AAAI 2023 accepted papers on Time series
37 of the 2,023 papers accepted at AAAI 2023 (1.8%) are on Time series, compared with 1.1% at AAAI 2022. They fall into 4 topics.
See AAAI 2023 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Causal and generative time series · 17 papers
- Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecasting (119 citations)
- Causal Recurrent Variational Autoencoder for Medical Time Series Generation (75 citations)
- An Extreme-Adaptive Time Series Prediction Model Based on Probability-Enhanced LSTM Neural Networks (23 citations)
- AEC-GAN: Adversarial Error Correction GANs for Auto-Regressive Long Time-Series Generation (15 citations)
- Estimating Treatment Effects from Irregular Time Series Observations with Hidden Confounders (12 citations)
- Phase-Informed Bayesian Ensemble Models Improve Performance of COVID-19 Forecasts (10 citations)
- SLOTH: Structured Learning and Task-Based Optimization for Time Series Forecasting on Hierarchies (10 citations)
- Learnable Path in Neural Controlled Differential Equations (7 citations)
- C-NTPP: Learning Cluster-Aware Neural Temporal Point Process (5 citations)
- Symphony in the Latent Space: Provably Integrating High-Dimensional Techniques with Non-linear Machine Learning Models (5 citations)
- Data-Driven Machine Learning Models for a Multi-Objective Flapping Fin Unmanned Underwater Vehicle Control System (4 citations)
- Neural Spline Search for Quantile Probabilistic Modeling (4 citations)
and 5 more in the interactive map.
Long-term forecasting · 10 papers
- Are Transformers Effective for Time Series Forecasting? (3,150 citations)
- NHITS: Neural Hierarchical Interpolation for Time Series Forecasting (516 citations)
- Spatio-Temporal Meta-Graph Learning for Traffic Forecasting (311 citations)
- SVP-T: A Shape-Level Variable-Position Transformer for Multivariate Time Series Classification (48 citations)
- WaveForM: Graph Enhanced Wavelet Learning for Long Sequence Forecasting of Multivariate Time Series (37 citations)
- InParformer: Evolutionary Decomposition Transformers with Interactive Parallel Attention for Long-Term Time Series Forecasting (33 citations)
- Learning Decomposed Spatial Relations for Multi-Variate Time-Series Modeling (16 citations)
- An Explainable Forecasting System for Humanitarian Needs Assessment (4 citations)
- Learning Dynamic Temporal Relations with Continuous Graph for Multivariate Time Series Forecasting (Student Abstract) (4 citations)
- Fast Saturating Gate for Learning Long Time Scales with Recurrent Neural Networks (1 citation)
Foundation models for time series · 8 papers
- Time Series Contrastive Learning with Information-Aware Augmentations (100 citations)
- MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Series (47 citations)
- Temporal-Frequency Co-training for Time Series Semi-supervised Learning (37 citations)
- PrimeNet: Pre-training for Irregular Multivariate Time Series (27 citations)
- SEnsor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation (26 citations)
- Auto-CM: Unsupervised Deep Learning for Satellite Imagery Composition and Cloud Masking Using Spatio-Temporal Dynamics (9 citations)
- Supervised Contrastive Few-Shot Learning for High-Frequency Time Series (9 citations)
- Ripple: Concept-Based Interpretation for Raw Time Series Models in Education (6 citations)