.3401109

  66. Ragesh, R., Sellamanickam, S., Iyer, A., Bairi, R., Lingam, V.: Hetegcn: heterogeneous graph convolutional networks for text classification. In: WSDM, pp. 860–868 (2021). https://doi.org/10.1145/3437963.3441746

  67. Rastogi, V., Hay, M., Miklau, G., Suciu, D.: Relationship privacy: output perturbation for queries with joins. In: PODS (2009). https://doi.org/10.1145/1559795.1559812

  68. Rivest, R.L., Adleman, L., Dertouzos, M.L., et al.: On data banks and privacy homomorphisms. FSC 4(11), 169–180 (1978)

    MathSciNet  Google Scholar 

  69. Rossi, E., Frasca, F., Chamberlain, B., Eynard, D., Bronstein, M.M., Monti, F.: SIGN: scalable inception graph neural networks. CoRR (2020). arXiv:2004.11198

  70. Rouhani, B.D., Riazi, M.S., Koushanfar, F.: Deepsecure: scalable provably-secure deep learning. In: DAC, pp. 2:1–2:6 (2018). https://doi.org/10.1145/3195970.3196023

  71. Sajadmanesh, S., Gatica-Perez, D.: When differential privacy meets graph neural networks. CoRR (2020). arXiv:2006.05535

  72. Scannapieco, M., Figotin, I., Bertino, E., Elmagarmid, A.K.: Privacy preserving schema and data matching. In: SIGMOD (2007). https://doi.org/10.1145/1247480.1247553

  73. 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). https://doi.org/10.1109/TNN.2008.2005605

    Article  Google Scholar 

  74. Shao, Y., Liu, J., Shi, S., Zhang, Y., Cui, B.: Fast de-anonymization of social networks with structural information. Data Sci. Eng. 4(1), 76–92 (2019). https://doi.org/10.1007/s41019-019-0086-8

    Article  Google Scholar 

  75. Sharma, S., Powers, J., Chen, K.: Privategraph: privacy-preserving spectral analysis of encrypted graphs in the cloud. IEEE Trans. Knowl. Data Eng. 31(5), 981–995 (2019). https://doi.org/10.1109/TKDE.2018.2847662

    Article  Google Scholar 

  76. Sihag, V.K.: A clustering approach for structural k-anonymity in social networks using genetic algorithm. In: CUBE, pp. 701–706 (2012). https://doi.org/10.1145/2381716.2381850

  77. Sweeney, L.: k-Anonymity: a model for protecting privacy. IJUFKS 10(5), 557–570 (2002). https://doi.org/10.1142/S0218488502001648

    Article  MathSciNet  MATH  Google Scholar 

  78. Tang, X., Li, Y., Sun, Y., Yao, H., Mitra, P., Wang, S.: Transferring robustness for graph neural network against poisoning attacks. In: WSDM, pp. 600–608 (2020). https://doi.org/10.1145/3336191.3371851

  79. Wang, H., Wang, N., Yeung, D.: Collaborative deep learning for recommender systems. In: Cao, L., Zhang, C., Joachims, T., Webb, G.I., Margineantu, D.D., Williams, G. (eds.) Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, NSW, Australia, August 10–13, 2015, pp. 1235–1244. ACM (2015). https://doi.org/10.1145/2783258.2783273

  80. Wang, Y., Wu, X.: Preserving differential privacy in degree-correlation based graph generation. Trans. Data Priv. 6(2), 127–145 (2013). http://www.tdp.cat/issues11/abs.a113a12.php

  81. Wang, Y., Wu, X., Wu, L.: Differential privacy preserving spectral graph analysis. In: PAKDD, vol. 7819, pp. 329–340 (2013). https://doi.org/10.1007/978-3-642-37456-2_28

  82. Wei, K., Li, J., Ma, C., Ding, M., Wei, S., Wu, F., Chen, G., Ranbaduge, T.: Vertical federated learning: challenges, methodologies and experiments. CoRR (2022). arXiv:2202.04309

  83. Wu, C., Wu, F., Cao, Y., Huang, Y., Xie, X.: Fedgnn: federated graph neural network for privacy-preserving recommendation. CoRR (2021). arXiv:2102.04925

  84. Wu, F., Jr., A.H.S., Zhang, T., Fifty, C., Yu, T., Weinberger, K.Q.: Simplifying graph convolutional networks. In: ICML (2019). http://proceedings.mlr.press/v97/wu19e.html

  85. Wu, L., Yang, Y., Zhang, K., Hong, R., Fu, Y., Wang, M.: Joint item recommendation and attribute inference: An adaptive graph convolutional network approach. In: SIGIR, pp. 679–688 (2020). https://doi.org/10.1145/3397271.3401144

  86. Wu, X., Li, F., Kumar, A., Chaudhuri, K., Jha, S., Naughton, J.F.: Bolt-on differential privacy for scalable stochastic gradient descent-based analytics. In: SIGMOD, pp. 1307–1322 (2017). https://doi.org/10.1145/3035918.3064047

  87. Xu, K., Li, C., Tian, Y., Sonobe, T., Kawarabayashi, K., Jegelka, S.: Representation learning on graphs with jumping knowledge networks. In: ICML, vol. 80, pp. 5449–5458. PMLR (2018). http://proceedings.mlr.press/v80/xu18c.html

  88. Xu, X., Yuruk, N., Feng, Z., Schweiger, T.A.J.: SCAN: a structural clustering algorithm for networks. In: SIGKDD, pp. 824–833 (2007). https://doi.org/10.1145/1281192.1281280

  89. Yang, Q., Liu, Y., Chen, T., Tong, Y.: Federated machine learning: concept and applications. TIST (2), 12:1–12:19 (2019). https://doi.org/10.1145/3298981

  90. Ying, X., Wu, X.: Graph generation with prescribed feature constraints. In: SDM, pp. 966–977 (2009). https://doi.org/10.1137/1.9781611972795.83

  91. Yu, F., Zhu, Y., Liu, Q., Wu, S., Wang, L., Tan, T.: TAGNN: target attentive graph neural networks for session-based recommendation. In: SIGIR, pp. 1921–1924 (2020). https://doi.org/10.1145/3397271.3401319

  92. Yuan, M., Chen, L., Rao, W., Mei, H.: A general framework for publishing privacy protected and utility preserved graph. In: ICDM, pp. 1182–1187 (2012). https://doi.org/10.1109/ICDM.2012.62

  93. Yuan, M., Chen, L., Yu, P.S.: Personalized privacy protection in social networks. PVLDB 4(2), 141–150 (2010). https://doi.org/10.14778/1921071.1921080

    Article  Google Scholar 

  94. Yuan, M., Chen, L., Yu, P.S., Mei, H.: Privacy preserving graph publication in a distributed environment. WWW (2015). https://doi.org/10.1007/s11280-014-0290-4

  95. Zeng, K., Yang, J., Wang, H., Shao, B., Wang, Z.: A distributed graph engine for web scale RDF data. Proc. VLDB Endow. 6(4), 265–276 (2013). https://doi.org/10.14778/2535570.2488333

    Article  Google Scholar 

  96. Zhang, J., Cormode, G., Procopiuc, C.M., Srivastava, D., Xiao, X.: Private release of graph statistics using ladder functions. In: SIGMOD, pp. 731–745 (2015). https://doi.org/10.1145/2723372.2737785

  97. Zhang, J., Zhang, Z., Xiao, X., Yang, Y., Winslett, M.: Functional mechanism: regression analysis under differential privacy. PVLDB 5(11), 1364–1375 (2012). https://doi.org/10.14778/2350229.2350253. http://vldb.org/pvldb/vol5/p1364_junzhang_vldb2012.pdf

  98. Zhang, S., Yin, H., Chen, T., Nguyen, Q.V.H., Huang, Z., Cui, L.: Gcn-based user representation learning for unifying robust recommendation and fraudster detection. In: SIGIR, pp. 689–698 (2020). https://doi.org/10.1145/3397271.3401165

  99. Zhang, W., Miao, X., Shao, Y., Jiang, J., Chen, L., Ruas, O., Cui, B.: Reliable data distillation on graph convolutional network. In: SIGMOD, pp. 1399–1414 (2020). https://doi.org/10.1145/3318464.3389706

  100. Zheng, D., Song, X., Ma, C., Tan, Z., Ye, Z., Dong, J., Xiong, H., Zhang, Z., Karypis, G.: DGL-KE: training knowledge graph embeddings at scale. In: SIGIR, pp. 739–748 (2020). https://doi.org/10.1145/3397271.3401172

  101. Zhou, X., Sun, J., Li, G., Feng, J.: Query performance prediction for concurrent queries using graph embedding. Proc. VLDB Endow. 13(9), 1416–1428 (2020). https://doi.org/10.14778/3397230.3397238. http://www.vldb.org/pvldb/vol13/p1416-zhou.pdf

  102. Zhu, L., Liu, Z., Han, S.: Deep leakage from gradients. In: NeurIPS, pp. 14747–14756 (2019)

  103. Zou, L., Chen, L., Özsu, M.T.: K-automorphism: A general framework for privacy preserving network publication. PVLDB 2(1), 946–957 (2009). https://doi.org/10.14778/1687627.1687734

Download references

Acknowledgements

This work is supported by the National Key Research and Development Program of China (No. 2020AAA0105200), the National Natural Science Foundation of China (No. 61832001), PKU-Tencent joint research Lab. Yingxia Shao’s work is supported by the National Natural Science Foundation of China (Nos. 62272054, U1936104, 62192784), and CCF-Tencent Open Fund.

Author information

Author notes

  1. Xupeng Miao and Wentao Zhang are contributed equally to this work.

Authors and Affiliations

  1. School of CS & Key Laboratory of High Confidence Software Technologies (MOE), Peking University, Beijing, China

    Xupeng Miao, Wentao Zhang, Yuezihan Jiang, Fangcheng Fu & Bin Cui

  2. Beijing University of Posts and Telecommunications, BUPT, Beijing, China

    Yingxia Shao

  3. Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong

    Lei Chen

  4. TEG, Tencent Inc., Shenzhen, China

    Yangyu Tao

  5. Beijing Academy of Artificial Intelligence, Beijing, China

    Gang Cao

  6. Institute of Computational Social Science, Peking University (Qingdao), Beijing, China

    Bin Cui

  7. Department of Data Platform, TEG, Tencent Inc., Shenzhen, China

    Fangcheng Fu

Authors
  1. Xupeng Miao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wentao Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yuezihan Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Fangcheng Fu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yingxia Shao
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Lei Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Yangyu Tao
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Gang Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Bin Cui
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Xupeng Miao or Bin Cui.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Miao, X., Zhang, W., Jiang, Y. et al. P\(^2\)CG: a privacy preserving collaborative graph neural network training framework. The VLDB Journal 32, 717–736 (2023). https://doi.org/10.1007/s00778-022-00768-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00778-022-00768-8

Keywords

Search

Navigation