# Collaborative Graph Walk for Semi-supervised Multi-Label Node Classification

arXiv: https://arxiv.org/abs/1910.09706 · HTML: https://mlsanity.com/paper/1910.09706/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Oct 2019.

## Built on by (most cited first, 7 of 7)

- [Multi-label Node Classification On Graph-Structured Data](https://mlsanity.com/paper/2304.10398/) (2023)
- [Handling Feature Heterogeneity with Learnable Graph Patches](https://mlsanity.com/paper/2606.17667/) (2026)
- [AGALE: A Graph-Aware Continual Learning Evaluation Framework](https://mlsanity.com/paper/2406.01229/) (2024)
- [Multi-Label Node Classification with Label Influence Propagation](https://mlsanity.com/paper/2607.00671/) (2026)
- [A data-centric approach for assessing progress of Graph Neural Networks](https://mlsanity.com/paper/2406.12439/) (2024)
- [Extending Graph Condensation to Multi-Label Datasets: A Benchmark Study](https://mlsanity.com/paper/2412.17961/) (2024)
- [MLGIB: Multi-Label Graph Information Bottleneck for Expressive and Robust Message Passing](https://mlsanity.com/paper/2605.13126/) (2026)

## Abstract (arXiv)

In this work, we study semi-supervised multi-label node classification problem in attributed graphs. Classic solutions to multi-label node classification follow two steps, first learn node embedding and then build a node classifier on the learned embedding. To improve the discriminating power of the node embedding, we propose a novel collaborative graph walk, named Multi-Label-Graph-Walk, to finely tune node representations with the available label assignments in attributed graphs via reinforcement learning. The proposed method formulates the multi-label node classification task as simultaneous graph walks conducted by multiple label-specific agents. Furthermore, policies of the label-wise graph walks are learned in a cooperative way to capture first the predictive relation between node labels and structural attributes of graphs; and second, the correlation among the multiple label-specific classification tasks. A comprehensive experimental study demonstrates that the proposed method can achieve significantly better multi-label classification performance than the state-of-the-art approaches and conduct more efficient graph exploration.