# ESAM: Discriminative Domain Adaptation with Non-Displayed Items to Improve Long-Tail Performance

arXiv: https://arxiv.org/abs/2005.10545 · HTML: https://mlsanity.com/paper/2005.10545/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2020.

## Built on by (most cited first, 30 of 30)

- [Fairness in Graph Mining: A Survey](https://mlsanity.com/paper/2204.09888/) (2022)
- [AutoDebias: Learning to Debias for Recommendation](https://mlsanity.com/paper/2105.04170/) (2021)
- [Concept-Aware Denoising Graph Neural Network for Micro-Video Recommendation](https://mlsanity.com/paper/2109.13527/) (2021)
- [MELT: Mutual Enhancement of Long-Tailed User and Item for Sequential Recommendation](https://mlsanity.com/paper/2304.08382/) (2023)
- [Collaborative Filtering with Attribution Alignment for Review-based Non-overlapped Cross Domain Recommendation](https://mlsanity.com/paper/2202.04920/) (2022)
- [Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey](https://mlsanity.com/paper/2208.03197/) (2022)
- [Entire Space Counterfactual Learning for Reliable Content Recommendations](https://mlsanity.com/paper/2210.11039/) (2022)
- [Robust Collaborative Filtering to Popularity Distribution Shift](https://mlsanity.com/paper/2310.10696/) (2023)
- [Text Matching Improves Sequential Recommendation by Reducing Popularity Biases](https://mlsanity.com/paper/2308.14029/) (2023)
- [Cross Pairwise Ranking for Unbiased Item Recommendation](https://mlsanity.com/paper/2204.12176/) (2022)
- [Towards Heterogeneous Long-tailed Learning: Benchmarking, Metrics, and Toolbox](https://mlsanity.com/paper/2307.08235/) (2023)
- [Set2setRank: Collaborative Set to Set Ranking for Implicit Feedback based Recommendation](https://mlsanity.com/paper/2105.07377/) (2021)
- [Node Duplication Improves Cold-start Link Prediction](https://mlsanity.com/paper/2402.09711/) (2024)
- [On Explaining Unfairness: An Overview](https://mlsanity.com/paper/2402.10762/) (2024)
- [Robust Quantity-Aware Aggregation for Federated Learning](https://mlsanity.com/paper/2205.10848/) (2022)
- [PoF: Post-Training of Feature Extractor for Improving Generalization](https://mlsanity.com/paper/2207.01847/) (2022)
- [Biases in Scholarly Recommender Systems: Impact, Prevalence, and Mitigation](https://mlsanity.com/paper/2301.07483/) (2023)
- [Algorithmic Fairness: A Tolerance Perspective](https://mlsanity.com/paper/2405.09543/) (2024)
- [Warmer for Less: A Cost-Efficient Strategy for Cold-Start Recommendations at Pinterest](https://mlsanity.com/paper/2512.17277/) (2025)
- [Capturing Popularity Trends: A Simplistic Non-Personalized Approach for Enhanced Item Recommendation](https://mlsanity.com/paper/2308.08799/) (2023)
- [Reconsidering Learning Objectives in Unbiased Recommendation with Unobserved Confounders](https://mlsanity.com/paper/2206.03851/) (2022)
- [Improving Multi-Interest Network with Stable Learning](https://mlsanity.com/paper/2207.07910/) (2022)
- [Item Cold Start Recommendation via Adversarial Variational Auto-encoder Warm-up](https://mlsanity.com/paper/2302.14395/) (2023)
- [Multi-Task Learning For Reduced Popularity Bias In Multi-Territory Video Recommendations](https://mlsanity.com/paper/2310.03148/) (2023)
- [Domain Adaptation of Multilingual Semantic Search -- Literature Review](https://mlsanity.com/paper/2402.02932/) (2024)
- [Causality-aware Graph Aggregation Weight Estimator for Popularity Debiasing in Top-K Recommendation](https://mlsanity.com/paper/2510.04502/) (2025)
- [BPL: Bias-adaptive Preference Distillation Learning for Recommender System](https://mlsanity.com/paper/2510.16076/) (2025)
- [BiCoRec: Bias-Mitigated Context-Aware Sequential Recommendation Model](https://mlsanity.com/paper/2512.13848/) (2025)
- [Modeling User Exploration Saturation: When Recommender Systems Should Stop Pushing Novelty](https://mlsanity.com/paper/2604.16419/) (2026)
- [Debiasing Message Passing to Mitigate Popularity Bias in GNN-based Collaborative Filtering](https://mlsanity.com/paper/2605.11145/) (2026)

## Abstract (arXiv)

Most of ranking models are trained only with displayed items (most are hot items), but they are utilized to retrieve items in the entire space which consists of both displayed and non-displayed items (most are long-tail items). Due to the sample selection bias, the long-tail items lack sufficient records to learn good feature representations, i.e. data sparsity and cold start problems. The resultant distribution discrepancy between displayed and non-displayed items would cause poor long-tail performance. To this end, we propose an entire space adaptation model (ESAM) to address this problem from the perspective of domain adaptation (DA). ESAM regards displayed and non-displayed items as source and target domains respectively. Specifically, we design the attribute correlation alignment that considers the correlation between high-level attributes of the item to achieve distribution alignment. Furthermore, we introduce two effective regularization strategies, i.e. textitcenter-wise clustering and textitself-training to improve DA process. Without requiring any auxiliary information and auxiliary domains, ESAM transfers the knowledge from displayed items to non-displayed items for alleviating the distribution inconsistency. Experiments on two public datasets and a large-scale industrial dataset collected from Taobao demonstrate that ESAM achieves state-of-the-art performance, especially in the long-tail space. Besides, we deploy ESAM to the Taobao search engine, leading to significant improvement on online performance. The code is available at urlhttps://github.com/A-bone1/ESAM.git