Learning-with-Partial-Labels/Complementary-Labels

A curated list of most recent papers & codes in Learning with Partial/Complementary Labels

Competition

To be continued...

Content

To be continued...

Benchmarks & Leaderboard

Real-World partial-label benchmarks:

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	Website	Paper
FG-NET data	[Download link]	[Paper]
Lost data	[Download link]	[Paper]
MSRCv2 data	[Download link]	[Paper]
BirdSong data	[Download link]	[Paper]
Soccer Player data	[Download link]	[Paper]
Yahoo! News	[Download link]	[Paper]
Mirflicker data	[Download link]	[Paper]

Leaderboard, To be continued...

Papers & Code in 2022

TPAMI'22

• [SEU PALM Lab] Adaptive graph guided disambiguation for partial label learning. [Paper][Supplement][Code]

---

TKDD'22

• [SEU PALM Lab] Disambiguation enabled linear discriminant analysis for partial label dimensionality reduction. [Paper][Code]

---

IJCAI'22

• [SEU PALM Lab] Ambiguity-Induced Contrastive Learning for Instance-Dependent Partial Label Learning.
• Boosting Multi-Label Image Classification with Complementary Parallel Self-Distillation. [Paper]

---

ICLR'22

• PiCO: Contrastive Label Disambiguation for Partial-Label Learning. [Paper][Code]
• Exploiting Class Activation Value for Partial-Label Learning. [Paper][Code]

---

ICML'22

• [SEU PALM Lab] Revisiting consistency regularization for deep partial label learning. [Paper] [Code]
• Partial Label Learning via Label Influence Function.

---

KDD'22

• [SEU PALM Lab] Submodular feature selection for partial label learning. [Paper] [Code]
• [SEU PALM Lab] Partial label learning with discriminative augmentation.
• Partial-Label Learning with Semantic Label Representations.

---

ArXiv'22

• [SEU PALM Lab] On the Robustness of Average Losses for Partial-Label Learning. [Paper]
• Learning with Proper Partial Labels. [Paper]
• [SEU PALM Lab]Progressive Purification for Instance-Dependent Partial Label Learning.
• [SEU PALM Lab]Decompositional Generation Process for Instance-Dependent Partial Label Learning.

---

Papers & Code in 2021

TPAMI'21

• [SEU PALM Lab] Partial multi-label learning via credible label elicitation. [Paper][Code]
• Partial Multi-Label Learning with Noisy Label Identification. [Paper]

---

TNNLS'21

• Top-k Partial Label Machine. [Paper]
• Learning From a Complementary-Label Source Domain: Theory and Algorithms. [Paper]

---

TMM'21

• Generalized Large Margin kNN for Partial Label Learning. [Paper]
• Global-Local Label Correlation for Partial Multi-Label Learning. [Paper]

---

NeurIPS'21

• [SEU PALM Lab] Instance-Dependent Partial Label Learning. (oral) [Paper][Appendix][Code]
• Understanding Partial Multi-label Learning via Mutual Information. [Paper]

---

KDD'21

• [SEU PALM Lab] Partial label dimensionality reduction via confidence-based dependence maximization. [Paper][Code]
• Partial Multi-Label Learning with Meta Disambiguation. [Paper]

---

ICML'21

• [SEU PALM Lab] Discriminative complementary-label learning with weighted loss. [Paper][Code]
• Leveraged Weighted Loss for Partial Label Learning. [Paper][Supplement]

---

IJCAI'21

• [SEU PALM Lab] Learning from complementary labels via partial-output consistency regularization. [Paper][Code]
• Few-Shot Partial-Label Learning. [Paper]

---

AAAI'21

• [SEU PALM Lab] Exploiting unlabeled data via partial label assignment for multi-class semi-supervised learning. [Paper][Code]
• Adversarial Partial Multi-Label Learning with Label Disambiguation. [Paper]
• [SEU PALM Lab] Learning from Noisy Labels with Complementary Loss Functions. [Paper]

---

CVPR'21

• Joint Negative and Positive Learning for Noisy Labels. [Paper]

Papers & Code in 2020

NeruIPS'20

• [SEU PALM Lab] Semi-supervised partial label learning via confidence-rated margin maximization. [Paper][Code]
• [SEU PALM Lab] Provably Consistent Partial-Label Learning. [Paper][Code]

---

KDD'20

• [SEU PALM Lab] Feature-induced manifold disambiguation for multi-view partial multi-label learning. [Paper][Code]

---

ICML'20

• [SEU PALM Lab] Progressive Identification of True Labels for Partial-Label Learning. [Paper][Code]
• Bridging Ordinary-Label Learning and Complementary-Label Learning. [Paper]
• Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels. [Paper]
• Learning with Multiple Complementary Labels. [Paper]

---

IJCAI'20

• Partial Multi-Label Learning via Multi-Subspace Representation. [Paper]

---

AAAI'20

• [SEU PALM Lab] Multi-view partial multi-label learning with graph-based disambiguation. [Paper][Code]
• Partial Label Learning with Batch Label Correction. [Paper]
• Generative-Discriminative Complementary Learning. [Paper]
• Complementary Auxiliary Classifiers for Label-Conditional Text Generation. [Paper]

---

ECML'20

• Network Cooperation with Progressive Disambiguation for Partial Label Learning. [Paper]

Papers & Code in 2019

ICML'19

• Complementary-Label Learning for Arbitrary Losses and Models. [Paper]

---

ICCV'19

• NLNL: Negative Learning for Noisy Labels. [Paper]

Papers & Code in 2018

ECCV'18

• Learning with Biased Complementary Labels. [Paper]

---

CVPR'18

• Adversarial Complementary Learning for Weakly Supervised Object Localization. [Paper]

Papers & Code in 2017

NIPS'17

• Learning from Complementary Labels. [Paper]