# Deep Partial Multi-Label Learning with Graph Disambiguation

arXiv: https://arxiv.org/abs/2305.05882 · HTML: https://mlsanity.com/paper/2305.05882/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 49 references that are in the map.
- First posted on arXiv 10 May 2023.

## Builds on (most cited first, 21 of 21)

- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Robust Loss Functions under Label Noise for Deep Neural Networks](https://mlsanity.com/paper/1712.09482/) (2017)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [DeepInf: Social Influence Prediction with Deep Learning](https://mlsanity.com/paper/1807.05560/) (2018)
- [Learning a Deep ConvNet for Multi-label Classification with Partial Labels](https://mlsanity.com/paper/1902.09720/) (2019)
- [Learning From Noisy Large-Scale Datasets With Minimal Supervision](https://mlsanity.com/paper/1701.01619/) (2017)
- [The Emerging Trends of Multi-Label Learning](https://mlsanity.com/paper/2011.11197/) (2020)
- [Multi-Label Zero-Shot Learning with Structured Knowledge Graphs](https://mlsanity.com/paper/1711.06526/) (2017)
- [Large-scale Multi-label Learning with Missing Labels](https://mlsanity.com/paper/1307.5101/) (2013)
- [Learning with Multiple Complementary Labels](https://mlsanity.com/paper/1912.12927/) (2019)
- [Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations](https://mlsanity.com/paper/1611.05113/) (2016)
- [Multi-Label Learning with Global and Local Label Correlation](https://mlsanity.com/paper/1704.01415/) (2017)
- [Multi-label Co-regularization for Semi-supervised Facial Action Unit Recognition](https://mlsanity.com/paper/1910.11012/) (2019)
- [Disentangled Variational Autoencoder based Multi-Label Classification with Covariance-Aware Multivariate Probit Model](https://mlsanity.com/paper/2007.06126/) (2020)
- [One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancement](https://mlsanity.com/paper/2206.00517/) (2022)
- [Multi-Label Sentiment Analysis on 100 Languages with Dynamic Weighting for Label Imbalance](https://mlsanity.com/paper/2008.11573/) (2020)
- [Instance-Aware Hashing for Multi-Label Image Retrieval](https://mlsanity.com/paper/1603.03234/) (2016)
- [A Survey on Extreme Multi-label Learning](https://mlsanity.com/paper/2210.03968/) (2022)
- [Adversarial Partial Multi-Label Learning](https://mlsanity.com/paper/1909.06717/) (2019)
- [Recovering Accurate Labeling Information from Partially Valid Data for Effective Multi-Label Learning](https://mlsanity.com/paper/2006.11488/) (2020)

## Built on by (most cited first, 5 of 5)

- [TAI++: Text as Image for Multi-Label Image Classification by Co-Learning Transferable Prompt](https://mlsanity.com/paper/2405.06926/) (2024)
- [Pre-Trained Vision-Language Models as Partial Annotators](https://mlsanity.com/paper/2406.18550/) (2024)
- [Revisiting Sparsity Constraint Under High-Rank Property in Partial Multi-Label Learning](https://mlsanity.com/paper/2505.20938/) (2025)
- [Bridging Weakly-Supervised Learning and VLM Distillation: Noisy Partial Label Learning for Efficient Downstream Adaptation](https://mlsanity.com/paper/2506.03229/) (2025)
- [Calibrated Disambiguation for Partial Multi-label Learning](https://mlsanity.com/paper/2610.17635/) (2026)

## Abstract (arXiv)

In partial multi-label learning (PML), each data example is equipped with a candidate label set, which consists of multiple ground-truth labels and other false-positive labels. Recently, graph-based methods, which demonstrate a good ability to estimate accurate confidence scores from candidate labels, have been prevalent to deal with PML problems. However, we observe that existing graph-based PML methods typically adopt linear multi-label classifiers and thus fail to achieve superior performance. In this work, we attempt to remove several obstacles for extending them to deep models and propose a novel deep Partial multi-Label model with grAph-disambIguatioN (PLAIN). Specifically, we introduce the instance-level and label-level similarities to recover label confidences as well as exploit label dependencies. At each training epoch, labels are propagated on the instance and label graphs to produce relatively accurate pseudo-labels; then, we train the deep model to fit the numerical labels. Moreover, we provide a careful analysis of the risk functions to guarantee the robustness of the proposed model. Extensive experiments on various synthetic datasets and three real-world PML datasets demonstrate that PLAIN achieves significantly superior results to state-of-the-art methods.