Recommender Systems in Fashion and Retail: Proceedings of the Fourth Workshop at the Recommender Systems Conference (2022)

Description

This book includes the proceedings of the fourth workshop on recommender systems in fashion and retail (2022), and it aims to present a state-of-the-art view of the advancements within the field of recommendation systems with focused application to e-commerce, retail, and fashion by presenting readers with chapters covering contributions from academic as well as industrial researchers active within this emerging new field. Recommender systems are often used to solve different complex problems in this scenario, such as product recommendations, size and fit recommendations, and social media-influenced recommendations (outfits worn by influencers). Preface Contents Identification of Fine-Grained Fit Information from Customer Reviews in Fashion 1 Introduction 2 Related Work 2.1 Recommendation in Fashion 2.2 Topic Extraction Techniques 3 Experiments 3.1 LDA Versus Text Embedding Clustering 3.2 Zero-Shot Text Classification 4 Conclusion References Personalization Through User Attributes for Transformer-Based Sequential Recommendation 1 Introduction 2 Related Work 3 Problem Setting 4 User Attributes Personalization for Transformers 4.1 Layers 4.2 BERT4Rec 4.3 SASReccross 5 Datasets 6 Experiments 6.1 Evaluation Setup 6.2 User Attribute Baselines 6.3 Hyperparameters 6.4 Results 6.5 Session Length Influence 6.6 Recommendations Without User Interactions 6.7 Ablation Study 7 Conclusion References Reusable Self-attention-Based Recommender System for Fashion 1 Introduction 2 Related Work 3 Algorithm 3.1 Problem Formulation 3.2 Model Architecture 3.3 Input Embeddings 3.4 Modeling Sessions for Long and Short-Term Interests 4 Offline Evaluation 4.1 Dataset 4.2 Experimental Setting 4.3 Offline Experiments 5 Online Results 6 Conclusions References Adversarial Attacks Against Visually Aware Fashion Outfit Recommender Systems 1 Introduction and Related Work 2 Visual Attacks Against Fashion Classifiers 2.1 Explored Adversarial Attacks 2.2 CNN Architectures 3 Experimental Setup 3.1 Dataset 3.2 ML Model Implementation 3.3 Attacks Implementation 4 Results and Discussion 5 Conclusions References Contrastive Learning for Topic-Dependent Image Ranking 1 Introduction 2 Related Work 2.1 Creative Ranking 2.2 Contrastive Learning 3 Method 3.1 Problem Definition 3.2 Overview 3.3 Topic Matching 3.4 Image Ranking 3.5 Summary 4 Experiments 4.1 Online Special Exhibition 4.2 Data Collection 4.3 Experiment Settings 4.4 Offline Evaluation 4.5 Online Evaluation 5 Conclusion References A Dataset for Learning Graph Representations to Predict Customer Returns in Fashion Retail 1 Introduction 2 Data Description 3 Methodology 4 Experiment Results 5 Conclusion References End-to-End Image-Based Fashion Recommendation 1 Introduction 2 Related Work 3 Methodology 3.1 Problem Definition 3.2 Proposed Model 3.3 Training Strategy 4 Experiments 4.1 Datasets 4.2 Evaluation Protocol 4.3 Baselines 4.4 Comparative Study Against State-of-the-Art Image-Based Models (RQ1) 4.5 Ablation Study (RQ2) 4.6 Hyperparameters 5 Conclusion References