Automated message selection for robust Heterogeneous Graph Contrastive Learning

R Bing, G Yuan, Y Zhang, Y Zhou, Q Yan - Knowledge-Based Systems, 2025 - Elsevier
Abstract Heterogeneous Graph Contrastive Learning (HGCL) has attracted lots of attentions
because of eliminating the requirement of node labels. The encoders used in HGCL mainly …

Weakly-Supervised Cross-Contrastive Learning Network for Image Manipulation Detection and Localization

R Bai - Knowledge-Based Systems, 2025 - Elsevier
With the significant reduction in the cost of image manipulation due to advancements in
image editing tools, it is crucial to investigate methods for detecting image manipulation …

[HTML][HTML] Cross-modal recipe retrieval based on unified text encoder with fine-grained contrastive learning

B Zhang, H Kyutoku, K Doman, T Komamizu… - Knowledge-Based …, 2024 - Elsevier
Cross-modal recipe retrieval is vital for transforming visual food cues into actionable cooking
guidance, making culinary creativity more accessible. Existing methods separately encode …

Partial label learning via weighted centroid clustering disambiguation

Y Tian, X Niu, J Chai - Neurocomputing, 2024 - Elsevier
Abstract Partial Label Learning (PLL) is a weakly supervised learning problem that induces
a multi-class classifier from data with candidate labels, among which only one is the ground …

Cluster-guided Contrastive Class-imbalanced Graph Classification

W Ju, Z Mao, S Yi, Y Qin, Y Gu, Z **ao, J Shen… - arxiv preprint arxiv …, 2024 - arxiv.org
This paper studies the problem of class-imbalanced graph classification, which aims at
effectively classifying the categories of graphs in scenarios with imbalanced class …