Spectral Collaborative Filtering

Despite the popularity of Collaborative Filtering (CF), CF-based methods are haunted by the $\mathit{\text{cold-start}}$ problem, which has a significantly negative impact on users’ experiences with Recommender Systems (RS). In this paper, to overcome the aforementioned drawback, we first formulate the relationships between users and items as a bipartite graph. Then, we propose a new spectral convolution operation directly performing in the $\mathit{\text{spectral}}\mathit{\text{domain}}$, where not only the proximity information of a graph but also the connectivity information hidden in the graph are revealed. With the proposed spectral convolution operation, we build a deep recommendation model called Spectral Collaborative Filtering (SpectralCF). Benefiting from the rich information of connectivity existing in the $\mathit{\text{spectral}}\mathit{\text{domain}}$, SpectralCF is capable of discovering deep connections between users and items and therefore, alleviates the $\mathit{\text{cold-start}}$ problem for CF. To the best of our knowledge, SpectralCF is the first CF-based method directly learning from the $\mathit{\text{spectral}}\mathit{\text{domains}}$ of user-item bipartite graphs. We apply our method on several standard datasets. It is shown that SpectralCF significantly outperforms state-of-the-art models. Code and data are available at \url{https://github.com/lzheng21/SpectralCF}.