# Compatibility Family Learning for Item Recommendation and Generation

arXiv: https://arxiv.org/abs/1712.01262 · HTML: https://mlsanity.com/paper/1712.01262/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Dec 2017.

## Built on by (most cited first, 9 of 9)

- [A Survey on Diffusion Models for Recommender Systems](https://mlsanity.com/paper/2409.05033/) (2024)
- [From Culture to Clothing: Discovering the World Events Behind A Century of Fashion Images](https://mlsanity.com/paper/2102.01690/) (2021)
- [Exploring AI in Fashion: A Review of Aesthetics, Personalization, Virtual Try-On, and Forecasting](https://mlsanity.com/paper/2101.08301/) (2021)
- [Arbitrary Virtual Try-On Network: Characteristics Preservation and Trade-off between Body and Clothing](https://mlsanity.com/paper/2111.12346/) (2021)
- [Character-based Outfit Generation with Vision-augmented Style Extraction via LLMs](https://mlsanity.com/paper/2402.05941/) (2024)
- [Fashion Recommendation: Outfit Compatibility using GNN](https://mlsanity.com/paper/2404.18040/) (2024)
- [Sell It Before You Make It: Revolutionizing E-Commerce with Personalized AI-Generated Items](https://mlsanity.com/paper/2503.22182/) (2025)
- [Imitation Learning for Fashion Style Based on Hierarchical Multimodal Representation](https://mlsanity.com/paper/2004.06229/) (2020)
- [ICAR: Image-based Complementary Auto Reasoning](https://mlsanity.com/paper/2308.09119/) (2023)

## Abstract (arXiv)

Compatibility between items, such as clothes and shoes, is a major factor among customer's purchasing decisions. However, learning "compatibility" is challenging due to (1) broader notions of compatibility than those of similarity, (2) the asymmetric nature of compatibility, and (3) only a small set of compatible and incompatible items are observed. We propose an end-to-end trainable system to embed each item into a latent vector and project a query item into K compatible prototypes in the same space. These prototypes reflect the broad notions of compatibility. We refer to both the embedding and prototypes as "Compatibility Family". In our learned space, we introduce a novel Projected Compatibility Distance (PCD) function which is differentiable and ensures diversity by aiming for at least one prototype to be close to a compatible item, whereas none of the prototypes are close to an incompatible item. We evaluate our system on a toy dataset, two Amazon product datasets, and Polyvore outfit dataset. Our method consistently achieves state-of-the-art performance. Finally, we show that we can visualize the candidate compatible prototypes using a Metric-regularized Conditional Generative Adversarial Network (MrCGAN), where the input is a projected prototype and the output is a generated image of a compatible item. We ask human evaluators to judge the relative compatibility between our generated images and images generated by CGANs conditioned directly on query items. Our generated images are significantly preferred, with roughly twice the number of votes as others.