首页 > 其他分享 >SocialLGN Light graph convolution network for social recommendation

SocialLGN Light graph convolution network for social recommendation

时间:2023-08-22 11:33:28浏览次数:70  
标签:mathbf convolution SocialLGN tilde recommendation user social

目录

Liao J., Zhou W., Luo F., Wen J., Gao M., Li X. and Zeng J. SocialLGN: Light graph convolution network for social recommendation. Information Sciences, 2022.

LightGCN + Social. 方法很简单, 利于理解 social recommendation.

SocialLGN

  • 定义 \(\mathbf{R} \in \mathbb{R}^{N \times M}, \mathbf{S} \in \mathbb{R}^{N \times N}\) 分别为 interaction rating matrix 和 social adjacency matrix, \(N, M\) 分别表示 user 和 item 的数量. 即 social recommendation 比一般的协同过滤, 多了一部分 user-user 的信息.

  • \[\tilde{\mathbf{R}} := \mathbf{D}_{\mathbf{R}}^{-1/2} \mathbf{R} \mathbf{D}_{\mathbf{R}}^{-1/2}, \\ \tilde{\mathbf{R}}^T := \mathbf{D}_{\mathbf{R}^T}^{-1/2} \mathbf{R}^T \mathbf{D}_{\mathbf{R}^T}^{-1/2}, \\ \tilde{\mathbf{S}} := \mathbf{D}_{\mathbf{S}}^{-1/2} \mathbf{S} \mathbf{D}_{\mathbf{S}}^{-1/2}. \]

  • 于是第 \(k\) 层, 进行如下的操作:

    \[\tilde{\mathbf{E}}_{U}^{(k)} = \mathbf{W}_3[\sigma(\mathbf{W}_1 \tilde{\mathbf{R}} \mathbf{E}_{\mathbf{I}}^{(k-1)}) \| \sigma(\mathbf{W}_2 \tilde{\mathbf{S}} \mathbf{E}_{U}^{(k-1)})], \\ \mathbf{E}_{U}^{(k)} = \frac{\tilde{\mathbf{E}}_{U}^{(k)}}{\|\tilde{\mathbf{E}}_{U}^{(k)}\|_F}, \\ \mathbf{E}_{I}^{(k)} = \tilde{\mathbf{R}}^T \mathbf{E}_U^{(k-1)}. \]

    其中 \(\sigma\) 作者采用的是 tanh.

  • 其实思想很简单, Item 的 embedding 像 LightGCN 一样仅仅依靠 user-item 的交互来聚合信息, 而 User 的 embedding 则是融合了 social 和 interaction 两部分, 通过拼接 + \(\mathbf{W}_3\) 来保持维度上的一致.

代码

[official]

标签:mathbf,convolution,SocialLGN,tilde,recommendation,user,social
From: https://www.cnblogs.com/MTandHJ/p/17648120.html

相关文章

  • CS231n: Convolutional Neural Networks for Visual Recognition
    CS231n:ConvolutionalNeuralNetworksforVisualRecognitionEventTypeDateDescriptionCourseMaterialsLecture1Tuesday April4CourseIntroduction Computervisionoverview Historicalcontext Courselogistics[slides] [video]Lecture2Thursday April6Image......
  • 论文解读(LightGCL)《LightGCL: Simple Yet Effective Graph Contrastive Learning for
    Note:[wechat:Y466551|可加勿骚扰,付费咨询]论文信息论文标题:LightGCL:SimpleYetEffectiveGraphContrastiveLearningforRecommendation论文作者:Cai,XuhengandHuang,ChaoandXia,LianghaoandRen,Xubin论文来源:2023ICLR论文地址:download 论文代码:download视......
  • HS-GCN Hamming Spatial Graph Convolutional Networks for Recommendation
    目录概符号说明HS-GCNInitialLayerPropagationLayerHashCodeEncoding矩阵表示PredictionLayerOptimization代码LiuH.,WeiY.,YinJ.andNieL.HS-GCN:Hammingspatialgraphconvolutionalnetworksforrecommendation.IEEETKDE.概二值化的nodeembedding.符......
  • Unified Conversational Recommendation Policy Learning via Graph-based Reinforcem
    图的作用:图结构捕捉不同类型节点(即用户、项目和属性)之间丰富的关联信息,使我们能够发现协作用户对属性和项目的偏好。因此,我们可以利用图结构将推荐和对话组件有机地整合在一起,其中对话会话可以被视为在图中维护的节点序列,以动态地利用对话历史来预测下一轮的行动。由四个主要组......
  • 粗读Multi-Task Recommendations with Reinforcement Learning
    论文:Multi-TaskRecommendationswithReinforcementLearning地址:https://arxiv.org/abs/2302.03328摘要Inrecentyears,Multi-taskLearning(MTL)hasyieldedimmensesuccessinRecommenderSystem(RS)applications[41].However,currentMTL-basedrecommendati......
  • 【论文阅读】Pyramid Vision Transformer: A Versatile Backbone for Dense Predictio
    来自ICCV2021论文地址:[2102.12122]PyramidVisionTransformer:AVersatileBackboneforDensePredictionwithoutConvolutions(arxiv.org)代码地址:https://link.zhihu.com/?target=https%3A//github.com/whai362/PVT一、Motivation1.将金字塔结构引入视觉Transformer,使......
  • Visualizing and Understanding Convolutional Networks
    《VisualizingandUnderstandingConvolutionalNetworks》 MatthewDZeiler,RobFergus(ECCV2014) 论文:http://t.cn/RyYKQ8z视频: http://t.cn/RyYKQ87------------------------------------------------------------------------------------------------------一、相关......
  • Graph Masked Autoencoder for Sequential Recommendation
    目录概符号说明MAERecLearningtoMaskTransitionPathMaskingTask-AdaptiveAugmentation模型代码YeY.,XiaL.andHuangC.Graphmaskedautoencoderforsequentialrecommendation.SIGIR,2023.概图+MAE.符号说明\(\mathcal{U},\mathcal{V}\),users,items;......
  • 混合性对话:Towards Conversational Recommendation over Multi-Type Dialogs
    混合型对话传统的人机对话研究专注于单一类型的对话,并且往往预设用户一开始就清楚对话目标。但实际应用中,人机对话常常混合了多种类型,例如闲聊、任务导向对话、推荐对话、问答等,并且用户目标是未知的。在这样的混合型对话中,机器人需要主动自然地进行对话推荐。“混合型对话”这......
  • TheRoleofSpatialPyramidalPoolinginConvolutionalNeuralNe
    目录1.引言2.技术原理及概念2.1.基本概念解释2.2.技术原理介绍2.3.相关技术比较3.实现步骤与流程3.1.准备工作:环境配置与依赖安装3.2.核心模块实现3.3.集成与测试4.示例与应用4.1.实例分析4.2.核心代码实现4.3.代码讲解说明4.4.应用场景介绍5.优化与改进5.1.性能优......