采用Multi-head attention mechanism来表达source和target domain的用户行为序列,然后不同head进行cat(拼接),然后通过mean pooling得到最终的隐层表达。 3.1.2 ins-ins的对比学习(CL-I2I:Instance-to-instance Contrastive Learning) loss函数中,P_{k}^{s}:source domain中用户第k维序列特征表示,P_{k}^{t}:targe...
Prototypical Contrastive Learning of Unsupervised Representations（标题）A Simple Framework for Contrastive...
Prototypical Contrastive Learning of Unsupervised Representations（标题）A Simple Framework for Contrastive...
In this paper, we propose a cross-domain recommendation method: Self-supervised Interest Transfer Network (SITN), which can effectively transfer invariant knowledge between domains via prototypical contrastive learning. Specifically, we perform two levels of cross-domain contrastive learning: 1) instance...
Paper tables with annotated results for Self-Supervised Interest Transfer Network via Prototypical Contrastive Learning for Recommendation
Prototypical contrastive learning of unsu- pervised representations. arXiv preprint arXiv:2005.04966, 2020. 1, 2, 3 [37] Xueting Li, Sifei Liu, Shalini De Mello, Xiaolong Wang, Jan Kautz, and Ming-Hsuan Yang. Joint-task self-supervised learnin...
In this paper, a novel self-supervised method named dual prototypical contrastive network (DPCN) is proposed for cross-domain few-shot fault diagnosis. The proposed method contains two different prototypical contrastive learning stages. Specifically, in the first stage, intra-domain prototypical ...
(AAAI'2023) Self-Supervised Interest Transfer Network via Prototypical Contrastive Learning for Recommendation [paper] (DASFAA'2023) CATCL: Joint Cross-Attention Transfer and Contrastive Learning for Cross-Domain Recommendation [paper] (DASFAA'2023) Disentangled Contrastive Learning for Cross-Domain Recomme...
prototype 原型向量 【Deep Clustering】Prototypical Contrastive Learning of Unsupervised Representations - 知乎 (zhihu.com) 自监督蒸馏 整个模型分为师生两部分。我们以学生模型为例: 首先,我们得到图特征:zit=ft(Gi)∈RD由于我们有k个学生,假设第k个学生的原型向量为qk∈RD×Dk那么,我们可以利用原型向量计算软...
【2】 Adaptive Prototypical Networks 标题:自适应原型网络 链接:https://arxiv.org/abs/2211.12479 作者:Manas Gogoi,Sambhavi Tiwari,Shekhar Verma 机构:Department of Information Technology, Indian Institute of Information Technology, Allahabad 【3】 ProCC: Progressive Cross-primitive Consistency for Open-...