Please login to be able to save your searches and receive alerts for new content matching your search criteria.
In this paper, we investigate the problem of personalized ranking from implicit feedback (PRIF). It is a more common scenario (e.g. purchase history, click log and page visitation) in recommender systems. The training data are only binary in these problems, reflecting the users’ actions or inactions. One shortcoming of previous PRIF algorithms is noise sensitivity: outliers in training data might bring significant fluctuations in the training process and lead to inaccuracy of the algorithm. In this paper, we propose two robust PRIF algorithms to solve the noise sensitivity problem of existing PRIF algorithms by using the pairwise sigmoid and pairwise fidelity loss functions. These two pairwise loss functions are flexible and can easily be adopted by popular collaborative filtering models such as the matrix factorization (MF) model and the K-nearest-neighbor (KNN) model. A learning process based on stochastic gradient descent with bootstrap sampling is utilized for the optimization. Experiments are conducted on practical datasets containing noisy data points or outliers. Results demonstrate that the proposed algorithms outperform several state-of-the-art one class collaborative filtering (OCCF) algorithms on both the MF and KNN models over different evaluation metrics.
With the popularization of the Internet of Things technology and the improvement of 5G communication technology, the influence of mobile devices on the network structure is increasing. The devices in the network are usually regarded as social users that transmit information. Because the movement of users is dynamic and random, it is more difficult for complex networks to grasp the changing rules of their topological structure. The data transmission model established by considering only the historical behavior of users can no longer meet the demand for fast transmission of large-capacity data. Based on this, this paper proposes a dynamic personalized data transmission model (GRDPS) that considers the recurrent neural network and attention mechanism. First, it uses a recurrent neural network to build users’ personalized preferences and model the user’s historical behavior. Then, GRDPS introduces an attention mechanism to dynamically weight historical user behaviors based on the user’s current message transmission. It is different from the previous methods of modeling user historical behaviors. Based on the requirements of user dynamics, GRDPS effectively considers the temporal characteristics of user historical behaviors and automatically learns the evolution law of user behaviors. Based on the demand of user randomness, GRDPS fully considers the characteristic correlation between the user’s historical behavior and current transmission demand. Finally, GRDPS combines these two points to obtain a personalized ranking of users. The simulation results show that the delivery rate of GRDPS is up to 0.95. Moreover, its data transmission delay and network overhead are better than other methods in the experiment.