# Toward Subgraph-Guided Knowledge Graph Question Generation with Graph Neural Networks

arXiv: https://arxiv.org/abs/2004.06015 · HTML: https://mlsanity.com/paper/2004.06015/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2020.

## Built on by (most cited first, 25 of 25)

- [JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs](https://mlsanity.com/paper/2106.10502/) (2021)
- [Federated Graph Neural Networks: Overview, Techniques and Challenges](https://mlsanity.com/paper/2202.07256/) (2022)
- [Graph Transformers: A Survey](https://mlsanity.com/paper/2407.09777/) (2024)
- [Prompting Large Language Models with Chain-of-Thought for Few-Shot Knowledge Base Question Generation](https://mlsanity.com/paper/2310.08395/) (2023)
- [Deep Generative Model for Periodic Graphs](https://mlsanity.com/paper/2201.11932/) (2022)
- [Towards LifeSpan Cognitive Systems](https://mlsanity.com/paper/2409.13265/) (2024)
- [Bottom-up Domain-specific Superintelligence: A Reliable Knowledge Graph is What We Need](https://mlsanity.com/paper/2507.13966/) (2025)
- [Relation-aware Graph Attention Model With Adaptive Self-adversarial Training](https://mlsanity.com/paper/2102.07186/) (2021)
- [Towards Transparent Interactive Semantic Parsing via Step-by-Step Correction](https://mlsanity.com/paper/2110.08345/) (2021)
- [QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevance](https://mlsanity.com/paper/2204.13921/) (2022)
- [AutoQGS: Auto-Prompt for Low-Resource Knowledge-based Question Generation from SPARQL](https://mlsanity.com/paper/2208.12461/) (2022)
- [How Proficient Are Large Language Models in Formal Languages? An In-Depth Insight for Knowledge Base Question Answering](https://mlsanity.com/paper/2401.05777/) (2024)
- [A Survey on Neural Question Generation: Methods, Applications, and Prospects](https://mlsanity.com/paper/2402.18267/) (2024)
- [Generating Faithful Text From a Knowledge Graph with Noisy Reference Text](https://mlsanity.com/paper/2308.06488/) (2023)
- [KNIGHT: Knowledge Graph-Driven Multiple-Choice Question Generation with Adaptive Hardness Calibration](https://mlsanity.com/paper/2602.20135/) (2026)
- [Question Answering with Deep Neural Networks for Semi-Structured Heterogeneous Genealogical Knowledge Graphs](https://mlsanity.com/paper/2307.16214/) (2023)
- [SkillQG: Learning to Generate Question for Reading Comprehension Assessment](https://mlsanity.com/paper/2305.04737/) (2023)
- [Knowledge Graph for NLG in the context of conversational agents](https://mlsanity.com/paper/2307.01548/) (2023)
- [Synergizing Machine Learning & Symbolic Methods: A Survey on Hybrid Approaches to Natural Language Processing](https://mlsanity.com/paper/2401.11972/) (2024)
- [Enhancing Clinical Multiple-Choice Questions Benchmarks with Knowledge Graph Guided Distractor Generation](https://mlsanity.com/paper/2506.00612/) (2025)
- [Graph Neural Networks for Natural Language Processing: A Survey](https://mlsanity.com/paper/2106.06090/) (2021)
- [Compositionality-Aware Graph2Seq Learning](https://mlsanity.com/paper/2201.12178/) (2022)
- [GNN2R: Weakly-Supervised Rationale-Providing Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2312.02317/) (2023)
- [Generating Multiple-Choice Knowledge Questions with Interpretable Difficulty Estimation using Knowledge Graphs and Large Language Models](https://mlsanity.com/paper/2604.10748/) (2026)
- [Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey](https://mlsanity.com/paper/2607.09666/) (2026)

## Abstract (arXiv)

Knowledge graph (KG) question generation (QG) aims to generate natural language questions from KGs and target answers. Previous works mostly focus on a simple setting which is to generate questions from a single KG triple. In this work, we focus on a more realistic setting where we aim to generate questions from a KG subgraph and target answers. In addition, most of previous works built on either RNN-based or Transformer based models to encode a linearized KG sugraph, which totally discards the explicit structure information of a KG subgraph. To address this issue, we propose to apply a bidirectional Graph2Seq model to encode the KG subgraph. Furthermore, we enhance our RNN decoder with node-level copying mechanism to allow directly copying node attributes from the KG subgraph to the output question. Both automatic and human evaluation results demonstrate that our model achieves new state-of-the-art scores, outperforming existing methods by a significant margin on two QG benchmarks. Experimental results also show that our QG model can consistently benefit the Question Answering (QA) task as a mean of data augmentation.