mlsanityData to 14 Oct 2026

Task Affinity with Maximum Bipartite Matching in Few-Shot Learning

arXiv 2110.02399 ↗First posted 5 Oct 2021cs.LG cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

We propose an asymmetric affinity score for representing the complexity of utilizing the knowledge of one task for learning another one. Our method is based on the maximum bipartite matching algorithm and utilizes the Fisher Information matrix. We provide theoretical analyses demonstrating that the proposed score is mathematically well-defined, and subsequently use the affinity score to propose a novel algorithm for the few-shot learning problem. In particular, using this score, we find relevant training data labels to the test data and leverage the discovered relevant data for episodically fine-tuning a few-shot model. Results on various few-shot benchmark datasets demonstrate the efficacy of the proposed approach by improving the classification accuracy over the state-of-the-art methods even when using smaller models.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 36 of its 60 references that are in the map. First posted on arXiv 5 Oct 2021.

Builds on

36 of 60 references.

References · 36

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  5. 2016Matching Networks for One Shot Learningcited by 2,255
  6. 2016Progressive Neural Networkscited by 1,361
  7. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  8. 2018On First-Order Meta-Learning Algorithmscited by 1,018
  9. 2019A Closer Look at Few-shot Classificationcited by 684
  10. 2018Taskonomy: Disentangling Task Transfer Learningcited by 634
  11. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  12. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
24 more
  1. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  2. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  3. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  4. 2018Meta-learning with differentiable closed-form solverscited by 397
  5. 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 375
  6. 2017PathNet: Evolution Channels Gradient Descent in Super Neural Networkscited by 364
  7. 2014CNN Features off-the-shelf: an Astounding Baseline for Recognitioncited by 316
  8. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  9. 2019A Baseline for Few-Shot Image Classificationcited by 298
  10. 2019Task2Vec: Task Embedding for Meta-Learningcited by 205
  11. 2018Recasting Gradient-Based Meta-Learning as Hierarchical Bayescited by 180
  12. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  13. 2015Deep Spatial Autoencoders for Visuomotor Learningcited by 153
  14. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 136
  15. 2017Few-Shot Image Recognition by Predicting Parameters from Activationscited by 122
  16. 2019Improved Few-Shot Visual Classificationcited by 115
  17. 2019Representation Similarity Analysis for Efficient Task taxonomy & Transfer Learningcited by 86
  18. 2020Embedding Propagation: Smoother Manifold for Few-Shot Classificationcited by 80
  19. 2019Transductive Episodic-Wise Adaptive Metric for Few-Shot Learningcited by 67
  20. 2019Few-Shot Learning with Embedded Class Models and Shot-Free Meta Trainingcited by 57
  21. 2021Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learningcited by 56
  22. 2017Label Efficient Learning of Transferable Representations across Domains and Taskscited by 49
  23. 2019Zero-Shot Task Transfercited by 26
  24. 2018Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weightscited by 11

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2; 2024: 1; 2025: 3.

8 papers.

  1. 2022RankDNN: Learning to Rank for Few-shot Learningcited by 7
  2. 2022Transfer Learning for Individual Treatment Effect Estimationcited by 5
  3. 2023Improving Open-Domain Dialogue Evaluation with a Causal Inference Modelcited by 4
  4. 2023Mode-Aware Continual Learning for Conditional Generative Adversarial Networkscited by 2
  5. 2024Task Attribute Distance for Few-Shot Learning: Theoretical Analysis and Applicationscited by 1
  6. 2025TLXML: Task-Level Explanation of Meta-Learning via Influence Functionscited by 0
  7. 2025Task-Aware Multi-Expert Architecture For Lifelong Deep Learningcited by 0
  8. 2025Advantages and limitations in the use of transfer learning for individual treatment effects in causal machine learningcited by 0