REGE: A Method for Incorporating Uncertainty in Graph Embeddings
This addresses uncertainty issues in graph machine learning for real-world applications, but it is incremental as it builds on existing methods like curriculum and conformal learning.
The paper tackled the problem of uncertainty in graph embeddings from incomplete/noisy data and model output uncertainty, introducing REGE to incorporate uncertainty and showing it improves accuracy by an average of 1.5% under adversarial attacks compared to state-of-the-art methods.
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.