Related papers: Generative Risk Minimization for Out-of-Distributi…

Graph neural networks have shown remarkable success in exploiting the spatial and temporal patterns on dynamic graphs. However, existing GNNs exhibit poor generalization ability under distribution shifts, which is inevitable in dynamic…

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-world scenarios. These shifts may severely deteriorate…

Despite recent success in using the invariance principle for out-of-distribution (OOD) generalization on Euclidean data (e.g., images), studies on graph data are still limited. Different from images, the complex nature of graphs poses…

Out-of-distribution (OOD) detection in graphs is critical for ensuring model robustness in open-world and safety-sensitive applications. Existing graph OOD detection approaches typically train an in-distribution (ID) classifier on ID data…

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-world scenarios, this assumption may not always be valid.…

Graph-level representation learning is important in a wide range of applications. Existing graph-level models are generally built on i.i.d. assumption for both training and testing graphs. However, in an open world, models can encounter…

Out-of-distribution (OOD) generalization has emerged as a significant challenge in graph recommender systems. Traditional graph neural network algorithms often fail because they learn spurious environmental correlations instead of stable…

Out-of-distribution (OOD) detection is critical for ensuring the safety and reliability of machine learning systems, particularly in dynamic and open-world environments. In the vision and text domains, zero-shot OOD detection - which…

This paper studies a novel problem of out-of-distribution graph models merging, which aims to construct a generalized model from multiple graph models pre-trained on different domains with distribution discrepancy. This problem is…

Existing methods for graph out-of-distribution (OOD) detection typically depend on training graph neural network (GNN) classifiers using a substantial amount of labeled in-distribution (ID) data. However, acquiring high-quality labeled…

Graph Out-of-Distribution (OOD) classification often suffers from sharp performance drops, particularly under category imbalance and structural noise. This work tackles two pressing challenges in this context: (1) the underperformance of…

Graph Transformers (GTs) have demonstrated great effectiveness across various graph analytical tasks. However, the existing GTs focus on training and testing graph data originated from the same distribution, but fail to generalize under…

Spatiotemporal prediction over graphs (STPG) is challenging, because real-world data suffers from the Out-of-Distribution (OOD) generalization problem, where test data follow different distributions from training ones. To address this…

Learning on graphs, where instance nodes are inter-connected, has become one of the central problems for deep learning, as relational structures are pervasive and induce data inter-dependence which hinders trivial adaptation of existing…

Graph Neural Network-based methods face privacy leakage risks due to the introduction of topological structures about the targets, which allows attackers to bypass the target's prior knowledge of the sensitive attributes and realize…

Out-of-distribution (OoD) generalization occurs when representation learning encounters a distribution shift. This occurs frequently in practice when training and testing data come from different environments. Covariate shift is a type of…

The problem of out-of-distribution detection for graph classification is far from being solved. The existing models tend to be overconfident about OOD examples or completely ignore the detection task. In this work, we consider this problem…

Gradient-based meta-learning (GBML) algorithms are able to fast adapt to new tasks by transferring the learned meta-knowledge, while assuming that all tasks come from the same distribution (in-distribution, ID). However, in the real world,…

Graphs Neural Networks (GNNs) demonstrate high-performance on the link prediction (LP) task. However, these models often rely on all dataset samples being drawn from the same distribution. In addition, graph generative models (GGMs) show a…

Due to the performance degradation of graph neural networks (GNNs) under distribution shifts, the work on out-of-distribution (OOD) generalization on graphs has received widespread attention. A novel perspective involves distinguishing…