# Neural Message Passing for Multi-Label Classification

arXiv: https://arxiv.org/abs/1904.08049 · HTML: https://mlsanity.com/paper/1904.08049/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2019.

## Built on by (most cited first, 20 of 20)

- [Pathways: Asynchronous Distributed Dataflow for ML](https://mlsanity.com/paper/2203.12533/) (2022)
- [A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective](https://mlsanity.com/paper/2209.13232/) (2022)
- [A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges](https://mlsanity.com/paper/2210.12089/) (2022)
- [PatchCT: Aligning Patch Set and Label Set with Conditional Transport for Multi-Label Image Classification](https://mlsanity.com/paper/2307.09066/) (2023)
- [Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification](https://mlsanity.com/paper/2112.00976/) (2021)
- [Evaluating Multi-label Classifiers with Noisy Labels](https://mlsanity.com/paper/2102.08427/) (2021)
- [Multi-label Node Classification On Graph-Structured Data](https://mlsanity.com/paper/2304.10398/) (2023)
- [HOT-VAE: Learning High-Order Label Correlation for Multi-Label Classification via Attention-Based Variational Autoencoders](https://mlsanity.com/paper/2103.06375/) (2021)
- [MASK-CNN-Transformer For Real-Time Multi-Label Weather Recognition](https://mlsanity.com/paper/2304.14857/) (2023)
- [Materials Representation and Transfer Learning for Multi-Property Prediction](https://mlsanity.com/paper/2106.02225/) (2021)
- [Improve Learning from Crowds via Generative Augmentation](https://mlsanity.com/paper/2107.10449/) (2021)
- [A Comparative Study on Robust Graph Neural Networks to Structural Noises](https://mlsanity.com/paper/2112.06070/) (2021)
- [Multi-relation Message Passing for Multi-label Text Classification](https://mlsanity.com/paper/2202.04844/) (2022)
- [Zero Training Overhead Portfolios for Learning to Solve Combinatorial Problems](https://mlsanity.com/paper/2102.03002/) (2021)
- [Improving Multi-Label Contrastive Learning by Leveraging Label Distribution](https://mlsanity.com/paper/2501.19145/) (2025)
- [Dynamic Graph Induced Contour-aware Heat Conduction Network for Event-based Object Detection](https://mlsanity.com/paper/2505.12908/) (2025)
- [Interval Type-2 Fuzzy Neural Networks for Multi-Label Classification](https://mlsanity.com/paper/2302.10430/) (2023)
- [Examining the Rat in the Tunnel: Interpretable Multi-Label Classification of Tor-based Malware](https://mlsanity.com/paper/2409.16639/) (2024)
- [Estimating Conditional Covariance between labels for Multilabel Data](https://mlsanity.com/paper/2508.18951/) (2025)
- [HyperLabel: Multi-Label Classification via Hypergraph-Based Label Correlation Modeling](https://mlsanity.com/paper/2609.32276/) (2026)

## Abstract (arXiv)

Multi-label classification (MLC) is the task of assigning a set of target labels for a given sample. Modeling the combinatorial label interactions in MLC has been a long-haul challenge. We propose Label Message Passing (LaMP) Neural Networks to efficiently model the joint prediction of multiple labels. LaMP treats labels as nodes on a label-interaction graph and computes the hidden representation of each label node conditioned on the input using attention-based neural message passing. Attention enables LaMP to assign different importance to neighbor nodes per label, learning how labels interact (implicitly). The proposed models are simple, accurate, interpretable, structure-agnostic, and applicable for predicting dense labels since LaMP is incredibly parallelizable. We validate the benefits of LaMP on seven real-world MLC datasets, covering a broad spectrum of input/output types and outperforming the state-of-the-art results. Notably, LaMP enables intuitive interpretation of how classifying each label depends on the elements of a sample and at the same time rely on its interaction with other labels. We provide our code and datasets at https://github.com/QData/LaMP