Cross-modal hashing has emerged as a pivotal solution for efficient retrieval across diverse modalities, such as images and texts, by mapping them into compact binary hash spaces. However, in real-world scenarios, the modalities data is often missing or misaligned. Existing methods are most rely on fully paired training data and ignore missing or misaligned modalities data, resulting in the semantic inconsistencies. To address these challenges, we propose an Adaptive Graph Attention-Based Discrete Hashing (AGADH) method, which consists of three parts. First, to solve the problem of missing modalities, AGADH employs a masked completion strategy to reconstruct missing modalities. Second, to mitigate semantic misalignment, AGADH leverages a Graph Attention Network (GAT) encoder-decoder architecture with alignment module to construct features from different modalities. Additionally, to enhance the fusion performance, an adaptive fusion module dynamically adjusting the contributions of image and text modalities with learnable weighting coefficients is proposed. Extensive experiments on three benchmark datasets, MS-COCO, NUS-WIDE, and MIRFlickr-25K, demonstrating that AGADH outperforms state-of-the-art methods in both fully paired and incompletely paired scenarios, showing its robustness and effectiveness in cross-modal retrieval tasks.

Knowledge Graphs (KGs) serve as valuable auxiliary information to improve the accuracy of recommendation systems. Previous methods have leveraged the knowledge graph to enhance item representation and thus achieve excellent performance. However, these approaches heavily rely on high-quality knowledge graphs and learn enhanced representations with the assistance of carefully designed triplets. Furthermore, the emergence of knowledge graphs has led to models that ignore the inherent relationships between items and entities. To address these challenges, we propose a Self-Derived Knowledge Graph Contrastive Learning framework (CL-SDKG) to enhance recommendation systems. Specifically, we employ the variational graph reconstruction technique to estimate the Gaussian distribution of user-item nodes corresponding to the graph neural network aggregation layer. This process generates multiple KGs, referred to as self-derived KGs. The self-derived KG acquires more robust perceptual representations through the consistency of the estimated structure. Besides, the self-derived KG allows models to focus on user-item interactions and reduce the negative impact of miscellaneous dependencies introduced by conventional KGs. Finally, we apply contrastive learning to the self-derived KG to further improve the robustness of CL-SDKG through the traditional KG contrast-enhanced process. We conducted comprehensive experiments on three public datasets, and the results demonstrate that our CL-SDKG outperforms state-of-the-art baselines.

Location factor of recommender systems has been extensively studied in the past decade. However, there is no research thoroughly analyzing location’s role in news recommendation. In this paper, a comprehensive exploration on role of location in news recommendation is presented. First of all, based on analysis of real news datasets, we find that news recommendation differs from spatial item recommendation. Location affects news consumption behaviors of users with two-fold aspects including geographic feature and semantic feature. Regarding geographic feature, location influences news recommendation according to region rather than latitude-longitude level. Furthermore, interesting news topics are also impacted by semantic feature of location. Semantic feature may play a more positive role than geographic feature. The novel findings consistently manifest that, as non-spatial items, news differ from spatial items in that location influences users' selection in terms of different pattern and degree. In summary, geographic and semantic features influence reading preference through mapping locations into special topics. Changing of location topics leads to varying of reading preference. The news datasets in this paper belong to check in data. NewsREEL dataset is from a company, and it is provided by German researcher. The location data in Twitter dataset is also check in data. NetEase news dataset are collected from NetEase news websites, and the type of location data is city or region.

Machine Learning technologies have obtained breakthrough in various fields, and medical information extraction has also successfully made great progress through deep learning methods. However, entity relationship overlap is a key issue and challenge in the field of medical entity relationship extraction. Hence, we propose an intelligent extraction method for Chinese medicine entity relationship through improving graph neural network and structure optimization strategy. We optimize model structure and introduce global pointer network. The sentence feature information is captured by attention mechanism and Bi-LSTM. Grammatical relations between entities are parsed using GCN layer. Finally, multiple decoders are used for joint extraction of entity relations through the global pointer network. The model learns the graph structure data by GCN, while the challenge of entity relationship overlap is solved through using the pointer network. The experiments demonstrate that the model achieves 83.77% in terms of F1 value, which is better than other baseline models.

Event recommendation is an essential means to enable people to find attractive upcoming social events, such as party, exhibition, and concert. While growing line of research has focused on suggesting events to individuals, making event recommendation for a group of users has not been well studied. In this paper, we aim to recommend upcoming events for a group of users. We formalize group recommendation as a ranking problem and propose a group event recommendation framework GERF based on learning-to-rank technique. Specifically, we first analyze different contextual influences on user's event attendance, and extract preference of user to event considering each contextual influence. Then, the preference scores of the users in a group are taken as the features for learningto-rank to model the preference of the group. Moreover, a fast pairwise learning-to-rank algorithm, Bayesian group ranking, is proposed to learn ranking model for each group. Our framework is easily to incorporate additional contextual influences, and can be applied to other group recommendation scenarios. Extensive experiments have been conducted to evaluate the performance of GERF on two real-world datasets and demonstrate the appealing performance of our method on both accuracy and time efficiency.

News recommendation has become an essential way to help readers discover interesting stories. While a growing line of research has focused on modeling reading preferences for news recommendation, they neglect the instability of reader consumption behaviors, i.e., consumption behaviors of readers may be influenced by other factors in addition to user interests, which degrades the recommendation effectiveness of existing methods. In this article, we propose a probabilistic generative model, BoRe, where user interests and crowd effects are used to adapt to the instability of reader consumption behaviors, and reading sequences are utilized to adapt user interests evolving over time. Further, the extreme sparsity problem in the domain of news severely hinders accurately modeling user interests and reading sequences, which discounts BoRe’s ability to adapt to the instability. Accordingly, we leverage domain-specific features to model user interests in the situation of extreme sparsity. Meanwhile, we consider groups of users instead of individuals to capture reading sequences. Besides, we study how to reduce the computation to allow online application. Extensive experiments have been conducted to evaluate the effectiveness and efficiency of BoRe on real-world datasets. The experimental results show the superiority of BoRe, compared with the state-of-the-art competing methods.

There are rich data resources residing in available materials websites, and most of these data resources are shown in the form of HTML tables. However, it is difficult to distinguish the attributes and values because of the semi-structured feature of HTML tables. Therefore, identifying attributes in HTML tables is the key issue for the information acquisition. In this paper, based on sibling comparison, a method for materials knowledge extraction from HTML tables is proposed, which consists of three steps: acquiring sibling tables, identifying table pattern and extracting table data. We show how to use [Formula: see text]-measure to find the appropriate thresholds for matching of tables from materials websites when acquiring sibling tables. Further, we propose a strategy named FRFC (i.e. the First Row matching and First Column matching) to distinguish attributes and values, so that table pattern is identified. Moreover, the data from HTML tables is extracted based on their corresponding table patterns and mapped to a predefined schema, which will facilitate the population to materials ontology. The proposed approach is applicable to circumstances, where an attribute in the table may span multiple cells and matched attributes in sibling tables are more. We acquire desired accuracy ([Formula: see text]%) through using FRFC for identifying table pattern. The time about extraction may not increase significantly with increasing number of documents and cells in tables, so our approach is effective to process a large number of documents. A prototype named MTES is developed and demonstrates the effectiveness of our proposed approach.