Causal reasoning is viewed as crucial for achieving human-level machine intelligence.
Recent advances in language models have expanded the horizons of artificial intelligence …

Graph out-of-distribution (OOD) generalization remains a major challenge in graph learning
since graph neural networks (GNNs) often suffer from severe performance degradation …

Ensemble of deep neural networks has achieved great success in hedging against single-
model failure under distribution shift. However, existing techniques suffer from producing …

Despite great success in modeling visual perception, deep neural network based image
quality assessment (IQA) still remains unreliable in real-world applications due to its …

An effective paradigm of multi-modal learning (MML) is to learn unified representations
among modalities. From a causal perspective, constraining the consistency between …

Abstract Graph Neural Networks (GNNs) have been proven to easily overfit spurious
subgraphs in the available data, which reduces their trustworthiness in high-stakes real …

Deep learning methods often struggle with the domain shift problem, leading to poor
generalization on out-of-domain (OOD) data. To address the problem, domain …

Incorrect labels as well as the discrepancy between training and test domain data
distributions can significantly affect the effectiveness of supervised data-driven models in …

Graph Neural Networks (GNNs) have emerged as powerful representation learning tools for
capturing complex dependencies within diverse graph-structured data. Despite their …

Abstract Graph Out-of-Distribution (OOD), requiring that models trained on biased data
generalize to the unseen test data, has considerable real-world applications. One of the …