Recommender Systems in Fashion and Retail: Proceedings of the Third Workshop at the Recommender Systems Conference (2021) (Lecture Notes in Electrical Engineering, 830)

Contents
Graph Recommendations
Using Relational Graph Convolutional Networks to Assign Fashion Communities to Users
	1 Introduction
	2 Proposed Method
		2.1 Definitions
		2.2 Method
		2.3 Model Training
		2.4 Neural Collaborative Filtering Baseline
	3 Experiments
		3.1 Datasets
		3.2 Hyperparameters and Best Configurations
		3.3 Results
	4 Conclusions and Future Work
	References
Generative Recommendations
What Users Want? WARHOL: A Generative Model for Recommendation
	1 Introduction
		1.1 The Growing Impact of Machine Learning on Quantitative Marketing
		1.2 Product Innovation as a Machine Learning Problem
	2 Related Work
		2.1 Generative Models for New Item Creation:
		2.2 Generative Models for Image Synthesis
	3 WARHOL: The Proposed Approach
		3.1 The WARHOL Model
		3.2 WARHOL Training
	4 Experiments
		4.1 Performance on the Reco Task
		4.2 Conditional Product Generation
	5 Conclusions
	6 Out of Distribution on Fashion Gen
	References
Sizing and Fit Recommendations
Knowing When You Don\'t Know in Online Fashion: An Uncertainty-Aware Size Recommendation Framework
	1 Introduction
	2 Related Work
	3 Approach
		3.1 Size Recommendation Task Formulation
		3.2 Uncertainty-Based Decision-Making
		3.3 Uncertainty-Aware Framework for Learning in the Presence of Noise
	4 Experimental Setup
		4.1 Dataset, Model, and Evaluation Metric
	5 Results
		5.1 Comparison of Uncertainty Metrics
		5.2 Dataset Pruning and Re-weighting
	6 Conclusion
	References
SkillSF: In the Sizing Game, Your Size is Your Skill
	1 Introduction
	2 SkillSF
		2.1 Skill Inference
		2.2 Size Recommendation
		2.3 Hyper-parameters
	3 Experimental Set-Up
	4 Results
		4.1 Hyper-Parameters Tuning
		4.2 Size Recommendation
		4.3 Size Initialization
		4.4 Insights into Article Sizes
		4.5 Return Data
	5 Discussion and Future Work
	References
Style-Based Interactive Eyewear Recommendations
	1 Introduction
	2 Expert-Based Recommendation and High-Level Expression Attributes
	3 Implementation Details
		3.1 Customer and Glasses Feature Extraction
		3.2 Harmonic and Style Attribute Ranking
	4 Discussion
	5 Conclusion
	References
Fashion Understanding
A Critical Analysis of Offline Evaluation Decisions Against Online Results: A Real-Time Recommendations Case Study
	1 Introduction
	2 Related Works
	3 Methodology
		3.1 How to Do Offline Evaluation
		3.2 Dataset
		3.3 Experimentation
	4 Results
		4.1 Live Experiment
		4.2 Offline Results
	5 Conclusion
	6 Future Work
	References
Attentive Hierarchical Label Sharing for Enhanced Garment and Attribute Classification of Fashion Imagery
	1 Introduction
	2 Related Work
	3 Methodology
		3.1 Problem Formulation
		3.2 Proposed Architectures
	4 Experimental Setup
		4.1 Datasets
		4.2 Evaluation
	5 Results
		5.1 Object Type Detection
		5.2 Category and Attribute Classification
	6 Conclusions
	References