基于图卷积网络的联邦式隐私保护交通预测方法

doi:10.1007/s12204-021-2382-5

摘要/Abstract

摘要： 现有的交通流预测框架由于拥有庞大的交通数据集和深度学习模型的能力，已经取得了巨大的成功。然而，数据隐私和安全性始终是数据需要上传至云端时面临的一大挑战。联邦学习（FL）是一种新兴的分布式数据训练趋势。其主要目标是在不损害数据隐私的前提下训练出高效的通信模型。交通数据具有强大的时空相关性，但先前提出的各种方法并未考虑到交通数据的空间相关性。本文提出了一种基于联邦学习的交通流预测方法，考虑了时空相关性。这项工作采用了差分隐私（DP）方案来保护参与者数据隐私。据我们所知，这是首次在考虑交通数据的时空相关性和差分隐私保护的同时，将联邦学习应用于车辆交通预测。所提出的框架在客户端本地使用差分隐私方案对数据进行训练。然后，在服务器端使用联邦图卷积网络（FedGCN）模型聚合机制来求取本地训练模型的平均值。实验结果表明，FedGCN模型能够准确地预测交通流量。客户端的差分隐私方案有助于用户设置隐私损失预算。

关键词: 联邦学习（FL），交通流量预测，数据隐私，图卷积网络（GCN），差分隐私（DP）

Abstract: Existing traffic flow prediction frameworks have already achieved enormous success due to large traffic datasets and capability of deep learning models. However, data privacy and security are always a challenge in every field where data need to be uploaded to the cloud. Federated learning (FL) is an emerging trend for distributed training of data. The primary goal of FL is to train an efficient communication model without compromising data privacy. The traffic data have a robust spatio-temporal correlation, but various approaches proposed earlier have not considered spatial correlation of the traffic data. This paper presents FL-based traffic flow prediction with spatio-temporal correlation. This work uses a differential privacy (DP) scheme for privacy preservation of participant’s data. To the best of our knowledge, this is the first time that FL is used for vehicular traffic prediction while considering the spatio-temporal correlation of traffic data with DP preservation. The proposed framework trains the data locally at the client-side with DP. It then uses the model aggregation mechanism federated graph convolutional network (FedGCN) at the server-side to find the average of locally trained models. The results of the proposed work show that the FedGCN model accurately predicts the traffic. DP scheme at client-side helps clients to set a budget for privacy loss.

Key words: federated learning (FL), traffic flow prediction, data privacy, graph convolutional network (GCN), differential privacy (DP)

中图分类号:

TP391.4

LONARE Savita1,2, BHRAMARAMBA Ravi2. 基于图卷积网络的联邦式隐私保护交通预测方法[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(3): 509-517.

LONARE Savita^1，2* , BHRAMARAMBA Ravi². Federated Approach for Privacy-Preserving Traffic Prediction Using Graph Convolutional Network[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(3): 509-517.

参考文献

[1] AHMED M S, COOK A R. Analysis of freeway traffic time-series data by using box-jenkins techniques [J]. Transportation Research Record, 1979(722): 1-9.
[2] ALGHAMDI T, ELGAZZAR K, BAYOUMI M, et al. Forecasting traffic congestion using ARIMA modeling [C]/ 2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC ). Tangier, Morocco: IEEE, 2019: 1227-1232.
[3] KUMAR S V, VANAJAKSHI L. Short-term traffic flow prediction using seasonal ARIMA model with limited input data [J]. European Transport Research Review, 2015, 7(3): 1-9.
[4] PAVLYUK D. Short-term traffic forecasting using multivariate autoregressive models [J]. Procedia Engineering, 2017, 178: 57-66.
[5] WEI W Y, WU H H, MA H D. An AutoEncoder and LSTM-based traffic flow prediction method [J]. Sensors, 2019, 19(13): 2946.
[6] AHN J, KO E, KIM E Y. Highway traffic flow prediction using support vector regression and Bayesian classifier [C]//2016 International Conference on Big Data and Smart Computing (BigComp). Hong Kong, China: IEEE, 2016: 239-244.
[7] ZHANG L, LIU Q C, YANG W C, et al. An improved K-nearest neighbor model for short-term traffic flow prediction [J]. Procedia - Social and Behavioral Sciences, 2013, 96: 653-662.
[8] LONARE S, BHRAMARAMBA R. Traffic flow prediction using regression and deep learning approach [M]//New trends in computational vision and bioinspired computing. Cham: Springer, 2020: 641-648.
[9] ZHAO Z, CHEN W H, WU X M, et al. LSTM network: A deep learning approach for short-term traffic forecast [J]. IET Intelligent Transport Systems, 2017, 11(2): 68-75.
[10] ZHANG W B, YU Y H, QI Y, et al. Short-term traffic flow prediction based on spatio-temporal analysis and CNN deep learning [J]. Transportmetrica A: Transport Science, 2019, 15(2): 1688-1711.
[11] MIN W L, WYNTER L. Real-time road traffic prediction with spatio-temporal correlations [J]. Transportation Research Part C : Emerging Technologies, 2011, 19(4): 606-616.
[12] WU Z H, PAN S R, CHEN F W, et al. A comprehensive survey on graph neural networks [J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(1): 4-24.
[13] ZHAO L, SONG Y J, ZHANG C, et al. T-GCN: A temporal graph convolutional network for traffic prediction [J] IEEE Transactions on Intelligent Transportation Systems, 2020, 21(9): 3848-3858.
[14] KHODABANDELOU G, KATRANJI M, KRAIEM S, et al. Attention-based gated recurrent unit for links traffic speed forecasting [C]//2019 IEEE Intelligent Transportation Systems Conference (ITSC ). Auckland, New Zealand: IEEE, 2019: 2577-2583.
[15] LI Y G, YU R, SHAHABI C, et al. Diffusion convolutional recurrent neural network: Datadriven traffic forecasting [EB/OL]. (2018-02-22). https://arxiv.org/abs/1707.01926.
[16] ZHAO L, SONG Y J, ZHANG C, et al. T-GCN: A temporal graph convolutional network for traffic prediction [J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(9): 3848-3858.
[17] PAN Z Y, LIANG Y X, WANG W F, et al. Urban traffic prediction from spatio-temporal data using deep meta learning [C]//25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. Anchorage, AK, USA: ACM, 2019: 1720-1730.
[18] DE MEDRANO R, AZNARTE J L. A spatio-temporal attention-based spot-forecasting framework for urban traffic prediction [J]. Applied Soft Computing, 2020, 96: 106615.
[19] YU B, YIN H T, ZHU Z X. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting [C]//Twenty-Seventh International Joint Conference on Artificial Intelligence. Stockholm, Sweden: International Joint Conferences on Artificial Intelligence Organization, 2018: 3634-3640.
[20] GUO S N, LIN Y F, FENG N, et al. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting [J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33: 922-929.
[21] ELBIR A M, SONER B, COLERI S. Federated learning in vehicular networks [EB/OL]. (2020-09-19). https://arxiv.org/abs/2006.01412.
[22] LIM W Y B, HUANG J Q, XIONG Z H, et al. Towards federated learning in UAV-enabled Internet of vehicles: A multi-dimensional contract-matching approach [J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(8): 5140-5154.
[23] SHIRI H, PARK J, BENNIS M. Communicationefficient massive UAV online path control: Federated learning meets mean-field game theory [J]. IEEE Transactions on Communications, 2020, 68(11): 6840- 6857.
[24] SAPUTRA Y M, NGUYEN D, DINH H T, et al. Federated learning meets contract theory: Economicefficiency framework for electric vehicle networks [J]. IEEE Transactions on Mobile Computing, 2020. https://doi.org/10.1109/TMC.2020.3045987 (published online).
[25] VAN HULST J M, ZENI M, KR ¨OLLER A, et al. Beyond privacy regulations: An ethical approach to data usage in transportation [EB/OL]. (2020-04-01). https://arxiv.org/abs/2004.00491.
[26] LIU Y, YU J J Q, KANG J W, et al. Privacypreserving traffic flow prediction: A federated learning approach [J]. IEEE Internet of Things Journal, 2020, 7(8): 7751-7763.
[27] YIN F, LIN Z D, KONG Q L, et al. FedLoc: federated learning framework for data-driven cooperative localization and location data processing [J]. IEEE Open Journal of Signal Processing, 2020, 1: 187-215.
[28] CHEN C C, ZHOU J, WU B Z, et al. Practical privacy preserving POI recommendation [J]. ACM Transactions on Intelligent Systems and Technology, 2020, 11(5): 1-20.
[29] CIFTLER B S, ALBASEER A, LASLA N, et al. Federated learning for RSS fingerprint-based localization: A privacy-preserving crowdsourcing method [C]//2020 International Wireless Communications and Mobile Computing (IWCMC ). Limassol, Cyprus: IEEE, 2020: 2112-2117.
[30] LIANG X L, LIU Y, CHEN T J, et al. Federated transfer reinforcement learning for autonomous driving [EB/OL]. (2019-10-14). https://arxiv.org/abs/1910.06001.
[31] SAPUTRA Y M, HOANG D T, NGUYEN D N, et al. Energy demand prediction with federated learning for electric vehicle networks [C]//2019 IEEE Global Communications Conference (GLOBECOM ). Waikoloa, HI, USA: IEEE, 2019: 1-6.
[32] MCMAHAN H B, MOORE E, RAMAGE D, et al. Communication-efficient learning of deep networks from decentralized data [EB/OL]. (2017-02-28). https://arxiv.org/abs/1602.05629.
[33] DEFFERRARD M, BRESSON X, VANDERGHEYNST P. Convolutional neural networks on graphs with fast localized spectral filtering [C]//30th Annual Conference on Neural Information Processing Systems. Barcelona, Spain: Curran Associates, Inc., 2016: 3844-3852.
[34] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks [EB/OL] (2017-02-22). https://arxiv.org/abs/1609.02907.
[35] HUANG Z H, HU R, GUO Y X, et al. DP-ADMM: ADMM-based distributed learning with differential privacy [J]. IEEE Transactions on Information Forensics and Security, 2020, 15: 1002-1012.
[36] DWORK C, MCSHERRY F, NISSIM K, et al. Calibrating noise to sensitivity in private data analysis [M]//Theory of cryptography. Berlin, Heidelberg: Springer Berlin Heidelberg, 2006: 265-284.
[37] HOLOHAN N, LEITH D J, MASON O. Optimal differentially private mechanisms for randomised response [J]. IEEE Transactions on Information Forensics and Security, 2017, 12(11): 2726-2735.
[38] WANG Y, WU X, HU D. Using randomized response for differential privacy-preserving data collection [C]//Workshop Proceedings of the EDBT/ICDT 2016 Joint Conference. Bordeaux: CEUR-WS, 2016.
[39] DU W L, ZHAN Z J. Using randomized response techniques for privacy-preserving data mining [C]//Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Washington, DC, USA: ACM, 2003: 505-510.
[40] PHAN N, WU X T, HU H, et al. Adaptive Laplace mechanism: Differential privacy preservation in deep learning [C]//2017 IEEE International Conference on Data Mining (ICDM ). New Orleans, LA, USA. IEEE, 2017: 385-394.
[41] COSTEA S, TAPUS N. Input validation for the Laplace differential privacy mechanism [C]//2015 20th International Conference on Control Systems and Computer Science. Bucharest, Romania: IEEE, 2015: 469-474.
[42] ILVENTO C. Implementing the exponential mechanism with base-2 differential privacy [C]//Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security. Virtual Event, USA: ACM, 2020: 117-142.
[43] GEIPING J, BAUERMEISTER H, DR¨OGE H, et al. Inverting gradients: How easy is it to break privacy in federated learning? [EB/OL]. (2020-09-11). https://arxiv.org/abs/2003.14053.