mlsanityData to 14 Oct 2026

TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecasting

arXiv 2412.20810 ↗First posted 30 Dec 2024cs.LGcited by 17

On the map: Retrieval-augmented generation → Time series and agricultural RAG

Abstract (arXiv)

Time series forecasting plays a crucial role in data mining, driving rapid advancements across numerous industries. With the emergence of large models, time series foundation models (TSFMs) have exhibited remarkable generalization capabilities, such as zero-shot learning, through large-scale pre-training. Meanwhile, Retrieval-Augmented Generation (RAG) methods have been widely employed to enhance the performance of foundation models on unseen data, allowing models to access to external knowledge. In this paper, we introduce TimeRAF, a Retrieval-Augmented Forecasting model that enhance zero-shot time series forecasting through retrieval-augmented techniques. We develop customized time series knowledge bases that are tailored to the specific forecasting tasks. TimeRAF employs an end-to-end learnable retriever to extract valuable information from the knowledge base. Additionally, we propose Channel Prompting for knowledge integration, which effectively extracts relevant information from the retrieved knowledge along the channel dimension. Extensive experiments demonstrate the effectiveness of our model, showing significant improvement across various domains and datasets.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Placed in Time series and agricultural RAG, one of 15 directions in Retrieval-augmented generation. Builds on 13 of its 38 references that are in the map. First posted on arXiv 30 Dec 2024.

Builds on

13 of 38 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024RATSF: Empowering Customer Service Volume Management through Retrieval-Augmented Time-Series Forecasting7 Mar

Other references · 12

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  3. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  4. 2024Chronos: Learning the Language of Time Seriescited by 759
  5. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 614
  6. 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 482
  7. 2021Monash Time Series Forecasting Archivecited by 267
  8. 2023TimeGPT-1cited by 158
  9. 2022DocPrompting: Generating Code by Retrieving the Docscited by 153
  10. 2023Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecastingcited by 113
  11. 2023Temporal Data Meets LLM -- Explainable Financial Time Series Forecastingcited by 77
  12. 2022Retrieval Based Time Series Forecastingcited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 12.

17 papers.

Sort:

By area:

  1. 2025TRACE: Grounding Time Series in Context for Multimodal Embedding and Retrievalcited by 7
  2. 2025Large Language models for Time Series Analysis: Techniques, Applications, and Challengescited by 3
  3. 2026Post-Training in Time Series Foundation Models: A Unifying Frameworkcited by 3
  4. 2025EventTSF: Event-Aware Non-Stationary Time Series Forecastingcited by 2
  5. 2026Semantics-Enhanced Retrieval-Augmented Time Series Forecastingcited by 2
  6. 2026WPBench: A Comprehensive Benchmark for Wind Power Forecastingcited by 2
  7. 2025Contrastive Prompt Clustering for Weakly Supervised Semantic Segmentationcited by 1
  8. 2026Retrieval-Augmented Generation with Covariate Time Seriescited by 1
  9. 2026Factorize to Generalize: Retrieval-Guided Invariant-Dynamic Decomposition for Time Series Forecastingcited by 1
  10. 2025Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Seriescited by 0
  11. 2026DDT: A Dual-Masking Dual-Expert Transformer for Energy Time-Series Forecastingcited by 0
  12. 2026Align-RAG: Alignment Is All You Need for TSFM In-Context Learningcited by 0
5 more
  1. 2026Model-agnostic Retrieval-Augmented Extended Forecasting for time seriescited by 0
  2. 2026Knowledge-Graph-Augmented Chronos-2 for HEC-RAS Surrogate Forecastingcited by 0
  3. 2026GNA: Granular Neighbor Assembly for Retrieval-Augmented Multivariate Time-Series Forecastingcited by 0
  4. 2026GRAM: Correcting Frozen Time-Series Foundation Models via Graph-Retrieved Amplitude Memorycited by 0
  5. 2026ECHO: Correcting Time Series Foundation Model Forecasts with Historical Analogues and Errorscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster
  2. 2025QuiZSF: A Retrieval-Augmented Framework for Zero-Shot Time Series Forecasting
  3. 2024Retrieval Augmented Time Series Forecasting
  4. 2026Not All Retrievals are Useful: Cross-Attention for Input-Aware RAG in Time Series Forecasting
  5. 2024TimeRAG: BOOSTING LLM Time Series Forecasting via Retrieval-Augmented Generation
  6. 2026Stationarity-Aware Retrieval-Augmented Time Series Forecasting
  7. 2026TS-RAG: Retrieval Augmented Generation for Time Series Forecasting
  8. 2025Retrieval Augmented Time Series Forecasting