Reinforcement learning-based knowledge graph reasoning requires complex logical reasoning based on given query relations. Existing methods rely exclusively on delayed reward signals to train the model to perceive the logical reasonableness of the whole reasoning path. This paradigm cannot recognize the logical reasonableness of intermediate reasoning actions, thereby limiting its performance. The logical reasonableness of the same reasoning action changes under different reasoning histories, which makes it difficult for the model to perceive the logical reasonableness of reasoning actions. This paper proposes a Dynamic Logic Alignment-based knowledge graph reasoning method (DLA). DLA dynamically combines the reasoning history and actions, and aligns its logical meaning with the query relation to assess the reasonableness of actions. Firstly, considering that actions have different logical meanings under different history paths, we design a reasoning history-aware dynamic action enhancement mechanism. The mechanism enhances the representation of the current action by injecting the logical composition of history and action at each time step. Secondly, considering that logical composition can provide the reasoning basis for the reinforcement learning agent, we design a query enhancement mechanism for logical composition alignment. The mechanism selects the action with high reasonableness by aligning the logical composition and query relation. Our method has been evaluated on five datasets of different scales, and the experimental results reveal that our method outperforms existing methods.

Online reviews allow consumers to provide detailed feedback on various aspects of items. Existing methods utilize these aspects to model users' fine-grained preferences for specific item features through graph neural networks. We argue that the performance of items on different aspects is important for making precise recommendations, which has not been taken into account by existing approaches, due to lack of data. In this paper, we propose an aspect performance-aware hypergraph neural network (APH) for the review-based recommendation, which learns the performance of items from the conflicting sentiment polarity of user reviews. Specifically, APH comprehensively models the relationships among users, items, aspects, and sentiment polarity by systematically constructing an aspect hypergraph based on user reviews. In addition, APH aggregates aspects representing users and items by employing an aspect performance-aware hypergraph aggregation method. It aggregates the sentiment polarities from multiple users by jointly considering user preferences and the semantics of their sentiments, determining the weights of sentiment polarities to infer the performance of items on various aspects. Such performances are then used as weights to aggregate neighboring aspects. Experiments on six real-world datasets demonstrate that APH improves MSE, Precision@5, and Recall@5 by an average of 2.30%, 4.89%, and 1.60% over the best baseline. The source code and data are available at https://github.com/dianziliu/APH.

Reviews are valuable resources that have been widely researched and used to improve the quality of recommendation services. Recent methods use multiple full embedding layers to model various levels of individual preferences, increasing the risk of the data sparsity issue. Although it is a potential way to deal with this issue that models homophily among users who have similar behaviors, the existing approaches are implemented in a coarse-grained way. They calculate user similarities by considering the homophily in their global behaviors but ignore their local behaviors under a specific context. In this paper, we propose a two-tier shared embedding model (TSE), which fuses coarse- and fine-grained ways of modeling homophily. It considers global behaviors to model homophily in a coarse-grained way, and the high-level feature in the process of each user-item interaction to model homophily in a fine-grained way. TSE designs a whole-to-part principle-based process to fuse these ways in the review-based recommendation. Experiments on five real-world datasets demonstrate that TSE significantly outperforms state-of-the-art models. It outperforms the best baseline by 20.50% on the root-mean-square error (RMSE) and 23.96% on the mean absolute error (MAE), respectively. The source code is available at https://github.com/dianziliu/TSE.git.

Partial label learning (PLL) aims to learn a robust multi-class classifier from the ambiguous data, where each instance is given with several candidate labels, among which only one label is real. Most existing methods usually cope with such problem by utilizing a feature similarity graph to conduct label disambiguation. However, these methods construct the feature graph by only employing original features, while the influences of latent outliers and the contributions of label space are regrettably ignored. To tackle these issues, in this article, we propose aPrior KnOwledge ConsTrainedAdaptiveGraph FramEwork (POTAGE) for partial label learning, which utilizes an adaptive graph fused with label information to accurately describe the instance relationship and guide the desired model training. Compared with the feature-induced fixed graph, the adaptive graph is deemed to be more robust and accurate to reveal the intrinsic manifold structure within the data, and the embedding label information is expected to effectively alleviate the label ambiguities and enlarge the gap of label confidences between two instances from different classes. Extensive experiments demonstrate that POTAGE achieves state-of-the-art performance.

Social media has become a part of our daily life and we use it for many reasons. One of its uses is to get our questions answered. Given a multitude of social media sites, however, one immediate challenge is to pick the most relevant site for a question. This is a challenging problem because (1) questions are usually short, and (2) social media sites evolve. In this work, we propose to utilize topic specialization to find the most relevant social media site for a given question. In particular, semantic knowledge is considered for topic specialization as it can not only make a question more specific, but also dynamically represent the content of social sites, which relates a given question to a social media site. Thus, we propose to rank social media sites based on combined search engine query results. Our algorithm yields compelling results for providing a meaningful and consistent site recommendation. This work helps further understand the innate characteristics of major social media platforms for the design of social Q&A systems.