# Quantifying the Intrinsic Usefulness of Attributional Explanations for Graph Neural Networks with Artificial Simulatability Studies

arXiv: https://arxiv.org/abs/2305.15961 · HTML: https://mlsanity.com/paper/2305.15961/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 28 references that are in the map.
- First posted on arXiv 25 May 2023.

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

- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Parameterized Explainer for Graph Neural Network](https://mlsanity.com/paper/2011.04573/) (2020)
- [The (Un)reliability of saliency methods](https://mlsanity.com/paper/1711.00867/) (2017)
- [Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?](https://mlsanity.com/paper/2005.01831/) (2020)
- [On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection](https://mlsanity.com/paper/1811.07901/) (2018)
- [Generative Causal Explanations for Graph Neural Networks](https://mlsanity.com/paper/2104.06643/) (2021)
- [ProtGNN: Towards Self-Explaining Graph Neural Networks](https://mlsanity.com/paper/2112.00911/) (2021)
- [Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?](https://mlsanity.com/paper/2010.04119/) (2020)
- [Evaluating Explanations: How much do explanations from the teacher aid students?](https://mlsanity.com/paper/2012.00893/) (2020)
- ["Why is 'Chicago' deceptive?" Towards Building Model-Driven Tutorials for Humans](https://mlsanity.com/paper/2001.05871/) (2020)
- [Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning](https://mlsanity.com/paper/2202.08816/) (2022)
- [Towards Self-Explainable Graph Neural Network](https://mlsanity.com/paper/2108.12055/) (2021)
- [Do Explanations make VQA Models more Predictable to a Human?](https://mlsanity.com/paper/1810.12366/) (2018)
- [GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks](https://mlsanity.com/paper/2107.11889/) (2021)
- [CYBORG: Blending Human Saliency Into the Loss Improves Deep Learning](https://mlsanity.com/paper/2112.00686/) (2021)
- [Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations](https://mlsanity.com/paper/2112.09669/) (2021)
- [Learning to Scaffold: Optimizing Model Explanations for Teaching](https://mlsanity.com/paper/2204.10810/) (2022)
- [Encoding Concepts in Graph Neural Networks](https://mlsanity.com/paper/2207.13586/) (2022)
- [MEGAN: Multi-Explanation Graph Attention Network](https://mlsanity.com/paper/2211.13236/) (2022)
- [GRETEL: A unified framework for Graph Counterfactual Explanation Evaluation](https://mlsanity.com/paper/2206.02957/) (2022)
- [PAGE: Prototype-Based Model-Level Explanations for Graph Neural Networks](https://mlsanity.com/paper/2210.17159/) (2022)

## Built on by (most cited first, 1 of 1)

- [ALMANACS: A Simulatability Benchmark for Language Model Explainability](https://mlsanity.com/paper/2312.12747/) (2023)

## Abstract (arXiv)

Despite the increasing relevance of explainable AI, assessing the quality of explanations remains a challenging issue. Due to the high costs associated with human-subject experiments, various proxy metrics are often used to approximately quantify explanation quality. Generally, one possible interpretation of the quality of an explanation is its inherent value for teaching a related concept to a student. In this work, we extend artificial simulatability studies to the domain of graph neural networks. Instead of costly human trials, we use explanation-supervisable graph neural networks to perform simulatability studies to quantify the inherent usefulness of attributional graph explanations. We perform an extensive ablation study to investigate the conditions under which the proposed analyses are most meaningful. We additionally validate our methods applicability on real-world graph classification and regression datasets. We find that relevant explanations can significantly boost the sample efficiency of graph neural networks and analyze the robustness towards noise and bias in the explanations. We believe that the notion of usefulness obtained from our proposed simulatability analysis provides a dimension of explanation quality that is largely orthogonal to the common practice of faithfulness and has great potential to expand the toolbox of explanation quality assessments, specifically for graph explanations.