24 December 2020 in IEEE Access
Graph embedding aims to represent node structural as well as attribute information into a low-dimensional vector space so that some downstream application tasks such as node classification, link prediction, community detection, and recommendation can be easily performed by using simple machine learning algorithms. The graph convolutional network is a neural network framework for machine learning on graphs. Because of its powerful ability to model graph data, it is currently the best choice for graph embedding. However, most existing graph convolutional network-based embedding algorithms not only ignore the data distribution of the latent codes but also lose the high-order proximity between nodes in a graph, leading to inferior embedding. To mitigate this problem, we investigate how to enforce latent codes to match a prior distribution, and we introduce random walk to preserve high-order proximity in a graph. In this paper, we propose a novel graph embedding framework, Adversarial and Random Walk Regularized Graph Embedding (ARWR-GE), which jointly preserves structural and attribute information. ARWR-GE adopts an adversarial training scheme to enforce the latent codes to match a prior distribution, and by employing the skip-gram model, nodes in a random walk sequence are closer in the latent space. We evaluate our proposed framework by using three real-world datasets on link prediction, graph clustering, and visualization tasks. The results demonstrate that our framework achieves better performance than state-of-the-art graph embedding algorithms.
28 April 2022 in World Wide Web
4 July 2024 in IEEE Transactions on Consumer Electronics
Smart applications are essential in intelligent consumer electronics. With the rising focus on health concerns, self-diagnosis applications on smart devices have gained widespread popularity, attracting significant attention from both consumers and researchers. These applications play a crucial role in accurately predicting potential diseases based on user-provided symptom descriptions, thereby facilitating effective treatment. Distinguishing between diseases with similar symptoms yet requiring different treatments is essential. However, automated ICD coding faces challenges due to subtle differences between some ICD codes. Although existing methods has utilized contrastive learning to differentiate between codes, precise selection of high-quality negative samples and accurate matching of code descriptions with patient conditions remain critical factors influencing their performance. Drawing inspiration from medical practices, doctors tend to utilize back-reference knowledge to differentiate between similar diseases. We propose a novel framework for automated ICD coding via contrastive learning with back-reference and synonym knowledge (BRSK) for smart self-diagnosis applications. Specifically, by incorporating back-reference knowledge, we generate challenging negative samples, enhancing the effectiveness of contrastive learning. Additionally, multi-view synonym matching networks are used to fully leverage synonym knowledge, resulting in more precise modeling of semantic matching between codes and patient descriptions. Extensive experiments on MIMIC-III datasets demonstrate that BRSK significantly outperforms state-of-the-art baselines.
1 January 2021 in Computational Intelligence and Neuroscience
In recent years, due to the rise of online social platforms, social networks have more and more influence on our daily life, and social recommendation system has become one of the important research directions of recommendation system research. Because the graph structure in social networks and graph neural networks has strong representation capabilities, the application of graph neural networks in social recommendation systems has become more and more extensive, and it has also shown good results. Although graph neural networks have been successfully applied in social recommendation systems, their performance may still be limited in practical applications. The main reason is that they can only take advantage of pairs of user relations but cannot capture the higher‐order relations between users. We propose a model that applies the hypergraph attention network to the social recommendation system (HASRE) to solve this problem. Specifically, we take the hypergraph’s ability to model high‐order relations to capture high‐order relations between users. However, because the influence of the users’ friends is different, we use the graph attention mechanism to capture the users’ attention to different friends and adaptively model selection information for the user. In order to verify the performance of the recommendation system, this paper carries out analysis experiments on three data sets related to the recommendation system. The experimental results show that HASRE outperforms the state‐of‐the‐art method and can effectively improve the accuracy of recommendation.
30 April 2025 in IEEE Transactions on Multimedia
Multi-modal hashing achieves low storage costs and high retrieval speeds by using compact hash codes to represent complex and heterogeneous multi-modal data, effectively addressing the inefficiency and resource intensiveness challenges faced by the traditional multi-modal retrieval methods. However, balancing intraclass compactness and interclass separability remains a struggle in existing works due to coarse-grained feature limitations, simplified fusion strategies that overlook semantic complementarity, and neglect of the structural information within the multi-modal data. To address these limitations comprehensively, we propose a Proto-centric Multi-modal Hashing with Pronounced Category Differences (PMH-PCD) model. Specifically, PMH-PCD first learns modality-specific prototypes by deeply exploring within-modality class information, ensuring effective fusion of each modality's unique characteristics. Furthermore, it learns multi-modal integrated class prototypes that seamlessly incorporate semantic information across modalities to effectively capture and represent the intricate relationships and complementary semantic content embedded within the multi-modal data. Additionally, to generate more discriminative and representative binary hash codes, PMH-PCD integrates multifaceted semantic information, encompassing both low-level pairwise relations and high-level structural patterns, holistically capturing intricate data details and leveraging underlying structures. The experimental results demonstrate that, compared with existing advanced methods, PMH-PCD achieves superior and consistent performances in multi-modal retrieval tasks. To promote further research and reproducibility, we have publicly released the source code of PMH-PCD at https://github.com/vindahi/PMH-PCD.