Wenwen Qiang

Hierarchical Topology Isomorphism Expertise Embedded Graph Contrastive Learning

2024 · Proceedings of the AAAI Conference on Artificial Intelligence

Graph contrastive learning (GCL) aims to align the positive features while differentiating the negative features in the latent space by minimizing a pair-wise contrastive loss. As the embodiment of an outstanding discriminative unsupervised graph representation …

Towards the Causal Complete Cause of Multi-Modal Representation Learning

2024 · arXiv (Cornell University)

Multi-Modal Learning (MML) aims to learn effective representations across modalities for accurate predictions. Existing methods typically focus on modality consistency and specificity to learn effective representations. However, from a causal perspective, they may lead to …