Parameter-Efficient Adaptation of Pretrained Language Models for Time-Series Forecasting

• URL: http://arxiv.org/abs/2609.15344v1
• Date: Mon, 14 Sep 2026 10:30:59 GMT
• Title: Parameter-Efficient Adaptation of Pretrained Language Models for Time-Series Forecasting
• Abstract summary: We project fixed-length time-series patches directly into the embedding space of a pretrained GPT-2 backbone.<n>We analyze the effects of (i)representation strategy (continuous embeddings versus textual serialisation), (ii)adaptation regime (frozen backbone versus partial or full fine-tuning), and (iv)input context length.
• Score: 2.141079906482723
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study the adaptation of pretrained language models to univariate time-series forecasting through a parameter-efficient transfer learning framework, with the goal of understanding which design choices drive effective cross-modal transfer. While language models operate on discrete textual tokens, time series consist of continuous numerical observations with temporal dependencies. To bridge this modality gap, we project fixed-length time-series patches directly into the embedding space of a pretrained GPT-2 backbone, bypassing textual tokenization and treating the Transformer as a generic sequence encoder. Through controlled ablation studies on seven benchmark datasets spanning energy, weather, traffic, and finance, we analyze the effects of (i)~representation strategy (continuous embeddings versus textual serialisation), (ii)~adaptation regime (frozen backbone versus partial or full fine-tuning), (iii)~architectural components such as adapters, pooling strategies, and prediction heads, and (iv)~input context length. Continuous patch-based embeddings consistently outperform textual prompting and randomly initialised backbones. The adapted pipeline attains MASE within the range of specialised forecasting architectures while updating less than 1\% of total model parameters. Results further indicate that freezing the pretrained backbone and training lightweight projection and adapter modules provides a favourable accuracy--efficiency trade-off with stable behaviour across varying context lengths.

Related papers

• LeapTS: Rethinking Time Series Forecasting as Adaptive Multi-Horizon Scheduling [74.94985663101906]
  We present LeapTS, a novel framework that reformulates time series forecasting as a dynamic scheduling process over the prediction horizon.<n>We show that LeapTS improves overall forecasting performance by at least 7.4% while achieving a 2.6$times$ to 5.3$times$ inference speedup over representative Transformer-based models.
  arXiv  Detail & Related papers  (2026-05-11T09:54:02Z)
• IPatch: A Multi-Resolution Transformer Architecture for Robust Time-Series Forecasting [1.00150464907602]
  IPatch is a multi-resolution Transformer architecture that integrates point-wise and patch-wise tokens, modeling temporal information at multiple resolutions.<n>Experiments on 7 benchmark datasets demonstrate that IPatch consistently improves forecasting accuracy, to noise, and generalization across various prediction horizons.
  arXiv  Detail & Related papers  (2026-03-25T11:31:32Z)
• Baguan-TS: A Sequence-Native In-Context Learning Model for Time Series Forecasting with Covariates [31.296823831987748]
  Baguan-TS integrates the raw-sequence representation learning with ICL, instantiated by a 3D Transformer.<n>We tackle two key hurdles: (i) calibration and training stability, improved with a feature-agnostic, target-space retrieval-based local calibration, and (ii) output oversmoothing, mitigated via context-overfitting strategy.
  arXiv  Detail & Related papers  (2026-03-18T07:24:19Z)
• Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models [102.20309135516186]
  Cross-entropy (CE) training provides dense and scalable supervision for language models.<n>We introduce a feature-matching objective for language-model fine-tuning.<n>To optimize this objective efficiently, we propose energy-based fine-tuning.
  arXiv  Detail & Related papers  (2026-03-12T17:57:50Z)
• Patch-Level Tokenization with CNN Encoders and Attention for Improved Transformer Time-Series Forecasting [0.0]
  This paper proposes a two-stage forecasting framework that separates local temporal representation learning from global dependency modelling.<n>A convolutional neural network operates on fixed-length temporal patches to extract short-range temporal dynamics and non-linear feature interactions.<n> Token-level self-attention is applied during representation learning to refine these embeddings, after which a Transformer encoder models inter-patch temporal dependencies to generate forecasts.
  arXiv  Detail & Related papers  (2026-01-18T16:16:01Z)
• Estimating Time Series Foundation Model Transferability via In-Context Learning [74.65355820906355]
  Time series foundation models (TSFMs) offer strong zero-shot forecasting via large-scale pre-training.<n>Fine-tuning remains critical for boosting performance in domains with limited public data.<n>We introduce TimeTic, a transferability estimation framework that recasts model selection as an in-context-learning problem.
  arXiv  Detail & Related papers  (2025-09-28T07:07:13Z)
• Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization [74.3339999119713]
  We develop a wavelet-based tokenizer that allows models to learn complex representations directly in the space of time-localized frequencies.<n>Our method first scales and decomposes the input time series, then thresholds and quantizes the wavelet coefficients, and finally pre-trains an autoregressive model to forecast coefficients for the forecast horizon.
  arXiv  Detail & Related papers  (2024-12-06T18:22:59Z)
• Timer-XL: Long-Context Transformers for Unified Time Series Forecasting [67.83502953961505]
  We present Timer-XL, a causal Transformer for unified time series forecasting.<n>Based on large-scale pre-training, Timer-XL achieves state-of-the-art zero-shot performance.
  arXiv  Detail & Related papers  (2024-10-07T07:27:39Z)
• Adapting to Length Shift: FlexiLength Network for Trajectory Prediction [53.637837706712794]
  Trajectory prediction plays an important role in various applications, including autonomous driving, robotics, and scene understanding. Existing approaches mainly focus on developing compact neural networks to increase prediction precision on public datasets, typically employing a standardized input duration. We introduce a general and effective framework, the FlexiLength Network (FLN), to enhance the robustness of existing trajectory prediction against varying observation periods.
  arXiv  Detail & Related papers  (2024-03-31T17:18:57Z)
• Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning [22.28251586213348]
  aLLM4TS is an innovative framework that adapts Large Language Models (LLMs) for time-series representation learning. A distinctive element of our framework is the patch-wise decoding layer, which departs from previous methods reliant on sequence-level decoding.
  arXiv  Detail & Related papers  (2024-02-07T13:51:26Z)
• A Time Series is Worth 64 Words: Long-term Forecasting with Transformers [4.635547236305835]
  We propose an efficient design of Transformer-based models for time series forecasting and self-supervised representation learning. It is based on two key components: (i) segmentation of time series into subseries-level patches which are served as input tokens to Transformer. PatchTST can improve the long-term forecasting accuracy significantly when compared with that of SOTA Transformer-based models.
  arXiv  Detail & Related papers  (2022-11-27T05:15:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.