# InBox: Recommendation with Knowledge Graph using Interest Box Embedding

arXiv: https://arxiv.org/abs/2403.12649 · HTML: https://mlsanity.com/paper/2403.12649/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 37 references that are in the map.
- First posted on arXiv 19 Mar 2024.

## Builds on (most cited first, 18 of 18)

- [KGAT: Knowledge Graph Attention Network for Recommendation](https://mlsanity.com/paper/1905.07854/) (2019)
- [Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings](https://mlsanity.com/paper/2002.05969/) (2020)
- [RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems](https://mlsanity.com/paper/1803.03467/) (2018)
- [DKN: Deep Knowledge-Aware Network for News Recommendation](https://mlsanity.com/paper/1801.08284/) (2018)
- [Knowledge Graph Convolutional Networks for Recommender Systems](https://mlsanity.com/paper/1904.12575/) (2019)
- [Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systems](https://mlsanity.com/paper/1905.04413/) (2019)
- [Learning Intents behind Interactions with Knowledge Graph for Recommendation](https://mlsanity.com/paper/2102.07057/) (2021)
- [Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences](https://mlsanity.com/paper/1902.06236/) (2019)
- [Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation](https://mlsanity.com/paper/1805.03352/) (2018)
- [Knowledge-Enhanced Hierarchical Graph Transformer Network for Multi-Behavior Recommendation](https://mlsanity.com/paper/2110.04000/) (2021)
- [Modeling Scale-free Graphs with Hyperbolic Geometry for Knowledge-aware Recommendation](https://mlsanity.com/paper/2108.06468/) (2021)
- [An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph](https://mlsanity.com/paper/2007.00216/) (2020)
- [Relational Collaborative Filtering:Modeling Multiple Item Relations for Recommendation](https://mlsanity.com/paper/1904.12796/) (2019)
- [Explainable Reasoning over Knowledge Graphs for Recommendation](https://mlsanity.com/paper/1811.04540/) (2018)
- [HAKG: Hierarchy-Aware Knowledge Gated Network for Recommendation](https://mlsanity.com/paper/2204.04959/) (2022)
- [Knowledge-Enhanced Top-K Recommendation in Poincar'e Ball](https://mlsanity.com/paper/2101.04852/) (2021)
- [Word2Box: Capturing Set-Theoretic Semantics of Words using Box Embeddings](https://mlsanity.com/paper/2106.14361/) (2021)
- [UGRec: Modeling Directed and Undirected Relations for Recommendation](https://mlsanity.com/paper/2105.04183/) (2021)

## Built on by (most cited first, 1 of 1)

- [A Geometric Approach to Personalized Recommendation with Set-Theoretic Constraints Using Box Embeddings](https://mlsanity.com/paper/2502.10875/) (2025)

## Abstract (arXiv)

Knowledge graphs (KGs) have become vitally important in modern recommender systems, effectively improving performance and interpretability. Fundamentally, recommender systems aim to identify user interests based on historical interactions and recommend suitable items. However, existing works overlook two key challenges: (1) an interest corresponds to a potentially large set of related items, and (2) the lack of explicit, fine-grained exploitation of KG information and interest connectivity. This leads to an inability to reflect distinctions between entities and interests when modeling them in a single way. Additionally, the granularity of concepts in the knowledge graphs used for recommendations tends to be coarse, failing to match the fine-grained nature of user interests. This homogenization limits the precise exploitation of knowledge graph data and interest connectivity. To address these limitations, we introduce a novel embedding-based model called InBox. Specifically, various knowledge graph entities and relations are embedded as points or boxes, while user interests are modeled as boxes encompassing interaction history. Representing interests as boxes enables containing collections of item points related to that interest. We further propose that an interest comprises diverse basic concepts, and box intersection naturally supports concept combination. Across three training steps, InBox significantly outperforms state-of-the-art methods like HAKG and KGIN on recommendation tasks. Further analysis provides meaningful insights into the variable value of different KG data for recommendations. In summary, InBox advances recommender systems through box-based interest and concept modeling for sophisticated knowledge graph exploitation.