Advances in Partial/Complementary Label Learning

Advances in Partial/Complementary Label Learning provides the most advanced and detailed information on partial/complementary label learning field.

Partial/complementary label learning is an emerging framework in weakly supervised machine learning with broad application prospects. It handles the case in which each training example corresponds to a candidate label set and only one label concealed in the set is the ground-truth label.

This project is curated and maintained by Dong-Dong Wu. I will do my best to keep the project up to date. If you have any suggestions or are interested in being contributors, feel free to drop me an email.

How to submit a pull request?

• 🌐 Project Page
• Code
• 📖 bibtex

Latest Updates

• [2024/12/08] Update some code links of papers.
• [2024/09/13] A major overhaul of the original github repository.

Contents

• Main
  • Early Work
  • Survey
  • Generative Modeling
  • Understanding
  • Better Optimization
  • Partial Multi-Label Learning
  • Noisy Partial Label Learning
  • Semi-Supervised Partial Label Learning
  • Multi-Instance Partial Label Learning
  • Imbalanced Partial Label Problem
  • Out-of-distributrion Partial Label Learning
  • Federated Partial Label Learning
  • Partial Label Regression
  • Dimensionality Reduction
  • Multi-Complementary Label Learning
  • Multi-View Learning
  • Adversarial Training
  • Negative Learning
  • Incremental Learning
  • Online Learning
  • Conformal Prediction
  • Few-Shot Learning
  • Open-Set Problem
  • Data Augmentation
  • Multi-Dimensional
  • Domain Adaptation
• Applications
  • Audio
  • Text
  • Sequence
  • Recognition
  • Object Localization
  • Map Reconstruction
  • Semi-Supervised Learning
  • Active Learning
  • Noisy Label Learning
  • Test-Time Adaptation

Main

• Learning from Complementary Labels (NeurIPS 2017)
• Learning from Partial Labels (JMLR 2011)

Early Work

• To be continue.

Survey

• Partial label learning: Taxonomy, analysis and outlook (NN 2023)

Generative Modeling

• Learning with Biased Complementary Labels (ECCV 2018)
• Complementary-Label Learning for Arbitrary Losses and Models (ICML 2019)
• Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels (ICML 2020)
• Provably Consistent Partial-Label Learning (NeurIPS 2020)
• Leveraged Weighted Loss for Partial Label Learning (ICML 2021)
• Unbiased Risk Estimator to Multi-Labeled Complementary Label Learning (IJCAI 2023)
• Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical (ICML 2024)
• Towards Unbiased Exploration in Partial Label Learning (2023)

Understanding

• Bridging Ordinary-Label Learning and Complementary-Label Learning (ACML 2020)
• On the Power of Deep but Naive Partial Label Learning (ICASSP 2021)
• Learning from a Complementary-label Source Domain: Theory and Algorithms (TNNLS 2021)
• A Unifying Probabilistic Framework for Partially Labeled Data Learning (TPAMI 2023)
• Candidate Label Set Pruning: A Data-centric Perspective for Deep Partial-label Learning (ICLR 2024)
• Understanding Self-Distillation and Partial Label Learning in Multi-Class Classification with Label Noise (2024)

Better Optimization

• A Conditional Multinomial Mixture Model for Superset Label Learning (NeurIPS 2012)
• GM-PLL: Graph Matching based Partial Label Learning (TKDE 2019)
• Partial Label Learning via Label Enhancement (AAAI 2019)
• Partial Label Learning with Self-Guided Retraining (AAAI 2019)
• Partial Label Learning by Semantic Difference Maximization (IJCAI 2019)
• Partial Label Learning with Unlabeled Data (IJCAI 2019)
• Adaptive Graph Guided Disambiguation for Partial Label Learning (KDD 2019)
• A Self-Paced Regularization Framework for Partial-Label Learning (TYCB 2020)
• Large Margin Partial Label Machine (TNNLS 2020)
• Learning with Noisy Partial Labels by Simultaneously Leveraging Global and Local Consistencies (CIKM 2020)
• Network Cooperation with Progressive Disambiguation for Partial Label Learning (ECML-PKDD 2020)
• Deep Discriminative CNN with Temporal Ensembling for Ambiguously-Labeled Image Classification (AAAI 2020)
• Generative-Discriminative Complementary Learning (AAAI 2020)
• Partial Label Learning with Batch Label Correction (AAAI 2020)
• Progressive Identification of True Labels for Partial-Label Learning (ICML 2020)
• Generalized Large Margin -NN for Partial Label Learning (TMM2021)
• Adaptive Graph Guided Disambiguation for Partial Label Learning (TPAMI 2022)
• Discriminative Metric Learning for Partial Label Learning (TNNLS 2021)
• Top-k Partial Label Machine (TNNLS 2021)
• Detecting the Fake Candidate Instances: Ambiguous Label Learning with Generative Adversarial Networks (CIKM 2021)
• Discriminative Complementary-Label Learning with Weighted Loss (ICML 2021)
• Instance-Dependent Partial Label Learning (NeurIPS 2021)
• A Generative Model for Partial Label Learning (ICME 2021)
• Learning with Proper Partial Labels (NearoComputing 2022)
• Biased Complementary-Label Learning Without True Labels (TNNLS 2022)
• Exploiting Class Activation Value for Partial-Label Learning (ICLR 2022)
• PiCO: Contrastive Label Disambiguation for Partial Label Learning (ICLR 2022)
• Deep Graph Matching for Partial Label Learning (IJCAI 2022)
• Exploring Binary Classification Hidden within Partial Label Learning (IJCAI 2022)
• Ambiguity-Induced Contrastive Learning for Instance-Dependent Partial Label Learning (IJCAI 2022)
• Partial Label Learning via Label Influence Function (ICML 2022)
• Revisiting Consistency Regularization for Deep Partial Label Learning (ICML 2022)
• Partial Label Learning with Semantic Label Representations (KDD 2022)
• Progressive Purification for Instance-Dependent Partial Label Learning (ICML 2023)
• GraphDPI: Partial label disambiguation by graph representation learning via mutual information maximization (PR 2023)
• Variational Label Enhancement (TPAMI 2023)
• CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning (TPAMI 2023)
• Reduction from Complementary-Label Learning to Probability Estimates (PAKDD 2023)
• Decompositional Generation Process for Instance-Dependent Partial Label Learning (ICLR 2023)
• Mutual Partial Label Learning with Competitive Label Noise (ICLR 2023)
• Can Label-Specific Features Help Partial-Label Learning? (AAAI 2023)
• Learning with Partial Labels from Semi-supervised Perspective (AAAI 2023)
• Consistent Complementary-Label Learning via Order-Preserving Losses (ICAIS 2023)
• Complementary Classifier Induced Partial Label Learning (KDD 2023)
• Towards Effective Visual Representations for Partial-Label Learning (CVPR 2023)
• Candidate-aware Selective Disambiguation Based On Normalized Entropy for Instance-dependent Partial-label Learning (ICCV 2023)
• Partial Label Learning with Dissimilarity Propagation guided Candidate Label Shrinkage (NeurIPS 2023)
• Learning From Biased Soft Labels (NeurIPS 2023)
• Meta Objective Guided Disambiguation for Partial Label Learning (2023)
• Adversary-Aware Partial label learning with Label distillation (2023)
• Solving Partial Label Learning Problem with Multi-Agent Reinforcement Learning (2023)
• Learning from Stochastic Labels (2023)
• Deep Duplex Learning for Weak Supervision (2023)
• Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations (2023)
• Self-distillation and self-supervision for partial label learning (PR 2023)
• Partial Label Learning with a Partner (AAAI 2024)
• Distilling Reliable Knowledge for Instance-Dependent Partial Label Learning (AAAI 2024)
• Disentangled Partial Label Learning (AAAI 2024)
• CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning (CVPR 2024)
• A General Framework for Learning from Weak Supervision (ICML 2024)
• Does Label Smoothing Help Deep Partial Label Learning? (ICML 2024)
• Label Dropout: Improved Deep Learning Echocardiography Segmentation Using Multiple Datasets With Domain Shift and Partial Labelling (SCIS 2024)
• Appeal: Allow Mislabeled Samples the Chance to be Rectified in Partial Label Learning (2024)
• Graph Partial Label Learning with Potential Cause Discovering (2024)
• Reduction-based Pseudo-label Generation for Instance-dependent Partial Label Learning (2024)

Partial-Multi Label Learning

• Learning a Deep ConvNet for Multi-label Classification with Partial Labels (CVPR 2019)
• Multi-View Partial Multi-Label Learning with Graph-Based Disambiguation (AAAI 2020)
• Partial Multi-Label Learning via Multi-Subspace Representation (IJCAI 2020)
• Feature-Induced Manifold Disambiguation for Multi-View Partial Multi-label Learning (KDD 2020)
• Prior Knowledge Regularized Self-Representation Model for Partial Multilabel Learning (TYCB 2021)
• Global-Local Label Correlation for Partial Multi-Label Learning (TMM 2021)
• Progressive Enhancement of Label Distributions for Partial Multilabel Learning (TNNLS 2021)
• Partial Multi-Label Learning With Noisy Label Identification (TPAMI 2021)
• Partial Multi-Label Learning via Credible Label Elicitation (TPAMI 2021)
• Adversarial Partial Multi-Label Learning (AAAI 2021)
• Learning from Complementary Labels via Partial-Output Consistency Regularization (IJCAI 2021)
• Partial Multi-Label Learning with Meta Disambiguation (KDD 2021)
• Understanding Partial Multi-Label Learning via Mutual Information (NeurIPS 2021)
• Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels (AAAI 2022)
• Structured Semantic Transfer for Multi-Label Recognition with Partial Labels) (AAAI 2022)
• Boosting Multi-Label Image Classification with Complementary Parallel Self-Distillation (IJCAI 2022)
• Multi-label Classification with Partial Annotations using Class-aware Selective Loss (CVPR 2022)
• Deep Double Incomplete Multi-View Multi-Label Learning With Incomplete Labels and Missing Views (TNNLS 2023)
• Towards Enabling Binary Decomposition for Partial Multi-Label Learning (TPAMI 2023)
• Deep Partial Multi-Label Learning with Graph Disambiguation (IJCAI 2023)
• Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labels (ICCV 2023)
• Partial Multi-Label Learning with Probabilistic Graphical Disambiguation (NeurIPS 2023)
• ProPML: Probability Partial Multi-label Learning (DSAA 2023)
• A Deep Model for Partial Multi-Label Image Classification with Curriculum Based Disambiguation (ML 2024)
• Partial Multi-View Multi-Label Classification via Semantic Invariance Learning and PrototypeModeling (ICML 2024)
• Reliable Representations Learning for Incomplete Multi-View Partial Multi-Label Classification (2024)
• PLMCL: Partial-Label Momentum Curriculum Learning for Multi-Label Image Classification (2024)
• Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels (2024)
• Free Performance Gain from Mixing Multiple Partially Labeled Samples in Multi-label Image Classification (2024)

Noisy Partial Label Learning

• PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning (TPAMI 2023)
• On the Robustness of Average Losses for Partial-Label Learning (TPAMI 2023)
• FREDIS: A Fusion Framework of Refinement and Disambiguation for Unreliable Partial Label Learning (ICML 2023)
• Unreliable Partial Label Learning with Recursive Separation (IJCAI 2023)
• ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning (NeurIPS 2023)
• IRNet: Iterative Refinement Network for Noisy Partial Label Learning (2023)
• Robust Representation Learning for Unreliable Partial Label Learning (2023)
• Pseudo-labelling meets Label Smoothing for Noisy Partial Label Learning (2024)

Semi-Supervised Partial Label Learning

• Semi-Supervised Partial Label Learning via Confidence-Rated Margin Maximization (NeurIPS 2020)
• Exploiting Unlabeled Data via Partial Label Assignment for Multi-Class Semi-Supervised Learning (AAAI 2021)
• Distributed Semisupervised Partial Label Learning Over Networks (AI 2022)
• Learning with Partial-Label and Unlabeled Data: A Uniform Treatment for Supervision Redundancy and Insufficiency (ICML 2024)
• FairMatch: Promoting Partial Label Learning by Unlabeled Samples (KDD 2024)

Multi-Instance Partial Label Learning

• Multi-Instance Partial-Label Learning: Towards Exploiting Dual Inexact Supervision (SCIS 2023)
• Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning (NeurIPS 2023)
• Exploiting Conjugate Label Information for Multi-Instance Partial-Label Learning (2024)
• On Characterizing and Mitigating Imbalances in Multi-Instance Partial Label Learning (2024)

Imblanced Partial Label Learning

• Towards Mitigating the Class-Imbalance Problem for Partial Label Learning (KDD 2018)
• A Partial Label Metric Learning Algorithm for Class Imbalanced Data (ACML 2021)
• SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning (NeurIPS 2022)
• Class-Imbalanced Complementary-Label Learning via Weighted Loss (NN 2023)
• Long-Tailed Partial Label Learning via Dynamic Rebalancing (ICLR 2023)
• Long-Tailed Partial Label Learning by Head Classifier and Tail Classifier Cooperation (AAAI 2024)
• Pseudo Labels Regularization for Imbalanced Partial-Label Learning (ICASSP 2024)

Out-of-distribution Partial Label Learning

• Out-of-distribution Partial Label Learning (2024)

Federated Partial Label Learning

• Federated Partial Label Learning with Local-Adaptive Augmentation and Regularization (AAAI 2024)

Partial Label Regression

• Partial-Label Regression (AAAI 2023)
• Partial-Label Learning with a Reject Option (2024)

Dimensionality Reduction

• Partial Label Dimensionality Reduction via Confidence-Based Dependence Maximization (KDD 2021)
• Disambiguation Enabled Linear Discriminant Analysis for Partial Label Dimensionality Reduction (TKDD 2022)
• Submodular Feature Selection for Partial Label Learning (KDD 2022)
• Dimensionality Reduction for Partial Label Learning: A Unified and Adaptive Approach (TKDE 2024)

Multi-Complementary Label Learning

• Learning with Multiple Complementary Labels (ICML 2020)
• Multi-Complementary and Unlabeled Learning for Arbitrary Losses and Models (PR 2022)

Multi-View Learning

• Deep Partial Multi-View Learning (TPAMI 2022)

Adversarial Training

• Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks (NeurIPS 2022)

Negative Learning

• NLNL: Negative Learning for Noisy Labels (ICCV 2019)

Incremental Learning

• Partial label learning with emerging new labels (ML 2022)
• Complementary Labels Learning with Augmented Classes （2022）
• An Unbiased Risk Estimator for Partial Label Learning with Augmented Classes (2024)

Online Learning

• Online Partial Label Learning (ECML-PKDD 2020)

Conformal Prediction

• Conformal Prediction with Partially Labeled Data (SCPPA 2023)

Few-Shot Learning

• Few-Shot Partial-Label Learning (IJCAI 2021)

Open-set Problem

• Partial-label Learning with Mixed Closed-set and Open-set Out-of-candidate Examples (KDD 2023)

Data Augmentation

• Partial Label Learning with Discrimination Augmentation (KDD 2022)
• Enhancing Label Sharing Efficiency in Complementary-Label Learning with Label Augmentation (2023)

Multi-Dimensional

• Learning From Multi-Dimensional Partial Labels (IJCAI 2020)

Domain Adaptation

• Partial Label Unsupervised Domain Adaptation with Class-Prototype Alignment (ICLR 2023)

Applications

Audio

• Semi-Supervised Audio Classification with Partially Labeled Data (2021)

Text

• Complementary Auxiliary Classifiers for Label-Conditional Text Generation (AAAI 2020)

Sequence

• Star Temporal Classification: Sequence Classification with Partially Labeled Data (2022)

Recognition

• Webly-Supervised Fine-Grained Recognition with Partial Label Learning (IJCAI 2022)
• Partial Label Learning with Focal Loss for Sea Ice Classification Based on Ice Charts (AEORS 2023)
• Partial Label Learning for Emotion Recognition from EEG (2023)
• A Confidence-based Partial Label Learning Model for Crowd-Annotated Named Entity Recognition (ACL 2023)

Object Localization

• Adversarial Complementary Learning for Weakly Supervised Object Localization (CVPR 2018)
• Learning to Detect Instance-level Salient Objects Using Complementary Image Labels (2021)

Map Reconstruction

• Deep Learning with Partially Labeled Data for Radio Map Reconstruction (2023)

Semi-supervised Learning

• Boosting Semi-Supervised Learning with Contrastive Complementary Labeling (NN 2023)
• Controller-Guided Partial Label Consistency Regularization with Unlabeled Data (2024)
• Semi-supervised Contrastive Learning Using Partial Label Information (2024)

Active Learning

• Exploiting counter-examples for active learning with partial labels (ML 2023)
• Active Learning with Partial Labels (2023)

Noisy Label Learning

• Learning from Noisy Labels with Complementary Loss Functions (AAAI 2021)
• Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 2024)
• Partial Label Supervision for Agnostic Generative Noisy Label Learning (2024)

Test-Time Adaptation

• Rethinking Precision of Pseudo Label: Test-Time Adaptation via Complementary Learning (2023)

Dataset

Tabular Dataset:

Notice: The following partial label learning data sets were collected and pre-processed by Prof. Min-Ling Zhang, with courtesy and proprietary to the authors of referred literatures on them. The pre-processed data sets can be used at your own risk and for academic purpose only. More information can be found in here.

Dataset for partial label learning:

FG-NET	Lost	MSRCv2	BirdSong	Soccer Player	Yahoo! News	Mirflickr

Dataset for partial multi-label learning:

Music_emotion	Music_style	Mirflickr	YeastBP	YeastCC	YeastMF

Data sets for multi-instance partial-label learning:

MNIST	FMNIST	Newsgroups	Birdsong	SIVAL	CRC-Row	CRC-SBN	CRC-KMeansSeg	CRC-SIFT

Image Dataset:

• CLImage: Human-Annotated Datasets for Complementary-Label Learning (2024)

Learderboard

To be continue.

Star History

Citing Advances in Partial/Complementary Label Learning

If you find this project useful for your research, please use the following BibTeX entry.

@misc{Wu2022advances,
  author={Dong-Dong Wu},
  title={Advances in Partial/Complementary Label Learning },
  howpublished={\url{wu-dd/Advances-in-Partial-and-Complementary-Label-Learning}},
  year={2022}
}

Acknowledgments