Health-guided recipe recommendation over knowledge graphs

While the availability of large-scale online recipe collections presents opportunities for health consumers to access a wide variety of recipes, it can be challenging for them to discover relevant recipes. Whereas most recommender systems are designed to offer selections consistent with users’ past behavior, it remains an open problem to offer selections that can help users’ transition from one type of behavior to another, intentionally. In this paper, we introduce health-guided recipe recommendation as a way to incrementally shift users towards healthier recipe options while respecting the preferences reflected in their past choices. Introducing a knowledge graph (KG) into recommender systems as side information has attracted great interest, but its use in recipe recommendation has not been studied. To fill this gap, we consider the task of recipe recommendation over knowledge graphs. In particular, we jointly learn recipe representations via graph neural networks over two graphs extracted from a large-scale Food KG, which capture different semantic relationships, namely, user preferences and recipe healthiness, respectively. To integrate the nutritional aspects into recipe representations and the recommendation task, instead of simple fusion, we utilize a knowledge transfer scheme to enable the transfer of useful semantic information across the preferences and healthiness aspects. Experimental results on two large real-world recipe datasets showcase our model’s ability to recommend tasty as well as healthy recipes to users.     

LaSER: Language-specific event recommendation

While societal events often impact people worldwide, a significant fraction of events has a local focus that primarily affects specific language communities. Examples include national elections, the development of the Coronavirus pandemic in different countries, and local film festivals such as the César Awards in France and the Moscow International Film Festival in Russia. However, existing entity recommendation approaches do not sufficiently address the language context of recommendation. This article introduces the novel task of language-specific event recommendation, which aims to recommend events relevant to the user query in the language-specific context. This task can support essential information retrieval activities, including web navigation and exploratory search, considering the language context of user information needs. We propose LaSER, a novel approach toward language-specific event recommendation. LaSER blends the language-specific latent representations (embeddings) of entities and events and spatio-temporal event features in a learning to rank model. This model is trained on publicly available Wikipedia Clickstream data. The results of our user study demonstrate that LaSER outperforms state-of-the-art recommendation baselines by up to 33 percentage points in MAP@5 concerning the language-specific relevance of recommended events.     

异质信息网络高阶层次化嵌入学习与推荐预测

异质信息网络是一种异质数据表示形式,如何融合异质数据复杂语义信息,是推荐系统面临的挑战之一.利用弱关系具有的丰富语义和信息传递能力,构建一种面向推荐系统的异质信息网络高阶嵌入学习框架,主要包括:初始化信息嵌入、高阶信息嵌入聚合与推荐预测3个模块.初始化信息嵌入模块首先采用基于弱关系的异质信息网络最佳信任路径筛选算法,有效地避免在全关系异质信息网络中,采样固定数量邻居造成的信息损失,其次利用新定义的基于多头图注意力的多任务共享特征重要性度量因子,筛选出节点的语义信息,并结合交互结构,有效地表征网络节点;高阶信息嵌入聚合模块通过融入弱关系及网络嵌入对知识良好的表征能力,实现高阶信息表达,并利用异质信息网络的层级传播机制,将被采样节点的特征聚合到待预测节点;推荐预测模块利用高阶信息的影响力推荐方法,实现了推荐任务.该框架具有嵌入节点类型丰富、融合共享属性和隐式交互信息等特点.最后,实验验证UI-HEHo学习框架可有效地改善评级预测的准确性,以及推荐生成的针对性、新颖性和多样性,尤其是在数据稀疏的应用场景中,具有良好的推荐效果.     

开启联邦学习的个性化时代：隐私、安全与效率的平衡探索

人工智能为公共和国防安全的发展和应用提供了巨大的机遇,然而国防安全数据包含了敏感的军事、情报和战略信息,一旦泄露或被滥用,可能对国家安全造成严重威胁,如何确保国防安全数据的隐私保护成为一项重要挑战。个性化联邦学习是近年来发展起来的一种新型的机器学习方法,它旨在通过将分布式的数据在本地进行训练和更新,从而实现在保护数据隐私的前提下提高本地模型的准确性和鲁棒性。与传统的中心化机器学习方法不同,个性化联邦学习允许不同数据拥有者之间共享模型的信息,而不是数据本身。这种方法已经在医疗、金融、物联网等领域得到了广泛的应用。本文从全局模型个性化和本地模型个性化两个方面分别介绍了个性化联邦学习的基本原理以及研究现状,总结了各个方法的优缺点,并讨论了现有方法的评价指标和常用数据集,最后展望了它在未来的发展前景。     

融合用户信任度的概率矩阵分解群组推荐算法

利用推荐系统进行群组推荐时,群组成员之间的交互关系对推荐结果有很大影响,但传统的群组推荐算法较少考虑用户信任度的重要性,致使社交关系信息不能得到充分利用。在群组融合时考虑群组内用户间的交互关系,提出一种基于用户信任度和概率矩阵的群组推荐算法。在获取用户信任度数据后,使用概率矩阵分解（PMF）算法补全信任度矩阵并进行归一化处理,得到相似度矩阵,同时在后验概率计算过程中加入用户间的信任度因素,通过极大化后验概率获得预测评分。在此基础上,对群组中用户的权重进行归一化处理,使用基于用户交互关系的权重策略融合群组成员偏好,得到最终的推荐结果。在Epinions和FilmTrust数据集上的实验结果表明,该算法可使融合结果更具群组特性,同时提高推荐结果的可靠性和可解释性,且均方根误差和命中率均优于PMF、NeuMF、RippleNet等对比算法。     

Personalized Cancer Immunotherapy via Transporting Endogenous Tumor Antigens to Lymph Nodes Mediated by Nano Fe3O4

While immunotherapy has a tremendous clinical potential to combat cancer, immune responses generated by conventional cancer immunotherapy remain not enough to completely eliminate tumors, mainly due to the tumor's immunosuppressive microenvironment and heterogeneity of tumor immunogenicity. To improve antitumor immune responses and realize personalized immunotherapy, in this report, endogenous tumor antigens (ETAs) that dynamically present on tumor cells are transported to lymph nodes (LNs). Based on the hypothesis that nano Fe₃O₄ (≈10 nm) could serve as the nanocarrier for transporting ETAs from the tumor to LNs, we wondrously find that Fe₃O₄ has a tremendous potential to improve cancer immunotherapy, because of its excellent protein‐captured efficiency and LNs‐targeted ability. To ensure the optimal ETAs‐bound efficiency of Fe₃O₄, a core–shell formulation (denoted as Ce6/Fe₃O₄‐L) is developed and specific release of Fe₃O₄ in tumor is enabled. These findings provide a simple and general strategy for boosting cytotoxic T‐cell response and realizing personalized cancer immunotherapy simultaneously.     

作业评价系统的研究与设计

作业评价作为课程评价的一个重要方面,反映了学生在学习过程中的发展情况.本文在分析过程性评价、多元化评价以及个性化反馈理念的基础上,设计了基于Web的作业评价与反馈系统.将作业展示在学习平台中,通过自评、互评、教评层层递进的形式对学习过程进行多元化的全面评价,针对互动评价过程进行个性化反馈和指导,引导学生自我反思,调动学生积极性,促进学生全面发展.     

一种基于领域本体的用户建模方法

针对当前大多数个性化服务系统的不足,以旅游领域为背景,提出了一种新的基于本体的用户模型构建方法,利用领域本体中的概念、实例和属性描述用户兴趣特征,实现了在语义层次上理解用户兴趣。实验表明,该方法能有效提高用户模型的质量。     

基于多代理的个性化推荐学习系统

针对现有学习系统存在信息过载、缺乏个性化服务能力、不能提供检索服务的问题,提出基于多代理构建个性化推荐学习系统。该系统利用JADE设计学习者Agent与推荐Agent,采用Lucene设计带有个性化能力的搜索引擎支持推荐,并融合3种推荐方法发挥多Agent间协商与协作的优势。实验结果表明,相比单一推荐方法,该系统具有较好的推荐效果和效率。