ICLR 2022 accepted papers on Time series
25 of the 1,095 papers accepted at ICLR 2022 (2.3%) are on Time series, compared with 1.5% at ICLR 2021. They fall into 4 topics.
See ICLR 2022 in the interactive map
Submitting to ICLR? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Causal and generative time series · 15 papers
- Graph-Guided Network for Irregularly Sampled Multivariate Time Series (24 citations)
- PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series (14 citations)
- Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future (4 citations)
- Neural graphical modelling in continuous-time: consistency guarantees and algorithms (4 citations)
- Gradient Importance Learning for Incomplete Observations (2 citations)
- Heteroscedastic Temporal Variational Autoencoder For Irregularly Sampled Time Series (2 citations)
- DriPP: Driven Point Processes to Model Stimuli Induced Patterns in M/EEG Signals (1 citation)
- LORD: Lower-Dimensional Embedding of Log-Signature in Neural Rough Differential Equations (1 citation)
- Neural Spectral Marked Point Processes (1 citation)
- On the benefits of maximum likelihood estimation for Regression and Forecasting (1 citation)
- Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one Maps
- Imbedding Deep Neural Networks
and 3 more in the interactive map.
Long-term forecasting · 4 papers
- Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networks (39 citations)
- DEPTS: Deep Expansion Learning for Periodic Time Series Forecasting (17 citations)
- Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting
- TAMP-S2GCNets: Coupling Time-Aware Multipersistence Knowledge Representation with Spatio-Supra Graph Convolutional Networks for Time-Series Forecasting
Foundation models for time series · 4 papers
- CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting (87 citations)
- Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification (53 citations)
- Coherence-based Label Propagation over Time Series for Accelerated Active Learning
- T-WaveNet: A Tree-Structured Wavelet Neural Network for Time Series Signal Analysis
