CnGAN: Generative Adversarial Networks for Cross-network user preference generation for non-overlapped users
This addresses a major limitation in cross-network recommendation for non-overlapped users, who form the majority, by enabling broader application of these systems.
The paper tackles the problem of cross-network recommender systems being limited to overlapped users by proposing CnGAN, which generates synthetic source network preferences for non-overlapped users, resulting in improved recommendations with superior accuracy, novelty, and diversity compared to state-of-the-art methods.
A major drawback of cross-network recommender solutions is that they can only be applied to users that are overlapped across networks. Thus, the non-overlapped users, which form the majority of users are ignored. As a solution, we propose CnGAN, a novel multi-task learning based, encoder-GAN-recommender architecture. The proposed model synthetically generates source network user preferences for non-overlapped users by learning the mapping from target to source network preference manifolds. The resultant user preferences are used in a Siamese network based neural recommender architecture. Furthermore, we propose a novel user based pairwise loss function for recommendations using implicit interactions to better guide the generation process in the multi-task learning environment.We illustrate our solution by generating user preferences on the Twitter source network for recommendations on the YouTube target network. Extensive experiments show that the generated preferences can be used to improve recommendations for non-overlapped users. The resultant recommendations achieve superior performance compared to the state-of-the-art cross-network recommender solutions in terms of accuracy, novelty and diversity.