A survey of deep graph learning under distribution shifts: from graph out-of-distribution generalization to adaptation
Distribution shifts on graphs--the discrepancies in data distribution between training and
employing a graph machine learning model--are ubiquitous and often unavoidable in real …
employing a graph machine learning model--are ubiquitous and often unavoidable in real …
[PDF][PDF] CONC: complex-noise-resistant open-set node classification with adaptive noise detection
As a popular task in graph learning, node classification seeks to assign labels to nodes,
taking into account both their features and connections. However, an important challenge for …
taking into account both their features and connections. However, an important challenge for …
RTG-GNN: A novel rock topology-guided approach for permeability prediction using graph neural networks
X Zhao, Y Zhong, P Li - Geoenergy Science and Engineering, 2024 - Elsevier
Digital core permeability is a crucial factor in rock engineering, reservoir simulation, and
underground applications, serving as the foundation for evaluating fluid flow underground …
underground applications, serving as the foundation for evaluating fluid flow underground …
Conditional Shift-Robust Conformal Prediction for Graph Neural Network
S Akansha - arxiv preprint arxiv:2405.11968, 2024 - arxiv.org
Graph Neural Networks (GNNs) have emerged as potent tools for predicting outcomes in
graph-structured data. Despite their efficacy, a significant drawback of GNNs lies in their …
graph-structured data. Despite their efficacy, a significant drawback of GNNs lies in their …
Grasp the Key Takeaways from Source Domain for Few Shot Graph Domain Adaptation
X Lv, J Chen, M Li, Y Sui, Z Liu, B Liao - THE WEB CONFERENCE 2025 - openreview.net
Graph Neural Networks (GNNs) have achieved remarkable success in node classification
tasks on individual graphs. However, existing GNNs trained within a specific domain (aka …
tasks on individual graphs. However, existing GNNs trained within a specific domain (aka …
Filling in the GAP: Achieving Robust and Adaptive GNNs through Post-Processing
D Lee, M Kong, J Yoo - openreview.net
Graph neural networks (GNNs) have shown significant success in modeling graph-
structured data. However, their performance often deteriorates when faced with a change in …
structured data. However, their performance often deteriorates when faced with a change in …
Conditional Shift-Robust Conformal Prediction for Graph Neural Network
A Singh - Available at SSRN 4934720 - papers.ssrn.com
This article presents the first systematic study of the impact of distributional shift on
uncertainty in Graph Neural Network (GNN) predictions. We introduce Conditional Shift …
uncertainty in Graph Neural Network (GNN) predictions. We introduce Conditional Shift …