Self-supervised Learning for Large-scale Item Recommendations

Abstract

Large scale recommender models find most relevant items from huge catalogs, and they play a critical role in modern search and recommendation systems. To model the input space with large-vocab categorical features, a typical recommender model learns a joint embedding space through neural networks for both queries and items from user feedback data. However, with millions to billions of items in the corpus, users tend to provide feedback for a very small set of them, causing a power-law distribution. This makes the feedback data for long-tail items extremely sparse. Inspired by the recent success in self-supervised representation learning research in both computer vision and natural language understanding, we propose a multi-task self-supervised learning (SSL) framework for large-scale item recommendations. The framework is designed to tackle the label sparsity problem by learning better latent relationship of item features. Specifically, SSL improves item representation learning as well as serving as additional regularization to improve generalization. Furthermore, we propose a novel data augmentation method that utilizes feature correlations within the proposed framework. We evaluate our framework using two real-world datasets with 500M and 1B training examples respectively. Our results demonstrate the effectiveness of SSL regularization and show its superior performance over the state-of-the-art regularization techniques. We also have already launched the proposed techniques to a web-scale commercial app-to-app recommendation system, with significant improvements top-tier business metrics demonstrated in A/B experiments on live traffic. Our online results also verify our hypothesis that our framework indeed improves model performance even more on slices that lack supervision.

References in corpus (7)

• A Simple Framework for Contrastive Learning of Visual Representations
• Unsupervised Learning of Video Representations using LSTMs
• Big Self-Supervised Models are Strong Semi-Supervised Learners
• Deep Learning Recommendation Model for Personalization and Recommendation Systems
• Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination
• Pre-training Tasks for Embedding-based Large-scale Retrieval
• End-to-End Retrieval in Continuous Space

Cited by in corpus (12)

• Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation
• Contrastive Self-supervised Sequential Recommendation with Robust Augmentation
• Graph-less Collaborative Filtering
• Poisoning Deep Learning Based Recommender Model in Federated Learning Scenarios
• UPRec: User-Aware Pre-training for Recommender Systems
• Socially-Aware Self-Supervised Tri-Training for Recommendation
• SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption
• Click-through Rate Prediction with Auto-Quantized Contrastive Learning
• MISS: Multi-Interest Self-Supervised Learning Framework for Click-Through Rate Prediction
• Intrinsic and Extrinsic Factor Disentanglement for Recommendation in Various Context Scenarios
• False Negative Distillation and Contrastive Learning for Personalized Outfit Recommendation
• Hyperbolic Hypergraphs for Sequential Recommendation