返回
Variational inference framework for partial multi-view multi-label representation learning
DOI:10.1016/j.patcog.2026.113742.png)
摘要
En 中文
多视角随机丢弃增强改进模型泛化能力。• 通过优化三个互信息项学习联合表示。• 所提出的框架解释了学习最优共享信息的过程。
Keyword:
multi-view learning
variational inference
mutual information
representation learning
random dropping augmentation
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
An effective bipartite graph fusion and contrastive label correlation for multi-view multi-label classification一种有效的二分图融合和对比标签相关性方法,用于多视角多标签分类
PATTERN RECOGNITION
IF7.6
Multi-level information fusion for missing multi-label learning based on stochastic concept clustering
INFORMATION FUSION
IF15.5
Ji, J., Feng, S., & Li, Y. (2024). Tensorized unaligned multi-view clustering with multi-scale representation learning. In Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining (pp. 1246–1256).Ji, J., Feng, S., & Li, Y. (2024). 张量化未对齐多视图聚类与多尺度表示学习. 在第30届ACM SIGKDD知识发现与数据挖掘会议论文集(第1246-1256页).
A novel approach for effective multi-view clustering with information-theoretic perspective基于信息论视角的有效多视图聚类新方法

