# Two Is Better Than One: Dual Embeddings for Complementary Product Recommendations

arXiv: https://arxiv.org/abs/2211.14982 · HTML: https://mlsanity.com/paper/2211.14982/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 44 references that are in the map.
- First posted on arXiv 28 Nov 2022.

## Builds on (most cited first, 24 of 24)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [Tune: A Research Platform for Distributed Model Selection and Training](https://mlsanity.com/paper/1807.05118/) (2018)
- [Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba](https://mlsanity.com/paper/1803.02349/) (2018)
- [Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph](https://mlsanity.com/paper/1707.00143/) (2017)
- [Inferring Networks of Substitutable and Complementary Products](https://mlsanity.com/paper/1506.08839/) (2015)
- [A Comprehensive Survey and Experimental Comparison of Graph-Based Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2101.12631/) (2021)
- [Item2Vec: Neural Item Embedding for Collaborative Filtering](https://mlsanity.com/paper/1603.04259/) (2016)
- [Multi-layer Representation Learning for Medical Concepts](https://mlsanity.com/paper/1602.05568/) (2016)
- [Results of the NeurIPS'21 Challenge on Billion-Scale Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2205.03763/) (2022)
- [Meta-Prod2Vec - Product Embeddings Using Side-Information for Recommendation](https://mlsanity.com/paper/1607.07326/) (2016)
- [E-commerce in Your Inbox: Product Recommendations at Scale](https://mlsanity.com/paper/1606.07154/) (2016)
- [Personalized Bundle List Recommendation](https://mlsanity.com/paper/1904.01933/) (2019)
- [Word2Vec applied to Recommendation: Hyperparameters Matter](https://mlsanity.com/paper/1804.04212/) (2018)
- [A Dual Embedding Space Model for Document Ranking](https://mlsanity.com/paper/1602.01137/) (2016)
- [Inferring Complementary Products from Baskets and Browsing Sessions](https://mlsanity.com/paper/1809.09621/) (2018)
- [Tuning Word2vec for Large Scale Recommendation Systems](https://mlsanity.com/paper/2009.12192/) (2020)
- [Studying Product Competition Using Representation Learning](https://mlsanity.com/paper/2005.10402/) (2020)

## Built on by (most cited first, 2 of 2)

- [Complementary Recommendation in E-commerce: Definition, Approaches, and Future Directions](https://mlsanity.com/paper/2403.16135/) (2024)
- [Revisiting Graph Projections for Effective Complementary Product Recommendation](https://mlsanity.com/paper/2506.09209/) (2025)

## Abstract (arXiv)

Embedding based product recommendations have gained popularity in recent years due to its ability to easily integrate to large-scale systems and allowing nearest neighbor searches in real-time. The bulk of studies in this area has predominantly been focused on similar item recommendations. Research on complementary item recommendations, on the other hand, still remains considerably under-explored. We define similar items as items that are interchangeable in terms of their utility and complementary items as items that serve different purposes, yet are compatible when used with one another. In this paper, we apply a novel approach to finding complementary items by leveraging dual embedding representations for products. We demonstrate that the notion of relatedness discovered in NLP for skip-gram negative sampling (SGNS) models translates effectively to the concept of complementarity when training item representations using co-purchase data. Since sparsity of purchase data is a major challenge in real-world scenarios, we further augment the model using synthetic samples to extend coverage. This allows the model to provide complementary recommendations for items that do not share co-purchase data by leveraging other abundantly available data modalities such as images, text, clicks etc. We establish the effectiveness of our approach in improving both coverage and quality of recommendations on real world data for a major online retail company. We further show the importance of task specific hyperparameter tuning in training SGNS. Our model is effective yet simple to implement, making it a great candidate for generating complementary item recommendations at any e-commerce website.