mlsanityData to 14 Oct 2026

GraphNarrator: Generating Textual Explanations for Graph Neural Networks

arXiv 2410.15268 ↗First posted 20 Oct 2024cs.LG cs.CLcited by 7

Not on the map. Why?

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.

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

34 of 50 references.

References · 34

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Inductive Representation Learning on Large Graphscited by 6,320
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  4. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
  5. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  6. 2023RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignmentcited by 686
  7. 2023Reinforced Self-Training (ReST) for Language Modelingcited by 500
  8. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  9. 2020Parameterized Explainer for Graph Neural Networkcited by 426
  10. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  11. 2016Rationalizing Neural Predictionscited by 281
  12. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
22 more
  1. 2020Measuring Association Between Labels and Free-Text Rationalescited by 160
  2. 2020WT5?! Training Text-to-Text Models to Explain their Predictionscited by 148
  3. 2021GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graphcited by 143
  4. 2024Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Modelscited by 105
  5. 2019GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verificationcited by 100
  6. 2019Rethinking Cooperative Rationalization: Introspective Extraction and Complement Controlcited by 96
  7. 2020Evaluating Explanations: How much do explanations from the teacher aid students?cited by 94
  8. 2023On Measuring Faithfulness or Self-consistency of Natural Language Explanationscited by 73
  9. 2023Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactualscited by 44
  10. 2021InfoLM: A New Metric to Evaluate Summarization & Data2Text Generationcited by 33
  11. 2019Layerwise Relevance Visualization in Convolutional Text Graph Classifierscited by 32
  12. 2021Unsupervised Extractive Summarization using Pointwise Mutual Informationcited by 23
  13. 2023D-Separation for Causal Self-Explanationcited by 21
  14. 2023Tell Me a Story! Narrative-Driven XAI with Large Language Modelscited by 20
  15. 2024Distilling Large Language Models for Text-Attributed Graph Learningcited by 20
  16. 2018Patient representation learning and interpretable evaluation using clinical notescited by 15
  17. 2023Enhancing the Rationale-Input Alignment for Self-explaining Rationalizationcited by 15
  18. 2020Evaluating Explanation Methods for Neural Machine Translationcited by 14
  19. 2022Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methodscited by 13
  20. 2024ELAD: Explanation-Guided Large Language Models Active Distillationcited by 12
  21. 2022Logical Satisfiability of Counterfactuals for Faithful Explanations in NLIcited by 11
  22. 2024textttCOSMIC: Mutual Information for Task-Agnostic Summarization Evaluationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 4.

7 papers.

  1. 2024GraphXAIN: Narratives to Explain Graph Neural Networkscited by 11
  2. 2024Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Taskscited by 10
  3. 2025Towards Automatic Evaluation and Selection of PHI De-identification Models via Multi-Agent Collaborationcited by 3
  4. 2026TeachPro: Multi-Label Qualitative Teaching Evaluation via Cross-View Graph Synergy and Semantic Anchored Evidence Encodingcited by 0
  5. 2026Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learningcited by 0
  6. 2026On the Importance and Evaluation of Narrativity in Natural Language AI Explanationscited by 0
  7. 2026CIExplainer++: Generating Causal and Interpretable Explanations for Graph Neural Networkscited by 0