It's mid-July, and the yacht on the Hudson is called Praying for Overtime -- an apt name for the boat hosting the Laws of Motion event, where founder Carly Bigi and her crew's passion for beautiful, perfect-fitting clothing bubbles up alongside the Aperol spritzes at the bar. Bigi herself wears a vibrant pink romper that manages to strike the balance between totally chic and still professional, a throughline for the collection, and the pieces on deck: a rack of white with subtle feathers ringing sleeves and hems. Laws of Motion's styles are modern takes on timeless silhouettes, but that's where any resemblance to other brands begins and ends. That's because Laws of Motion, which counts Rent the Runway co-founder Jenny Fleiss among its investors, relies on data to help customers find the ideal fit and reduce the impact of fast fashion (there's an estimated 92 million tons of textile waste each year, globally). Related: This Fashion Founder's Company Will Take Back Any Piece of Clothing for Any Reason.

Bipartite graph embedding has recently attracted much attention due to the fact that bipartite graphs are widely used in various application domains. Most previous methods, which adopt random walk-based or reconstruction-based objectives, are typically effective to learn local graph structures. However, the global properties of bipartite graph, including community structures of homogeneous nodes and long-range dependencies of heterogeneous nodes, are not well preserved. In this paper, we propose a bipartite graph embedding called BiGI to capture such global properties by introducing a novel local-global infomax objective. Specifically, BiGI first generates a global representation which is composed of two prototype representations. BiGI then encodes sampled edges as local representations via the proposed subgraph-level attention mechanism. Through maximizing the mutual information between local and global representations, BiGI enables nodes in bipartite graph to be globally relevant. Our model is evaluated on various benchmark datasets for the tasks of top-K recommendation and link prediction. Extensive experiments demonstrate that BiGI achieves consistent and significant improvements over state-of-the-art baselines. Detailed analyses verify the high effectiveness of modeling the global properties of bipartite graph.