mlsanityData to 7 Oct 2026

Continuous Meta-Learning without Tasks

arXiv 1912.08866 ↗First posted 18 Dec 2019cs.LG cs.CV cs.NEcited by 50

Not on the map. Why?

Abstract (arXiv)

Meta-learning is a promising strategy for learning to efficiently learn within new tasks, using data gathered from a distribution of tasks. However, the meta-learning literature thus far has focused on the task segmented setting, where at train-time, offline data is assumed to be split according to the underlying task, and at test-time, the algorithms are optimized to learn in a single task. In this work, we enable the application of generic meta-learning algorithms to settings where this task segmentation is unavailable, such as continual online learning with a time-varying task. We present meta-learning via online changepoint analysis (MOCA), an approach which augments a meta-learning algorithm with a differentiable Bayesian changepoint detection scheme. The framework allows both training and testing directly on time series data without segmenting it into discrete tasks. We demonstrate the utility of this approach on a nonlinear meta-regression benchmark as well as two meta-image-classification benchmarks.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 14; 2023: 15; 2024: 7; 2025: 4; 2026: 2.

50 papers.

Sort:

By area:

  1. 2024Variational Bayesian Last Layerscited by 67
  2. 2021Continual Learning via Local Module Compositioncited by 61
  3. 2022On the Soft-Subnetwork for Few-shot Class Incremental Learningcited by 37
  4. 2026MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wildcited by 35
  5. 2021Continual Learning for Recurrent Neural Networks: an Empirical Evaluationcited by 34
  6. 2022A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biasescited by 30
  7. 2022Expanding the Deployment Envelope of Behavior Prediction via Adaptive Meta-Learningcited by 23
  8. 2022Learning Options via Compressioncited by 22
  9. 2021Sequoia: A Software Framework to Unify Continual Learning Researchcited by 19
  10. 2022Discrete Key-Value Bottleneckcited by 18
  11. 2023Learning to Learn from APIs: Black-Box Data-Free Meta-Learningcited by 18
  12. 2023Curious Replay for Model-based Adaptationcited by 16
38 more
  1. 2021CoMPS: Continual Meta Policy Searchcited by 15
  2. 2022Learning Mixtures of Linear Dynamical Systemscited by 15
  3. 2022Is Bayesian Model-Agnostic Meta Learning Better than Model-Agnostic Meta Learning, Provably?cited by 13
  4. 2022Self-Adaptive Driving in Nonstationary Environments through Conjectural Online Lookahead Adaptationcited by 12
  5. 2023When Meta-Learning Meets Online and Continual Learning: A Surveycited by 12
  6. 2023Architecture, Dataset and Model-Scale Agnostic Data-free Meta-Learningcited by 10
  7. 2021Bayesian Embeddings for Few-Shot Open World Recognitioncited by 8
  8. 2021Meta Learning on a Sequence of Imbalanced Domains with Difficulty Awarenesscited by 8
  9. 2023Clustering-based Domain-Incremental Learningcited by 8
  10. 2025On-device edge learning for IoT data streams: a surveycited by 8
  11. 2022Meta-Learning Parameterized Skillscited by 7
  12. 2023On Sequential Bayesian Inference for Continual Learningcited by 6
  13. 2022Time-Varying Propensity Score to Bridge the Gap between the Past and Presentcited by 5
  14. 2022Fully Online Meta-Learning Without Task Boundariescited by 4
  15. 2023Few-Shot Learning Patterns in Financial Time-Series for Trend-Following Strategiescited by 4
  16. 2023T-SaS: Toward Shift-aware Dynamic Adaptation for Streaming Datacited by 3
  17. 2025Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Taskscited by 3
  18. 2025Meta-Learning Online Dynamics Model Adaptation in Off-Road Autonomous Drivingcited by 3
  19. 2023On the Generalization Error of Meta Learning for the Gibbs Algorithmcited by 2
  20. 2023Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identificationcited by 2
  21. 2021Generalising via Meta-Examples for Continual Learning in the Wildcited by 1
  22. 2022Lifelong Wandering: A realistic few-shot online continual learning settingcited by 1
  23. 2023Algorithm Design for Online Meta-Learning with Task Boundary Detectioncited by 1
  24. 2023Neurosymbolic Meta-Reinforcement Lookahead Learning Achieves Safe Self-Driving in Non-Stationary Environmentscited by 1
  25. 2021Signal Transformer: Complex-valued Attention and Meta-Learning for Signal Recognitioncited by 0
  26. 2022Reinforcement Learning with Brain-Inspired Modulation can Improve Adaptation to Environmental Changescited by 0
  27. 2022Expanding continual few-shot learning benchmarks to include recognition of specific instancescited by 0
  28. 2023Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adaptercited by 0
  29. 2023GMTR: Graph Matching Transformerscited by 0
  30. 2023DarkShot: Lighting Dark Images with Low-Compute and High-Qualitycited by 0
  31. 2024TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processingcited by 0
  32. 2024TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networkscited by 0
  33. 2024T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Imagecited by 0
  34. 2024Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithmscited by 0
  35. 2024Towards General Deepfake Detection with Dynamic Curriculumcited by 0
  36. 2024Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphscited by 0
  37. 2025Mask6D: Masked Pose Priors For 6D Object Pose Estimationcited by 0
  38. 2026CoMetaPNS: Continually Meta-learning Personalized Neural Surrogates for Cardiac Electrophysiology Simulationscited by 0