Differentiable Topics Guided New Paper Recommendation

There are a large number of scientific papers published each year. Since the progresses on scientific theories and technologies are quite different, it is challenging to recommend valuable new papers to the interested researchers. In this paper, we investigate the new paper recommendation task from the point of involved topics and use the concept of subspace to distinguish the academic contributions. We model the papers as topic distributions over subspaces through the neural topic model. The academic influences between papers are modeled as the topic propagation, which are learned by the asymmetric graph convolution on the academic network, reflecting the asymmetry of academic knowledge propagation. The experimental results on real datasets show that our model is better than the baselines on new paper recommendation. Specially, the introduced subspace concept can help find the differences between high quality papers and others, which are related to their innovations. Besides, we conduct the experiments from multiple aspects to verify the robustness of our model.