Beyond Data Scarcity: A Frequency-Driven Framework for Zero-Shot Forecasting
- URL: http://arxiv.org/abs/2411.15743v1
- Date: Sun, 24 Nov 2024 07:44:39 GMT
- Title: Beyond Data Scarcity: A Frequency-Driven Framework for Zero-Shot Forecasting
- Authors: Liran Nochumsohn, Michal Moshkovitz, Orly Avner, Dotan Di Castro, Omri Azencot,
- Abstract summary: Time series forecasting is critical in numerous real-world applications.
Traditional forecasting techniques struggle when data is scarce or not available at all.
Recent advancements often leverage large-scale foundation models for such tasks.
- Score: 15.431513584239047
- License:
- Abstract: Time series forecasting is critical in numerous real-world applications, requiring accurate predictions of future values based on observed patterns. While traditional forecasting techniques work well in in-domain scenarios with ample data, they struggle when data is scarce or not available at all, motivating the emergence of zero-shot and few-shot learning settings. Recent advancements often leverage large-scale foundation models for such tasks, but these methods require extensive data and compute resources, and their performance may be hindered by ineffective learning from the available training set. This raises a fundamental question: What factors influence effective learning from data in time series forecasting? Toward addressing this, we propose using Fourier analysis to investigate how models learn from synthetic and real-world time series data. Our findings reveal that forecasters commonly suffer from poor learning from data with multiple frequencies and poor generalization to unseen frequencies, which impedes their predictive performance. To alleviate these issues, we present a novel synthetic data generation framework, designed to enhance real data or replace it completely by creating task-specific frequency information, requiring only the sampling rate of the target data. Our approach, Freq-Synth, improves the robustness of both foundation as well as nonfoundation forecast models in zero-shot and few-shot settings, facilitating more reliable time series forecasting under limited data scenarios.
Related papers
- Tackling Data Heterogeneity in Federated Time Series Forecasting [61.021413959988216]
Time series forecasting plays a critical role in various real-world applications, including energy consumption prediction, disease transmission monitoring, and weather forecasting.
Most existing methods rely on a centralized training paradigm, where large amounts of data are collected from distributed devices to a central cloud server.
We propose a novel framework, Fed-TREND, to address data heterogeneity by generating informative synthetic data as auxiliary knowledge carriers.
arXiv Detail & Related papers (2024-11-24T04:56:45Z) - Context is Key: A Benchmark for Forecasting with Essential Textual Information [87.3175915185287]
"Context is Key" (CiK) is a time series forecasting benchmark that pairs numerical data with diverse types of carefully crafted textual context.
We evaluate a range of approaches, including statistical models, time series foundation models, and LLM-based forecasters.
Our experiments highlight the importance of incorporating contextual information, demonstrate surprising performance when using LLM-based forecasting models, and also reveal some of their critical shortcomings.
arXiv Detail & Related papers (2024-10-24T17:56:08Z) - Learning Graph Structures and Uncertainty for Accurate and Calibrated Time-series Forecasting [65.40983982856056]
We introduce STOIC, that leverages correlations between time-series to learn underlying structure between time-series and to provide well-calibrated and accurate forecasts.
Over a wide-range of benchmark datasets STOIC provides 16% more accurate and better-calibrated forecasts.
arXiv Detail & Related papers (2024-07-02T20:14:32Z) - TimeSieve: Extracting Temporal Dynamics through Information Bottlenecks [31.10683149519954]
We propose an innovative time series forecasting model TimeSieve.
Our approach employs wavelet transforms to preprocess time series data, effectively capturing multi-scale features.
Our results validate the effectiveness of our approach in addressing the key challenges in time series forecasting.
arXiv Detail & Related papers (2024-06-07T15:58:12Z) - Probing the Robustness of Time-series Forecasting Models with
CounterfacTS [1.823020744088554]
We present and publicly release CounterfacTS, a tool to probe the robustness of deep learning models in time-series forecasting tasks.
CounterfacTS has a user-friendly interface that allows the user to visualize, compare and quantify time series data and their forecasts.
arXiv Detail & Related papers (2024-03-06T07:34:47Z) - Lag-Llama: Towards Foundation Models for Probabilistic Time Series
Forecasting [54.04430089029033]
We present Lag-Llama, a general-purpose foundation model for time series forecasting based on a decoder-only transformer architecture.
Lag-Llama is pretrained on a large corpus of diverse time series data from several domains, and demonstrates strong zero-shot generalization capabilities.
When fine-tuned on relatively small fractions of such previously unseen datasets, Lag-Llama achieves state-of-the-art performance.
arXiv Detail & Related papers (2023-10-12T12:29:32Z) - Pushing the Limits of Pre-training for Time Series Forecasting in the
CloudOps Domain [54.67888148566323]
We introduce three large-scale time series forecasting datasets from the cloud operations domain.
We show it is a strong zero-shot baseline and benefits from further scaling, both in model and dataset size.
Accompanying these datasets and results is a suite of comprehensive benchmark results comparing classical and deep learning baselines to our pre-trained method.
arXiv Detail & Related papers (2023-10-08T08:09:51Z) - Mitigating Cold-start Forecasting using Cold Causal Demand Forecasting
Model [10.132124789018262]
We introduce the Cold Causal Demand Forecasting (CDF-cold) framework that integrates causal inference with deep learning-based models.
Our experiments demonstrate that the CDF-cold framework outperforms state-of-the-art forecasting models in predicting future values of multivariate time series data.
arXiv Detail & Related papers (2023-06-15T16:36:34Z) - Towards Synthetic Multivariate Time Series Generation for Flare
Forecasting [5.098461305284216]
One of the limiting factors in training data-driven, rare-event prediction algorithms is the scarcity of the events of interest.
In this study, we explore the usefulness of the conditional generative adversarial network (CGAN) as a means to perform data-informed oversampling.
arXiv Detail & Related papers (2021-05-16T22:23:23Z) - Learning summary features of time series for likelihood free inference [93.08098361687722]
We present a data-driven strategy for automatically learning summary features from time series data.
Our results indicate that learning summary features from data can compete and even outperform LFI methods based on hand-crafted values.
arXiv Detail & Related papers (2020-12-04T19:21:37Z)
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.