Self-supervised learning for time series analysis: Taxonomy, progress, and prospects

K Zhang, Q Wen, C Zhang, R Cai, M **… - … on Pattern Analysis …, 2024 - ieeexplore.ieee.org
Self-supervised learning (SSL) has recently achieved impressive performance on various
time series tasks. The most prominent advantage of SSL is that it reduces the dependence …

A survey on time-series pre-trained models

Q Ma, Z Liu, Z Zheng, Z Huang, S Zhu… - … on Knowledge and …, 2024 - ieeexplore.ieee.org
Time-Series Mining (TSM) is an important research area since it shows great potential in
practical applications. Deep learning models that rely on massive labeled data have been …

Time-llm: Time series forecasting by reprogramming large language models

M **, S Wang, L Ma, Z Chu, JY Zhang, X Shi… - ar**_with_unsupervised_multi-modal_representation_learning_from_VHR_images_and_POIs/links/6569aa153fa26f66f4439837/Geographic-map**-with-unsupervised-multi-modal-representation-learning-from-VHR-images-and-POIs.pdf" data-clk="hl=el&sa=T&oi=gga&ct=gga&cd=6&d=16152546633759592403&ei=ocKxZ7O7KNqy6rQP56ab0AE" data-clk-atid="0w8sY5VfKeAJ" target="_blank">[PDF] researchgate.net

Geographic map** with unsupervised multi-modal representation learning from VHR images and POIs

L Bai, W Huang, X Zhang, S Du, G Cong… - ISPRS Journal of …, 2023 - Elsevier
Most supervised geographic map** methods with very-high-resolution (VHR) images are
designed for a specific task, leading to high label-dependency and inadequate task …

MHCCL: masked hierarchical cluster-wise contrastive learning for multivariate time series

Q Meng, H Qian, Y Liu, L Cui, Y Xu… - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Learning semantic-rich representations from raw unlabeled time series data is critical for
downstream tasks such as classification and forecasting. Contrastive learning has recently …

Graph transformers: A survey

A Shehzad, F **a, S Abid, C Peng, S Yu… - arxiv preprint arxiv …, 2024 - arxiv.org
Graph transformers are a recent advancement in machine learning, offering a new class of
neural network models for graph-structured data. The synergy between transformers and …

Self-supervised multimodal learning: A survey

Y Zong, O Mac Aodha, T Hospedales - arxiv preprint arxiv:2304.01008, 2023 - arxiv.org
Multimodal learning, which aims to understand and analyze information from multiple
modalities, has achieved substantial progress in the supervised regime in recent years …