# Learning Diverse Fashion Collocation by Neural Graph Filtering

arXiv: https://arxiv.org/abs/2003.04888 · HTML: https://mlsanity.com/paper/2003.04888/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2020.

## Built on by (most cited first, 8 of 8)

- [Smart Fashion: A Review of AI Applications in the Fashion & Apparel Industry](https://mlsanity.com/paper/2111.00905/) (2021)
- [SAT: Self-adaptive training for fashion compatibility prediction](https://mlsanity.com/paper/2206.12622/) (2022)
- [Attribute-Guided Multi-Level Attention Network for Fine-Grained Fashion Retrieval](https://mlsanity.com/paper/2301.13014/) (2022)
- [fAshIon after fashion: A Report of AI in Fashion](https://mlsanity.com/paper/2105.03050/) (2021)
- [Integrating Domain Knowledge into Large Language Models for Enhanced Fashion Recommendations](https://mlsanity.com/paper/2502.15696/) (2025)
- [A Multihead Continual Learning Framework for Fine-Grained Fashion Image Retrieval with Contrastive Learning and Exponential Moving Average Distillation](https://mlsanity.com/paper/2603.20648/) (2026)
- [Recommendation of Compatible Outfits Conditioned on Style](https://mlsanity.com/paper/2203.16161/) (2022)
- [Semi-supervised Fashion Compatibility Prediction by Color Distortion Prediction](https://mlsanity.com/paper/2212.14680/) (2022)

## Abstract (arXiv)

Fashion recommendation systems are highly desired by customers to find visually-collocated fashion items, such as clothes, shoes, bags, etc. While existing methods demonstrate promising results, they remain lacking in flexibility and diversity, e.g. assuming a fixed number of items or favoring safe but boring recommendations. In this paper, we propose a novel fashion collocation framework, Neural Graph Filtering, that models a flexible set of fashion items via a graph neural network. Specifically, we consider the visual embeddings of each garment as a node in the graph, and describe the inter-garment relationship as the edge between nodes. By applying symmetric operations on the edge vectors, this framework allows varying numbers of inputs/outputs and is invariant to their ordering. We further include a style classifier augmented with focal loss to enable the collocation of significantly diverse styles, which are inherently imbalanced in the training set. To facilitate a comprehensive study on diverse fashion collocation, we reorganize Amazon Fashion dataset with carefully designed evaluation protocols. We evaluate the proposed approach on three popular benchmarks, the Polyvore dataset, the Polyvore-D dataset, and our reorganized Amazon Fashion dataset. Extensive experimental results show that our approach significantly outperforms the state-of-the-art methods with over 10% improvements on the standard AUC metric on the established tasks. More importantly, 82.5% of the users prefer our diverse-style recommendations over other alternatives in a real-world perception study.