# Self-supervised Learning for Large-scale Item Recommendations

arXiv: https://arxiv.org/abs/2007.12865 · HTML: https://mlsanity.com/paper/2007.12865/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2020.

## Built on by (most cited first, 11 of 11)

- [Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning](https://mlsanity.com/paper/2202.06200/) (2022)
- [Contrastive Self-supervised Sequential Recommendation with Robust Augmentation](https://mlsanity.com/paper/2108.06479/) (2021)
- [Augmenting Sequential Recommendation with Pseudo-Prior Items via Reversely Pre-training Transformer](https://mlsanity.com/paper/2105.00522/) (2021)
- [Adaptive Clustering and Personalization in Multi-Agent Stochastic Linear Bandits](https://mlsanity.com/paper/2106.08902/) (2021)
- [Self Contrastive Learning for Session-based Recommendation](https://mlsanity.com/paper/2306.01266/) (2023)
- [Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis](https://mlsanity.com/paper/2308.00404/) (2023)
- [Self-supervised Graph-based Point-of-interest Recommendation](https://mlsanity.com/paper/2210.12506/) (2022)
- [GARCIA: Powering Representations of Long-tail Query with Multi-granularity Contrastive Learning](https://mlsanity.com/paper/2304.12537/) (2023)
- [AdaptiveRec: Adaptively Construct Pairs for Contrastive Learning in Sequential Recommendation](https://mlsanity.com/paper/2307.05469/) (2023)
- [Bilateral Unsymmetrical Graph Contrastive Learning for Recommendation](https://mlsanity.com/paper/2403.15075/) (2024)
- [Multi-intent Aware Contrastive Learning for Sequential Recommendation](https://mlsanity.com/paper/2409.08733/) (2024)

## Abstract (arXiv)

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.