A Recommendation Algorithm Combining Local and Global Interest Features
نویسندگان
چکیده
Due to the ability of knowledge graph effectively solve sparsity problem collaborative filtering, (KG) has been widely studied and applied as auxiliary information in field recommendation systems. However, existing KG-based methods mainly focus on learning its representation from neighborhood target items, ignoring influence other items item. The focuses local feature item, which is not sufficient explore user’s preference degree for To address above issues, this paper, an approach combining users’ interest features with global (KGG) proposed efficiently level learns item through Knowledge Graph Convolutional Network Generative Adversarial (GAN). Specifically, paper first utilizes mine related attributes capture correlations obtain then uses matrix factorization method learn items. Secondly, it GAN implicit interaction matrix. Finally, a linear fusion layer designed fuse interests towards final click prediction. Experimental results three real datasets show that only integrates but also further alleviates data sparsity. Compared current baselines graph-based systems, KGG achieves maximum improvement 8.1% 7.6% AUC ACC, respectively.
منابع مشابه
Online 3D Ear Recognition by Combining Global and Local Features
The three-dimensional shape of the ear has been proven to be a stable candidate for biometric authentication because of its desirable properties such as universality, uniqueness, and permanence. In this paper, a special laser scanner designed for online three-dimensional ear acquisition was described. Based on the dataset collected by our scanner, two novel feature classes were defined from a t...
متن کاملA Novel Method for Content Base Image Retrieval Using Combination of Local and Global Features
Content-based image retrieval (CBIR) has been an active research topic in the last decade. In this paper we proposed an image retrieval method using global and local features. Firstly, for local features extraction, SURF algorithm produces a set of interest points for each image and a set of 64-dimensional descriptors for each interest points and then to use Bag of Visual Words model, a cluster...
متن کاملA Novel Approach for Trademark Image Retrieval by Combining Global Features and Local Features
Traditional trademark image retrieval algorithm only using global feature easily makes mistaken retrieval, and scale invariant feature transform (SIFT) features have limited descriptive ability for image contour and high algorithm complexity. This paper proposes a trademark retrieval algorithm combining the image global features and local features. In this paper, we will firstly, extract Zernik...
متن کاملA Novel Method for Content Base Image Retrieval Using Combination of Local and Global Features
Content-based image retrieval (CBIR) has been an active research topic in the last decade. In this paper we proposed an image retrieval method using global and local features. Firstly, for local features extraction, SURF algorithm produces a set of interest points for each image and a set of 64-dimensional descriptors for each interest points and then to use Bag of Visual Words model, a cluster...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Electronics
سال: 2023
ISSN: ['2079-9292']
DOI: https://doi.org/10.3390/electronics12081857