SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.11413 · NeurIPS · 2024

Large Pre-trained time series models for cross-domain Time series analysis tasks

B Prakash, Harshavardhan Kamarthi

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 9 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
adityalab/samay canonical 9 of 10
FunctionStatusWhere it lives
MAE Ran adityalab/samay/src/samay/metric.py
code served (permissive licence) · get_code("3d45af2dc19af0af")
MASE Ran adityalab/samay/src/samay/metric.py
code served (permissive licence) · get_code("ab4f6a5fa72f667b")
MSE Ran adityalab/samay/src/samay/metric.py
code served (permissive licence) · get_code("bddb4a39908fde27")
filter_dict Ran adityalab/samay/src/samay/moirai_utils.py
code served (permissive licence) · get_code("79566c6a8f0aad1a")
freq_mapping Ran adityalab/samay/src/samay/dataset.py
code served (permissive licence) · get_code("1a96712a90c9bc00")
get_multivariate_data Ran adityalab/samay/src/samay/utils.py
code served (permissive licence) · get_code("53b5bc00f1f8e4f8")
handle_distr_output Ran adityalab/samay/src/samay/moirai_utils.py
code served (permissive licence) · get_code("af458dcb2674cce8")
load_args Ran adityalab/samay/src/samay/utils.py
code served (permissive licence) · get_code("b51cc76a36acc599")
read_yaml Ran adityalab/samay/src/samay/utils.py
code served (permissive licence) · get_code("cba288293510660e")
quantize_linear_layers Not yet run adityalab/samay/src/samay/quantization.py
code served (permissive licence) · get_code("c9d2804d2f08ed7e")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large pre-trained models have been vital in recent advancements in domains like language and vision, making model training for individual downstream tasks more efficient and provide superior performance. However, tackling time-series analysis tasks usually involves designing and training a separate model from scratch leveraging training data and domain expertise specific to the task. We tackle a significant challenge for pre-training a foundational time-series model from multidomain time-series datasets: extracting semantically useful tokenized inputs to the model across heterogenous time-series from different domains. We propose Large Pre-trained Time-series Models (LPTM) that introduces a novel method of adaptive segmentation that automatically identifies optimal dataset-specific segmentation strategy during pre-training. This enables LPTM to perform similar to or better than domain-specific state-of-art model when fine-tuned to different downstream time-series analysis tasks and under zero-shot settings. LPTM achieves superior forecasting and time-series classification results taking up to 40% less data and 50% less training time compared to state-of-art baselines.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2311.11413")
get_code_for_paper("2311.11413")
have("2311.11413")

Connect an agent — have() is free.