Chunting Wei

Chunting Wei

Auto-generated profile, based on publicly available information

Chunting Wei

School of Information Science and Engineering, Xinjiang University, Urumqi 830046, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 December 2021 in IEEE Access
Verified
Journal Article
Open access
WZWei Zeng
Wei Zeng
JQJiwei Qin
Jiwei Qin
CWChunting Wei
Chunting Wei
Collaborative filtering is the one of the most successful methods used by recommendation system to solve the information overload problem. Nevertheless, most collaborative filtering only uses explicit rating information to model the user, ignoring the impact of implicit information. In addition, they still utilize inner product to fit user-item interaction behavior, which leads to poor recommendation results. Thus, in this paper, we propose an autoencoder model based on implicit trust relationship between users, where we combine the intrinsic relationship of both the implicit trust information and user-item interaction behavior for collaborative recommendation. Two key challenges emerged in this process: first, how to extract implicit trust information of users, and second, how to model the complex user-item interaction behavior for recommendation. To solve these two challenges, we design a model named the Neural Collaborative Autoencoder for Recommendation with Co-occurrence Embedding (NCAR), which is divided into two parts: (1) the user co-occurrence matrix embedding part; (2) the collaborative neural recommendation part. First, NCAR extracts the user co-occurrence matrix from the rating information. Then, the autoencoder is used to learn the co-occurrence embedding of each user with the correlation regularization method. Finally, this paper employs an interaction prediction module based on a deep neural network to learn the complex interaction behaviors between users and items. Experiments conducted on four public datasets show that the performance of NCAR is significantly better than that of the baseline method.

10 November 2022 in Sensors
Verified
Journal Article
Open access
PDF file
CWChunting Wei
Chunting Wei
JQJiwei Qin
Jiwei Qin
QRQiulin Ren
Qiulin Ren
In recent years, hybrid recommendation techniques based on feature fusion have gained extensive attention in the field of list ranking. Most of them fuse linear and nonlinear models to simultaneously learn the linear and nonlinear features of entities and jointly fit user-item interactions. These methods are based on implicit feedback, which can reduce the difficulty of data collection and the time of data preprocessing, but will lead to the lack of entity interaction depth information due to the lack of user satisfaction. This is equivalent to artificially reducing the entity interaction features, limiting the overall performance of the model. To address this problem, we propose a two-stage recommendation model named A-DNR, short for Attention-based Deep Neural Ranking. In the first stage, user short-term preferences are modeled through an attention mechanism network. Then the user short-term preferences and user long-term preferences are fused into dynamic user preferences. In the second stage, the high-order and low-order feature interactions are modeled by a matrix factorization (MF) model and a multi-layer perceptron (MLP) model, respectively. Then, the features are fused through a fully connected layer, and the vectors are mapped to scores. Finally, a ranking list is output through the scores. Experiments on three real-world datasets (Movielens100K, Movielens1M and Yahoo Movies) show that our proposed model achieves significant improvements compared to existing methods.

23 November 2021 in IEEE Access
Verified
Journal Article
Open access
CWChunting Wei
Chunting Wei
JQJiwei Qin
Jiwei Qin
WZWei Zeng
Wei Zeng
In recent years, list ranking learning has attracted further attention in the field of recommendation. Most of the existing list ranking methods use traditional or deep learning methods to fit user-item interactions and output a personalized ranking list. These solutions mainly focus on a certain aspect of linear and nonlinear interactions when learning latent structures of users and items. In fact, linear interactions and nonlinear interactions coexist and play complementary roles in a recommendation system. Once any type of interaction is ignored, it will result in the loss of linear or nonlinear features, which will further affect the overall performance of the model. To address this problem, we propose a general framework, DNR, short for Deep Neural Rank. To jointly learn linear and nonlinear features, it uses both traditional and deep learning methods to fit user-item interactions. This is a flexible architecture that can not only be extended to the integration of various linear models and nonlinear models but also be simplified for pairwise learning to rank. This paper focuses on the feasibility of integrating matrix factorization (MF) and multi-layer perceptron (MLP) into the framework as linear and nonlinear methods. Eventually, we conduct extensive experiments on three data sets (Movielens100K, Movielens1M, and Yahoo Movies). The results show that our proposed DNR framework achieves a significant improvement compared to existing methods.