Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering

Abstract

Building a successful recommender system depends on understanding both the dimensions of people's preferences as well as their dynamics. In certain domains, such as fashion, modeling such preferences can be incredibly difficult, due to the need to simultaneously model the visual appearance of products as well as their evolution over time. The subtle semantics and non-linear dynamics of fashion evolution raise unique challenges especially considering the sparsity and large scale of the underlying datasets. In this paper we build novel models for the One-Class Collaborative Filtering setting, where our goal is to estimate users' fashion-aware personalized ranking functions based on their past feedback. To uncover the complex and evolving visual factors that people consider when evaluating products, our method combines high-level visual features extracted from a deep convolutional neural network, users' past feedback, as well as evolving trends within the community. Experimentally we evaluate our method on two large real-world datasets from Amazon.com, where we show it to outperform state-of-the-art personalized ranking measures, and also use it to visualize the high-level fashion trends across the 11-year span of our dataset.

11 pages, 5 figures

Cited by in corpus (106)

• Neural Graph Collaborative Filtering
• KGAT: Knowledge Graph Attention Network for Recommendation
• Deep Learning based Recommender System: A Survey and New Perspectives
• Representation Learning for Attributed Multiplex Heterogeneous Network
• Reinforcement Knowledge Graph Reasoning for Explainable Recommendation
• A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation
• Mining Latent Structures for Multimedia Recommendation
• Denoising Implicit Feedback for Recommendation
• Bootstrap Latent Representations for Multi-modal Recommendation
• MMALFM: Explainable Recommendation by Leveraging Reviews and Images
• Multi-Pointer Co-Attention Networks for Recommendation
• A Tale of Two Graphs: Freezing and Denoising Graph Structures for Multimodal Recommendation
• Does a Technique for Building Multimodal Representation Matter? -- Comparative Analysis
• HDMI: High-order Deep Multiplex Infomax
• Leveraging Large Language Models for Sequential Recommendation
• Attentive Aspect Modeling for Review-aware Recommendation
• Vista: A Visually, Socially, and Temporally-aware Model for Artistic Recommendation
• MetaKG: Meta-learning on Knowledge Graph for Cold-start Recommendation
• A Meta-Analysis of the Utility of Explainable Artificial Intelligence in Human-AI Decision-Making
• A Systematic Review of Aspect-based Sentiment Analysis: Domains, Methods, and Trends
• Open-world Learning and Application to Product Classification
• Time-aware Path Reasoning on Knowledge Graph for Recommendation
• How Useful are Reviews for Recommendation? A Critical Review and Potential Improvements
• Joint Multi-grained Popularity-aware Graph Convolution Collaborative Filtering for Recommendation
• Explainable Fairness in Recommendation
• Machine Learning at Microsoft with ML .NET
• Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selection
• Regularizing Matrix Factorization with User and Item Embeddings for Recommendation
• Unbiased Learning for the Causal Effect of Recommendation
• Cross-Market Product Recommendation
• A Review of Text Style Transfer using Deep Learning
• Spectrum-based Modality Representation Fusion Graph Convolutional Network for Multimodal Recommendation
• HPRA: Hyperedge Prediction using Resource Allocation
• Exploring Adapter-based Transfer Learning for Recommender Systems: Empirical Studies and Practical Insights
• Formalizing Multimedia Recommendation through Multimodal Deep Learning
• Graph Contrastive Learning with Generative Adversarial Network
• Similarity Learning for Authorship Verification in Social Media
• Adversarial Attacks and Detection on Reinforcement Learning-Based Interactive Recommender Systems
• CausalRec: Causal Inference for Visual Debiasing in Visually-Aware Recommendation
• When Search Meets Recommendation: Learning Disentangled Search Representation for Recommendation
• Content-aware Neural Hashing for Cold-start Recommendation
• Signed Distance-based Deep Memory Recommender
• Recommendation Unlearning via Influence Function
• Mutually-Regularized Dual Collaborative Variational Auto-encoder for Recommendation Systems
• Modeling Dynamic User Preference via Dictionary Learning for Sequential Recommendation
• Making Users Indistinguishable: Attribute-wise Unlearning in Recommender Systems
• Low-Resource Text Classification using Domain-Adversarial Learning
• KuaiSAR: A Unified Search And Recommendation Dataset
• Leveraging Two Types of Global Graph for Sequential Fashion Recommendation
• Graph-based Alignment and Uniformity for Recommendation
• INMO: A Model-Agnostic and Scalable Module for Inductive Collaborative Filtering
• Improving Collaborative Metric Learning with Efficient Negative Sampling
• Scaling Sequential Recommendation Models with Transformers
• Consumer-side Fairness in Recommender Systems: A Systematic Survey of Methods and Evaluation
• Using Stable Matching to Optimize the Balance between Accuracy and Diversity in Recommendation
• Learning Personalized Risk Preferences for Recommendation
• Rethinking Collaborative Metric Learning: Toward an Efficient Alternative without Negative Sampling
• Learning Explicit User Interest Boundary for Recommendation
• AutoLossGen: Automatic Loss Function Generation for Recommender Systems
• Supporting Serendipitous Discovery and Balanced Analysis of Online Product Reviews with Interaction-Driven Metrics and Bias-Mitigating Suggestions
• EAGER-LLM: Enhancing Large Language Models as Recommenders through Exogenous Behavior-Semantic Integration
• Hierarchically Fusing Long and Short-Term User Interests for Click-Through Rate Prediction in Product Search
• Boosting Item-based Collaborative Filtering via Nearly Uncoupled Random Walks
• Orthogonal Inductive Matrix Completion
• Dynamic Embedding Size Search with Minimum Regret for Streaming Recommender System
• Recommending on graphs: a comprehensive review from a data perspective
• Collaboration and Transition: Distilling Item Transitions into Multi-Query Self-Attention for Sequential Recommendation
• Estimating Error and Bias in Offline Evaluation Results
• Adaptive In-Context Learning with Large Language Models for Bundle Generation
• Exploring AI in Fashion: A Review of Aesthetics, Personalization, Virtual Try-On, and Forecasting
• Balanced Multi-Relational Graph Clustering
• Negative Confidence-Aware Weakly Supervised Binary Classification for Effective Review Helpfulness Classification
• Preventing the Popular Item Embedding Based Attack in Federated Recommendations
• CPMR: Context-Aware Incremental Sequential Recommendation with Pseudo-Multi-Task Learning
• Semi-supervised Adversarial Learning for Complementary Item Recommendation
• FairSort: Learning to Fair Rank for Personalized Recommendations in Two-Sided Platforms
• A Dynamic Embedding Model of the Media Landscape
• Identifying Substitute and Complementary Products for Assortment Optimization with Cleora Embeddings
• Fairness-aware Differentially Private Collaborative Filtering
• Item Graph Convolution Collaborative Filtering for Inductive Recommendations
• Projected Hamming Dissimilarity for Bit-Level Importance Coding in Collaborative Filtering
• AVeCQ: Anonymous Verifiable Crowdsourcing with Worker Qualities
• Detection of Review Abuse via Semi-Supervised Binary Multi-Target Tensor Decomposition
• Sparse MTTKRP Acceleration for Tensor Decomposition on GPU
• HeterRec: Heterogeneous Information Transformer for Scalable Sequential Recommendation
• Popularity Debiasing from Exposure to Interaction in Collaborative Filtering
• DM${}^2$S${}^2$: Deep Multi-Modal Sequence Sets with Hierarchical Modality Attention
• Inference at Scale Significance Testing for Large Search and Recommendation Experiments
• Breaking the Top-$K$ Barrier: Advancing Top-$K$ Ranking Metrics Optimization in Recommender Systems
• Evaluating the Effectiveness of Pre-trained Language Models in Predicting the Helpfulness of Online Product Reviews
• HEAT: A Highly Efficient and Affordable Training System for Collaborative Filtering Based Recommendation on CPUs
• A Dataset for Learning Graph Representations to Predict Customer Returns in Fashion Retail
• Dynamic Interleaving of Content and Structure for Robust Indexing of Semi-Structured Hierarchical Data (Extended Version)
• MMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptation
• Extracting Aspects Hierarchies using Rhetorical Structure Theory
• Algorithmic Fairness Datasets: the Story so Far
• Pure Spectral Graph Embeddings: Reinterpreting Graph Convolution for Top-N Recommendation
• Separated Contrastive Learning for Matching in Cross-domain Recommendation with Curriculum Scheduling
• Evaluating and Addressing Fairness Across User Groups in Negative Sampling for Recommender Systems
• RecPS: Privacy Risk Scoring for Recommender Systems
• MVIGER: Multi-View Variational Integration of Complementary Knowledge for Generative Recommender
• A Use-Case Specific Dataset for Measuring Dimensions of Responsible Performance in LLM-generated Text
• Coarse-to-Fine Lightweight Meta-Embedding for ID-Based Recommendation
• Scalable Personalised Item Ranking through Parametric Density Estimation
• A Universal Framework for Offline Serendipity Evaluation in Recommender Systems via Large Language Models
• Securing Visually-Aware Recommender Systems: An Adversarial Image Reconstruction and Detection Framework