Evolving Deep Neural Networks for Collaborative Filtering
This work addresses the limitation of requiring expertise in both CF and DNNs for designing neural networks in recommender systems, though it is incremental as it applies an existing method (genetic algorithm) to a known bottleneck.
The paper tackles the problem of manually designing deep neural networks for collaborative filtering by introducing a genetic algorithm to automatically design architectures and connection weights initialization, resulting in outperforming several manually designed state-of-the-art neural networks on two benchmark datasets.
Collaborative Filtering (CF) is widely used in recommender systems to model user-item interactions. With the great success of Deep Neural Networks (DNNs) in various fields, advanced works recently have proposed several DNN-based models for CF, which have been proven effective. However, the neural networks are all designed manually. As a consequence, it requires the designers to develop expertise in both CF and DNNs, which limits the application of deep learning methods in CF and the accuracy of recommended results. In this paper, we introduce the genetic algorithm into the process of designing DNNs. By means of genetic operations like crossover, mutation, and environmental selection strategy, the architectures and the connection weights initialization of the DNNs can be designed automatically. We conduct extensive experiments on two benchmark datasets. The results demonstrate the proposed algorithm outperforms several manually designed state-of-the-art neural networks.