摘要
节点排序任务在社交网络与科研合作等领域的应用愈加广泛,准确评估网络节点重要性的课题备受关注。然而,合作网络通常存在大量噪声、不完整信息以及动态变化,传统节点排序方法往往难以取得令人满意的结果。为此,提出一种基于深度主动学习的方法进行科研合作网络中节点的排序。该方法结合深度学习的优势以及主动学习的查询策略,能够在数据标签稀缺和噪声干扰较大的情况下自适应地根据网络中节点的重要性进行排序。具体而言,首先利用深度学习模型从节点的多模态特征中进行表示学习,将节点表示与其重要性相结合,形成一个综合排序指标;然后通过主动学习方法选择对排序结果具有较大影响的节点进行标注,从而逐步优化排序模型。在真实的科研合作网络数据集上进行验证实验,发现与传统排序方法相比,基于深度主动学习的方法在节点排序准确性和稳定性方面有显著提升。
The application of node sorting tasks in social networks and scientific research cooperation is becoming increasingly widespread,and the issue of accurately evaluating the importance of network nodes has attracted much attention.However,cooperative networks often con-tain a large amount of noise,incomplete information,and dynamic changes,and traditional sorting methods often find it difficult to achieve satisfactory results.To this end,a method based on deep active learning is proposed for sorting nodes in scientific research collaboration net-works.This method combines the advantages of deep learning and the query strategy of active learning,and can adaptively sort nodes based on their importance in the network when data labels are scarce and noise interference is high.First utilizes deep learning models to learn represen-tations from the multimodal features of nodes,combining node representations with their importance to form a comprehensive ranking index;Then,active learning methods are used to select nodes that have a significant impact on the ranking results for annotation,gradually optimiz-ing the ranking model.Validation experiments were conducted on real research collaboration network datasets,and it was found that compared with traditional sorting methods,deep active learning based methods have significantly improved accuracy and stability in node sorting.
作者
刘臣
宋雪
LIU Chen;SONG Xue(School of Business,University of Shanghai for Science and Technology,Shanghai 200093,China)
出处
《软件导刊》
2024年第4期186-192,共7页
Software Guide
基金
上海市哲学社会科学规划课题(2021BTQ003)。
关键词
科研合作网络
深度主动学习
学习排序
置信度
scientific collaboration network
deep active learning
learning rank
confidence
