Lune

ACL Findings2023

SConE: Simplified Cone Embeddings with Symbolic Operators for Complex Logical Queries

Chau D. M. Nguyen, Tim French, Wei Liu, Michael Stewart

Abstract

Geometric representation of query embeddings (using points, particles, rectangles and cones) can effectively achieve the task of answering complex logical queries expressed in first-order logic (FOL) form over knowledge graphs, allowing intuitive encodings. However, current geometric-based methods depend on the neural approach to model FOL operators (conjunction, disjunction and negation), which are not easily explainable with considerable computation cost. We overcome this challenge by introducing a symbolic modeling approach for the FOL operators, emphasizing the direct calculation of the intersection between geometric shapes, particularly sector-cones in the embedding space, to model the conjunction operator. This approach reduces the computation cost as a non-neural approach is involved in the core logic operators. Moreover, we propose to accelerate the learning in the relation projection operator using the neural approach to emphasize the essential role of this operator in all query structures. Although empirical evidence for explainability is challenging, our approach demonstrates a significant improvement in answering complex logical queries (both non-negative and negative FOL forms) over previous geometric-based models.

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.

2 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

  • ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs cites Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings
  • ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs cites Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs
  • ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs cites Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction
  • Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs cites Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings
  • Neural-Symbolic Models for Logical Queries on Knowledge Graphs cites Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings
  • Neural-Symbolic Models for Logical Queries on Knowledge Graphs cites ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs
  • Neural-Symbolic Models for Logical Queries on Knowledge Graphs cites Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs
  • Query2GMM: Learning Representation with Gaussian Mixture Model for Reasoning over Knowledge Graphs cites Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings
  • Query2GMM: Learning Representation with Gaussian Mixture Model for Reasoning over Knowledge Graphs cites ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs
  • Query2GMM: Learning Representation with Gaussian Mixture Model for Reasoning over Knowledge Graphs cites Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs
  • Query2GMM: Learning Representation with Gaussian Mixture Model for Reasoning over Knowledge Graphs cites Neural-Symbolic Models for Logical Queries on Knowledge Graphs
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. Query2GMM: Learning Representation with Gaussian Mixture Model for Reasoning over Knowledge GraphsYuhan Wu, Yuanyuan Xu, Wenjie Zhang, Xiwei Xu et al.WWW 2024 · 11 citations
  2. Moment Detection in Long Tutorial VideosIoana Croitoru, Simion-Vlad Bogolin, Samuel Albanie, Yang Liu et al.ICCV 2023 · 7 citations

Builds on16

  1. Learning Hierarchy-Aware Knowledge Graph Embeddings for Link PredictionZhanqiu Zhang, Jianyu Cai, Yongdong Zhang, Jie WangAAAI 2020 · 481 citations
  2. Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box EmbeddingsHongyu Ren, Weihua Hu, Jure LeskovecICLR 2020 · 355 citations
  3. Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge GraphsHongyu Ren, Jure LeskovecNeurIPS 2020 · 267 citations
  4. ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge GraphsZhanqiu Zhang, Jie Wang, Jiajun Chen, Shuiwang Ji et al.NeurIPS 2021 · 161 citations
  5. Neural-Symbolic Models for Logical Queries on Knowledge GraphsZhaocheng Zhu, Mikhail Galkin, Zuobai Zhang, Jian TangICML 2022 · 106 citations

Related papers

  1. Spherical Embeddings for Atomic Relation Projection Reaching Complex Logical Query AnsweringChau D. M. Nguyen, Tim French, Michael Stewart, Melinda Hodkiewicz et al.WWW 2025 · 1 citation
  2. Neural Methods for Logical Reasoning over Knowledge GraphsAlfonso Amayuelas, Shuai Zhang, Susie Xi Rao, Ce ZhangICLR 2022 · 27 citations
  3. Neural-Symbolic Entangled Framework for Complex Query AnsweringZezhong Xu, Wen Zhang, Peng Ye, Hui Chen et al.NeurIPS 2022 · 31 citations
  4. A Holistic Approach for Answering Logical Queries on Knowledge GraphsYuhan Wu, Yuanyuan Xu, Xuemin Lin, Wenjie ZhangICDE 2023 · 6 citations
  5. LinE: Logical Query Reasoning over Hierarchical Knowledge GraphsZijian Huang, Meng-Fen Chiang, Wang-Chien LeeKDD 2022 · 17 citations
Dusk over the sea between two cliffs drawn in fine vertical lines