# GraphNarrator: Generating Textual Explanations for Graph Neural Networks

arXiv: https://arxiv.org/abs/2410.15268 · HTML: https://mlsanity.com/paper/2410.15268/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 50 references that are in the map.
- First posted on arXiv 20 Oct 2024.

## Builds on (most cited first, 30 of 34)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment](https://mlsanity.com/paper/2304.06767/) (2023)
- [Reinforced Self-Training (ReST) for Language Modeling](https://mlsanity.com/paper/2308.08998/) (2023)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Parameterized Explainer for Graph Neural Network](https://mlsanity.com/paper/2011.04573/) (2020)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [Rationalizing Neural Predictions](https://mlsanity.com/paper/1606.04155/) (2016)
- [XGNN: Towards Model-Level Explanations of Graph Neural Networks](https://mlsanity.com/paper/2006.02587/) (2020)
- [Measuring Association Between Labels and Free-Text Rationales](https://mlsanity.com/paper/2010.12762/) (2020)
- [WT5?! Training Text-to-Text Models to Explain their Predictions](https://mlsanity.com/paper/2004.14546/) (2020)
- [GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph](https://mlsanity.com/paper/2105.02605/) (2021)
- [Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models](https://mlsanity.com/paper/2402.04614/) (2024)
- [GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification](https://mlsanity.com/paper/1908.01843/) (2019)
- [Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control](https://mlsanity.com/paper/1910.13294/) (2019)
- [Evaluating Explanations: How much do explanations from the teacher aid students?](https://mlsanity.com/paper/2012.00893/) (2020)
- [On Measuring Faithfulness or Self-consistency of Natural Language Explanations](https://mlsanity.com/paper/2311.07466/) (2023)
- [Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals](https://mlsanity.com/paper/2310.00603/) (2023)
- [InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation](https://mlsanity.com/paper/2112.01589/) (2021)
- [Layerwise Relevance Visualization in Convolutional Text Graph Classifiers](https://mlsanity.com/paper/1909.10911/) (2019)
- [Unsupervised Extractive Summarization using Pointwise Mutual Information](https://mlsanity.com/paper/2102.06272/) (2021)
- [D-Separation for Causal Self-Explanation](https://mlsanity.com/paper/2309.13391/) (2023)
- [Tell Me a Story! Narrative-Driven XAI with Large Language Models](https://mlsanity.com/paper/2309.17057/) (2023)
- [Distilling Large Language Models for Text-Attributed Graph Learning](https://mlsanity.com/paper/2402.12022/) (2024)
- [Patient representation learning and interpretable evaluation using clinical notes](https://mlsanity.com/paper/1807.01395/) (2018)
- [Enhancing the Rationale-Input Alignment for Self-explaining Rationalization](https://mlsanity.com/paper/2312.04103/) (2023)
- [Evaluating Explanation Methods for Neural Machine Translation](https://mlsanity.com/paper/2005.01672/) (2020)

## Built on by (most cited first, 7 of 7)

- [GraphXAIN: Narratives to Explain Graph Neural Networks](https://mlsanity.com/paper/2411.02540/) (2024)
- [Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks](https://mlsanity.com/paper/2412.12456/) (2024)
- [Towards Automatic Evaluation and Selection of PHI De-identification Models via Multi-Agent Collaboration](https://mlsanity.com/paper/2510.16194/) (2025)
- [TeachPro: Multi-Label Qualitative Teaching Evaluation via Cross-View Graph Synergy and Semantic Anchored Evidence Encoding](https://mlsanity.com/paper/2601.09246/) (2026)
- [Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learning](https://mlsanity.com/paper/2604.11986/) (2026)
- [On the Importance and Evaluation of Narrativity in Natural Language AI Explanations](https://mlsanity.com/paper/2604.18311/) (2026)
- [CIExplainer++: Generating Causal and Interpretable Explanations for Graph Neural Networks](https://mlsanity.com/paper/2606.20747/) (2026)

## Abstract (arXiv)

Graph representation learning has garnered significant attention due to its broad applications in various domains, such as recommendation systems and social network analysis. Despite advancements in graph learning methods, challenges still remain in explainability when graphs are associated with semantic features. In this paper, we present GraphNarrator, the first method designed to generate natural language explanations for Graph Neural Networks. GraphNarrator employs a generative language model that maps input-output pairs to explanations reflecting the model's decision-making process. To address the lack of ground truth explanations to train the model, we propose first generating pseudo-labels that capture the model's decisions from saliency-based explanations, then using Expert Iteration to iteratively train the pseudo-label generator based on training objectives on explanation quality. The high-quality pseudo-labels are finally utilized to train an end-to-end explanation generator model. Extensive experiments are conducted to demonstrate the effectiveness of GraphNarrator in producing faithful, concise, and human-preferred natural language explanations.