← Search

Jiedong Wang

2 accepted papers

2025

Disentangling Multi-view Representations via Curriculum Learning with Learnable Prior

IJCAI 2025

Multi-view representation learning methods typically follow a consistent-and-specific pipeline that aims at extracting latent representations for an entity from its multiple observable views to facilitate downstream tasks. However, most of them overlook the complex underlying correlation between dif

2025

Learning Robust Multi-view Representation Using Dual-masked VAEs

IJCAI 2025

Most existing multi-view representation learning methods assume view-completeness and noise-free data. However, such assumptions are strong in real-world applications. Despite advances in methods tailored to view-missing or noise problems individually, a one-size-fits-all approach that concurrently