性上瘾
发表于 2025-3-26 23:47:43
http://reply.papertrans.cn/27/2635/263437/263437_31.png
拔出
发表于 2025-3-27 01:41:11
Hyperbolic Personalized Tag Recommendationovel PTR model that operates on hyperbolic space, namely HPTR. HPTR learns the representations of entities by modeling their interactive relationships in hyperbolic space and utilizes hyperbolic distance to measure semantic relevance between entities. Specially, we adopt tangent space optimization t
背书
发表于 2025-3-27 05:30:11
Diffusion-Based Graph Contrastive Learning for Recommendation with Implicit Feedbacks. A symmetric contrastive learning objective is used to contrast local node representations of the diffusion graph with those of the user-item interaction graph for learning better user and item representations. Extensive experiments on real datasets demonstrate that GDCL consistently outperforms s
Consensus
发表于 2025-3-27 11:48:11
Multi-behavior Recommendation with Two-Level Graph Attentional Networksn, we learn the dynamic feature of target users and target items by modeling the dependency relation between them. The results show that our model achieves great improvement for recommendation accuracy compared with other state-of-the-art recommendation methods.
DEFT
发表于 2025-3-27 15:27:41
http://reply.papertrans.cn/27/2635/263437/263437_35.png
我不重要
发表于 2025-3-27 19:42:25
http://reply.papertrans.cn/27/2635/263437/263437_36.png
albuminuria
发表于 2025-3-27 22:07:54
César Fernández-de-las-Peñas,Kimberly Bensen and fuse users’ personalized preferences on different modalities with a multi-modal probabilistic graph. Then, to filter out irrelevant and redundant information in multi-modal data, we extend the information bottleneck theory from single-modal to multi-modal scenario and design a multi-modal infor
支柱
发表于 2025-3-28 04:55:30
Occlusal Diagnosis and Treatment of TMDrogeneous graphs from ratings and reviews to preserve inter- and intra-domain relations. Then, a relation-aware graph convolutional network is designed to simultaneously distill domain-shared and domain-specific features, by exploring the multi-hop heterogeneous connections across different graphs.
Emg827
发表于 2025-3-28 10:13:28
http://reply.papertrans.cn/27/2635/263437/263437_39.png
cognizant
发表于 2025-3-28 10:59:50
https://doi.org/10.1007/978-3-319-99909-8l, we not only design a personalized controller to enhance the deep knowledge tracing model for modeling learner’s forgetting behavior, but also use personality to model the individual differences based on the theory of cognitive psychology. In CRT, we adaptively combine learner’s knowledge level ob