# Robust Representation Learning for Unreliable Partial Label Learning

arXiv: https://arxiv.org/abs/2308.16718 · HTML: https://mlsanity.com/paper/2308.16718/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 71 references that are in the map.
- First posted on arXiv 31 Aug 2023.

## Builds on (most cited first, 23 of 23)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [Progressive Identification of True Labels for Partial-Label Learning](https://mlsanity.com/paper/2002.08053/) (2020)
- [Provably Consistent Partial-Label Learning](https://mlsanity.com/paper/2007.08929/) (2020)
- [Leveraged Weighted Loss for Partial Label Learning](https://mlsanity.com/paper/2106.05731/) (2021)
- [Instance-Dependent Partial Label Learning](https://mlsanity.com/paper/2110.12911/) (2021)
- [Partial Label Learning with Self-Guided Retraining](https://mlsanity.com/paper/1902.03045/) (2019)
- [SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning](https://mlsanity.com/paper/2209.10365/) (2022)
- [Learning from Ambiguously Labeled Face Images](https://mlsanity.com/paper/1702.04455/) (2017)
- [Long-Tailed Partial Label Learning via Dynamic Rebalancing](https://mlsanity.com/paper/2302.05080/) (2023)
- [A Regularization Approach for Instance-Based Superset Label Learning](https://mlsanity.com/paper/1904.02832/) (2019)
- [On the Robustness of Average Losses for Partial-Label Learning](https://mlsanity.com/paper/2106.06152/) (2021)
- [A Self-paced Regularization Framework for Partial-Label Learning](https://mlsanity.com/paper/1804.07759/) (2018)
- [Multi-Level Generative Models for Partial Label Learning with Non-random Label Noise](https://mlsanity.com/paper/2005.05407/) (2020)
- [Partial-Label Regression](https://mlsanity.com/paper/2306.08968/) (2023)

## Built on by (most cited first, 2 of 2)

- [Pre-Trained Vision-Language Models as Partial Annotators](https://mlsanity.com/paper/2406.18550/) (2024)
- [Bridging Weakly-Supervised Learning and VLM Distillation: Noisy Partial Label Learning for Efficient Downstream Adaptation](https://mlsanity.com/paper/2506.03229/) (2025)

## Abstract (arXiv)

Partial Label Learning (PLL) is a type of weakly supervised learning where each training instance is assigned a set of candidate labels, but only one label is the ground-truth. However, this idealistic assumption may not always hold due to potential annotation inaccuracies, meaning the ground-truth may not be present in the candidate label set. This is known as Unreliable Partial Label Learning (UPLL) that introduces an additional complexity due to the inherent unreliability and ambiguity of partial labels, often resulting in a sub-optimal performance with existing methods. To address this challenge, we propose the Unreliability-Robust Representation Learning framework (URRL) that leverages unreliability-robust contrastive learning to help the model fortify against unreliable partial labels effectively. Concurrently, we propose a dual strategy that combines KNN-based candidate label set correction and consistency-regularization-based label disambiguation to refine label quality and enhance the ability of representation learning within the URRL framework. Extensive experiments demonstrate that the proposed method outperforms state-of-the-art PLL methods on various datasets with diverse degrees of unreliability and ambiguity. Furthermore, we provide a theoretical analysis of our approach from the perspective of the expectation maximization (EM) algorithm. Upon acceptance, we pledge to make the code publicly accessible.