mlsanityData to 14 Oct 2026

Similarity of Classification Tasks

arXiv 2101.11201 ↗First posted 27 Jan 2021cs.LG stat.MLcited by 7

Not on the map. Why?

Abstract (arXiv)

Recent advances in meta-learning has led to remarkable performances on several few-shot learning benchmarks. However, such success often ignores the similarity between training and testing tasks, resulting in a potential bias evaluation. We, therefore, propose a generative approach based on a variant of Latent Dirichlet Allocation to analyse task similarity to optimise and better understand the performance of meta-learning. We demonstrate that the proposed method can provide an insightful evaluation for meta-learning algorithms on two few-shot classification benchmarks that matches common intuition: the more similar the higher performance. Based on this similarity measure, we propose a task-selection strategy for meta-learning and show that it can produce more accurate classification results than methods that randomly select training tasks.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 14 of its 34 references that are in the map. First posted on arXiv 27 Jan 2021.

Builds on

14 of 34 references.

References · 14

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  3. 2016Matching Networks for One Shot Learningcited by 2,255
  4. 2019A Closer Look at Few-shot Classificationcited by 684
  5. 2018Taskonomy: Disentangling Task Transfer Learningcited by 634
  6. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  7. 2019A Baseline for Few-Shot Image Classificationcited by 298
  8. 2019Task2Vec: Task Embedding for Meta-Learningcited by 205
  9. 2018Bayesian Model-Agnostic Meta-Learningcited by 194
  10. 2020LEEP: A New Measure to Evaluate Transferability of Learned Representationscited by 188
  11. 2019Transferability and Hardness of Supervised Classification Taskscited by 127
  12. 2019A Principled Approach for Learning Task Similarity in Multitask Learningcited by 32
2 more
  1. 2019Uncertainty in Model-Agnostic Meta-Learning using Variational Inferencecited by 23
  2. 2013Stochastic Collapsed Variational Bayesian Inference for Latent Dirichlet Allocationcited by 5

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 2; 2023: 1; 2024: 2.

7 papers.

  1. 2021Probing transfer learning with a model of synthetic correlated datasetscited by 25
  2. 2024Features are fate: a theory of transfer learning in high-dimensional regressioncited by 13
  3. 2022Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasetscited by 5
  4. 2021Probabilistic task modelling for meta-learningcited by 4
  5. 2023Provable Pathways: Learning Multiple Tasks over Multiple Pathscited by 3
  6. 2024Beyond Knowledge Silos: Task Fingerprinting for Democratization of Medical Imaging AIcited by 2
  7. 2022Few-Shot Image Classification Benchmarks are Too Far From Reality: Build Back Better with Semantic Task Samplingcited by 1