mlsanityData to 14 Oct 2026

RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression

arXiv 2205.15236 ↗First posted 30 May 2022cs.LG cs.AI cs.CVcited by 52

Not on the map. Why?

Abstract (arXiv)

Data imbalance, in which a plurality of the data samples come from a small proportion of labels, poses a challenge in training deep neural networks. Unlike classification, in regression the labels are continuous, potentially boundless, and form a natural ordering. These distinct features of regression call for new techniques that leverage the additional information encoded in label-space relationships. This paper presents the RankSim (ranking similarity) regularizer for deep imbalanced regression, which encodes an inductive bias that samples that are closer in label space should also be closer in feature space. In contrast to recent distribution smoothing based approaches, RankSim captures both nearby and distant relationships: for a given data sample, RankSim encourages the sorted list of its neighbors in label space to match the sorted list of its neighbors in feature space. RankSim is complementary to conventional imbalanced learning techniques, including re-weighting, two-stage training, and distribution smoothing, and lifts the state-of-the-art performance on three imbalanced regression benchmarks: IMDB-WIKI-DIR, AgeDB-DIR, and STS-B-DIR.

Key facts. Cited by 52 papers in the map (data through 14 Oct 2026). Builds on 28 of its 40 references that are in the map. First posted on arXiv 30 May 2022.

Builds on

28 of 40 references.

References · 28

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  2. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  3. 2017SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluationcited by 1,001
  4. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  5. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  6. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
  7. 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 513
  8. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 400
  9. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  10. 2018What is the Effect of Importance Weighting in Deep Learning?cited by 251
  11. 2019Differentiation of Blackbox Combinatorial Solverscited by 226
  12. 2020Rethinking the Value of Labels for Improving Class-Imbalanced Learningcited by 216
16 more
  1. 2021Improving Calibration for Long-Tailed Recognitioncited by 212
  2. 2019Learning with Average Precision: Training Image Retrieval with a Listwise Losscited by 185
  3. 2021Delving into Deep Imbalanced Regressioncited by 158
  4. 2020Remix: Rebalanced Mixupcited by 144
  5. 2019Differentiable Ranks and Sorting using Optimal Transportcited by 113
  6. 2019Implicit Semantic Data Augmentation for Deep Networkscited by 106
  7. 2019Optimizing Rank-based Metrics with Blackbox Differentiationcited by 58
  8. 2020Posterior Re-calibration for Imbalanced Datasetscited by 53
  9. 2016Learning Deep Embeddings with Histogram Losscited by 52
  10. 2021Self-Damaging Contrastive Learningcited by 48
  11. 2021Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspectivecited by 39
  12. 2021PML: Progressive Margin Loss for Long-tailed Age Classificationcited by 32
  13. 2019SoDeep: a Sorting Deep net to learn ranking loss surrogatescited by 28
  14. 2021Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detectioncited by 27
  15. 2015Training Deep Neural Networks via Direct Loss Minimizationcited by 25
  16. 2017Hashing as Tie-Aware Learning to Rankcited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 15; 2024: 12; 2025: 15; 2026: 9.

52 papers.

Sort:

By area:

  1. 2022Rank-N-Contrast: Learning Continuous Representations for Regressioncited by 76
  2. 2023Improving Deep Regression with Ordinal Entropycited by 45
  3. 2023Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classificationcited by 21
  4. 2023ConR: Contrastive Regularizer for Deep Imbalanced Regressioncited by 19
  5. 2023A step towards understanding why classification helps regressioncited by 15
  6. 2023Semi-Supervised Graph Imbalanced Regressioncited by 14
  7. 2024AFreeCA: Annotation-Free Counting for Allcited by 12
  8. 2025CLOC: Contrastive Learning for Ordinal Classification with Multi-Margin N-pair Losscited by 11
  9. 2025A Comprehensive Survey on Imbalanced Data Learningcited by 10
  10. 2023Deep Imbalanced Regression via Hierarchical Classification Adjustmentcited by 9
  11. 2024IM-Context: In-Context Learning for Imbalanced Regression Taskscited by 7
  12. 2024Interpretable Cascading Mixture-of-Experts for Urban Traffic Congestion Predictioncited by 7
38 more
  1. 2024Rank and Align: Towards Effective Source-free Graph Domain Adaptationcited by 7
  2. 2025Improve Representation for Imbalanced Regression through Geometric Constraintscited by 7
  3. 2024Are we making much progress? Revisiting chemical reaction yield prediction from an imbalanced regression perspectivecited by 6
  4. 2024Data Augmentation with Variational Autoencoder for Imbalanced Datasetcited by 5
  5. 2023Uncertainty Voting Ensemble for Imbalanced Deep Regressioncited by 4
  6. 2023Continual Learning in Predictive Autoscalingcited by 4
  7. 2023Generalized Oversampling for Learning from Imbalanced datasets and Associated Theorycited by 4
  8. 2025Sample Selection via Contrastive Fragmentation for Noisy Label Regressioncited by 4
  9. 2024Dist Loss: Enhancing Regression in Few-Shot Region through Distribution Distance Constraintcited by 3
  10. 2023AdaFlood: Adaptive Flood Regularizationcited by 2
  11. 2024Gradient Aligned Regression via Pairwise Lossescited by 2
  12. 2024Boarding for ISS: Imbalanced Self-Supervised: Discovery of a Scaled Autoencoder for Mixed Tabular Datasetscited by 2
  13. 2025PoGDiff: Product-of-Gaussians Diffusion Models for Imbalanced Text-to-Image Generationcited by 2
  14. 2025Improving Deep Regression with Tightnesscited by 2
  15. 2023Ranking Regularization for Critical Rare Classes: Minimizing False Positives at a High True Positive Ratecited by 1
  16. 2023Variational Imbalanced Regression: Fair Uncertainty Quantification via Probabilistic Smoothingcited by 1
  17. 2024Optimizing Automatic Speech Assessment: W-RankSim Regularization and Hybrid Feature Fusion Strategiescited by 1
  18. 2024Deep Imbalanced Regression to Estimate Vascular Age from PPG Data: a Novel Digital Biomarker for Cardiovascular Healthcited by 1
  19. 2024Leveraging Group Classification with Descending Soft Labeling for Deep Imbalanced Regressioncited by 1
  20. 2025ACCon: Angle-Compensated Contrastive Regularizer for Deep Regressioncited by 1
  21. 2025Disentangled Deep Smoothed Bootstrap for Fair Imbalanced Regressioncited by 1
  22. 2025Balanced Sharpness-Aware Minimization for Imbalanced Regressioncited by 1
  23. 2025SPECTRA: Spectral Domain-Aware Graph Generation for Imbalanced Molecular Property Regressioncited by 1
  24. 2026Hybrid Imbalanced Regression Through Unified Data-Level and Algorithm-Level Balancingcited by 1
  25. 2023Learning Subjective Time-Series Data via Utopia Label Distribution Approximationcited by 0
  26. 2023Noise-in, Bias-out: Balanced and Real-time MoCap Solvingcited by 0
  27. 2023Survey on Imbalanced Data, Representation Learning and SEP Forecastingcited by 0
  28. 2025AdaPRL: Adaptive Pairwise Regression Learning with Uncertainty Estimation for Universal Regression Taskscited by 0
  29. 2025VOCAL: Visual Odometry via ContrAstive Learningcited by 0
  30. 2025AI-driven Remote Facial Skin Hydration and TEWL Assessment from Selfie Images: A Systematic Solutioncited by 0
  31. 2025Highly Imbalanced Regression with Tabular Data in SEP and Other Applicationscited by 0
  32. 2025More Data or Better Algorithms: Latent Diffusion Augmentation for Deep Imbalanced Regressioncited by 0
  33. 2026LLM-Augmented Computational Phenotyping of Long Covidcited by 0
  34. 2026Chronological Contrastive Learning: Few-Shot Progression Assessment in Irreversible Diseasescited by 0
  35. 2026LOPA: Enhancing Spoken Language Assessment via Latent Ordinal Prototype Alignmentcited by 0
  36. 2026Contrastive Order Learning: A General Framework for Ordinal Regressioncited by 0
  37. 2026DeMMO: Longitudinal and Cross-Disease Modelling of Digital Mobility Outcomes via Multi-Task Learningcited by 0
  38. 2026Beyond Homoscedasticity: Decoupled Uncertainty Optimization for Deep Imbalanced Regressioncited by 0

50 most cited of 52 All 52 (JSON)