With the arrival of the big data era,the phenomenon of information overload is becoming increasingly severe.In response to the common issue of sparse user rating matrices in recommendation systems,a collaborative filt...With the arrival of the big data era,the phenomenon of information overload is becoming increasingly severe.In response to the common issue of sparse user rating matrices in recommendation systems,a collaborative filtering recommendation algorithm was proposed based on improved user profiles in this study.Firstly,a profile labeling system was constructed based on user characteristics.This study proposed that user profile labels should be created using basic user information and basic item information,in order to construct multidimensional user profiles.TF-IDF algorithm was used to determine the weights of user-item feature labels.Secondly,user similarity was calculated by weighting both profile-based collaborative filtering and user-based collaborative filtering algorithms,and the final user similarity was obtained by harmonizing these weights.Finally,personalized recommendations were generated using Top-N method.Validation with the MovieLens-1M dataset revealed that this algorithm enhances both recommendation Precision and Recall compared to single-method approaches(recommendation algorithm based on user portrait and user-based collaborative filtering algorithm).展开更多
Code review is an important process to reduce code defects and improve software quality. In social coding communities like GitHub, as everyone can submit Pull-Requests, code review plays a more important role than eve...Code review is an important process to reduce code defects and improve software quality. In social coding communities like GitHub, as everyone can submit Pull-Requests, code review plays a more important role than ever before, and the process is quite time-consuming. Therefore, finding and recommending proper reviewers for the emerging Pull-Requests becomes a vital task. However, most of the current studies mainly focus on recommending reviewers by checking whether they will participate or not without differentiating the participation types. In this paper, we develop a two-layer reviewer recommendation model to recommend reviewers for Pull-Requests （PRs） in GitHub projects from the technical and managerial perspectives. For the first layer, we recommend suitable developers to review the target PRs based on a hybrid recommendation method. For the second layer, after getting the recommendation results from the first layer, we specify whether the target developer will technically or managerially participate in the reviewing process. We conducted experiments on two popular projects in GitHub, and tested the approach using PRs created between February 2016 and February 2017. The results show that the first layer of our recommendation model performs better than the previous work, and the second layer can effectively differentiate the types of participation.展开更多
In order to improve our military ’s level of intelligent accusation decision-making in future intelligent joint warfare, this paper studies operation loop recommendation methods for kill web based on the fundamental ...In order to improve our military ’s level of intelligent accusation decision-making in future intelligent joint warfare, this paper studies operation loop recommendation methods for kill web based on the fundamental combat form of the future, i.e.,“web-based kill,” and the operation loop theory. Firstly, we pioneer the operation loop recommendation problem with operation ring quality as the objective and closed-loop time as the constraint, and construct the corresponding planning model.Secondly, considering the case where there are multiple decision objectives for the combat ring recommendation problem,we propose for the first time a multi-objective optimization algorithm, the multi-objective ant colony evolutionary algorithm based on decomposition(MOACEA/D), which integrates the multi-objective evolutionary algorithm based on decomposition(MOEA/D) with the ant colony algorithm. The MOACEA/D can converge the optimal solutions of multiple single objectives nondominated solution set for the multi-objective problem. Finally,compared with other classical multi-objective optimization algorithms, the MOACEA/D is superior to other algorithms superior in terms of the hyper volume(HV), which verifies the effectiveness of the method and greatly improves the quality and efficiency of commanders’ decision-making.展开更多
The cloud computing has been growing over the past few years, and service providers are creating an intense competitive world of business. This proliferation makes it hard for new users to select a proper service amon...The cloud computing has been growing over the past few years, and service providers are creating an intense competitive world of business. This proliferation makes it hard for new users to select a proper service among a large amount of service candidates. A novel user preferences-aware recommendation approach for trustworthy services is presented. For describing the requirements of new users in different application scenarios, user preferences are identified by usage preference, trust preference and cost preference. According to the similarity analysis of usage preference between consumers and new users, the candidates are selected, and these data about service trust provided by them are calculated as the fuzzy comprehensive evaluations. In accordance with the trust and cost preferences of new users, the dynamic fuzzy clusters are generated based on the fuzzy similarity computation. Then, the most suitable services can be selected to recommend to new users. The experiments show that this approach is effective and feasible, and can improve the quality of services recommendation meeting the requirements of new users in different scenario.展开更多
Deep learning based recommendation methods, such as the recurrent neural network based recommendation method(RNNRec) and the gated recurrent unit(GRU) based recommendation method(GRURec), are proposed to solve the pro...Deep learning based recommendation methods, such as the recurrent neural network based recommendation method(RNNRec) and the gated recurrent unit(GRU) based recommendation method(GRURec), are proposed to solve the problem of time heterogeneous feedback recommendation. These methods out-perform several state-of-the-art methods. However, in RNNRec and GRURec, action vectors and item vectors are shared among users. The different meanings of the same action for different users are not considered. Similarly, different user preference for the same item is also ignored. To address this problem, the models of RNNRec and GRURec are modified in this paper. In the proposed methods, action vectors and item vectors are transformed into the user space for each user firstly, and then the transformed vectors are fed into the original neural networks of RNNRec and GRURec. The transformed action vectors and item vectors represent the user specified meaning of actions and the preference for items, which makes the proposed method obtain more accurate recommendation results. The experimental results on two real-life datasets indicate that the proposed method outperforms RNNRec and GRURec as well as other state-of-the-art approaches in most cases.展开更多
Attackers inject the designed adversarial sample into the target recommendation system to achieve illegal goals,seriously affecting the security and reliability of the recommendation system.It is difficult for attacke...Attackers inject the designed adversarial sample into the target recommendation system to achieve illegal goals,seriously affecting the security and reliability of the recommendation system.It is difficult for attackers to obtain detailed knowledge of the target model in actual scenarios,so using gradient optimization to generate adversarial samples in the local surrogate model has become an effective black‐box attack strategy.However,these methods suffer from gradients falling into local minima,limiting the transferability of the adversarial samples.This reduces the attack's effectiveness and often ignores the imperceptibility of the generated adversarial samples.To address these challenges,we propose a novel attack algorithm called PGMRS‐KL that combines pre‐gradient‐guided momentum gradient optimization strategy and fake user generation constrained by Kullback‐Leibler divergence.Specifically,the algorithm combines the accumulated gradient direction with the previous step's gradient direction to iteratively update the adversarial samples.It uses KL loss to minimize the distribution distance between fake and real user data,achieving high transferability and imperceptibility of the adversarial samples.Experimental results demonstrate the superiority of our approach over state‐of‐the‐art gradient‐based attack algorithms in terms of attack transferability and the generation of imperceptible fake user data.展开更多
随着互联网技术的发展以及社交网络的扩大,网络平台已经成为人们获取信息的一个重要途径。标签的引入提升了信息分类及检索效率。同时,标签推荐系统的出现不仅方便了用户输入标签,还提高了标签的质量。传统的标签推荐算法通常只考虑标...随着互联网技术的发展以及社交网络的扩大,网络平台已经成为人们获取信息的一个重要途径。标签的引入提升了信息分类及检索效率。同时,标签推荐系统的出现不仅方便了用户输入标签,还提高了标签的质量。传统的标签推荐算法通常只考虑标签和项目两个主体,而忽略了用户在选择标签时个人意图所起到的重要作用。由于在标签推荐系统中标签最终由用户确定,因此用户的偏好在标签推荐中起着关键作用。为此,引入用户作为主体,并结合用户发布的历史帖子的先后顺序,将标签推荐任务建模为更加符合真实场景的序列标签推荐任务。提出了一种基于MLP的序列标签推荐方法(MLP for Sequential Tag Recommendation, MLP4STR),该方法显式地建模用户偏好用于引导整体标签推荐。MLP4STR采用一种跨特征对齐的MLP序列特征提取框架,将文本和标签的特征对齐,获取用户的历史帖子信息和历史标签信息中隐含的用户动态兴趣。最后,结合帖子内容和用户偏好进行标签推荐。在4个真实世界的数据集上得到的实验结果表明,MLP4STR能够有效地学习序列标签推荐中的用户历史行为序列的信息,其中,评价指标F1@5较最优的对比算法有显著提升。展开更多
文摘With the arrival of the big data era,the phenomenon of information overload is becoming increasingly severe.In response to the common issue of sparse user rating matrices in recommendation systems,a collaborative filtering recommendation algorithm was proposed based on improved user profiles in this study.Firstly,a profile labeling system was constructed based on user characteristics.This study proposed that user profile labels should be created using basic user information and basic item information,in order to construct multidimensional user profiles.TF-IDF algorithm was used to determine the weights of user-item feature labels.Secondly,user similarity was calculated by weighting both profile-based collaborative filtering and user-based collaborative filtering algorithms,and the final user similarity was obtained by harmonizing these weights.Finally,personalized recommendations were generated using Top-N method.Validation with the MovieLens-1M dataset revealed that this algorithm enhances both recommendation Precision and Recall compared to single-method approaches(recommendation algorithm based on user portrait and user-based collaborative filtering algorithm).
基金Project(2016-YFB1000805)supported by the National Grand R&D Plan,ChinaProjects(61502512,61432020,61472430,61532004)supported by the National Natural Science Foundation of China
文摘Code review is an important process to reduce code defects and improve software quality. In social coding communities like GitHub, as everyone can submit Pull-Requests, code review plays a more important role than ever before, and the process is quite time-consuming. Therefore, finding and recommending proper reviewers for the emerging Pull-Requests becomes a vital task. However, most of the current studies mainly focus on recommending reviewers by checking whether they will participate or not without differentiating the participation types. In this paper, we develop a two-layer reviewer recommendation model to recommend reviewers for Pull-Requests （PRs） in GitHub projects from the technical and managerial perspectives. For the first layer, we recommend suitable developers to review the target PRs based on a hybrid recommendation method. For the second layer, after getting the recommendation results from the first layer, we specify whether the target developer will technically or managerially participate in the reviewing process. We conducted experiments on two popular projects in GitHub, and tested the approach using PRs created between February 2016 and February 2017. The results show that the first layer of our recommendation model performs better than the previous work, and the second layer can effectively differentiate the types of participation.
基金supported by the National Natural Science Foundation of China (72071206,71690233)the Science and Technology Innovation Program of Hunan Province (2020RC4046)。
文摘In order to improve our military ’s level of intelligent accusation decision-making in future intelligent joint warfare, this paper studies operation loop recommendation methods for kill web based on the fundamental combat form of the future, i.e.,“web-based kill,” and the operation loop theory. Firstly, we pioneer the operation loop recommendation problem with operation ring quality as the objective and closed-loop time as the constraint, and construct the corresponding planning model.Secondly, considering the case where there are multiple decision objectives for the combat ring recommendation problem,we propose for the first time a multi-objective optimization algorithm, the multi-objective ant colony evolutionary algorithm based on decomposition(MOACEA/D), which integrates the multi-objective evolutionary algorithm based on decomposition(MOEA/D) with the ant colony algorithm. The MOACEA/D can converge the optimal solutions of multiple single objectives nondominated solution set for the multi-objective problem. Finally,compared with other classical multi-objective optimization algorithms, the MOACEA/D is superior to other algorithms superior in terms of the hyper volume(HV), which verifies the effectiveness of the method and greatly improves the quality and efficiency of commanders’ decision-making.
基金Project(61272148) supported by the National Natural Science Foundation of ChinaProject(2014FJ3122) supported by the Science and Technology Project of Hunan Province,China
文摘The cloud computing has been growing over the past few years, and service providers are creating an intense competitive world of business. This proliferation makes it hard for new users to select a proper service among a large amount of service candidates. A novel user preferences-aware recommendation approach for trustworthy services is presented. For describing the requirements of new users in different application scenarios, user preferences are identified by usage preference, trust preference and cost preference. According to the similarity analysis of usage preference between consumers and new users, the candidates are selected, and these data about service trust provided by them are calculated as the fuzzy comprehensive evaluations. In accordance with the trust and cost preferences of new users, the dynamic fuzzy clusters are generated based on the fuzzy similarity computation. Then, the most suitable services can be selected to recommend to new users. The experiments show that this approach is effective and feasible, and can improve the quality of services recommendation meeting the requirements of new users in different scenario.
基金supported by the National Natural Science Foundation of China(61403350)。
文摘Deep learning based recommendation methods, such as the recurrent neural network based recommendation method(RNNRec) and the gated recurrent unit(GRU) based recommendation method(GRURec), are proposed to solve the problem of time heterogeneous feedback recommendation. These methods out-perform several state-of-the-art methods. However, in RNNRec and GRURec, action vectors and item vectors are shared among users. The different meanings of the same action for different users are not considered. Similarly, different user preference for the same item is also ignored. To address this problem, the models of RNNRec and GRURec are modified in this paper. In the proposed methods, action vectors and item vectors are transformed into the user space for each user firstly, and then the transformed vectors are fed into the original neural networks of RNNRec and GRURec. The transformed action vectors and item vectors represent the user specified meaning of actions and the preference for items, which makes the proposed method obtain more accurate recommendation results. The experimental results on two real-life datasets indicate that the proposed method outperforms RNNRec and GRURec as well as other state-of-the-art approaches in most cases.
基金The National Natural Science Foundation of China (61876001)Opening Foundation of State Key Laboratory of Cognitive Intelligence,Opening Foundation of State Key Laboratory of Cognitive Intelligence(iED2022-006)Scientific Research Planning Project of Anhui Province (2022AH050072)
文摘Attackers inject the designed adversarial sample into the target recommendation system to achieve illegal goals,seriously affecting the security and reliability of the recommendation system.It is difficult for attackers to obtain detailed knowledge of the target model in actual scenarios,so using gradient optimization to generate adversarial samples in the local surrogate model has become an effective black‐box attack strategy.However,these methods suffer from gradients falling into local minima,limiting the transferability of the adversarial samples.This reduces the attack's effectiveness and often ignores the imperceptibility of the generated adversarial samples.To address these challenges,we propose a novel attack algorithm called PGMRS‐KL that combines pre‐gradient‐guided momentum gradient optimization strategy and fake user generation constrained by Kullback‐Leibler divergence.Specifically,the algorithm combines the accumulated gradient direction with the previous step's gradient direction to iteratively update the adversarial samples.It uses KL loss to minimize the distribution distance between fake and real user data,achieving high transferability and imperceptibility of the adversarial samples.Experimental results demonstrate the superiority of our approach over state‐of‐the‐art gradient‐based attack algorithms in terms of attack transferability and the generation of imperceptible fake user data.
文摘随着互联网技术的发展以及社交网络的扩大,网络平台已经成为人们获取信息的一个重要途径。标签的引入提升了信息分类及检索效率。同时,标签推荐系统的出现不仅方便了用户输入标签,还提高了标签的质量。传统的标签推荐算法通常只考虑标签和项目两个主体,而忽略了用户在选择标签时个人意图所起到的重要作用。由于在标签推荐系统中标签最终由用户确定,因此用户的偏好在标签推荐中起着关键作用。为此,引入用户作为主体,并结合用户发布的历史帖子的先后顺序,将标签推荐任务建模为更加符合真实场景的序列标签推荐任务。提出了一种基于MLP的序列标签推荐方法(MLP for Sequential Tag Recommendation, MLP4STR),该方法显式地建模用户偏好用于引导整体标签推荐。MLP4STR采用一种跨特征对齐的MLP序列特征提取框架,将文本和标签的特征对齐,获取用户的历史帖子信息和历史标签信息中隐含的用户动态兴趣。最后,结合帖子内容和用户偏好进行标签推荐。在4个真实世界的数据集上得到的实验结果表明,MLP4STR能够有效地学习序列标签推荐中的用户历史行为序列的信息,其中,评价指标F1@5较最优的对比算法有显著提升。
