ICML 2024 accepted papers on Time series
52 of the 2,610 papers accepted at ICML 2024 (2.0%) are on Time series, compared with 1.5% at ICML 2023. They fall into 4 topics.
See ICML 2024 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 · 25 papers
- Integrating Multimodal Data for Joint Generative Modeling of Complex Dynamics (5 citations)
- Time Weaver: A Conditional Time Series Generation Model (3 citations)
- An Analysis of Linear Time Series Forecasting Models (2 citations)
- BayOTIDE: Bayesian Online Multivariate Time Series Imputation with Functional Decomposition (2 citations)
- Conformal prediction for multi-dimensional time series by ellipsoidal sets (2 citations)
- Log Neural Controlled Differential Equations: The Lie Brackets Make A Difference (2 citations)
- TimeX++: Learning Time-Series Explanations with Information Bottleneck (2 citations)
- SiBBlInGS: Similarity-driven Building-Block Inference using Graphs across States (1 citation)
- The Merit of River Network Topology for Neural Flood Forecasting (1 citation)
- Time Series Diffusion in the Frequency Domain (1 citation)
- An Empirical Examination of Balancing Strategy for Counterfactual Estimation on Time Series
- Conformalized Adaptive Forecasting of Heterogeneous Trajectories
and 13 more in the interactive map.
Foundation models for time series · 15 papers
- A decoder-only foundation model for time-series forecasting (44 citations)
- Unified Training of Universal Time Series Forecasting Transformers (33 citations)
- MOMENT: A Family of Open Time-series Foundation Models (27 citations)
- Position: What Can Large Language Models Tell Us about Time Series Analysis (17 citations)
- Timer: Generative Pre-trained Transformers Are Large Time Series Models (6 citations)
- Multi-Patch Prediction: Adapting Language Models for Time Series Representation Learning (5 citations)
- TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning (3 citations)
- $S^2$IP-LLM: Semantic Space Informed Prompt Learning with LLM for Time Series Forecasting (1 citation)
- TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling (1 citation)
- An Unsupervised Approach for Periodic Source Detection in Time Series
- CauDiTS: Causal Disentangled Domain Adaptation of Multivariate Time Series
- MF-CLR: Multi-Frequency Contrastive Learning Representation for Time Series
and 3 more in the interactive map.
Long-term forecasting · 11 papers
- SparseTSF: Modeling Long-term Time Series Forecasting with *1k* Parameters (10 citations)
- Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modeling (7 citations)
- CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables (6 citations)
- Efficient and Effective Time-Series Forecasting with Spiking Neural Networks (5 citations)
- Graph-based Time Series Clustering for End-to-End Hierarchical Forecasting (4 citations)
- Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling (2 citations)
- SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention (1 citation)
- Loss Shaping Constraints for Long-Term Time Series Forecasting
- Irregular Multivariate Time Series Forecasting: A Transformable Patching Graph Neural Networks Approach
- SIN: Selective and Interpretable Normalization for Long-Term Time Series Forecasting
- TSLANet: Rethinking Transformers for Time Series Representation Learning