# REGE: A Method for Incorporating Uncertainty in Graph Embeddings

arXiv: https://arxiv.org/abs/2412.05735 · HTML: https://mlsanity.com/paper/2412.05735/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 65 references that are in the map.
- First posted on arXiv 7 Dec 2024.

## Builds on (most cited first, 12 of 12)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification](https://mlsanity.com/paper/2107.07511/) (2021)
- [Word Representations via Gaussian Embedding](https://mlsanity.com/paper/1412.6623/) (2014)
- [A Review on Graph Neural Network Methods in Financial Applications](https://mlsanity.com/paper/2111.15367/) (2021)
- [Uncertainty in Graph Neural Networks: A Survey](https://mlsanity.com/paper/2403.07185/) (2024)
- [Towards Robust Graph Contrastive Learning](https://mlsanity.com/paper/2102.13085/) (2021)
- [DefenseVGAE: Defending against Adversarial Attacks on Graph Data via a Variational Graph Autoencoder](https://mlsanity.com/paper/2006.08900/) (2020)
- [Adversarial Defense Framework for Graph Neural Network](https://mlsanity.com/paper/1905.03679/) (2019)
- [Network reconstruction via the minimum description length principle](https://mlsanity.com/paper/2405.01015/) (2024)
- [Enhancing the Resilience of Graph Neural Networks to Topological Perturbations in Sparse Graphs](https://mlsanity.com/paper/2406.03097/) (2024)
- [Talos: A More Effective and Efficient Adversarial Defense for GNN Models Based on the Global Homophily of Graphs](https://mlsanity.com/paper/2406.03833/) (2024)

## Abstract (arXiv)

Machine learning models for graphs in real-world applications are prone to two primary types of uncertainty: (1) those that arise from incomplete and noisy data and (2) those that arise from uncertainty of the model in its output. These sources of uncertainty are not mutually exclusive. Additionally, models are susceptible to targeted adversarial attacks, which exacerbate both of these uncertainties. In this work, we introduce Radius Enhanced Graph Embeddings (REGE), an approach that measures and incorporates uncertainty in data to produce graph embeddings with radius values that represent the uncertainty of the model's output. REGE employs curriculum learning to incorporate data uncertainty and conformal learning to address the uncertainty in the model's output. In our experiments, we show that REGE's graph embeddings perform better under adversarial attacks by an average of 1.5% (accuracy) against state-of-the-art methods.