A Collaborative Deep and Shallow Semisupervised Learning Framework for Mobile App Classification
المؤلفون المشاركون
Chen, Tieming
Lv, MingQi
Huang, Chao
Wang, Ting
المصدر
العدد
المجلد 2020، العدد 2020 (31 ديسمبر/كانون الأول 2020)، ص ص. 1-12، 12ص.
الناشر
Hindawi Publishing Corporation
تاريخ النشر
2020-02-14
دولة النشر
مصر
عدد الصفحات
12
التخصصات الرئيسية
الملخص EN
With the rapid growth of mobile Apps, it is necessary to classify the mobile Apps into predefined categories.
However, there are two problems that make this task challenging.
First, the name of a mobile App is usually short and ambiguous to reflect its real semantic meaning.
Second, it is usually difficult to collect adequate labeled samples to train a good classifier when a customized taxonomy of mobile Apps is required.
For the first problem, we leverage Web knowledge to enrich the textual information of mobile Apps.
For the second problem, the mostly utilized approach is the semisupervised learning, which exploits unlabeled samples in a cotraining scheme.
However, how to enhance the diversity between base learners to maximize the power of the cotraining scheme is still an open problem.
Aiming at this problem, we exploit totally different machine learning paradigms (i.e., shallow learning and deep learning) to ensure a greater degree of diversity.
To this end, this paper proposes Co-DSL, a collaborative deep and shallow semisupervised learning framework, for mobile App classification using only a few labeled samples and a large number of unlabeled samples.
The experiment results demonstrate the effectiveness of Co-DSL, which could achieve over 85% classification accuracy by using only two labeled samples from each mobile App category.
نمط استشهاد جمعية علماء النفس الأمريكية (APA)
Lv, MingQi& Huang, Chao& Chen, Tieming& Wang, Ting. 2020. A Collaborative Deep and Shallow Semisupervised Learning Framework for Mobile App Classification. Mobile Information Systems،Vol. 2020, no. 2020, pp.1-12.
https://search.emarefa.net/detail/BIM-1192385
نمط استشهاد الجمعية الأمريكية للغات الحديثة (MLA)
Lv, MingQi…[et al.]. A Collaborative Deep and Shallow Semisupervised Learning Framework for Mobile App Classification. Mobile Information Systems No. 2020 (2020), pp.1-12.
https://search.emarefa.net/detail/BIM-1192385
نمط استشهاد الجمعية الطبية الأمريكية (AMA)
Lv, MingQi& Huang, Chao& Chen, Tieming& Wang, Ting. A Collaborative Deep and Shallow Semisupervised Learning Framework for Mobile App Classification. Mobile Information Systems. 2020. Vol. 2020, no. 2020, pp.1-12.
https://search.emarefa.net/detail/BIM-1192385
نوع البيانات
مقالات
لغة النص
الإنجليزية
الملاحظات
Includes bibliographical references
رقم السجل
BIM-1192385
قاعدة معامل التأثير والاستشهادات المرجعية العربي "ارسيف Arcif"
أضخم قاعدة بيانات عربية للاستشهادات المرجعية للمجلات العلمية المحكمة الصادرة في العالم العربي
تقوم هذه الخدمة بالتحقق من التشابه أو الانتحال في الأبحاث والمقالات العلمية والأطروحات الجامعية والكتب والأبحاث باللغة العربية، وتحديد درجة التشابه أو أصالة الأعمال البحثية وحماية ملكيتها الفكرية. تعرف اكثر