Visual representation learning is ubiquitous in various real-world applications, including
visual comprehension, video understanding, multi-modal analysis, human-computer …

Graph representation learning has shown effectiveness when testing and training graph
data come from the same distribution, but most existing approaches fail to generalize under …

Existing visual question answering methods often suffer from cross-modal spurious
correlations and oversimplified event-level reasoning processes that fail to capture event …

Reinforcement learning is an essential paradigm for solving sequential decision problems
under uncertainty. Despite many remarkable achievements in recent decades, applying …

In graph classification, attention-and pooling-based graph neural networks (GNNs) prevail to
extract the critical features from the input graph and support the prediction. They mostly …

Machine learning systems are known to be sensitive to spurious correlations between non-
essential features of the inputs (eg, background, texture, and secondary objects) and the …

A good visual representation is an inference map from observations (images) to features
(vectors) that faithfully reflects the hidden modularized generative factors (semantics). In this …

Abstract Open Set Domain Adaptation (OSDA) transfers the model from a label-rich domain
to a label-free one containing novel-class samples. Existing OSDA works overlook abundant …

Neural networks are prone to be biased towards spurious correlations between classes and
latent attributes exhibited in a major portion of training data, which ruins their generalization …

Fair face recognition is all about learning invariant feature that generalizes to unseen faces
in any demographic group. Unfortunately, face datasets inevitably capture the imbalanced …