Distributionally Robust Semi-Supervised Learning Over Graphs

by   Alireza Sadeghi, et al.
University of Minnesota

Semi-supervised learning (SSL) over graph-structured data emerges in many network science applications. To efficiently manage learning over graphs, variants of graph neural networks (GNNs) have been developed recently. By succinctly encoding local graph structures and features of nodes, state-of-the-art GNNs can scale linearly with the size of graph. Despite their success in practice, most of existing methods are unable to handle graphs with uncertain nodal attributes. Specifically whenever mismatches between training and testing data distribution exists, these models fail in practice. Challenges also arise due to distributional uncertainties associated with data acquired by noisy measurements. In this context, a distributionally robust learning framework is developed, where the objective is to train models that exhibit quantifiable robustness against perturbations. The data distribution is considered unknown, but lies within a Wasserstein ball centered around empirical data distribution. A robust model is obtained by minimizing the worst expected loss over this ball. However, solving the emerging functional optimization problem is challenging, if not impossible. Advocating a strong duality condition, we develop a principled method that renders the problem tractable and efficiently solvable. Experiments assess the performance of the proposed method.


page 1

page 2

page 3

page 4


Improving the Training of Graph Neural Networks with Consistency Regularization

Graph neural networks (GNNs) have achieved notable success in the semi-s...

GraFN: Semi-Supervised Node Classification on Graph with Few Labels via Non-Parametric Distribution Assignment

Despite the success of Graph Neural Networks (GNNs) on various applicati...

On Size Generalization in Graph Neural Networks

Graph neural networks (GNNs) can process graphs of different sizes but t...

Graph Partition Neural Networks for Semi-Supervised Classification

We present graph partition neural networks (GPNN), an extension of graph...

Distributionally Robust Multi-Output Regression Ranking

Despite their empirical success, most existing listwiselearning-to-rank ...

Certifiable Distributional Robustness with Principled Adversarial Training

Neural networks are vulnerable to adversarial examples and researchers h...

Principled Learning Method for Wasserstein Distributionally Robust Optimization with Local Perturbations

Wasserstein distributionally robust optimization (WDRO) attempts to lear...

Please sign up or login with your details

Forgot password? Click here to reset