mlsanityData to 14 Oct 2026

Hierarchically Structured Meta-learning

arXiv 1905.05301 ↗First posted 13 May 2019cs.LG stat.MLcited by 68

Not on the map. Why?

Abstract (arXiv)

In order to learn quickly with few samples, meta-learning utilizes prior knowledge learned from previous tasks. However, a critical challenge in meta-learning is task uncertainty and heterogeneity, which can not be handled via globally sharing knowledge among tasks. In this paper, based on gradient-based meta-learning, we propose a hierarchically structured meta-learning (HSML) algorithm that explicitly tailors the transferable knowledge to different clusters of tasks. Inspired by the way human beings organize knowledge, we resort to a hierarchical task clustering structure to cluster tasks. As a result, the proposed approach not only addresses the challenge via the knowledge customization to different clusters of tasks, but also preserves knowledge generalization among a cluster of similar tasks. To tackle the changing of task relationship, in addition, we extend the hierarchical structure to a continual learning environment. The experimental results show that our approach can achieve state-of-the-art performance in both toy-regression and few-shot image classification problems.

Key facts. Cited by 68 papers in the map (data through 14 Oct 2026). First posted on arXiv 13 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 24; 2022: 16; 2023: 14; 2024: 7; 2025: 4; 2026: 3.

68 papers.

Sort:

By area:

  1. 2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
  2. 2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
  3. 2021Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learningcited by 49
  4. 2021Meta-Learning Dynamics Forecasting Using Task Inferencecited by 38
  5. 2021Meta Discovery: Learning to Discover Novel Classes given Very Limited Datacited by 31
  6. 2022Gradient-based Bi-level Optimization for Deep Learning: A Surveycited by 26
  7. 2021How to Train Your MAML to Excel in Few-Shot Classificationcited by 22
  8. 2021Multimodal Emergent Fake News Detection via Meta Neural Process Networkscited by 21
  9. 2021An Optimization-Based Meta-Learning Model for MRI Reconstruction with Diverse Datasetcited by 18
  10. 2024Predicting Configuration Performance in Multiple Environments with Sequential Meta-learningcited by 17
  11. 2021Meta-Inductive Node Classification across Graphscited by 16
  12. 2021Few-Shot Learning with a Strong Teachercited by 16
38 more
  1. 2021Meta-Learning with Neural Tangent Kernelscited by 15
  2. 2022Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregationcited by 14
  3. 2023Contextual Stochastic Bilevel Optimizationcited by 14
  4. 2021Conditional Meta-Learning of Linear Representationscited by 12
  5. 2021Knowledge-Aware Meta-learning for Low-Resource Text Classificationcited by 10
  6. 2023Glocal Energy-based Learning for Few-Shot Open-Set Recognitioncited by 10
  7. 2022Multidimensional Belief Quantification for Label-Efficient Meta-Learningcited by 9
  8. 2022Hierarchically Structured Task-Agnostic Continual Learningcited by 9
  9. 2022Doing More with Less: Overcoming Data Scarcity for POI Recommendation via Cross-Region Transfercited by 8
  10. 2022Personalized Federated Learning via Heterogeneous Modular Networkscited by 8
  11. 2023Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Promptcited by 8
  12. 2023Episodic Multi-Task Learning with Heterogeneous Neural Processescited by 8
  13. 2024Deep Configuration Performance Learning: A Systematic Survey and Taxonomycited by 8
  14. 2024FREE: Faster and Better Data-Free Meta-Learningcited by 8
  15. 2021Prototype Completion for Few-Shot Learningcited by 7
  16. 2022Transfering Hierarchical Structure with Dual Meta Imitation Learningcited by 7
  17. 2022Neural Collaborative Filtering Bandits via Meta Learningcited by 7
  18. 2024Meta Clustering of Neural Banditscited by 7
  19. 2021Few-shot Learning for Topic Modelingcited by 5
  20. 2021Contextualizing Meta-Learning via Learning to Decomposecited by 5
  21. 2021Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learningcited by 5
  22. 2021ST-MAML: A Stochastic-Task based Method for Task-Heterogeneous Meta-Learningcited by 4
  23. 2023Meta-Reinforcement Learning via Exploratory Task Clusteringcited by 4
  24. 2023M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptationcited by 4
  25. 2022StratDef: Strategic Defense Against Adversarial Attacks in ML-based Malware Detectioncited by 3
  26. 2023Provable Pathways: Learning Multiple Tasks over Multiple Pathscited by 3
  27. 2024XB-MAML: Learning Expandable Basis Parameters for Effective Meta-Learning with Wide Task Coveragecited by 3
  28. 2025CICADA: Cross-Domain Interpretable Coding for Anomaly Detection and Adaptation in Multivariate Time Seriescited by 3
  29. 2021Meta-Learning with MAML on Treescited by 2
  30. 2022PAVI: Plate-Amortized Variational Inferencecited by 2
  31. 2022Robust Meta-Representation Learning via Global Label Inference and Classificationcited by 2
  32. 2023EMO: Episodic Memory Optimization for Few-Shot Meta-Learningcited by 2
  33. 2024Atomas: Hierarchical Alignment on Molecule-Text for Unified Molecule Understanding and Generationcited by 2
  34. 2025Tailored Forecasting from Short Time Series via Meta-learningcited by 2
  35. 2021Generalising via Meta-Examples for Continual Learning in the Wildcited by 1
  36. 2021Meta-learning for Matrix Factorization without Shared Rows or Columnscited by 1
  37. 2021A Meta-learning Approach to Reservoir Computing: Time Series Prediction with Limited Datacited by 1
  38. 2022EEML: Ensemble Embedded Meta-learningcited by 1

50 most cited of 68 All 68 (JSON)