mlsanityData to 7 Oct 2026

Meta-learning Amidst Heterogeneity and Ambiguity

arXiv 2107.02228 ↗First posted 5 Jul 2021cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Meta-learning aims to learn a model that can handle multiple tasks generated from an unknown but shared distribution. However, typical meta-learning algorithms have assumed the tasks to be similar such that a single meta-learner is sufficient to aggregate the variations in all aspects. In addition, there has been less consideration on uncertainty when limited information is given as context. In this paper, we devise a novel meta-learning framework, called Meta-learning Amidst Heterogeneity and Ambiguity (MAHA), that outperforms previous works in terms of prediction based on its ability on task identification. By extensively conducting several experiments in regression and classification, we demonstrate the validity of our model, which turns out to be robust to both task heterogeneity and ambiguity.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 81 of its 122 references that are in the map. First posted on arXiv 5 Jul 2021.

Builds on

81 of 122 references.

References · 81

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2016Layer Normalizationcited by 5,579
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2013Auto-Encoding Variational Bayescited by 3,980
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  7. 2016Matching Networks for One Shot Learningcited by 2,246
  8. 2015Variational Inference with Normalizing Flowscited by 2,161
  9. 2013Describing Textures in the Wildcited by 2,110
  10. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
  11. 2017Deep Setscited by 1,394
  12. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
38 more
  1. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  2. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  3. 2016Deep Variational Information Bottleneckcited by 915
  4. 2016Pixel Recurrent Neural Networkscited by 814
  5. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  6. 2015Generating Sentences from a Continuous Spacecited by 607
  7. 2017Deep Learning Scaling is Predictable, Empiricallycited by 556
  8. 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 498
  9. 2019Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillationcited by 491
  10. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  11. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  12. 2015Deep Kernel Learningcited by 440
  13. 2018Conditional Neural Processescited by 421
  14. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  15. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  16. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 371
  17. 2016Ladder Variational Autoencoderscited by 315
  18. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
  19. 2018Neural Processescited by 307
  20. 2019Attentive Neural Processescited by 280
  21. 2018Probabilistic Model-Agnostic Meta-Learningcited by 254
  22. 2018Meta-Learning: A Surveycited by 254
  23. 2017Distral: Robust Multitask Reinforcement Learningcited by 231
  24. 2016Variational Deep Embedding: An Unsupervised and Generative Approach to Clusteringcited by 219
  25. 2018Bayesian Model-Agnostic Meta-Learningcited by 194
  26. 2019Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishingcited by 191
  27. 2016Variational Lossy Autoencodercited by 175
  28. 2019Convolutional Conditional Neural Processescited by 139
  29. 2018Inference Suboptimality in Variational Autoencoderscited by 131
  30. 2019Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processescited by 131
  31. 2018Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networkscited by 129
  32. 2019Lagging Inference Networks and Posterior Collapse in Variational Autoencoderscited by 124
  33. 2017Few-Shot Image Recognition by Predicting Parameters from Activationscited by 122
  34. 2016Towards a Neural Statisticiancited by 119
  35. 2018Maximizing acquisition functions for Bayesian optimizationcited by 113
  36. 2018Meta-Learning Probabilistic Inference For Predictioncited by 108
  37. 2017Interpretable Learning for Self-Driving Cars by Visualizing Causal Attentioncited by 106
  38. 2020Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learningcited by 99

50 most cited of 81 All 81 (JSON)

Built on by

Not cited yet.