VITRO: Vocabulary Inversion for Time-series Representation Optimization

• URL: http://arxiv.org/abs/2412.17921v1
• Date: Mon, 23 Dec 2024 19:24:51 GMT
• Title: VITRO: Vocabulary Inversion for Time-series Representation Optimization
• Authors: Filippos Bellos, Nam H. Nguyen, Jason J. Corso,
• Abstract summary: We propose VITRO to bridge the gap between the discrete, semantic nature of natural language and the continuous, numerical nature of time series data.<n>We show that learnable time series-specific pseudo-word embeddings represent time series data better than existing general language model vocabularies.
• Score: 21.338428379212704
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although LLMs have demonstrated remarkable capabilities in processing and generating textual data, their pre-trained vocabularies are ill-suited for capturing the nuanced temporal dynamics and patterns inherent in time series. The discrete, symbolic nature of natural language tokens, which these vocabularies are designed to represent, does not align well with the continuous, numerical nature of time series data. To address this fundamental limitation, we propose VITRO. Our method adapts textual inversion optimization from the vision-language domain in order to learn a new time series per-dataset vocabulary that bridges the gap between the discrete, semantic nature of natural language and the continuous, numerical nature of time series data. We show that learnable time series-specific pseudo-word embeddings represent time series data better than existing general language model vocabularies, with VITRO-enhanced methods achieving state-of-the-art performance in long-term forecasting across most datasets.

Related papers

• Enhancing Time Series Forecasting via Multi-Level Text Alignment with LLMs [6.612196783595362]
  We propose a multi-level text alignment framework for time series forecasting using large language models (LLMs) Our method decomposes time series into trend, seasonal, and residual components, which are then reprogrammed into component-specific text representations. Experiments on multiple datasets demonstrate that our method outperforms state-of-the-art models in accuracy while providing good interpretability.
  arXiv  Detail & Related papers  (2025-04-10T01:02:37Z)
• LLM-PS: Empowering Large Language Models for Time Series Forecasting with Temporal Patterns and Semantics [56.99021951927683]
  Time Series Forecasting (TSF) is critical in many real-world domains like financial planning and health monitoring. Existing Large Language Models (LLMs) usually perform suboptimally because they neglect the inherent characteristics of time series data. We propose LLM-PS to empower the LLM for TSF by learning the fundamental textitPatterns and meaningful textitSemantics from time series data.
  arXiv  Detail & Related papers  (2025-03-12T11:45:11Z)
• PICASO: Permutation-Invariant Context Composition with State Space Models [98.91198288025117]
  State Space Models (SSMs) offer a promising solution by allowing a database of contexts to be mapped onto fixed-dimensional states. We propose a simple mathematical relation derived from SSM dynamics to compose multiple states into one that efficiently approximates the effect of concatenating raw context tokens. We evaluate our resulting method on WikiText and MSMARCO in both zero-shot and fine-tuned settings, and show that we can match the strongest performing baseline while enjoying on average 5.4x speedup.
  arXiv  Detail & Related papers  (2025-02-24T19:48:00Z)
• Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrative [65.84249211767921]
  Texts as Time Series (TaTS) considers the time-series-paired texts to be auxiliary variables of the time series. TaTS can be plugged into any existing numerical-only time series models and enable them to handle time series data with paired texts effectively.
  arXiv  Detail & Related papers  (2025-02-13T03:43:27Z)
• LAST SToP For Modeling Asynchronous Time Series [19.401463051705377]
  We present a novel prompt design for Large Language Models (LLMs) tailored to Asynchronous Time Series. Our approach effectively utilizes the rich natural language of event descriptions, allowing LLMs to benefit from their broad world knowledge for reasoning across different domains and tasks. We further introduce Soft Prompting, a novel prompt-tuning mechanism that significantly improves model performance, outperforming existing fine-tuning methods such as QLoRA.
  arXiv  Detail & Related papers  (2025-02-04T01:42:45Z)
• Time Series Language Model for Descriptive Caption Generation [11.796431549951055]
  We introduce TSLM, a novel time series language model designed specifically for time series captioning. TSLM operates as an encoder-decoder model, leveraging both text prompts and time series data representations. We show that TSLM outperforms existing state-of-the-art approaches from multiple data modalities by a significant margin.
  arXiv  Detail & Related papers  (2025-01-03T14:34:30Z)
• 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)
• Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classification [4.5939667818289385]
  HiTime is a hierarchical multi-modal model that seamlessly integrates temporal information into large language models. Our findings highlight the potential of integrating temporal features into LLMs, paving the way for advanced time series analysis.
  arXiv  Detail & Related papers  (2024-10-24T12:32:19Z)
• Metadata Matters for Time Series: Informative Forecasting with Transformers [70.38241681764738]
  We propose a Metadata-informed Time Series Transformer (MetaTST) for time series forecasting. To tackle the unstructured nature of metadata, MetaTST formalizes them into natural languages by pre-designed templates. A Transformer encoder is employed to communicate series and metadata tokens, which can extend series representations by metadata information.
  arXiv  Detail & Related papers  (2024-10-04T11:37:55Z)
• Time Machine GPT [15.661920010658626]
  Large language models (LLMs) are often trained on extensive, temporally indiscriminate text corpora. This approach is not aligned with the evolving nature of language. This paper presents a new approach: a series of point-in-time LLMs called Time Machine GPT (TiMaGPT)
  arXiv  Detail & Related papers  (2024-04-29T09:34:25Z)
• AutoTimes: Autoregressive Time Series Forecasters via Large Language Models [67.83502953961505]
  AutoTimes projects time series into the embedding space of language tokens and autoregressively generates future predictions with arbitrary lengths. We formulate time series as prompts, extending the context for prediction beyond the lookback window. AutoTimes achieves state-of-the-art with 0.1% trainable parameters and over $5times$ training/inference speedup.
  arXiv  Detail & Related papers  (2024-02-04T06:59:21Z)
• Large Language Models Are Zero-Shot Time Series Forecasters [48.73953666153385]
  By encoding time series as a string of numerical digits, we can frame time series forecasting as next-token prediction in text. We find that large language models (LLMs) such as GPT-3 and LLaMA-2 can surprisingly zero-shot extrapolate time series at a level comparable to or exceeding the performance of purpose-built time series models trained on the downstream tasks.
  arXiv  Detail & Related papers  (2023-10-11T19:01:28Z)
• 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)
• Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding [8.45908939323268]
  We propose a self-supervised framework for learning generalizable representations for non-stationary time series. Our motivation stems from the medical field, where the ability to model the dynamic nature of time series data is especially valuable.
  arXiv  Detail & Related papers  (2021-06-01T19:53:24Z)

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.