Uncertainty-Aware Robust Learning on Noisy Graphs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Shuyi, Ding, Kaize, Zhu, Shixiang
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912273064263680
author Chen, Shuyi
Ding, Kaize
Zhu, Shixiang
author_facet Chen, Shuyi
Ding, Kaize
Zhu, Shixiang
contents Graph neural networks (GNNs) have excelled in various graph learning tasks, particularly node classification. However, their performance is often hampered by noisy measurements in real-world graphs, which can corrupt critical patterns in the data. To address this, we propose a novel uncertainty-aware graph learning framework inspired by distributionally robust optimization. Specifically, we use a graph neural network-based encoder to embed the node features and find the optimal node embeddings by minimizing the worst-case risk through a minimax formulation. Such an uncertainty-aware learning process leads to improved node representations and a more robust graph predictive model that effectively mitigates the impact of uncertainty arising from data noise. Our experimental results demonstrate superior predictive performance over baselines across noisy scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2306_08210
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Uncertainty-Aware Robust Learning on Noisy Graphs
Chen, Shuyi
Ding, Kaize
Zhu, Shixiang
Machine Learning
Graph neural networks (GNNs) have excelled in various graph learning tasks, particularly node classification. However, their performance is often hampered by noisy measurements in real-world graphs, which can corrupt critical patterns in the data. To address this, we propose a novel uncertainty-aware graph learning framework inspired by distributionally robust optimization. Specifically, we use a graph neural network-based encoder to embed the node features and find the optimal node embeddings by minimizing the worst-case risk through a minimax formulation. Such an uncertainty-aware learning process leads to improved node representations and a more robust graph predictive model that effectively mitigates the impact of uncertainty arising from data noise. Our experimental results demonstrate superior predictive performance over baselines across noisy scenarios.
title Uncertainty-Aware Robust Learning on Noisy Graphs
topic Machine Learning
url https://arxiv.org/abs/2306.08210