OccamVTS: Distilling Vision Models to 1% Parameters for Time Series Forecasting

• URL: http://arxiv.org/abs/2508.01727v1
• Date: Sun, 03 Aug 2025 11:43:52 GMT
• Title: OccamVTS: Distilling Vision Models to 1% Parameters for Time Series Forecasting
• Authors: Sisuo Lyu, Siru Zhong, Weilin Ruan, Qingxiang Liu, Qingsong Wen, Hui Xiong, Yuxuan Liang,
• Abstract summary: Time series forecasting is fundamental to diverse applications, with recent approaches leveraging large vision models (LVMs) to capture temporal patterns through visual representations.<n>We propose OccamVTS, a knowledge distillation framework that extracts only the essential 1% of predictive information from LVMs into lightweight networks.
• Score: 32.875367552611266
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Time series forecasting is fundamental to diverse applications, with recent approaches leverage large vision models (LVMs) to capture temporal patterns through visual representations. We reveal that while vision models enhance forecasting performance, 99% of their parameters are unnecessary for time series tasks. Through cross-modal analysis, we find that time series align with low-level textural features but not high-level semantics, which can impair forecasting accuracy. We propose OccamVTS, a knowledge distillation framework that extracts only the essential 1% of predictive information from LVMs into lightweight networks. Using pre-trained LVMs as privileged teachers, OccamVTS employs pyramid-style feature alignment combined with correlation and feature distillation to transfer beneficial patterns while filtering out semantic noise. Counterintuitively, this aggressive parameter reduction improves accuracy by eliminating overfitting to irrelevant visual features while preserving essential temporal patterns. Extensive experiments across multiple benchmark datasets demonstrate that OccamVTS consistently achieves state-of-the-art performance with only 1% of the original parameters, particularly excelling in few-shot and zero-shot scenarios.

Related papers

• Multi-Scale Finetuning for Encoder-based Time Series Foundation Models [56.503053716053]
  Time series foundation models (TSFMs) demonstrate impressive zero-shot performance for time series forecasting.<n>We argue that it falls short of fully leveraging TSFMs' capabilities, often resulting in overfitting and suboptimal performance.<n>We propose textbftextscfinetextbftextsctuning (textbfMSFT), a simple yet general framework that explicitly integrates multi-scale modeling into the finetuning process.
  arXiv  Detail & Related papers  (2025-06-17T01:06:01Z)
• CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial Correlations [13.515201493037917]
  We present CMoS, a super-lightweight time series forecasting model.<n>CMoS directly models the spatial correlations between different time series chunks.
  arXiv  Detail & Related papers  (2025-05-25T11:01:53Z)
• TSPulse: Dual Space Tiny Pre-Trained Models for Rapid Time-Series Analysis [12.034816114258803]
  TSPulse is an ultra-compact time-series pre-trained model with only 1M parameters.<n>It performs strongly across classification, anomaly detection, imputation, and retrieval tasks.<n>Results are achieved with just 1M parameters (10-100X smaller than existing SOTA models)
  arXiv  Detail & Related papers  (2025-05-19T12:18:53Z)
• Small but Mighty: Enhancing Time Series Forecasting with Lightweight LLMs [11.1036247482657]
  We present SMETimes, the first systematic investigation of sub-3B parameter SLMs for efficient and accurate time series forecasting.<n>Our approach centers on three key innovations: A statistically-enhanced prompting mechanism that bridges numerical time series with textual semantics through statistical features; A adaptive fusion embedding architecture that aligns temporal patterns with language model token spaces through learnable parameters.
  arXiv  Detail & Related papers  (2025-03-05T15:27:36Z)
• 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)
• Visual Fourier Prompt Tuning [63.66866445034855]
  We propose the Visual Fourier Prompt Tuning (VFPT) method as a general and effective solution for adapting large-scale transformer-based models. Our approach incorporates the Fast Fourier Transform into prompt embeddings and harmoniously considers both spatial and frequency domain information. Our results demonstrate that our approach outperforms current state-of-the-art baselines on two benchmarks.
  arXiv  Detail & Related papers  (2024-11-02T18:18:35Z)
• ReAugment: Model Zoo-Guided RL for Few-Shot Time Series Augmentation and Forecasting [74.00765474305288]
  We present a pilot study on using reinforcement learning (RL) for time series data augmentation.<n>Our method, ReAugment, tackles three critical questions: which parts of the training set should be augmented, how the augmentation should be performed, and what advantages RL brings to the process.
  arXiv  Detail & Related papers  (2024-09-10T07:34:19Z)
• SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameters [16.966008476215258]
  This paper introduces SparseTSF, a novel, extremely lightweight model for Long-term Time Series Forecasting (LTSF) At the heart of SparseTSF lies the Cross-Period Sparse Forecasting technique, which simplifies the forecasting task by decoupling the periodicity and trend in time series data. SparseTSF showcases remarkable generalization capabilities, making it well-suited for scenarios with limited computational resources, small samples, or low-quality data.
  arXiv  Detail & Related papers  (2024-05-02T02:15:23Z)
• Distillation Enhanced Time Series Forecasting Network with Momentum Contrastive Learning [7.4106801792345705]
  We propose DE-TSMCL, an innovative distillation enhanced framework for long sequence time series forecasting. Specifically, we design a learnable data augmentation mechanism which adaptively learns whether to mask a timestamp. Then, we propose a contrastive learning task with momentum update to explore inter-sample and intra-temporal correlations of time series. By developing model loss from multiple tasks, we can learn effective representations for downstream forecasting task.
  arXiv  Detail & Related papers  (2024-01-31T12:52:10Z)
• Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecasting [46.63798583414426]
  Long-term time series forecasting (LTSF) represents a critical frontier in time series analysis. Our study demonstrates, through both analytical and empirical evidence, that decomposition is key to containing excessive model inflation. Remarkably, by tailoring decomposition to the intrinsic dynamics of time series data, our proposed model outperforms existing benchmarks.
  arXiv  Detail & Related papers  (2024-01-22T13:15:40Z)
• Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series [11.635608108358575]
  We introduce Tiny Time Mixers (TTM), a compact model with effective transfer learning capabilities, trained exclusively on public TS datasets. TTM incorporates innovations like adaptive patching, diverse resolution sampling, and resolution prefix tuning to handle pre-training on varied dataset resolutions. It outperforms existing popular benchmarks in zero/few-shot forecasting by (4-40%), while reducing computational requirements significantly.
  arXiv  Detail & Related papers  (2024-01-08T15:21:21Z)
• Embedded feature selection in LSTM networks with multi-objective evolutionary ensemble learning for time series forecasting [49.1574468325115]
  We present a novel feature selection method embedded in Long Short-Term Memory networks. Our approach optimize the weights and biases of the LSTM in a partitioned manner. Experimental evaluations on air quality time series data from Italy and southeast Spain demonstrate that our method substantially improves the ability generalization of conventional LSTMs.
  arXiv  Detail & Related papers  (2023-12-29T08:42:10Z)
• Time-LLM: Time Series Forecasting by Reprogramming Large Language Models [110.20279343734548]
  Time series forecasting holds significant importance in many real-world dynamic systems. We present Time-LLM, a reprogramming framework to repurpose large language models for time series forecasting. Time-LLM is a powerful time series learner that outperforms state-of-the-art, specialized forecasting models.
  arXiv  Detail & Related papers  (2023-10-03T01:31:25Z)

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.