SWAG: Item Recommendations using Convolutions on Weighted Graphs

TL;DR

This paper introduces SWAG, a graph convolutional network that efficiently generates item embeddings from weighted graphs, improving recommendation quality by integrating graph structure and node features.

Contribution

SWAG adapts graphSAGE for weighted graphs, combining random walks, weighting, and aggregation to enhance item recommendation embeddings.

Findings

SWAG outperforms baseline methods in offline evaluations.

SWAG improves online recommendation click-through rates.

High-quality embeddings lead to better product suggestions.

Abstract

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.