Article
Computer Science, Artificial Intelligence
Bingbing Dong, Yi Zhu, Lei Li, Xindong Wu
Summary: Personalized recommendation systems have been a focus of attention in recent decades for recommending products and services to users. The proposed Item-Agrec model utilizes a semi-autoencoder to co-embed the attributes and graph features of items, improving recommendation accuracy.
Article
Computer Science, Information Systems
Israr ur Rehman, Muhammad Shehzad Hanif, Zulfiqar Ali, Zahoor Jan, Cobbinah Bernard Mawuli, Waqar Ali
Summary: The rapid growth of multimedia on various application platforms has created the need for additional assistive technologies to handle information overload. As a result, various multimedia recommendation systems, including Neural Collaborative Filtering (NCF), have been developed. This research proposes a Weighted Context-based Neural Collaborative Filtering (WNCF) model that incorporates weighted contextual information into NCF to improve the understanding of user behavior. Experimental results demonstrate the significance of this proposal in comparison to state-of-the-art models and indicate the potential for context-aware recommender systems.
MULTIMEDIA SYSTEMS
(2023)
Article
Automation & Control Systems
Jiangzhou Deng, Xun Ran, Yong Wang, Leo Yu Zhang, Junpeng Guo
Summary: Most previous studies in matrix factorization-based collaborative filtering have mainly focused on user rating information for recommendations. This article proposes a new method that integrates multiple information sources, including reviews and rating reliability, to improve the performance of recommender systems.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Biochemical Research Methods
Yajie Meng, Changcheng Lu, Min Jin, Junlin Xu, Xiangxiang Zeng, Jialiang Yang
Summary: In this study, a novel neural collaborative filtering approach is proposed for drug repositioning, which utilizes deep-learning approaches based on a heterogeneous network. The approach takes advantage of localized information in different networks and models the complex drug-disease associations effectively. The effectiveness of the approach is verified through benchmarking comparisons and validated against clinical trials and authoritative databases.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Geography, Physical
Shengwen Li, Renyao Chen, Chenpeng Sun, Hong Yao, Xuyang Cheng, Zhuoru Li, Tailong Li, Xiaojun Kang
Summary: This study proposes a region-aware neural graph collaborative filtering (RA-NGCF) model that improves the accuracy of personalized recommendations by introducing geographical regions. The experiment results show that introducing region entities can enhance the effectiveness of personalized recommendations.
INTERNATIONAL JOURNAL OF DIGITAL EARTH
(2022)
Article
Automation & Control Systems
Zhibin Hu, Xuebin Zhou, Zhiwei He, Zehang Yang, Jian Chen, Jin Huang
Summary: In recent years, there has been significant attention on social recommendation due to the growth of online social platforms such as Twitter and Facebook. However, the efficiency of existing social recommender systems is hindered by the computation and storage of real-valued models as the number of users increases rapidly. To address this efficiency problem, researchers have introduced hashing techniques, mapping real values to discrete values, to improve computational speed and reduce storage costs. However, these methods have limitations regarding quantization loss and the presence of noise in social relations. This paper proposes a novel social recommendation method called Discrete Limited Attentional Collaborative Filtering (DLACF), which models recommendation with limited attention as a mix-integer optimization problem. Experimental results demonstrate the effectiveness of DLACF compared to state-of-the-art methods, with average improvements of 118.7% and 54.7%.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Yi Zhu, Xindong Wu, Jipeng Qiang, Yunhao Yuan, Yun Li
Summary: The CAPR method uses collaborative autoencoder for personalized recommendation, learning feature representations of users and items to address different characteristics and sparsity issues. Experimental results demonstrate the effectiveness of this method compared to others.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Mathematics, Interdisciplinary Applications
Lei Fu, XiaoMing Ma
Summary: With the popularization of the Internet and the increasing complexity of e-commerce systems, the application of network marketing recommendation systems has greatly improved these issues, although challenges such as data sparsity and user interest drift still exist.
Article
Computer Science, Artificial Intelligence
Nawaf Alharbe, Mohamed Ali Rakrouki, Abeer Aljohani
Summary: This paper proposes a collaborative filtering algorithm UI2vec based on embedding representation and word embedding techniques, and its generative model VUI2vec. The experimental results show that compared with the baseline model, these methods perform well in recommendation performance.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Yuefang Gao, Zhen-Wei Huang, Zi-Yuan Huang, Ling Huang, Yingjie Kuang, Xiaojun Yang
Summary: Recently, neighborhood-based collaborative filtering has been used more and more in personalized recommender systems. However, the traditional approach of selecting a fixed number of nearest users/items as neighbors has limitations. To address this issue, a new recommender system called Multi-scale Broad Collaborative Filtering (MBCF) is proposed, which captures rich information from different numbers of nearest users/items. Instead of using deep neural networks (DNNs), the Broad Learning System (BLS) is adopted to learn the complex nonlinear relationships between users and items, achieving satisfactory recommendation performance while avoiding overfitting. Extensive experiments on eight benchmark datasets demonstrate the effectiveness of the proposed MBCF algorithm.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Theory & Methods
Haichi Huang, Xuan Tian, Sisi Luo, Yanli Shi
Summary: This study proposes a novel item-item interaction sequential graph to globally aggregate hidden interaction sequences among all items, and an item-enhanced graph collaborative network (IEGCN) to mix item-item sequences with user-item interactions for collaborative filtering. Experiments show substantial improvements in recall and normalized discounted cumulative gain with IEGCN.
Article
Mathematics
Zhiqiang Pan, Honghui Chen
Summary: This research introduces the Collaborative Knowledge-Enhanced Recommendation (CKER) method, which utilizes a collaborative graph convolution network (CGCN) to learn user and item representations and incorporates self-supervised learning to maximize mutual information between user preferences. Experimental results demonstrate that CKER outperforms state-of-the-art baselines in the field of knowledge-enhanced recommendation.
Article
Computer Science, Information Systems
Shitao Xiao, Yingxia Shao, Yawen Li, Hongzhi Yin, Yanyan Shen, Bin Cui
Summary: The paper introduces a novel collaborative filtering framework, LECF, which models interactions between users and items as edges and captures complex relationships. LECF predicts the existence probability of edges based on weighted similarities in a line graph and utilizes an efficient propagation algorithm for training and inference. Experimental results demonstrate that LECF outperforms state-of-the-art methods on four public datasets.
SCIENCE CHINA-INFORMATION SCIENCES
(2022)
Article
Construction & Building Technology
Yao Zhang, Shuangliang Tai, Kunhui Ye
Summary: This study introduces and verifies a credit network recommendation model based on a collaborative filtering algorithm, which can help owners select efficient contractors with high credit, thereby promoting the healthy development of the construction market.
Article
Immunology
Xinyue Yin, Xinming Rang, Xiangxiang Hong, Yinglian Zhou, Chaohan Xu, Jin Fu
Summary: In this study, target genes and target pathways for drug repositioning in multiple sclerosis (MS) were identified based on transcriptomic changes in MS immune cells. The study found that targeting both the PI3K-Akt signaling pathway and Chemokine signaling pathway, or using tyrosine kinase inhibitors may be potential therapies for the treatment of MS.
FRONTIERS IN IMMUNOLOGY
(2022)
Correction
Biochemical Research Methods
Makbule Gulcin Ozsoy, Tansel Ozyer, Faruk Polat, Reda Alhajj
BMC BIOINFORMATICS
(2018)
Article
Computer Science, Information Systems
Ahmet Engin Bayrak, Faruk Polat
JOURNAL OF INFORMATION SCIENCE
(2019)
Article
Mathematics, Interdisciplinary Applications
Alper Demir, Erkin Cilden, Faruk Polat
ADVANCES IN COMPLEX SYSTEMS
(2019)
Article
Automation & Control Systems
Omer Ekmekci, Faruk Polat
ROBOTICS AND AUTONOMOUS SYSTEMS
(2019)
Article
Automation & Control Systems
Fatih Semiz, Faruk Polat
ROBOTICS AND AUTONOMOUS SYSTEMS
(2020)
Article
Computer Science, Theory & Methods
Huseyin Aydin, Erkin Cilden, Faruk Polat
Summary: Reinforcement learning can benefit from proper task decomposition in large and partially observable problem domains. Experimental study shows that early decomposition based on useful bottleneck transitions reduces memory requirements and improves learning performance.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Alper Demir, Erkin Cilden, Faruk Polat
Summary: This paper introduces an algorithm that accelerates reinforcement learning for partially observable problems by utilizing landmarks to construct an abstract transition model and providing guiding rewards for the agent. Experimental results demonstrate that the proposed algorithm not only improves learning speed but also finds better policies.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2023)
Article
Computer Science, Artificial Intelligence
Fatih Semiz, Mucahit Alkan Yorganci, Faruk Polat
Summary: In this study, a new industry-inspired generalization of the multi-agent path finding (MAPF) problem is proposed. The problem aims to minimize the total path cost by assigning incoming jobs to agents. The agents must also determine the order of visiting the assigned tasks to minimize the total distance traveled. New job-distribution methods, including heuristic algorithms and a brute force algorithm, are presented to solve the problem.
ADVANCED ENGINEERING INFORMATICS
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Ahmet Engin Bayrak, Faruk Polat
PROCEEDINGS OF THE 2019 IEEE/ACM INTERNATIONAL CONFERENCE ON ADVANCES IN SOCIAL NETWORKS ANALYSIS AND MINING (ASONAM 2019)
(2019)
Review
Computer Science, Artificial Intelligence
Alper Demir, Erkin Cilden, Faruk Polat
KNOWLEDGE ENGINEERING REVIEW
(2019)
Proceedings Paper
Computer Science, Theory & Methods
Alper Demir, Erkin Cilden, Faruk Polat
AAMAS '19: PROCEEDINGS OF THE 18TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS
(2019)
Article
Mathematical & Computational Biology
Makbule Gulcin Ozsoy, Faruk Polat, Reda Alhajj
INTERNATIONAL JOURNAL OF DATA MINING AND BIOINFORMATICS
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Ahmet Engin Bayrak, Faruk Polat
2018 IEEE/ACM INTERNATIONAL CONFERENCE ON ADVANCES IN SOCIAL NETWORKS ANALYSIS AND MINING (ASONAM)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Huseyin Aydin, Erkin Cilden, Faruk Polat
2017 IEEE 29TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2017)
(2017)