REVIEW 12 cited by
Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Large pre-trained models excel in zero/few-shot learning for language and vision tasks but face challenges in multivariate time series (TS) forecasting due to diverse data characteristics. Consequently, recent research efforts have focused on developing pre-trained TS forecasting models. These models, whether built from scratch or adapted from large language models (LLMs), excel in zero/few-shot forecasting tasks. However, they are limited by slow performance, high computational demands, and neglect of cross-channel and exogenous correlations. To address this, we introduce Tiny Time Mixers (TTM), a compact model (starting from 1M parameters) with effective transfer learning capabilities, trained exclusively on public TS datasets. TTM, based on the light-weight TSMixer architecture, incorporates innovations like adaptive patching, diverse resolution sampling, and resolution prefix tuning to handle pre-training on varied dataset resolutions with minimal model capacity. Additionally, it employs multi-level modeling to capture channel correlations and infuse exogenous signals during fine-tuning. TTM outperforms existing popular benchmarks in zero/few-shot forecasting by (4-40%), while reducing computational requirements significantly. Moreover, TTMs are lightweight and can be executed even on CPU-only machines, enhancing usability and fostering wider adoption in resource-constrained environments. The model weights for reproducibility and research use are available at https://huggingface.co/ibm/ttm-research-r2/, while enterprise-use weights under the Apache license can be accessed as follows: the initial TTM-Q variant at https://huggingface.co/ibm-granite/granite-timeseries-ttm-r1, and the latest variants (TTM-B, TTM-E, TTM-A) weights are available at https://huggingface.co/ibm-granite/granite-timeseries-ttm-r2.
Forward citations
Cited by 12 Pith papers
-
CENTILE: A Telemetry Foundation Model Evaluated by the Decisions It Drives
One pretrained telemetry model, CENTILE, improves both HPC backfilling and ISP capacity provisioning decisions under replay, with zero-shot transfer across months and domains.
-
Trend strength predicts when generative foundation models win: a power-controlled benchmark, a mechanism, and an actionable selection rule
Zero-shot Chronos wins time-series benchmarks by under-extrapolating trend, and trend strength computed before forecasting predicts when it will beat classical models.
-
Time Series Foundation Models for Multivariate Financial Time Series Forecasting
Pretrained TTM shows large transfer and sample-efficiency gains in three financial forecasting tasks relative to training from scratch, but methodological flaws including possible look-ahead bias weaken the quantitati...
-
EPBench: A Benchmark for Short-term Earthquake Prediction with Neural Networks
A new global regional-scale benchmark provides data, splits, evaluation metrics, and neural network plus ETAS baselines for short-term earthquake prediction.
-
MoTime: A Dataset Suite for Multimodal Time Series Forecasting
MoTime provides a large multimodal forecasting benchmark and shows that external text or images can improve forecasts in some datasets, especially cold-start and sparse settings, though gains are inconsistent.
-
Investigating Compositional Reasoning in Time Series Foundation Models
On a benchmark where models train on Fourier components and test on their sums, patch-based Transformers and residual MLP architectures show the strongest compositional generalization, while most standard transformers...
-
RhyMix: A Lightweight Adaptive Multi-Rhythm Network for Long-Term Time Series Forecasting
RhyMix reaches state-of-the-art long-term multivariate forecasting on 10 of 12 public benchmarks with a ~40K-parameter dual-path adaptive architecture of linear complexity.
-
Hopformer: Homogeneity-Pursuit Transformer for Time Series Forecasting
A two-stage forecaster (SPA trend extraction + LoRA-fine-tuned residual Transformer) that the paper claims beats prior models by 6.56% MASE, though the claim is not robust to its own extended baseline tables.
-
Causal Graph Fuzzy LLMs: A First Introduction and Applications in Time Series Forecasting
CGF-LLM combines fuzzy time series and PCMCI causal graphs into text input for fine-tuned GPT-2, reporting improved one-step-ahead forecast NRMSE and a reduction in token count on four datasets.
-
Beyond Data Scarcity: A Frequency-Driven Framework for Zero-Shot Forecasting
Freq-Synth trains zero-shot forecasters on harmonic sine waves generated from the target sampling rate and beats real-data training on 6 of 8 benchmarks.
-
Causal Time-Series Synchronization for Multi-Dimensional Forecasting
Aligning cause-effect pairs by their estimated Granger lag improves channel-dependent forecasting accuracy and transfer learning on synthetic time-series data.
-
A Survey of AIOps in the Era of Large Language Models
A systematic survey that categorizes LLM-based AIOps research into four dimensions: data sources, tasks, methods, and evaluation, claiming to be the first comprehensive such overview.
Discussion (0). Continue with ORCID to comment.