# Neuro-Symbolic Entity Alignment via Variational Inference

arXiv: https://arxiv.org/abs/2410.04153 · HTML: https://mlsanity.com/paper/2410.04153/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 45 references that are in the map.
- First posted on arXiv 5 Oct 2024.

## Builds on (most cited first, 22 of 22)

- [Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment](https://mlsanity.com/paper/1611.03954/) (2016)
- [Cross-lingual Entity Alignment via Joint Attribute-Preserving Embedding](https://mlsanity.com/paper/1708.05045/) (2017)
- [A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs](https://mlsanity.com/paper/2003.07743/) (2020)
- [RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs](https://mlsanity.com/paper/2010.04029/) (2020)
- [ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs](https://mlsanity.com/paper/2402.11235/) (2024)
- [Probabilistic Logic Neural Networks for Reasoning](https://mlsanity.com/paper/1906.08495/) (2019)
- [Relational Reflection Entity Alignment](https://mlsanity.com/paper/2008.07962/) (2020)
- [Knowledge Graph Embedding with Iterative Guidance from Soft Rules](https://mlsanity.com/paper/1711.11231/) (2017)
- [Efficient Probabilistic Logic Reasoning with Graph Neural Networks](https://mlsanity.com/paper/2001.11850/) (2020)
- [GSLB: The Graph Structure Learning Benchmark](https://mlsanity.com/paper/2310.05174/) (2023)
- [Boosting the Speed of Entity Alignment 10*: Dual Attention Matching Network with Normalized Hard Sample Mining](https://mlsanity.com/paper/2103.15452/) (2021)
- [Entity Alignment with Noisy Annotations from Large Language Models](https://mlsanity.com/paper/2405.16806/) (2024)
- [Neurosymbolic AI for Reasoning over Knowledge Graphs: A Survey](https://mlsanity.com/paper/2302.07200/) (2023)
- [Neural Compositional Rule Learning for Knowledge Graph Reasoning](https://mlsanity.com/paper/2303.03581/) (2023)
- [Unsupervised Knowledge Graph Alignment by Probabilistic Reasoning and Semantic Embedding](https://mlsanity.com/paper/2105.05596/) (2021)
- [LightEA: A Scalable, Robust, and Interpretable Entity Alignment Framework via Three-view Label Propagation](https://mlsanity.com/paper/2210.10436/) (2022)
- [RSC: Accelerating Graph Neural Networks Training via Randomized Sparse Computations](https://mlsanity.com/paper/2210.10737/) (2022)
- [Contrastive Knowledge Graph Error Detection](https://mlsanity.com/paper/2211.10030/) (2022)
- [Structure Guided Large Language Model for SQL Generation](https://mlsanity.com/paper/2402.13284/) (2024)
- [Logical Reasoning with Relation Network for Inductive Knowledge Graph Completion](https://mlsanity.com/paper/2406.01140/) (2024)
- [MQuinE: a cure for "Z-paradox" in knowledge graph embedding models](https://mlsanity.com/paper/2402.03583/) (2024)
- [Guiding Neural Entity Alignment with Compatibility](https://mlsanity.com/paper/2211.15833/) (2022)

## Built on by (most cited first, 8 of 8)

- [A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models](https://mlsanity.com/paper/2501.13958/) (2025)
- [LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora](https://mlsanity.com/paper/2510.10114/) (2025)
- [You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures](https://mlsanity.com/paper/2508.06105/) (2025)
- [AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction](https://mlsanity.com/paper/2510.15339/) (2025)
- [LoSemB: Logic-Guided Semantic Bridging for Inductive Tool Retrieval](https://mlsanity.com/paper/2508.07690/) (2025)
- [DeepRefine: Agentic Knowledge Refinement via Reinforcement Learning](https://mlsanity.com/paper/2605.10488/) (2026)
- [MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2606.00610/) (2026)
- [Harnessing Structural Context for Entity Alignment Foundation Models](https://mlsanity.com/paper/2606.06109/) (2026)

## Abstract (arXiv)

Entity alignment (EA) aims to merge two knowledge graphs (KGs) by identifying equivalent entity pairs. Existing methods can be categorized into symbolic and neural models. Symbolic models, while precise, struggle with substructure heterogeneity and sparsity, whereas neural models, although effective, generally lack interpretability and cannot handle uncertainty. We propose NeuSymEA, a unified neuro-symbolic reasoning framework that combines the strengths of both methods to fully exploit the cross-KG structural pattern for robust entity alignment. NeuSymEA models the joint probability of all possible pairs' truth scores in a Markov random field, regulated by a set of rules, and optimizes it with the variational EM algorithm. In the E-step, a neural model parameterizes the truth score distributions and infers missing alignments. In the M-step, the rule weights are updated based on the observed and inferred alignments, handling uncertainty. We introduce an efficient symbolic inference engine driven by logic deduction, enabling reasoning with extended rule lengths. NeuSymEA achieves a significant 7.6% hit@1 improvement on DBP15KZH-EN compared with strong baselines and demonstrates robustness in low-resource settings, achieving 73.7% hit@1 accuracy on DBP15KFR-EN with only 1% pairs as seed alignments. Codes are released at https://github.com/chensyCN/NeuSymEA-NeurIPS25.