Inductive learning for product assortment graph completion
This addresses the challenge of sparse manual graph data for global retailers, though it is incremental as it builds on existing graph and inductive learning methods.
The paper tackled the problem of incomplete style compatibility graphs in fashion assortments by using inductive learning with textual and visual data to enhance graph coverage, resulting in substantial performance improvements on transductive tasks with minimal impact on graph sparsity.
Global retailers have assortments that contain hundreds of thousands of products that can be linked by several types of relationships like style compatibility, "bought together", "watched together", etc. Graphs are a natural representation for assortments, where products are nodes and relations are edges. Relations like style compatibility are often produced by a manual process and therefore do not cover uniformly the whole graph. We propose to use inductive learning to enhance a graph encoding style compatibility of a fashion assortment, leveraging rich node information comprising textual descriptions and visual data. Then, we show how the proposed graph enhancement improves substantially the performance on transductive tasks with a minor impact on graph sparsity.