Wang J, Feng S. Contrastive and View-Interaction Structure Learning for Multi-view Clus...
发简信
IP属地：贵州
Wang J, Feng S. Contrastive and View-Interaction Structure Learning for Multi-view Clus...
Wang J, Feng S, Lyu G, et al. SURER: Structure-Adaptive Unified Graph Neural Network fo...
Submitted to Tiny Papers @ ICLR 2023 基于文本的游戏 （TBG） 是一种解谜的交互式对话语言任务，有可能成为大型语言模型 （LLM） 具有...
Deep Cross-Modal Subspace Clustering with Contrastive Neighbour Embedding 摘要导读 深度跨模态聚类近...
Semantically Consistent Multi-view Representation Learning (KBS2023, on line) 摘要导读 该项工作...
@那我也很开心 怎么发给你呢
论文粗读“Multi-view representation model based on graph autoencoder”Li J, Lu G, Wu Z, et al. Multi-view representation model based on graph autoencoder[J]....
感谢大佬
论文粗读“Dual Mutual Information Constraints for Discriminative Clustering”Li, Hongyu et al. “Dual Mutual Information Constraints for Discriminative Clustering.” ...
感觉互信息工作已经有很多人做了，多模态聚类这块的可以看看DMIM(好像是郑州大学)，COMPLETER(pengxi)，Self-supervised Information Bottleneck based Multi-view Subspace Clustering (SIB-MSC)
Li, Hongyu et al. “Dual Mutual Information Constraints for Discriminative Clustering.” ...
Li J, Lu G, Wu Z, et al. Multi-view representation model based on graph autoencoder[J]....
他前面有个映射的 我理解的是映射p是样本级的映射 因此是对应于每个样本都有一个输出所以是N 而映射g是类簇级别的映射 应该做的是样本到类簇的对应 这样的话 把每个类簇的表示作为了一个对比输入 因此是K。你可以理解成一个是以行做对比，一个是以列做对比，这不过这个列被压缩到了K维。而2N和2K则是对应了两个输入，直接堆叠起来了。
论文阅读“A Clustering-guided Contrastive Fusion for Multi-view Representation Learning”Ke G, Chao G, Wang X, et al. A Clustering-guided Contrastive Fusion for Multi-view Repr...
Zhu R, Li S. Self-supervision based semantic alignment for unsupervised domain adaptati...
Zhong W, Cui R, Guo Y, et al. Agieval: A human-centric benchmark for evaluating foundat...
有没有可能是我翻译的问题？总体来说，我觉得作者使用gan网络相当于对不完整视图进行了生成，这里的具有辨别性的特征可能是因为缺失视图被完善了，得到的样本描述更加具体，因此具有更强的可辨别性？
论文阅读“Consistent graph embedding network with optimal transport for incomplete multi-view clustering”Lin R, Du S, Wang S, et al. Consistent graph embedding network with optimal transport f...
Lin R, Du S, Wang S, et al. Consistent graph embedding network with optimal transport f...
Yu X, Liu H, Zhang Y, et al. Multi-view clustering via efficient representation learnin...
Li Y, Ma S, Zhou Q, et al. Learning from the Dictionary: Heterogeneous Knowledge Guided...
Klein T, Nabi M. miCSE: Mutual Information Contrastive Learning for Low-shot Sentence E...
Yang C, An Z, Cai L, et al. Mutual contrastive learning for visual representation learn...