
邻域扩展机制增强的图平行聚焦注意力社会化推荐系统
李伟玥, 朱志国, 董昊, 高明, 张俊, 刘子龙
邻域扩展机制增强的图平行聚焦注意力社会化推荐系统
Neighborhood Extension Mechanism Enhanced Graph Parallel Focused Attention Networks for Social Recommender System
社会化推荐系统旨在基于用户的评分历史和社交关系,预测其对未交互商品的评分.现有的社会化推荐系统大多基于图神经网络,然而,低效率的注意力机制和过度平滑问题在一定程度上限制评分预测的精准性和可解释性.为此,文中提出邻域扩展机制增强的图平行聚焦注意力社会化推荐系统.首先,平行图聚焦注意力网络,将用户的整体偏好分解为多方面的细粒度偏好,并引入聚焦注意力机制作为消息传递算法,根据用户-商品交互历史识别最符合用户相应偏好的商品,同时从社交网络中识别用户基于不同偏好的可信朋友.然后,提出邻域扩展机制,建立快捷链接的方式,直接实现中心节点与高阶节点间的消息传递,有效提升图聚焦注意力网络在高阶自我中心网络中捕获社交信息的能力.最后,在3个公开基准数据集上的实验表明文中系统在精准推荐方面的优越性,一系列可视化案例分析展示出其良好的可解释性.代码地址详见:https://github.com/usernameAI/NEGA.
Social recommender systems are designed to predict the ratings of users for unexplored items based on their historical ratings and social connections. Most existing social recommender systems are based on graph neural networks. However, the inefficiency of attention mechanisms and the over-smoothing problem limit the precision and interpretability of rating predictions. Therefore, a neighborhood extension mechanism enhanced graph parallel focused attention network is proposed to address these issues. The overall preferences of users are decomposed into nuanced facets and a focused attention mechanism is introduced as message passing algorithm to pinpoint the item most aligned with the preferences of users based on their interaction history. Meanwhile, the mechanism identifies trustworthy friends from the social network based on diverse preferences. Furthermore, a neighborhood extension mechanism is proposed, which establishes quick link to facilitate the direct message passing between central and higher-order nodes, effectively enhancing the ability of graph focused attention network to capture the social information in higher-order ego network. Experimental results on three public benchmark datasets demonstrate the superiority of the proposed system in accurate rating prediction. Moreover, a series of visual case studies illustrate the interpretability of the system. The code for this paper can be found at: https://github.com/usernameAI/NEGA.
社会化推荐系统 / 图注意力网络 / 自我中心网络 / 平行注意力机制 {{custom_keyword}} /
Social Recommender System / Graph Attention Networks / Ego Network / Parallel Attention Mechanism {{custom_keyword}} /
表1 实验数据集部分统计指标Table 1 Some statistical indexes of experimental datasets |
统计指标 | Filmtrust | CiaoDVD | Yelp |
---|---|---|---|
用户数量 | 1508 | 17615 | 16239 |
商品数量 | 2071 | 16121 | 14284 |
评分数量 | 35497 | 72665 | 198397 |
评分密度/% | 1.1366 | 0.0256 | 0.0855 |
社交关系发起用户数量 | 609 | 1438 | 10580 |
社交关系接受用户数量 | 732 | 4299 | 10580 |
社交关系数量 | 3264 | 44986 | 317180 |
社交关系密度/% | 0.7322 | 0.7277 | 0.2834 |
表2 各系统在3个数据集上的对比实验结果Table 2 Contrast experiment results of different systems on 3 datasets |
系统 | Filmtrust | CiaoDVD | Yelp | |||
---|---|---|---|---|---|---|
MAE | RMSE | MAE | RMSE | MAE | RMSE | |
MF | 0.7090 | 0.9616 | 0.8735 | 1.1845 | 1.0308 | 1.3562 |
PMF | 0.6955 | 0.9370 | 0.8655 | 1.1634 | 1.0316 | 1.3518 |
SVD++ | 0.6980 | 0.9401 | 0.8416 | 1.1328 | 1.0361 | 1.3673 |
SoRec | 0.6824 | 0.9139 | 0.8503 | 1.1405 | 0.8778 | 1.1347 |
RSTE | 0.7084 | 0.9548 | 0.8603 | 1.1424 | 0.8877 | 1.1483 |
SocialMF | 0.6813 | 0.9163 | 0.8383 | 1.1288 | 0.8863 | 1.1402 |
文献[39]系统 | 0.6832 | 0.9141 | 0.7971 | 1.0871 | 0.9042 | 1.1690 |
CUNE-MF | 0.6803 | 0.9148 | 0.8102 | 1.0823 | 0.8273 | 1.0498 |
GraphRec | 0.7087 | 0.9221 | 0.7899 | 1.0207 | 0.8006 | 1.0344 |
ConsisRec | 1.2886 | 1.6701 | 0.7537 | 0.9656 | 0.9017 | 1.1400 |
GDSRec | 1.2813 | 1.6298 | 0.7448 | 0.9774 | 0.8100 | 1.0515 |
REST | 0.7176 | 0.8841 | 0.7318 | 0.9552 | 0.8198 | 1.0392 |
CDRSB | 0.7437 | 0.9002 | 0.7496 | 0.9467 | 0.8296 | 1.0413 |
NEGA | 0.6746 | 0.8712 | 0.7278 | 0.9418 | 0.7906 | 1.0234 |
表3 各模块的消融实验结果Table 3 Ablation experiment results of different modules |
系统 | Filmtrust | CiaoDVD | Yelp | |||
---|---|---|---|---|---|---|
MAE | RMSE | MAE | RMSE | MAE | RMSE | |
NEGA-OE-MLP | 0.6884 | 0.8782 | 0.7487 | 0.9665 | 0.8005 | 1.0243 |
NEGA-OE-VG | 0.6850 | 0.8798 | 0.7375 | 0.9611 | 0.7972 | 1.0237 |
NEGA-FF-MLP | 0.6786 | 0.8736 | 0.7590 | 0.9665 | 0.8053 | 1.0285 |
NEGA-FF-VG | 0.6806 | 0.8808 | 0.7296 | 0.9610 | 0.7932 | 1.0234 |
NEGA-P-MLP | 0.6898 | 0.8777 | 0.7287 | 0.9366 | 0.8031 | 1.0223 |
NEGA-P-VG | 0.6987 | 0.8997 | 0.7441 | 0.9620 | 0.8068 | 1.0279 |
NEGA-MP-SA | 0.7229 | 0.9316 | 0.7804 | 1.0027 | 0.7899 | 1.0406 |
NEGA-MP-IP | 0.6870 | 0.8849 | 0.7319 | 0.9499 | 0.7934 | 1.0278 |
NEGA-OS-RAW | 0.7115 | 0.9024 | 0.8661 | 1.0851 | 0.8038 | 1.0307 |
NEGA-OS-NORM | 0.7010 | 0.8989 | 0.8599 | 1.0771 | 0.8023 | 1.0295 |
NEGA-OS-RES | 0.7091 | 0.9017 | 0.8623 | 1.0805 | 0.8036 | 1.0305 |
NEGA | 0.6746 | 0.8712 | 0.7278 | 0.9418 | 0.7906 | 1.0234 |
[1] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[2] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[3] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[4] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[5] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[6] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[7] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[8] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[9] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[10] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[11] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[12] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[13] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[14] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[15] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[16] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[17] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[18] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[19] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[20] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[21] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[22] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[23] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[24] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[25] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[26] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[27] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[28] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[29] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[30] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[31] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[32] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[33] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[34] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[35] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[36] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[37] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[38] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[39] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[40] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[41] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[42] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[43] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[44] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[45] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[46] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[47] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[48] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[49] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[50] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[51] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[52] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[53] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[54] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[55] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[56] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[57] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[58] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[59] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[60] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[61] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[62] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[63] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[64] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[65] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[66] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[67] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[68] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[69] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[70] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[71] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[72] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[73] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[74] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[75] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[76] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[77] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[78] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[79] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[80] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[81] |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_ref.label}} |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
/
〈 |
|
〉 |