Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (9): 2545-2551.DOI: 10.11772/j.issn.1001-9081.2020111859

Special Issue: 人工智能

• Artificial intelligence • Previous Articles     Next Articles

Trajectory prediction model of social network users based on self-supervised learning

DAI Yurou1, YANG Qing1,2, ZHANG Fengli1, ZHOU Fan1   

  1. 1. School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu Sichuan 610054, China;
    2. The 10 th Research Institute of China Electronics Technology Group Corporation, Chengdu Sichuan 610036, China
  • Received:2020-11-26 Revised:2021-01-26 Online:2021-09-10 Published:2021-05-12
  • Supported by:
    This work is partially supported by the Surface Program of National Natural Science Foundation of China (62072077).


代雨柔1, 杨庆1,2, 张凤荔1, 周帆1   

  1. 1. 电子科技大学 信息与软件工程学院, 成都 610054;
    2. 中国电子科技集团公司第十研究所, 成都 610036
  • 通讯作者: 周帆
  • 作者简介:代雨柔(1997-),女,重庆人,硕士研究生,主要研究方向:轨迹预测、社交网络;杨庆(1996-),男,河南信阳人,硕士研究生,主要研究方向:深度学习、时空预测;张凤荔(1963-),女,四川成都人,教授,博士,主要研究方向:网络安全、深度学习;周帆(1981-),男,四川成都人,副教授,博士,主要研究方向:机器学习、数据挖掘。
  • 基金资助:

Abstract: Aiming at the existing problems in user trajectory data modeling such as the sparsity of check-in points, long-term dependencies and complex moving patterns, a social network user trajectory prediction model based on self-supervised learning, called SeNext, was proposed to model and train the user trajectory to predict the next Point Of Interest (POI) of the user. First, data augmentation was utilized to expand the training trajectory samples, which solved the problem of the deficiency of model generalization capability caused by insufficient data and too few footprints of some users. Second, Recurrent Neural Network (RNN), Convolutional Neural Network (CNN) and attention mechanism were adopted into the modeling of current and historical trajectories respectively, so as to extract effective representations from high-dimensional sparse data to match the most similar moving patterns of users in the past. Finally, SeNext learned the implicit representations in the latent space by combining self-supervised learning and introducing contrastive loss Noise Contrastive Estimation (InfoNCE) to predict the next POI of the user. Experimental results show that compared to the state-of-the-artVariational Attention based Next (VANext)model, SeNext improves the prediction accuracy about 11% on Top@1.

Key words: trajectory prediction, self-supervised learning, contrastive learning, attention mechanism, deep learning

摘要: 针对当前用户轨迹数据建模中存在的签到点稀疏性、长时间依赖性和移动模式复杂等问题,提出基于自监督学习的社交网络用户轨迹预测模型SeNext,对用户轨迹进行建模和训练来预测用户的下一个兴趣点(POI)。首先,使用数据增强的方式来丰富训练数据样本,以解决数据不足及个别用户足迹太少导致的模型泛化能力不足的问题;其次,将循环神经网络(RNN)、卷积神经网络(CNN)和注意力机制分别用于当前轨迹和历史轨迹的建模中,以此从高维稀疏的数据中提取有用的表示,用来匹配用户过去最相似的移动方式。最后,通过结合自监督学习并引入对比损失优化噪声对比估计(InfoNCE),SeNext在潜在空间学习隐含表示来预测用户的下一个POI。实验结果表明,在纽约数据集上,SeNext比最新的VANext(Variational Attention based Next)模型的预测准确度在Top@1上提高了11.10%左右。

关键词: 轨迹预测, 自监督学习, 对比学习, 注意力机制, 深度学习

CLC Number: