mlsanityData to 7 Oct 2026

SEAL: Simultaneous Label Hierarchy Exploration And Learning

arXiv 2304.13374 ↗First posted 26 Apr 2023cs.LG cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Label hierarchy is an important source of external knowledge that can enhance classification performance. However, most existing methods rely on predefined label hierarchies that may not match the data distribution. To address this issue, we propose Simultaneous label hierarchy Exploration And Learning (SEAL), a new framework that explores the label hierarchy by augmenting the observed labels with latent labels that follow a prior hierarchical structure. Our approach uses a 1-Wasserstein metric over the tree metric space as an objective function, which enables us to simultaneously learn a data-driven label hierarchy and perform (semi-)supervised learning. We evaluate our method on several datasets and show that it achieves superior results in both supervised and semi-supervised scenarios and reveals insightful label structures. Our implementation is available at https://github.com/tzq1999/SEAL.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 32 of its 53 references that are in the map. First posted on arXiv 26 Apr 2023.

Builds on

32 of 53 references.

References · 32

  1. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  2. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  3. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  4. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  5. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  6. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  7. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  8. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  9. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 537
  10. 2020Meta Pseudo Labelscited by 372
  11. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  12. 2015Semi-Supervised Learning with Ladder Networkscited by 246
20 more
  1. 2022FreeMatch: Self-adaptive Thresholding for Semi-supervised Learningcited by 232
  2. 2021Dash: Semi-Supervised Learning with Dynamic Thresholdingcited by 147
  3. 2023SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learningcited by 133
  4. 2021Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samplescited by 114
  5. 2019Making Better Mistakes: Leveraging Class Hierarchies with Deep Networkscited by 112
  6. 2022Debiased Learning from Naturally Imbalanced Pseudo-Labelscited by 85
  7. 2021SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classificationcited by 68
  8. 2017Do Convolutional Neural Networks Learn Class Hierarchy?cited by 61
  9. 2019Tree-Sliced Variants of Wasserstein Distancescited by 54
  10. 2020NBDT: Neural-Backed Decision Treescited by 46
  11. 2018Hierarchy-based Image Embeddings for Semantic Image Retrievalcited by 41
  12. 2021All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-trainingcited by 32
  13. 2022Learning Hierarchy Aware Features for Reducing Mistake Severitycited by 26
  14. 2020AlphaMatch: Improving Consistency for Semi-supervised Learning with Alpha-divergencecited by 22
  15. 2021No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networkscited by 21
  16. 2020Leveraging Class Hierarchies with Metric-Guided Prototype Learningcited by 20
  17. 2021Supervised Tree-Wasserstein Distancecited by 10
  18. 2022MaxMatch: Semi-Supervised Learning with Worst-Case Consistencycited by 9
  19. 2021HIERMATCH: Leveraging Label Hierarchies for Improving Semi-Supervised Learningcited by 7
  20. 2021Vision Xformers: Efficient Attention for Image Classificationcited by 4

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 3.

6 papers.

  1. 2023Wasserstein-Fisher-Rao Embedding: Logical Query Embeddings with Local Comparison and Global Transportcited by 16
  2. 2023RelationMatch: Matching In-batch Relationships for Semi-supervised Learningcited by 8
  3. 2023OTMatch: Improving Semi-Supervised Learning with Optimal Transportcited by 6
  4. 2024Unveiling the Dynamics of Information Interplay in Supervised Learningcited by 3
  5. 2024Learning Structured Representations by Embedding Class Hierarchy with Fast Optimal Transportcited by 3
  6. 2024Exploring Information-Theoretic Metrics Associated with Neural Collapse in Supervised Trainingcited by 1