Does invariant graph learning via environment augmentation learn invariance?

Y Chen, Y Bian, K Zhou, B Xie… - Advances in Neural …, 2024 - proceedings.neurips.cc
Invariant graph representation learning aims to learn the invariance among data from
different environments for out-of-distribution generalization on graphs. As the graph …

Investigating out-of-distribution generalization of GNNs: An architecture perspective

K Guo, H Wen, W Jin, Y Guo, J Tang… - Proceedings of the 30th …, 2024 - dl.acm.org
Graph neural networks (GNNs) have exhibited remarkable performance under the
assumption that test data comes from the same distribution of training data. However, in real …

Graph out-of-distribution generalization via causal intervention

Q Wu, F Nie, C Yang, T Bao, J Yan - Proceedings of the ACM on Web …, 2024 - dl.acm.org
Out-of-distribution (OOD) generalization has gained increasing attentions for learning on
graphs, as graph neural networks (GNNs) often exhibit performance degradation with …

Graph condensation for open-world graph learning

X Gao, T Chen, W Zhang, Y Li, X Sun… - Proceedings of the 30th …, 2024 - dl.acm.org
The burgeoning volume of graph data presents significant computational challenges in
training graph neural networks (GNNs), critically impeding their efficiency in various …

When Graph Neural Network Meets Causality: Opportunities, Methodologies and An Outlook

W Jiang, H Liu, H Xiong - arXiv preprint arXiv:2312.12477, 2023 - arxiv.org
Graph Neural Networks (GNNs) have emerged as powerful representation learning tools for
capturing complex dependencies within diverse graph-structured data. Despite their …

Identifying Semantic Component for Robust Molecular Property Prediction

Z Li, Z Xu, R Cai, Z Yang, Y Yan, Z Hao, G Chen… - arXiv preprint arXiv …, 2023 - arxiv.org
Although graph neural networks have achieved great success in the task of molecular
property prediction in recent years, their generalization ability under out-of-distribution …

Improving out-of-distribution generalization in graphs via hierarchical semantic environments

Y Piao, S Lee, Y Lu, S Kim - Proceedings of the IEEE/CVF …, 2024 - openaccess.thecvf.com
Abstract Out-of-distribution (OOD) generalization in the graph domain is challenging due to
complex distribution shifts and a lack of environmental contexts. Recent methods attempt to …

A survey of out‐of‐distribution generalization for graph machine learning from a causal view

J Ma - AI Magazine, 2024 - Wiley Online Library
Graph machine learning (GML) has been successfully applied across a wide range of tasks.
Nonetheless, GML faces significant challenges in generalizing over out‐of‐distribution …

Unleashing the Power of Knowledge Graph for Recommendation via Invariant Learning

S Wang, Y Sui, C Wang, H Xiong - Proceedings of the ACM on Web …, 2024 - dl.acm.org
Knowledge graph (KG) demonstrates substantial potential for enhancing the performance of
recommender systems. Due to its rich semantic content and associations among interactive …

Wasserstein distance regularized graph neural networks

Y Shi, L Zheng, P Quan, L Niu - Information Sciences, 2024 - Elsevier
Distribution shift widely exists in graph representation learning and often reduces model
performance. This work investigates how to improve the performance of a graph neural …