# Explainable Product Search with a Dynamic Relation Embedding Model

arXiv: https://arxiv.org/abs/1909.07212 · HTML: https://mlsanity.com/paper/1909.07212/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2019.

## Built on by (most cited first, 6 of 6)

- [Generate Natural Language Explanations for Recommendation](https://mlsanity.com/paper/2101.03392/) (2021)
- [Efficient Non-Sampling Knowledge Graph Embedding](https://mlsanity.com/paper/2104.10796/) (2021)
- [Learning to Ask: Conversational Product Search via Representation Learning](https://mlsanity.com/paper/2411.14466/) (2024)
- [MAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation Alignment](https://mlsanity.com/paper/2503.01711/) (2025)
- [GARCIA: Powering Representations of Long-tail Query with Multi-granularity Contrastive Learning](https://mlsanity.com/paper/2304.12537/) (2023)
- [Preference Shapes Relevance: Cross-component Hierarchical Semantic Alignment for Personalized Generative Retrieval](https://mlsanity.com/paper/2608.30553/) (2026)

## Abstract (arXiv)

Product search is one of the most popular methods for customers to discover products online. Most existing studies on product search focus on developing effective retrieval models that rank items by their likelihood to be purchased. They, however, ignore the problem that there is a gap between how systems and customers perceive the relevance of items. Without explanations, users may not understand why product search engines retrieve certain items for them, which consequentially leads to imperfect user experience and suboptimal system performance in practice. In this work, we tackle this problem by constructing explainable retrieval models for product search. Specifically, we propose to model the "search and purchase" behavior as a dynamic relation between users and items, and create a dynamic knowledge graph based on both the multi-relational product data and the context of the search session. Ranking is conducted based on the relationship between users and items in the latent space, and explanations are generated with logic inferences and entity soft matching on the knowledge graph. Empirical experiments show that our model, which we refer to as the Dynamic Relation Embedding Model (DREM), significantly outperforms the state-of-the-art baselines and has the ability to produce reasonable explanations for search results.