SWAG: Item Recommendations using Convolutions on Weighted Graphs
This work addresses the challenge of scalable and effective product recommendations for e-commerce platforms like Target, but it is incremental as it adapts an existing method (graphSAGE) to weighted graphs.
The paper tackles the problem of generating high-quality item recommendations by proposing SWAG, a Graph Convolutional Network algorithm that combines random walks and convolutions on weighted graphs to incorporate graph structure and node features like item descriptions and images, resulting in improved embeddings and recommendations as validated through offline and online evaluations on a large-scale dataset of over 500K products and 50M edges.
Recent advancements in deep neural networks for graph-structured data have led to state-of-the-art performance on recommender system benchmarks. In this work, we present a Graph Convolutional Network (GCN) algorithm SWAG (Sample Weight and AGgregate), which combines efficient random walks and graph convolutions on weighted graphs to generate embeddings for nodes (items) that incorporate both graph structure as well as node feature information such as item-descriptions and item-images. The three important SWAG operations that enable us to efficiently generate node embeddings based on graph structures are (a) Sampling of graph to homogeneous structure, (b) Weighting the sampling, walks and convolution operations, and (c) using AGgregation functions for generating convolutions. The work is an adaptation of graphSAGE over weighted graphs. We deploy SWAG at Target and train it on a graph of more than 500K products sold online with over 50M edges. Offline and online evaluations reveal the benefit of using a graph-based approach and the benefits of weighing to produce high quality embeddings and product recommendations.