A Simple Data Augmentation for Graph Classification: A Perspective of Equivariance and Invariance
In graph classification, the out-of-distribution (OOD) issue is attracting great attention. To
address this issue, a prevailing idea is to learn stable features, on the assumption that they …
address this issue, a prevailing idea is to learn stable features, on the assumption that they …
A Unified Invariant Learning Framework for Graph Classification
Invariant learning demonstrates substantial potential for enhancing the generalization of
graph neural networks (GNNs) with out-of-distribution (OOD) data. It aims to recognize …
graph neural networks (GNNs) with out-of-distribution (OOD) data. It aims to recognize …
Causal Interventional Prediction System for Robust and Explainable Effect Forecasting
Although the widespread use of AI systems in today's world is growing, many current AI
systems are found vulnerable due to hidden bias and missing information, especially in the …
systems are found vulnerable due to hidden bias and missing information, especially in the …
Graph Disentangle Causal Model: Enhancing Causal Inference in Networked Observational Data
Estimating individual treatment effects (ITE) from observational data is a critical task across
various domains. However, many existing works on ITE estimation overlook the influence of …
various domains. However, many existing works on ITE estimation overlook the influence of …
Empowering Federated Graph Rationale Learning with Latent Environments
The success of Graph Neural Networks (GNNs) in graph classification has heightened
interest in explainable GNNs, particularly through graph rationalization. This method aims to …
interest in explainable GNNs, particularly through graph rationalization. This method aims to …
Exploring Information Flow Through Graph Causal Networks for Multivariate Time Series Anomaly Detection
B Wang - 2024 - search.proquest.com
Multivariate time series is a common data format within complex systems. Its lack of patterns
and difficulty in reconstruction make it challenging for representation learning. To address …
and difficulty in reconstruction make it challenging for representation learning. To address …