REGE: A Method for Incorporating Uncertainty in Graph Embeddings

TL;DR

REGE introduces a novel approach to incorporate data and model uncertainty into graph embeddings, improving robustness against adversarial attacks by using curriculum and conformal learning techniques.

Contribution

The paper presents REGE, a new method that measures and integrates uncertainty into graph embeddings, enhancing their resilience to adversarial attacks.

Findings

REGE improves accuracy by 1.5% under adversarial attacks.

REGE effectively incorporates data and model uncertainty.

The approach outperforms state-of-the-art methods.

Abstract

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.