# Query2GMM: Learning Representation with Gaussian Mixture Model for Reasoning over Knowledge Graphs

arXiv: https://arxiv.org/abs/2306.10367 · HTML: https://mlsanity.com/paper/2306.10367/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2023.

## Built on by (most cited first, 4 of 4)

- [Effective Instruction Parsing Plugin for Complex Logical Query Answering on Knowledge Graphs](https://mlsanity.com/paper/2410.20321/) (2024)
- [NGDB-Zoo: Towards Efficient and Scalable Neural Graph Databases Training](https://mlsanity.com/paper/2602.21597/) (2026)
- [Type-based Neural Link Prediction Adapter for Complex Query Answering](https://mlsanity.com/paper/2401.16045/) (2024)
- [One Pass for All: A Discrete Diffusion Model for Knowledge Graph Triple Set Prediction](https://mlsanity.com/paper/2604.18344/) (2026)

## Abstract (arXiv)

Logical query answering over Knowledge Graphs (KGs) is a fundamental yet complex task. A promising approach to achieve this is to embed queries and entities jointly into the same embedding space. Research along this line suggests that using multi-modal distribution to represent answer entities is more suitable than uni-modal distribution, as a single query may contain multiple disjoint answer subsets due to the compositional nature of multi-hop queries and the varying latent semantics of relations. However, existing methods based on multi-modal distribution roughly represent each subset without capturing its accurate cardinality, or even degenerate into uni-modal distribution learning during the reasoning process due to the lack of an effective similarity measure. To better model queries with diversified answers, we propose Query2GMM for answering logical queries over knowledge graphs. In Query2GMM, we present the GMM embedding to represent each query using a univariate Gaussian Mixture Model (GMM). Each subset of a query is encoded by its cardinality, semantic center and dispersion degree, allowing for precise representation of multiple subsets. Then we design specific neural networks for each operator to handle the inherent complexity that comes with multi-modal distribution while alleviating the cascading errors. Last, we design a new similarity measure to assess the relationships between an entity and a query's multi-answer subsets, enabling effective multi-modal distribution learning for reasoning. Comprehensive experimental results show that Query2GMM outperforms the best competitor by an absolute average of 6.35%.