mlsanityData to 14 Oct 2026

Successive Model-Agnostic Meta-Learning for Few-Shot Fault Time Series Prognosis

arXiv 2311.02300 ↗First posted 4 Nov 2023cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Meta learning is a promising technique for solving few-shot fault prediction problems, which have attracted the attention of many researchers in recent years. Existing meta-learning methods for time series prediction, which predominantly rely on random and similarity matching-based task partitioning, face three major limitations: (1) feature exploitation inefficiency; (2) suboptimal task data allocation; and (3) limited robustness with small samples. To overcome these limitations, we introduce a novel 'pseudo meta-task' partitioning scheme that treats a continuous time period of a time series as a meta-task, composed of multiple successive short time periods. Employing continuous time series as pseudo meta-tasks allows our method to extract more comprehensive features and relationships from the data, resulting in more accurate predictions. Moreover, we introduce a differential algorithm to enhance the robustness of our method across different datasets. Through extensive experiments on several fault and time series prediction datasets, we demonstrate that our approach substantially enhances prediction performance and generalization capability under both few-shot and general conditions.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 40 references that are in the map. First posted on arXiv 4 Nov 2023.

Builds on

21 of 40 references.

References · 21

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  5. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  6. 2020Time Series Forecasting With Deep Learning: A Surveycited by 459
  7. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 394
  8. 2018How to train your MAMLcited by 309
  9. 2020Learning Long-Term Dependencies in Irregularly-Sampled Time Seriescited by 83
  10. 2020Meta-learning framework with applications to zero-shot time-series forecastingcited by 70
  11. 2022A Review of Deep Transfer Learning and Recent Advancementscited by 57
  12. 2021Offline Meta-Reinforcement Learning with Online Self-Supervisioncited by 53
9 more
  1. 2021Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learningcited by 49
  2. 2021Meta-Learning with Fewer Tasks through Task Interpolationcited by 45
  3. 2021Bootstrapped Meta-Learningcited by 45
  4. 2021Meta-learning with an Adaptive Task Schedulercited by 27
  5. 2019Meta-Learning for Few-Shot Time Series Classificationcited by 23
  6. 2021Task Aligned Generative Meta-learning for Zero-shot Learningcited by 19
  7. 2020A Concise Review of Recent Few-shot Meta-learning Methodscited by 13
  8. 2021Meta-Reinforcement Learning by Tracking Task Non-stationaritycited by 8
  9. 2021Multimodal Meta-Learning for Time Series Regressioncited by 7

Built on by

Not cited yet.