5.2 Graph Contrastive Learning 对比学习的目的是最大化具有相似语义信息的实例之间的MI,因此可以构造不同的前置任务来丰富来自这些信息的监督信号。现有工作可以分为两大主流:同尺度对比学习和跨尺度对比学习。前者以相等的比例区分图实例(如节点-节点),而后者将对比放在多个粒度上(如节点-图)。图8展示了方法流程。
[82] S. Wan, Y. Zhan, L. Liu, B. Yu, S. Pan, and C. Gong, “Contrastive graph poisson networks: Semi-supervised learning with extremely limited labels,” in NeurIPS, 2021. [83] X. Wang, N. Liu, H. Han, and C. Shi, “Self-supervised heterogeneous graph neural network with co...
graph diffusion graph sampling 1.2.1 Edge Addition/Dropping 即 保留原始节点顺序,对邻接矩阵种的元进行改写。 基于图稀疏性(graph sparsification)的图结构优化方法 [8、9],基于图结构整洁性(graph sanitation)的方法 [3],以及图采样(graph sampling)。
The choice of pretext task relies on the type of problem being solved. Although numerous methods have been proposed in contrastive learning, a separate track of research is still going on to identify the right pre-text task. Work has identified and proved that it is important to determine the...
Contrastive Learning Curriculum Learning Data Augmentation Deep Learning General Methods Deep Reinforcement Learning Diffusion Models Federated Learning Few-Shot and Zero-Shot Learning General Machine Learning Generative Adversarial Networks Graph Neural Networks Interpretability and Analysis Knowledge Distillation Meta...
A graph-based contrastive learning framework for medicare insurance fraud detection specializedinsurancesummarizedFrontiers of Computer Science -doi:10.1007/s11704-022-1734-0Song XIAOTing BAIXiangchong CUIBin WUXinkai MENGBai WANG中国计算机科学前沿:英文版...
GraphST [33] is a self-supervised graph-based technique of contrastive learning for spatial transcriptomics analysis that encompasses spatial clustering, multi-sample integration, and cell-type deconvolution. The contrastive learning framework in the spatial clustering module learns informative and ...
Although deep reinforcement learning has become a promising machine learning approach for sequential decision-making problems, it is still not mature enoug
A Review-aware Graph Contrastive Learning Framework for Recommendation 用于推荐的评论感知图对比学习框架 来源:SIGIR 2022 摘要:许多现有的基于评论的推荐模型通过历史评论增强了用户/项目嵌入学习能力,虽然已经取得了重大进展,但作者认为,目前基于评论的推荐的解决方案并没有全面地将评论信息融合到交互中。在本文中,作...
2024 ICIP Space Domain Deepfake Detection Via Separable Self-Consistency Learning - 2024 ICIP Space Domain Deepfake Detection With Combined Unsupervised-Supervised Contrastive Learning - 2024 CVPR Data Driven Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection - ...