No abstract

Artist recommendation plays a vital role in the artist domain. Accurate recommendation can help avoid ineffective searches and acquire comprehensive knowledge regarding relationships among artists. However, existing studies mainly focus on artists themselves or artistic works. They are incapable of exploring the relationships among artists in an effective way. In this paper, we study the problem of artist recommendation for the first time. We propose a artist dataset to analyze the similarity relationship from spatial and temporal aspects between artists. Specifically, based on the dataset, we propose a self-supervised learning approach to construct the artist graph. To incorporate the learned graph into existing models, we propose a novel network, SSAR-GNN for recommendation. SSAR-GNN applies a simplified Graph Convolution Network (GCN) on the artist graph to enrich the representation of each artist. Experimental results on the dataset show the effectiveness of our proposed method SSAR-GNN in terms of accuracy.

No abstract

Traffic flow forecasting plays a vital role in the transportation domain. Existing studies usually manually construct correlation graphs and design sophisticated models for learning spatial and temporal features to predict future traffic states. However, manually constructed correlation graphs cannot accurately extract the complex patterns hidden in the traffic data. In addition, it is challenging for the prediction model to fit traffic data due to its irregularly-shaped distribution. To solve the above-mentioned problems, in this paper, we propose a novel learning-based method to learn a spatial-temporal correlation graph, which could make good use of the traffic flow data. Moreover, we propose First-Order Gradient Supervision (FOGS), a novel method for traffic flow forecasting. FOGS utilizes first-order gradients, rather than specific flows, to train prediction model, which effectively avoids the problem of fitting irregularly-shaped distributions. Comprehensive numerical evaluations on four real-world datasets reveal that the proposed methods achieve state-of-the-art performance and significantly outperform the benchmarks.

No abstract