Lune

ACL Findings2023

Concept2Box: Joint Geometric Embeddings for Learning Two-View Knowledge Graphs

Zijie Huang, Daheng Wang, Binxuan Huang, Chenwei Zhang, Jingbo Shang, Yan Liang, Zhengyang Wang, Xian Li, Christos Faloutsos, Yizhou Sun, Wei Wang

Abstract

Knowledge graph embeddings (KGE) have been extensively studied to embed large-scale relational data for many real-world applications. Existing methods have long ignored the fact many KGs contain two fundamentally different views: high-level ontology-view concepts and fine-grained instance-view entities. They usually embed all nodes as vectors in one latent space. However, a single geometric representation fails to capture the structural differences between two views and lacks probabilistic semantics towards concepts' granularity. We propose Concept2Box, a novel approach that jointly embeds the two views of a KG using dual geometric representations. We model concepts with box embeddings, which learn the hierarchy structure and complex relations such as overlap and disjoint among them. Box volumes can be interpreted as concepts' granularity. Different from concepts, we model entities as vectors. To bridge the gap between concept box embeddings and entity vector embeddings, we propose a novel vector-to-box distance metric and learn both embeddings jointly. Experiments on both the public DBpedia KG and a newly-created industrial KG showed the effectiveness of Concept2Box.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

3 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Coupled Graph ODE for Learning Interacting System Dynamics cites Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations
  • Improving Local Identifiability in Probabilistic Box Embeddings cites Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings
  • BoxLM: Unifying Structures and Semantics of Medical Concepts for Diagnosis Prediction in Healthcare cites Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings
  • BoxLM: Unifying Structures and Semantics of Medical Concepts for Diagnosis Prediction in Healthcare cites Improving Local Identifiability in Probabilistic Box Embeddings
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers3

  1. GraphVis: Boosting LLMs with Visual Knowledge Graph IntegrationYihe Deng, Chenchen Ye, Zijie Huang, Mingyu Derek Ma et al.NeurIPS 2024 · 23 citations
  2. OntoTune: Ontology-Driven Self-training for Aligning Large Language ModelsZhiqiang Liu, Chengtao Gan, Junjie Wang, Yichi Zhang et al.WWW 2025 · 11 citations
  3. BoxLM: Unifying Structures and Semantics of Medical Concepts for Diagnosis Prediction in HealthcareYanchao Tan, Hang Lv, Yunfei Zhan, Guofang Ma et al.ICML 2025

Builds on9

  1. Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box EmbeddingsHongyu Ren, Weihua Hu, Jure LeskovecICLR 2020 · 355 citations
  2. Relational Graph Neural Network with Hierarchical Attention for Knowledge Graph CompletionZhao Zhang, Fuzhen Zhuang, Hengshu Zhu, Zhi-Ping Shi et al.AAAI 2020 · 215 citations
  3. Learning Continuous System Dynamics from Irregularly-Sampled Partial ObservationsZijie Huang, Yizhou Sun, Wei WangNeurIPS 2020 · 103 citations
  4. Improving Local Identifiability in Probabilistic Box EmbeddingsShib Sankar Dasgupta, Michael Boratko, Dongxu Zhang, Luke Vilnis et al.NeurIPS 2020 · 75 citations
  5. Coupled Graph ODE for Learning Interacting System DynamicsZijie Huang, Yizhou Sun, Wei WangKDD 2021 · 55 citations

Related papers

  1. Embedding Two-View Knowledge Graphs with Class Inheritance and Structural SimilarityKyuhwan Yeom, Hyeongjun Yang, Gayeon Park, Myeongheon Jeon et al.KDD 2024 · 4 citations
  2. Dual-Geometric Space Embedding Model for Two-View Knowledge GraphsRoshni G. Iyer, Yunsheng Bai, Wei Wang, Yizhou SunKDD 2022 · 17 citations
  3. DHGE: Dual-View Hyper-Relational Knowledge Graph Embedding for Link Prediction and Entity TypingHaoran Luo, Haihong E, Ling Tan, Gengxian Zhou et al.AAAI 2023 · 18 citations
  4. TranS: Transition-based Knowledge Graph Embedding with Synthetic Relation RepresentationXuanyu Zhang, Qing Yang, Dongliang XuEMNLP Findings 2022 · 14 citations
  5. InBox: Recommendation with Knowledge Graph using Interest Box EmbeddingZezhong Xu, Yincen Qu, Wen Zhang, Lei Liang et al.VLDB 2024 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines