Recently, as location-based social network(LBSN) rapidly grow, point-of-interest(POI) recommendation has become an important way to help people locate interesting places. Nowadays, there have been deep studies conduct...Recently, as location-based social network(LBSN) rapidly grow, point-of-interest(POI) recommendation has become an important way to help people locate interesting places. Nowadays, there have been deep studies conducted on the geographical and social influence in the point-of-interest recommendation model based on the rating prediction. The fact is, however, relying solely on the rating fails to reflect the user's preferences very accurately, because the users are most concerned with the list of ranked point-of-interests(POIs) on the actual output of recommender systems. In this paper, we propose a co-pairwise ranking model called Geo-Social Bayesian Personalized Ranking model(GSBPR), which is based on the pairwise ranking with the exploiting geo-social correlations by incorporating the method of ranking learning into the process of POI recommendation. In this model, we develop a novel BPR pairwise ranking assumption by injecting users' geo-social preference. Based on this assumption, the POI recommendation model is reformulated by a three-level joint pairwise ranking model. And the experimental results based on real datasets show that the proposed method in this paper enjoys better recommendation performance compared to other state-of-the-art POI recommendation models.展开更多
In mobile social networks,next point-of-interest(POI)recommendation is a very important function that can provide personalized location-based services for mobile users.In this paper,we propose a recurrent neural netwo...In mobile social networks,next point-of-interest(POI)recommendation is a very important function that can provide personalized location-based services for mobile users.In this paper,we propose a recurrent neural network(RNN)-based next POI recommendation approach that considers both the location interests of similar users and contextual information(such as time,current location,and friends’preferences).We develop a spatial-temporal topic model to describe users’location interest,based on which we form comprehensive feature representations of user interests and contextual information.We propose a supervised RNN learning prediction model for next POI recommendation.Experiments based on real-world dataset verify the accuracy and efficiency of the proposed approach,and achieve best F1-score of 0.196754 on the Gowalla dataset and 0.354592 on the Brightkite dataset.展开更多
The wide spread of location-based social networks brings about a huge volume of user check-in data, whichfacilitates the recommendation of points of interest （POIs）. Recent advances on distributed representation she...The wide spread of location-based social networks brings about a huge volume of user check-in data, whichfacilitates the recommendation of points of interest （POIs）. Recent advances on distributed representation shed light onlearning low dimensional dense vectors to alleviate the data sparsity problem. Current studies on representation learningfor POI recommendation embed both users and POIs in a common latent space, and users＇ preference is inferred basedon the distance/similarity between a user and a POI. Such an approach is not in accordance with the semantics of usersand POIs as they are inherently different objects. In this paper, we present a novel translation-based, time and locationaware （TransTL） representation, which models the spatial and temporal information as a relationship connecting users andPOIs. Our model generalizes the recent advances in knowledge graph embedding. The basic idea is that the embedding ofa 〈time, location〉 pair corresponds to a translation from embeddings of users to POIs. Since the POI embedding shouldbe close to the user embedding plus the relationship vector, the recommendation can be performed by selecting the top-kPOIs similar to the translated POI, which are all of the same type of objects. We conduct extensive experiments on tworeal-world data.sets. The results demonstrate that our TransTL model achieves the state-of-the-art performance. It is alsomuch more robust to data sparsity than the baselines.展开更多
在基于位置社交网络(Location-based Social Network,LBSNs)的服务中,有效的兴趣点(Point-of-Interest,POI)推荐具有极大的经济和社会效用,但如何深入理解LBSN中的位置、结构和行为等相关信息,并进行推理以及实现POI推荐仍然是一项挑战...在基于位置社交网络(Location-based Social Network,LBSNs)的服务中,有效的兴趣点(Point-of-Interest,POI)推荐具有极大的经济和社会效用,但如何深入理解LBSN中的位置、结构和行为等相关信息,并进行推理以及实现POI推荐仍然是一项挑战性任务。针对LBSNs中的多种异构数据,提出了一种能够挖掘用户社交和POI多种特征信息的用于POI推荐的图神经网络模型——POIR-GAT。首先POIR-GAT利用社交关系构建用户-用户图,并结合用户-POI交互图共同抽取用户特征向量;其次,基于POI的不同地理特征构造不同的特征矩阵,并通过矩阵分解获得不同的潜在因子,将这些潜在因子融入POI的特征向量,以学习它们对用户行为的共同影响,并用于实现融合社交因素和POI特征的推荐模型。通过在2个公开数据集上进行的实验,验证了所提POIR-GAT模型可以有效融合用户社交信息和POI特征信息,提高POI推荐质量。展开更多
随着基于位置社交网络(location-based social network,LBSN)的发展,兴趣点推荐成为满足用户个性化需求、减轻信息过载问题的重要手段.然而,已有的兴趣点推荐算法存在如下的问题:1)多数已有的兴趣点推荐算法简化用户签到频率数据,仅使...随着基于位置社交网络(location-based social network,LBSN)的发展,兴趣点推荐成为满足用户个性化需求、减轻信息过载问题的重要手段.然而,已有的兴趣点推荐算法存在如下的问题:1)多数已有的兴趣点推荐算法简化用户签到频率数据,仅使用二进制值来表示用户是否访问一个兴趣点;2)基于矩阵分解的兴趣点推荐算法把签到频率数据和传统推荐系统中的评分数据等同看待,使用高斯分布模型建模用户的签到行为;3)忽视用户签到数据的隐式反馈属性.为解决以上问题,提出一个基于Ranking的泊松矩阵分解兴趣点推荐算法.首先,根据LBSN中用户的签到行为特点,利用泊松分布模型替代高斯分布模型建模用户在兴趣点上签到行为;然后采用BPR(Bayesian personalized ranking)标准优化泊松矩阵分解的损失函数,拟合用户在兴趣点对上的偏序关系;最后,利用包含地域影响力的正则化因子约束泊松矩阵分解的过程.在真实数据集上的实验结果表明:基于Ranking的泊松矩阵分解兴趣点推荐算法的性能优于传统的兴趣点推荐算法.展开更多
兴趣点推荐是在基于位置社会网络(location-based social network,LBSN)中流行起来的一种全新形式的推荐.利用LBSN所包含的丰富信息进行个性化推荐能有效增强用户体验和提高用户对LBSN的依赖度.针对无显示用户偏好、兴趣非一致性和数据...兴趣点推荐是在基于位置社会网络(location-based social network,LBSN)中流行起来的一种全新形式的推荐.利用LBSN所包含的丰富信息进行个性化推荐能有效增强用户体验和提高用户对LBSN的依赖度.针对无显示用户偏好、兴趣非一致性和数据稀疏性等挑战性问题,研究一种针对LBSN的双重细粒度POI推荐策略,即一方面将用户的全部历史签到信息以小时为单位细分为24个时间段,另一方面将每个POI细分为多个潜在主题及其分布,同时利用用户的历史签到信息和评论信息挖掘出用户在不同时间段的主题偏好,以实现POI的Top-N推荐.为实现该推荐思路,首先,根据用户的评论信息,运用LDA模型提取出每个POI的主题分布;然后,对于每个用户,将其签到信息划分到24个时间段中,通过连接相应的POI主题分布映射出用户在不同时间段对每个主题的兴趣偏好.为解决数据稀疏问题,运用高阶奇异值分解算法对用户-主题-时间三阶张量进行分解,获取用户在每个时间段对每个主题更为准确的兴趣评分.在真实数据集上进行了性能测试,结果表明所提出的推荐策略具有较好的推荐效果.展开更多
兴趣点(Point-Of-Interest,POI)推荐是基于位置社交网络(Location-Based Social Network,LBSN)中一项重要的个性化服务,可以帮助用户发现其感兴趣的POI,提高信息服务质量。针对POI推荐中存在的数据稀疏性问题,提出一种融合社交关系和局...兴趣点(Point-Of-Interest,POI)推荐是基于位置社交网络(Location-Based Social Network,LBSN)中一项重要的个性化服务,可以帮助用户发现其感兴趣的POI,提高信息服务质量。针对POI推荐中存在的数据稀疏性问题,提出一种融合社交关系和局部地理因素的POI推荐算法。根据社交关系中用户间的共同签到和距离关系度量用户相似性,并基于用户的协同过滤方法构建社交影响模型。为每个用户划分一个局部活动区域,通过对区域内POIs间的签到相关性分析,建立局部地理因素影响模型。基于加权矩阵分解挖掘用户自身偏好,并融合社交关系和局部地理因素进行POI推荐。实验表明,所提出的POI推荐算法相比其他方法具有更高的准确率和召回率,能够有效缓解数据稀疏性问题,提高推荐质量。展开更多
兴趣点(point-of-interest,POI)推荐是基于位置的社交网络(location-based social networks,LBSN)中一项重要的服务。针对目前推荐算法存在的噪声数据影响推荐质量、用户个性化程度低的问题,提出了一种个性化联合推荐算法。提出了引入PO...兴趣点(point-of-interest,POI)推荐是基于位置的社交网络(location-based social networks,LBSN)中一项重要的服务。针对目前推荐算法存在的噪声数据影响推荐质量、用户个性化程度低的问题,提出了一种个性化联合推荐算法。提出了引入POI的位置因素去除不可能或可能性较小的POI,形成初步候选集;综合考虑POI的类别、流行度及用户的社会行为,增加用户个性化的程度,提高推荐结果的质量。在Foursquare真实签到数据集上的实验证明了提出的联合推荐算法与目前先进的算法相比,准确率提高11%,召回率提高8%。展开更多
在基于位置的社交网络中,兴趣点实时推荐数据和用户签到数据存在高稀疏性问题。提出一种基于时间效应的混合推荐模型。通过用户潜在兴趣点数据模型计算用户时间行为影响分数和地理位置影响分数,并用线性统一模型进行处理,选取Top S 个...在基于位置的社交网络中,兴趣点实时推荐数据和用户签到数据存在高稀疏性问题。提出一种基于时间效应的混合推荐模型。通过用户潜在兴趣点数据模型计算用户时间行为影响分数和地理位置影响分数,并用线性统一模型进行处理,选取Top S 个兴趣点作为用户的潜在兴趣点。将用户的潜在签到记录引入基于时间效应的矩阵分解模型中,考虑时间差异性和连续性对推荐结果的影响,在此基础上进行优化求解,提出推荐策略。实验结果表明,与LRT模型、UTE+SE模型相比,该模型的推荐效果较好,其准确率和召回率最高可达0.103 4和0.111 8。展开更多
With the booming of the Internet of Things(Io T)and the speedy advancement of Location-Based Social Networks(LBSNs),Point-Of-Interest(POI)recommendation has become a vital strategy for supporting people’s ability to ...With the booming of the Internet of Things(Io T)and the speedy advancement of Location-Based Social Networks(LBSNs),Point-Of-Interest(POI)recommendation has become a vital strategy for supporting people’s ability to mine their POIs.However,classical recommendation models,such as collaborative filtering,are not effective for structuring POI recommendations due to the sparseness of user check-ins.Furthermore,LBSN recommendations are distinct from other recommendation scenarios.With respect to user data,a user’s check-in record sequence requires rich social and geographic information.In this paper,we propose two different neural-network models,structural deep network Graph embedding Neural-network Recommendation system(SG-Neu Rec)and Deepwalk on Graph Neural-network Recommendation system(DG-Neu Rec)to improve POI recommendation.combined with embedding representation from social and geographical graph information(called SG-Neu Rec and DG-Neu Rec).Our model naturally combines the embedding representations of social and geographical graph information with user-POI interaction representation and captures the potential user-POI interactions under the framework of the neural network.Finally,we compare the performances of these two models and analyze the reasons for their differences.Results from comprehensive experiments on two real LBSNs datasets indicate the effective performance of our model.展开更多
基金supported by National Basic Research Program of China (2012CB719905)National Natural Science Funds of China (41201404)Fundamental Research Funds for the Central Universities of China (2042018gf0008)
文摘Recently, as location-based social network(LBSN) rapidly grow, point-of-interest(POI) recommendation has become an important way to help people locate interesting places. Nowadays, there have been deep studies conducted on the geographical and social influence in the point-of-interest recommendation model based on the rating prediction. The fact is, however, relying solely on the rating fails to reflect the user's preferences very accurately, because the users are most concerned with the list of ranked point-of-interests(POIs) on the actual output of recommender systems. In this paper, we propose a co-pairwise ranking model called Geo-Social Bayesian Personalized Ranking model(GSBPR), which is based on the pairwise ranking with the exploiting geo-social correlations by incorporating the method of ranking learning into the process of POI recommendation. In this model, we develop a novel BPR pairwise ranking assumption by injecting users' geo-social preference. Based on this assumption, the POI recommendation model is reformulated by a three-level joint pairwise ranking model. And the experimental results based on real datasets show that the proposed method in this paper enjoys better recommendation performance compared to other state-of-the-art POI recommendation models.
基金This work was partially supported by the National Key Research and Development Program of China under Grant No.2018YFB1004704the National Natural Science Foundation of China under Grant Nos.61972196,61832008,61832005+1 种基金the Key Research and Development Program of Jiangsu Province of China under Grant No.BE2018116,the open Project from the State Key Laboratory of Smart Grid Protection and Operation Control“Research on Smart Integration of Terminal-Edge-Cloud Techniques for Pervasive Internet of Things”the Collaborative Innovation Center of Novel Software Technology and Industrialization.
文摘In mobile social networks,next point-of-interest(POI)recommendation is a very important function that can provide personalized location-based services for mobile users.In this paper,we propose a recurrent neural network(RNN)-based next POI recommendation approach that considers both the location interests of similar users and contextual information(such as time,current location,and friends’preferences).We develop a spatial-temporal topic model to describe users’location interest,based on which we form comprehensive feature representations of user interests and contextual information.We propose a supervised RNN learning prediction model for next POI recommendation.Experiments based on real-world dataset verify the accuracy and efficiency of the proposed approach,and achieve best F1-score of 0.196754 on the Gowalla dataset and 0.354592 on the Brightkite dataset.
基金This work was supported by the National Natural Science Foundation of China under Grant Nos. 61572376 and 91646206, and the National Key Research and Development Program of China under Grant No. 2016YFB1000603.
文摘The wide spread of location-based social networks brings about a huge volume of user check-in data, whichfacilitates the recommendation of points of interest （POIs）. Recent advances on distributed representation shed light onlearning low dimensional dense vectors to alleviate the data sparsity problem. Current studies on representation learningfor POI recommendation embed both users and POIs in a common latent space, and users＇ preference is inferred basedon the distance/similarity between a user and a POI. Such an approach is not in accordance with the semantics of usersand POIs as they are inherently different objects. In this paper, we present a novel translation-based, time and locationaware （TransTL） representation, which models the spatial and temporal information as a relationship connecting users andPOIs. Our model generalizes the recent advances in knowledge graph embedding. The basic idea is that the embedding ofa 〈time, location〉 pair corresponds to a translation from embeddings of users to POIs. Since the POI embedding shouldbe close to the user embedding plus the relationship vector, the recommendation can be performed by selecting the top-kPOIs similar to the translated POI, which are all of the same type of objects. We conduct extensive experiments on tworeal-world data.sets. The results demonstrate that our TransTL model achieves the state-of-the-art performance. It is alsomuch more robust to data sparsity than the baselines.
文摘在基于位置社交网络(Location-based Social Network,LBSNs)的服务中,有效的兴趣点(Point-of-Interest,POI)推荐具有极大的经济和社会效用,但如何深入理解LBSN中的位置、结构和行为等相关信息,并进行推理以及实现POI推荐仍然是一项挑战性任务。针对LBSNs中的多种异构数据,提出了一种能够挖掘用户社交和POI多种特征信息的用于POI推荐的图神经网络模型——POIR-GAT。首先POIR-GAT利用社交关系构建用户-用户图,并结合用户-POI交互图共同抽取用户特征向量;其次,基于POI的不同地理特征构造不同的特征矩阵,并通过矩阵分解获得不同的潜在因子,将这些潜在因子融入POI的特征向量,以学习它们对用户行为的共同影响,并用于实现融合社交因素和POI特征的推荐模型。通过在2个公开数据集上进行的实验,验证了所提POIR-GAT模型可以有效融合用户社交信息和POI特征信息,提高POI推荐质量。
文摘随着基于位置社交网络(location-based social network,LBSN)的发展,兴趣点推荐成为满足用户个性化需求、减轻信息过载问题的重要手段.然而,已有的兴趣点推荐算法存在如下的问题:1)多数已有的兴趣点推荐算法简化用户签到频率数据,仅使用二进制值来表示用户是否访问一个兴趣点;2)基于矩阵分解的兴趣点推荐算法把签到频率数据和传统推荐系统中的评分数据等同看待,使用高斯分布模型建模用户的签到行为;3)忽视用户签到数据的隐式反馈属性.为解决以上问题,提出一个基于Ranking的泊松矩阵分解兴趣点推荐算法.首先,根据LBSN中用户的签到行为特点,利用泊松分布模型替代高斯分布模型建模用户在兴趣点上签到行为;然后采用BPR(Bayesian personalized ranking)标准优化泊松矩阵分解的损失函数,拟合用户在兴趣点对上的偏序关系;最后,利用包含地域影响力的正则化因子约束泊松矩阵分解的过程.在真实数据集上的实验结果表明:基于Ranking的泊松矩阵分解兴趣点推荐算法的性能优于传统的兴趣点推荐算法.
文摘兴趣点推荐是在基于位置社会网络(location-based social network,LBSN)中流行起来的一种全新形式的推荐.利用LBSN所包含的丰富信息进行个性化推荐能有效增强用户体验和提高用户对LBSN的依赖度.针对无显示用户偏好、兴趣非一致性和数据稀疏性等挑战性问题,研究一种针对LBSN的双重细粒度POI推荐策略,即一方面将用户的全部历史签到信息以小时为单位细分为24个时间段,另一方面将每个POI细分为多个潜在主题及其分布,同时利用用户的历史签到信息和评论信息挖掘出用户在不同时间段的主题偏好,以实现POI的Top-N推荐.为实现该推荐思路,首先,根据用户的评论信息,运用LDA模型提取出每个POI的主题分布;然后,对于每个用户,将其签到信息划分到24个时间段中,通过连接相应的POI主题分布映射出用户在不同时间段对每个主题的兴趣偏好.为解决数据稀疏问题,运用高阶奇异值分解算法对用户-主题-时间三阶张量进行分解,获取用户在每个时间段对每个主题更为准确的兴趣评分.在真实数据集上进行了性能测试,结果表明所提出的推荐策略具有较好的推荐效果.
文摘兴趣点(Point-Of-Interest,POI)推荐是基于位置社交网络(Location-Based Social Network,LBSN)中一项重要的个性化服务,可以帮助用户发现其感兴趣的POI,提高信息服务质量。针对POI推荐中存在的数据稀疏性问题,提出一种融合社交关系和局部地理因素的POI推荐算法。根据社交关系中用户间的共同签到和距离关系度量用户相似性,并基于用户的协同过滤方法构建社交影响模型。为每个用户划分一个局部活动区域,通过对区域内POIs间的签到相关性分析,建立局部地理因素影响模型。基于加权矩阵分解挖掘用户自身偏好,并融合社交关系和局部地理因素进行POI推荐。实验表明,所提出的POI推荐算法相比其他方法具有更高的准确率和召回率,能够有效缓解数据稀疏性问题,提高推荐质量。
文摘兴趣点(point-of-interest,POI)推荐是基于位置的社交网络(location-based social networks,LBSN)中一项重要的服务。针对目前推荐算法存在的噪声数据影响推荐质量、用户个性化程度低的问题,提出了一种个性化联合推荐算法。提出了引入POI的位置因素去除不可能或可能性较小的POI,形成初步候选集;综合考虑POI的类别、流行度及用户的社会行为,增加用户个性化的程度,提高推荐结果的质量。在Foursquare真实签到数据集上的实验证明了提出的联合推荐算法与目前先进的算法相比,准确率提高11%,召回率提高8%。
文摘在基于位置的社交网络中,兴趣点实时推荐数据和用户签到数据存在高稀疏性问题。提出一种基于时间效应的混合推荐模型。通过用户潜在兴趣点数据模型计算用户时间行为影响分数和地理位置影响分数,并用线性统一模型进行处理,选取Top S 个兴趣点作为用户的潜在兴趣点。将用户的潜在签到记录引入基于时间效应的矩阵分解模型中,考虑时间差异性和连续性对推荐结果的影响,在此基础上进行优化求解,提出推荐策略。实验结果表明,与LRT模型、UTE+SE模型相比,该模型的推荐效果较好,其准确率和召回率最高可达0.103 4和0.111 8。
文摘With the booming of the Internet of Things(Io T)and the speedy advancement of Location-Based Social Networks(LBSNs),Point-Of-Interest(POI)recommendation has become a vital strategy for supporting people’s ability to mine their POIs.However,classical recommendation models,such as collaborative filtering,are not effective for structuring POI recommendations due to the sparseness of user check-ins.Furthermore,LBSN recommendations are distinct from other recommendation scenarios.With respect to user data,a user’s check-in record sequence requires rich social and geographic information.In this paper,we propose two different neural-network models,structural deep network Graph embedding Neural-network Recommendation system(SG-Neu Rec)and Deepwalk on Graph Neural-network Recommendation system(DG-Neu Rec)to improve POI recommendation.combined with embedding representation from social and geographical graph information(called SG-Neu Rec and DG-Neu Rec).Our model naturally combines the embedding representations of social and geographical graph information with user-POI interaction representation and captures the potential user-POI interactions under the framework of the neural network.Finally,we compare the performances of these two models and analyze the reasons for their differences.Results from comprehensive experiments on two real LBSNs datasets indicate the effective performance of our model.
