Jiangmeng Li

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 …

HTG-GCL: Leveraging Hierarchical Topological Granularity from Cellular Complexes for Graph Contrastive Learning

2025 · arXiv (Cornell University)

Graph contrastive learning (GCL) aims to learn discriminative semantic invariance by contrasting different views of the same graph that share critical topological patterns. However, existing GCL approaches with structural augmentations often struggle to identify task-relevant …