interference
发表于 2025-3-23 12:12:15
Self-guided Contrastive Learning for Sequential Recommendationy resolve data sparsity issue of sequential recommendation with data augmentations. However, the semantic structure of sequences is typically corrupted by data augmentations, resulting in low-quality views. To tackle this issue, we propose .guided contrastive learning enhanced . for sequential recom
陪审团每个人
发表于 2025-3-23 16:07:55
Graph-Based Sequential Interpolation Recommender for Cold-Start Usersations. However, in many scenarios, there are a large number of cold-start users with limited user-item interactions. To address this challenge, some studies utilize auxiliary information to infer users’ interests. But with the increasing awareness of personal privacy protection, it is difficult to
来这真柔软
发表于 2025-3-23 21:20:21
http://reply.papertrans.cn/103/10217/1021670/1021670_13.png
哀悼
发表于 2025-3-24 02:01:09
Self-guided Contrastive Learning for Sequential Recommendationy resolve data sparsity issue of sequential recommendation with data augmentations. However, the semantic structure of sequences is typically corrupted by data augmentations, resulting in low-quality views. To tackle this issue, we propose .guided contrastive learning enhanced . for sequential recom
prodrome
发表于 2025-3-24 05:04:38
http://reply.papertrans.cn/103/10217/1021670/1021670_15.png
小母马
发表于 2025-3-24 06:57:02
http://reply.papertrans.cn/103/10217/1021670/1021670_16.png
遗弃
发表于 2025-3-24 13:03:02
A2TN: Aesthetic-Based Adversarial Transfer Network for Cross-Domain Recommendationely richer information from a richer domain to improve the recommendation performance in a sparser domain. Therefore, enhancing the transferability of features in different domains is crucial for improving the recommendation performance. However, existing methods are usually confronted with negative
创造性
发表于 2025-3-24 18:46:41
MORO: A Multi-behavior Graph Contrast Network for Recommendationsparsity and cold-start problems faced by classical recommendation methods. In real-world scenarios, the interactive behaviors between users and items are often complex and highly dependent. Existing multi-behavior recommendation models do not fully utilize multi-behavior information in the followin
Flat-Feet
发表于 2025-3-24 19:28:50
MORO: A Multi-behavior Graph Contrast Network for Recommendationsparsity and cold-start problems faced by classical recommendation methods. In real-world scenarios, the interactive behaviors between users and items are often complex and highly dependent. Existing multi-behavior recommendation models do not fully utilize multi-behavior information in the followin
progestogen
发表于 2025-3-25 00:49:38
Eir-Ripp: Enriching Item Representation for Recommendation with Knowledge Graphformation to the recommended items. Existing methods either use knowledge graph as an auxiliary information to mine users’ interests, or use knowledge graph to establish relationships between items via their hidden information. However, these methods usually ignore the interaction between users and