mlsanityData to 14 Oct 2026

L2CU: Learning to Complement Unseen Users

arXiv 2601.06119 ↗First posted 3 Jan 2026cs.LG cs.AI cs.HCcited by 2

Not on the map. Why?

Abstract (arXiv)

Recent research highlights the potential of machine learning models to learn to complement (L2C) human strengths; however, generalizing this capability to unseen users remains a significant challenge. Existing L2C methods oversimplify interaction between human and AI by relying on a single, global user model that neglects individual user variability, leading to suboptimal cooperative performance. Addressing this, we introduce L2CU, a novel L2C framework for human-AI cooperative classification with unseen users. Given sparse and noisy user annotations, L2CU identifies representative annotator profiles capturing distinct labeling patterns. By matching unseen users to these profiles, L2CU leverages profile-specific models to complement the user and achieve superior joint accuracy. We evaluate L2CU on datasets (CIFAR-10N, CIFAR-10H, Fashion-MNIST-H, Chaoyang and AgNews), demonstrating its effectiveness as a model-agnostic solution for improving human-AI cooperative classification.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 43 of its 56 references that are in the map. First posted on arXiv 3 Jan 2026.

Builds on

43 of 56 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  7. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  8. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  9. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
  10. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 665
  11. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 582
  12. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 416
31 more
  1. 2020Consistent Estimators for Learning to Defer to an Expertcited by 271
  2. 2021Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotationscited by 256
  3. 2019Human uncertainty makes classification more robustcited by 235
  4. 2017Predict Responsibly: Improving Fairness and Accuracy by Learning to Defercited by 233
  5. 2020Learning to Complement Humanscited by 124
  6. 2022Selective-Supervised Contrastive Learning with Noisy Labelscited by 112
  7. 2019The Algorithmic Automation Problem: Prediction, Triage, and Human Effortcited by 101
  8. 2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
  9. 2021Differentiable Learning Under Triagecited by 76
  10. 2023Who Should Predict? Exact Algorithms For Learning to Defer to Humanscited by 70
  11. 2021Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labelscited by 69
  12. 2022Calibrated Learning to Defer with One-vs-All Classifierscited by 69
  13. 2021Instance-dependent Label-noise Learning under a Structural Causal Modelcited by 50
  14. 2021Hard Sample Aware Noise Robust Learning for Histopathology Image Classificationcited by 48
  15. 2021Combining Human Predictions with Model Probabilities via Confusion Matrices and Calibrationcited by 40
  16. 2022Identifiability of Label Noise Transition Matrixcited by 34
  17. 2021"Brilliant AI Doctor" in Rural China: Tensions and Challenges in AI-Powered CDSS Deploymentcited by 28
  18. 2024Learning to Defer to a Population: A Meta-Learning Approachcited by 27
  19. 2022Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classificationcited by 26
  20. 2022Uncalibrated Models Can Improve Human-AI Collaborationcited by 26
  21. 2022CROWDLAB: Supervised learning to infer consensus labels and quality scores for data with multiple annotatorscited by 16
  22. 2022ADMoE: Anomaly Detection with Mixture-of-Experts from Noisy Labelscited by 15
  23. 2018Fast Dawid-Skene: A Fast Vote Aggregation Scheme for Sentiment Classificationcited by 12
  24. 2022Trustable Co-label Learning from Multiple Noisy Annotatorscited by 12
  25. 2023Transferring Annotator- and Instance-dependent Transition Matrix for Learning from Crowdscited by 11
  26. 2023Coupled Confusion Correction: Learning from Crowds with Sparse Annotationscited by 9
  27. 2024Learning to Complement and to Defer to Multiple Userscited by 7
  28. 2023Learning to Complement with Multiple Humanscited by 5
  29. 2023Instance-dependent Noisy-label Learning with Graphical Model Based Noise-rate Estimationcited by 4
  30. 2025Identity-Free Deferral For Unseen Expertscited by 4
  31. 2023FiFAR: A Fraud Detection Dataset for Learning to Defercited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Understanding Annotation Error Propagation and Learning an Adaptive Policy for Expert Intervention in Barrett's Video Segmentationcited by 0
  2. 2026DisMix: Order-Aware Mixup for Medical Imaging via Disentangling Ordinal and Non-Ordinal Featurescited by 0