Disentangled contrastive learning for fair graph representations
Abstract Graph Neural Networks (GNNs) play a key role in efficiently learning node
representations of graph-structured data through message passing, but their predictions are …
representations of graph-structured data through message passing, but their predictions are …
Discriminative Vision Transformer for Heterogeneous Cross-Domain Hyperspectral Image Classification
M Ye, J Ling, W Huo, Z Zhang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
The transformer has been introduced in the hyperspectral image (HSI) classification,
demonstrating outstanding capability in capturing global features compared to the …
demonstrating outstanding capability in capturing global features compared to the …
[HTML][HTML] Few-Shot Graph Anomaly Detection via Dual-Level Knowledge Distillation
X Li, D Cheng, L Zhang, C Zhang, Z Feng - Entropy, 2025 - mdpi.com
Graph anomaly detection is crucial in many high-impact applications across diverse fields. In
anomaly detection tasks, collecting plenty of annotated data tends to be costly and …
anomaly detection tasks, collecting plenty of annotated data tends to be costly and …
Multi-view Graph Neural Network for Fair Representation Learning
Abstract In Graph Neural Networks, connectivity is usually represented by a fixed adjacency
matrix, however, such a matrix fails to capture the complex entanglement present in …
matrix, however, such a matrix fails to capture the complex entanglement present in …