mlsanityData to 14 Oct 2026

xTime: Extreme Event Prediction with Hierarchical Knowledge Distillation and Expert Fusion

arXiv 2510.20651 ↗First posted 23 Oct 2025cs.LGcited by 0

On the map: Knowledge distillation → General knowledge distillation methods

Abstract (arXiv)

Extreme events frequently occur in real-world time series and often carry significant practical implications. In domains such as climate and healthcare, these events, such as floods, heatwaves, or acute medical episodes, can lead to serious consequences. Accurate forecasting of such events is therefore of substantial importance. Most existing time series forecasting models are optimized for overall performance within the prediction window, but often struggle to accurately predict extreme events, such as high temperatures or heart rate spikes. The main challenges are data imbalance and the neglect of valuable information contained in intermediate events that precede extreme events. In this paper, we propose xTime, a novel framework for extreme event forecasting in time series. xTime leverages knowledge distillation to transfer information from models trained on lower-rarity events, thereby improving prediction performance on rarer ones. In addition, we introduce a mixture of experts (MoE) mechanism that dynamically selects and fuses outputs from expert models across different rarity levels, which further improves the forecasting performance for extreme events. Experiments on multiple datasets show that xTime achieves consistent improvements, with forecasting accuracy on extreme events improving from 3% to 78%.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation. Builds on 24 of its 41 references that are in the map. First posted on arXiv 23 Oct 2025.

Builds on

24 of 41 references.

References · 24

  1. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  2. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  3. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  4. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  5. 2024Chronos: Learning the Language of Time Seriescited by 759
  6. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 700
  7. 2023A decoder-only foundation model for time-series forecastingcited by 692
  8. 2022Mixture-of-Experts with Expert Choice Routingcited by 623
  9. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 614
  10. 2018Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Networkcited by 420
  11. 2024Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Expertscited by 287
  12. 2019Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directionscited by 172
12 more
  1. 2024CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuningcited by 108
  2. 2024ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Datacited by 100
  3. 2024From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflectioncited by 98
  4. 2023SaDI: A Self-adaptive Decomposed Interpretable Framework for Electric Load Forecasting under Extreme Eventscited by 21
  5. 2024Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotationcited by 21
  6. 2023A Comprehensive Survey on Rare Event Predictioncited by 18
  7. 2022An Extreme-Adaptive Time Series Prediction Model Based on Probability-Enhanced LSTM Neural Networkscited by 9
  8. 2024Understanding the Ranking Loss for Recommendation with Sparse User Feedbackcited by 8
  9. 2024Empirical wavelet transformcited by 6
  10. 2024Enhancing Graph Neural Networks with Limited Labeled Data by Actively Distilling Knowledge from Large Language Modelscited by 3
  11. 2024ReFine: Boosting Time Series Prediction of Extreme Events by Reweighting and Fine-tuningcited by 2
  12. 2023Predicting Rare Events by Shrinking Towards Proportional Oddscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Beyond the Norm: A Survey of Synthetic Data Generation for Rare Events
  2. 2026M2FMoE: Multi-Resolution Multi-View Frequency Mixture-of-Experts for Extreme-Adaptive Time Series Forecasting
  3. 2025EWE: An Agentic Framework for Extreme Weather Analysis
  4. 2026Aurora-X: Built for Extreme Time Series Forecasting
  5. 2026SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting
  6. 2026Evaluating the Generalizability of Foundation Models for Extreme Environmental Events: Case Study of California Wildfire PM2.5
  7. 2025ClimaEmpact: Domain-Aligned Small Language Models and Datasets for Extreme Weather Analytics
  8. 2025ClimateLLM: Efficient Weather Forecasting via Frequency-Aware Large Language Models