[AAAI2023] 时空数据挖掘方向论文总结

时空数据

1. Spatio-Temporal Graph Neural Point Process for Traffic Congestion Event Prediction
2. Spatio-temporal Neural Structural Causal Models for Bike Flow Prediction
3. Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction
4. Spatio-Temporal Meta-Graph Learning for Traffic Forecasting
5. Trafformer: Unify Time and Space in Traffic Prediction
6. Transfer Learning Enhanced DeepONet for Long-Time Prediction of Evolution Equations
7. Exposing the Self-supervised Space-Time Correspondence Learning via Graph Kernels
8. N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting
9. WaveForM: Graph Enhanced Wavelet Learning for Long Sequence Forecasting of Multivariate Time Series
10. Temporal-Frequency Co-Training for Time Series Semi-Supervised Learning
11. SEnsor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation
12. Time-aware Random Walk Diffusion to Improve Dynamic Graph Learning
13. Causal Recurrent Variational Autoencoder for Medical Time Series Generation
14. AEC-GAN: Adversarial Error Correction GANs for Auto-Regressive Long Time-series Generation
15. Detecting Multivariate Time Series Anomalies with Zero Known Label
16. Learning Dynamic Temporal Relations with Continuous Graph for Multivariate Time Series Forecasting
17. ES-Mask: Evolutionary Strip Mask for Explaining Time Series Prediction
18. An Extreme-Adaptive Time Series Prediction Model Based on Probability Enhanced LSTM Neural Networks
19. Are Transformers Effective for Time Series Forecasting?
20. Supervised Contrastive Few-shot Learning for High-frequency Time Series
21. InParformer: Evolutionary Decomposition Transformers with Interactive Parallel Attention for Long-Term Time Series Forecasting
22. PrimeNet: Pre-Training for Irregular Multivariate Time Series
23. MHCCL: Masked Hierarchical Cluster-wise Contrastive Learning for Multivariate Time Series
24. SVP-T: A Shape-Level Variable-Position Transformer for Multivariate Time Series Classification
25. Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecasting
26. Time Series Contrastive Learning with Information-Aware Augmentations
27. Black-box Adversarial Attack on Time Series Classification
28. PDFormer: Propagation Delay-aware Dynamic Long-range Transformer for Traffic Flow Prediction
29. Ising-Traffic: Using Ising Machine Learning to Predict Traffic Congestion under Uncertainty
30. AirFormer: Predicting Nationwide Air Quality in China with Transformers
31. Learning Decomposed Spatial Relations for Multi-Variate Time-Series Modeling

轨迹数据

1. PateGail: A Privacy-preserving Mobility Trajectory Generator with Imitation Learning
2. WSiP: Wave Superposition Inspired Pooling for Dynamic InteractionsAware Trajectory Prediction
3. GRLSTM: Trajectory Similarity Computation with Graph-based Residual LSTM
4. Mobility Prediction via Sequential Trajectory Disentanglement
5. Continuous Trajectory Generation Based on Two-Stage GAN
6. Causal Intervention for Human Trajectory Prediction with Cross Attention Mechanism