# Positive-Unlabeled Node Classification with Structure-aware Graph Learning

arXiv: https://arxiv.org/abs/2310.13538 · HTML: https://mlsanity.com/paper/2310.13538/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 19 references that are in the map.
- First posted on arXiv 20 Oct 2023.

## Builds on (most cited first, 6 of 6)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Dist-PU: Positive-Unlabeled Learning from a Label Distribution Perspective](https://mlsanity.com/paper/2212.02801/) (2022)
- [Classification from Positive, Unlabeled and Biased Negative Data](https://mlsanity.com/paper/1810.00846/) (2018)
- [Hybrid Spatio-Temporal Graph Convolutional Network: Improving Traffic Prediction with Navigation Data](https://mlsanity.com/paper/2006.12715/) (2020)
- [Learning Graph Neural Networks with Positive and Unlabeled Nodes](https://mlsanity.com/paper/2103.04683/) (2021)

## Built on by (most cited first, 4 of 4)

- [Accurate Link Prediction for Edge-Incomplete Graphs via PU Learning](https://mlsanity.com/paper/2405.11911/) (2024)
- [Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning](https://mlsanity.com/paper/2405.19919/) (2024)
- [Novel Node Category Detection Under Subpopulation Shift](https://mlsanity.com/paper/2404.01216/) (2024)
- [ESA: Example Sieve Approach for Multi-Positive and Unlabeled Learning](https://mlsanity.com/paper/2412.02240/) (2024)

## Abstract (arXiv)

Node classification on graphs is an important research problem with many applications. Real-world graph data sets may not be balanced and accurate as assumed by most existing works. A challenging setting is positive-unlabeled (PU) node classification, where labeled nodes are restricted to positive nodes. It has diverse applications, e.g., pandemic prediction or network anomaly detection. Existing works on PU node classification overlook information in the graph structure, which can be critical. In this paper, we propose to better utilize graph structure for PU node classification. We first propose a distance-aware PU loss that uses homophily in graphs to introduce more accurate supervision. We also propose a regularizer to align the model with graph structure. Theoretical analysis shows that minimizing the proposed loss also leads to minimizing the expected loss with both positive and negative labels. Extensive empirical evaluation on diverse graph data sets demonstrates its superior performance over existing state-of-the-art methods.