Sherlock: Sparse Hierarchical Embeddings for Visually-aware One-class Collaborative Filtering

TL;DR

Sherlock introduces a hierarchical embedding model that captures both broad and subtle visual preferences in clothing recommendation, improving handling of data sparsity and variability.

Contribution

The paper proposes a novel hierarchical embedding architecture for visually-aware collaborative filtering, effectively modeling multi-level visual features across categories.

Findings

Improves recommendation accuracy on clothing datasets.

Effectively captures both high-level and subtle visual preferences.

Addresses data sparsity and cold-start issues.

Abstract

Building successful recommender systems requires uncovering the underlying dimensions that describe the properties of items as well as users' preferences toward them. In domains like clothing recommendation, explaining users' preferences requires modeling the visual appearance of the items in question. This makes recommendation especially challenging, due to both the complexity and subtlety of people's 'visual preferences,' as well as the scale and dimensionality of the data and features involved. Ultimately, a successful model should be capable of capturing considerable variance across different categories and styles, while still modeling the commonalities explained by `global' structures in order to combat the sparsity (e.g. cold-start), variability, and scale of real-world datasets. Here, we address these challenges by building such structures to model the visual dimensions across different product categories. With a novel hierarchical embedding architecture, our method accounts for both high-level (colorfulness, darkness, etc.) and subtle (e.g. casualness) visual characteristics simultaneously.