mlsanityData to 14 Oct 2026

KITE: A Knowledge-Injected Temporal Encoder for Time-Series Event Forecasting

arXiv 2610.12738 ↗First posted 8 Oct 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Forecasting rare, high-cost events in multivariate time-series systems is hard because their precursors are seldom observed, so a purely data-driven model has little to learn from. The engineers who run these systems, however, hold knowledge that precedes such events, information absent from the scarce labels. We call this a semantic prior and inject it into a self-supervised event forecaster through two switchable mechanisms, a covariate mechanism and an attention-bias mechanism, each the identity at its null, so one architecture serves every prior type with no per-dataset architecture search. A prior helps when it supplies information the observed window does not already contain: in a short context an informative prior beats no prior in-domain (pooled h-AUROC over the no-prior baseline: a periodicity clock +14%, p<0.001; a conservation residual +47% at a 0.25 label fraction), and a working prior transfers out-of-domain (+53%), substituting for feature transfer, while priors the window already recovers stay inert and the attention-bias mechanism shows no measurable gain. KITE is a switchable, attributable route to contextual conditioning, and a substrate for scaling toward cross-domain, pretrained time-series foundation world models that carry their governing structure explicitly.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 34 references that are in the map. First posted on arXiv 8 Oct 2026.

Builds on

24 of 34 references.

References · 24

  1. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  2. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  3. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  4. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
  5. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  6. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,057
  7. 2023Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecturecited by 1,039
  8. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
  9. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 761
  10. 2023A decoder-only foundation model for time-series forecastingcited by 692
  11. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 614
  12. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 301
12 more
  1. 2025LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristicscited by 254
  2. 2019Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systemscited by 205
  3. 2025Chronos-2: From Univariate to Universal Forecastingcited by 194
  4. 2020Multivariate Time-series Anomaly Detection via Graph Attention Networkcited by 167
  5. 2018A Scalable Discrete-Time Survival Model for Neural Networkscited by 72
  6. 2019Continuous and Discrete-Time Survival Prediction with Neural Networkscited by 70
  7. 2025UniCA: Unified Covariate Adaptation for Time Series Foundation Modelcited by 7
  8. 2026Rethinking Multimodal Time-Series Forecasting Evaluationcited by 7
  9. 2026Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddingscited by 5
  10. 2026FactoryNet: A Large-Scale Dataset toward Industrial Time-Series Foundation Modelscited by 3
  11. 2026HEPA: A Self-Supervised Horizon-Conditioned Event Predictive Architecture for Time Seriescited by 2
  12. 2026CITRAS-FM: Tiny Time Series Foundation Model for Covariate-Informed Zero-Shot Forecastingcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond Static Positional Encoding: Bayesian Time-aware Attention for Non-Stationary Long-term Time Series Forecasting
  2. 2026Deep TPC: Temporal-Prior Conditioning for Time Series Forecasting
  3. 2026SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting
  4. 2025Adapting LLMs to Time Series Forecasting via Temporal Heterogeneity Modeling and Representation Alignment
  5. 2025EventTSF: Event-Aware Non-Stationary Time Series Forecasting
  6. 2025STELLA: Guiding Large Language Models for Time Series Forecasting with Semantic Abstractions
  7. 2025Semantic-Enhanced Time-Series Forecasting via Large Language Models
  8. 2024A Temporal Kolmogorov-Arnold Transformer for Time Series Forecasting