mlsanityData to 7 Oct 2026

Meta-Learning with Fewer Tasks through Task Interpolation

arXiv 2106.02695 ↗First posted 4 Jun 2021cs.LGcited by 45

Not on the map. Why?

Abstract (arXiv)

Meta-learning enables algorithms to quickly learn a newly encountered task with just a few labeled examples by transferring previously learned knowledge. However, the bottleneck of current meta-learning algorithms is the requirement of a large number of meta-training tasks, which may not be accessible in real-world scenarios. To address the challenge that available tasks may not densely sample the space of tasks, we propose to augment the task set through interpolation. By meta-learning with task interpolation (MLTI), our approach effectively generates additional tasks by randomly sampling a pair of tasks and interpolating the corresponding features and labels. Under both gradient-based and metric-based meta-learning settings, our theoretical analysis shows MLTI corresponds to a data-adaptive meta-regularization and further improves the generalization. Empirically, in our experiments on eight datasets from diverse domains including image recognition, pose prediction, molecule property prediction, and medical image classification, we find that the proposed general MLTI framework is compatible with representative meta-learning algorithms and consistently outperforms other state-of-the-art strategies.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). Builds on 37 of its 66 references that are in the map. First posted on arXiv 4 Jun 2021.

Builds on

37 of 66 references.

References · 37

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  4. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  5. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  8. 2019Meta-Learning with Implicit Gradientscited by 523
  9. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  10. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  11. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 377
  12. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
25 more
  1. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  2. 2019A Baseline for Few-Shot Image Classificationcited by 298
  3. 2018Probabilistic Model-Agnostic Meta-Learningcited by 254
  4. 2020Few-Shot Learning via Learning the Representation, Provablycited by 213
  5. 2020How Does Mixup Help With Robustness and Generalization?cited by 193
  6. 2018Recasting Gradient-Based Meta-Learning as Hierarchical Bayescited by 180
  7. 2020Provable Meta-Learning of Linear Representationscited by 161
  8. 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
  9. 2019Online Meta-Learningcited by 137
  10. 2019Meta-Learning with Warped Gradient Descentcited by 98
  11. 2019Meta-Learning without Memorizationcited by 92
  12. 2019TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learningcited by 90
  13. 2019Meta-Curvaturecited by 70
  14. 2017Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithmcited by 65
  15. 2019Few-shot Text Classification with Distributional Signaturescited by 58
  16. 2020Meta-Learning Requires Meta-Augmentationcited by 57
  17. 2019Image Deformation Meta-Networks for One-Shot Learningcited by 56
  18. 2020Improving Generalization in Meta-learning via Task Augmentationcited by 55
  19. 2020Data Augmentation for Meta-Learningcited by 38
  20. 2020Dropout: Explicit Forms and Capacity Controlcited by 27
  21. 2019Difficulty-aware Meta-learning for Rare Disease Diagnosiscited by 24
  22. 2019Automated Skin Lesion Classification Using Ensemble of Deep Neural Networks in ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection Challengecited by 16
  23. 2020Regularizing Meta-Learning via Gradient Dropoutcited by 15
  24. 2019Towards Understanding Generalization in Gradient-Based Meta-Learningcited by 12
  25. 2018Prototypical Clustering Networks for Dermatological Disease Diagnosiscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 12; 2023: 16; 2024: 6; 2025: 7; 2026: 1.

45 papers.

Sort:

By area:

  1. 2022Improving Out-of-Distribution Robustness via Selective Augmentationcited by 202
  2. 2022C-Mixup: Improving Generalization in Regressioncited by 57
  3. 2022Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Expertscited by 50
  4. 2023Understanding Multimodal Contrastive Learning and Incorporating Unpaired Datacited by 43
  5. 2021Adversarial Training Helps Transfer Learning via Better Representationscited by 36
  6. 2022Meta Learning for Natural Language Processing: A Surveycited by 26
  7. 2024Prompt Learning via Meta-Regularizationcited by 26
  8. 2023Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detectioncited by 25
  9. 2022Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noisecited by 22
  10. 2023Explore to Generalize in Zero-Shot RLcited by 20
  11. 2023HappyMap: A Generalized Multi-calibration Methodcited by 17
  12. 2023ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusioncited by 15
33 more
  1. 2022FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Datacited by 13
  2. 2021Multimodality in Meta-Learning: A Comprehensive Surveycited by 11
  3. 2023Mnemosyne: Learning to Train Transformers with Transformerscited by 9
  4. 2023Federated Few-shot Learningcited by 9
  5. 2023Episodic Multi-Task Learning with Heterogeneous Neural Processescited by 8
  6. 2021Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stabilitycited by 7
  7. 2022Set-based Meta-Interpolation for Few-Task Meta-Learningcited by 7
  8. 2022Meta Reinforcement Learning with Finite Training Tasks -- a Density Estimation Approachcited by 6
  9. 2025Enhancing Unsupervised Graph Few-shot Learning via Set Functions and Optimal Transportcited by 6
  10. 2023Generating Synthetic Datasets by Interpolating along Generalized Geodesicscited by 5
  11. 2025Dual-level Mixup for Graph Few-shot Learning with Fewer Taskscited by 5
  12. 2023Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detectioncited by 4
  13. 2023MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Taskscited by 4
  14. 2023Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shiftcited by 4
  15. 2023Task-Distributionally Robust Data-Free Meta-Learningcited by 4
  16. 2022Interpolating Compressed Parameter Subspacescited by 3
  17. 2023Interpolation for Robust Learning: Data Augmentation on Wasserstein Geodesicscited by 3
  18. 2024Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfercited by 3
  19. 2022Improving Meta-Learning Generalization with Activation-Based Early-Stoppingcited by 2
  20. 2025Hyperbolic Dual Feature Augmentation for Open-Environmentcited by 2
  21. 2022Interval Bound Interpolation for Few-shot Learning with Few Taskscited by 1
  22. 2023Exploiting Style Transfer-based Task Augmentation for Cross-Domain Few-Shot Learningcited by 1
  23. 2024Rethinking Meta-Learning from a Learning Lenscited by 1
  24. 2025MetaTPT: Meta Test-time Prompt Tuning for Vision-Language Modelscited by 1
  25. 2022Learning to generate imaginary tasks for improving generalization in meta-learningcited by 0
  26. 2023Successive Model-Agnostic Meta-Learning for Few-Shot Fault Time Series Prognosiscited by 0
  27. 2024Meta-Task: A Method-Agnostic Framework for Learning to Regularize in Few-Shot Learningcited by 0
  28. 2024Virtual Node Generation for Node Classification in Sparsely-Labeled Graphscited by 0
  29. 2024Memory-Reduced Meta-Learning with Guaranteed Convergencecited by 0
  30. 2025One-Class Domain Adaptation via Meta-Learningcited by 0
  31. 2025Lightweight Relational Embedding in Task-Interpolated Few-Shot Networks for Enhanced Gastrointestinal Disease Classificationcited by 0
  32. 2025Neural Coherence : Find higher performance to out-of-distribution tasks from few samplescited by 0
  33. 2026CalibHyper: Chance-Corrected Relational Hypergraphs for Few-Shot Molecular Property Predictioncited by 0