Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning

Tan, Juntao; Geng, Shijie; Fu, Zuohui; Ge, Yingqiang; Xu, Shuyuan; Li, Yunqi; Zhang, Yongfeng

doi:10.1145/3485447.3511948

Cited by 57 publications

(42 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…3) Reasoning Rationale: From the causal perspective, most of today's explanation methods are based on factual reasoning (e.g., GNNExplainer [22], PGExplainer [56] XGNN [132], RG-Explainer [152], OrphicX [153]) or counterfactual reasoning (e.g., CF-GNNExplainer [162], Gem [155]). One recent study [164] shows that considering only factual reasoning will result in extra information being included in explanations (i.e., sufficient but not necessary explanations), while only considering counterfactual reasoning will break the complement graph of explanations (i.e., necessary but not sufficient explanations). Existing approaches that consider both forms of reasoning (e.g., RCExplainer [136], CF 2 [164]) show superiority in terms of explanation robustness [136] and quality (e.g., accuracy, precision) [164].…”

Section: Discussionmentioning

confidence: 99%

“…One recent study [164] shows that considering only factual reasoning will result in extra information being included in explanations (i.e., sufficient but not necessary explanations), while only considering counterfactual reasoning will break the complement graph of explanations (i.e., necessary but not sufficient explanations). Existing approaches that consider both forms of reasoning (e.g., RCExplainer [136], CF 2 [164]) show superiority in terms of explanation robustness [136] and quality (e.g., accuracy, precision) [164].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Trustworthy Graph Neural Networks: Aspects, Methods and Trends

Zhang¹,

Wu²,

Yuan³

et al. 2022

Preprint

View full text Add to dashboard Cite

Graph neural networks (GNNs) have emerged as a series of competent graph learning methods for diverse real-world scenarios, ranging from daily applications like recommendation systems and question answering to cutting-edge technologies such as drug discovery in life sciences and n-body simulation in astrophysics. However, task performance is not the only requirement for GNNs. Performance-oriented GNNs have exhibited potential adverse effects like vulnerability to adversarial attacks, unexplainable discrimination against disadvantaged groups, or excessive resource consumption in edge computing environments. To avoid these unintentional harms, it is necessary to build competent GNNs characterised by trustworthiness. To this end, we propose a comprehensive roadmap to build trustworthy GNNs from the view of the various computing technologies involved. In this survey, we introduce basic concepts and comprehensively summarise existing efforts for trustworthy GNNs from six aspects, including robustness, explainability, privacy, fairness, accountability, and environmental well-being. Additionally, we highlight the intricate cross-aspect relations between the above six aspects of trustworthy GNNs. Finally, we present a thorough overview of trending directions for facilitating the research and industrialisation of trustworthy GNNs.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Trustworthy Graph Neural Networks: Aspects, Methods and Trends

Zhang¹,

Wu²,

Yuan³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…However, an even more fundamental problem is to understand why a model is unfair, i.e., what reasons lead to unfair model outputs. There have been research on explaining recommendation results [44,76,172,196,216,217], explaining graph neural networks [122,171,195,204,205], explaining vision and language models [50,82,87,110,111], etc., but the research on explaining why a model is fair or unfair is still very limited. Understanding the "why" is not only helpful on technical perspectives but also on social perspectives.…”

Section: 38mentioning

confidence: 99%

Fairness in Recommendation: A Survey

Li¹,

Chen²,

Xu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Recently, there has been growing attention on fairness considerations in recommender systems with more and more literature on approaches to promote fairness in recommendation. However, the studies are rather fragmented and lack a systematic organization, thus making it difficult to penetrate for new researchers to the domain. This motivates us to provide a systematic survey of existing works on fairness in recommendation. This survey focuses on the foundations for fairness in recommendation literature. It first presents a brief introduction about fairness in basic machine learning tasks such as classification and ranking in order to provide a general overview of fairness research, as well as introduce the more complex situations and challenges that need to be considered when studying fairness in recommender systems. After that, the survey will introduce fairness in recommendation with a focus on the taxonomies of current fairness definitions, the typical techniques for improving fairness, as well as the datasets for fairness studies in recommendation. The survey also talks about the challenges and opportunities in fairness research with the hope of promoting the fair recommendation research area and beyond.

show abstract

“…In addition to text-based or image-based explainable recommendation, knowledge-aware explainable recommendation has also attracted research attention recently, such as [3,18,60,63,64]. Works using counterfactual reasoning to improve recommendation explainability [31,[56][57][58]67] have been proposed very recently. Ghazimatin et al [31] tried to generate provider-side counterfactual explanations by looking for a minimal set of user's historical actions (e.g.…”

Section: Explainable Recommendationmentioning

confidence: 99%

Explainable Fairness in Recommendation

Ge,

Tan,

Zhu

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Existing research on fairness-aware recommendation has mainly focused on the quantification of fairness and the development of fair recommendation models, neither of which studies a more substantial problem-identifying the underlying reason of model disparity in recommendation. This information is critical for recommender system designers to understand the intrinsic recommendation mechanism and provides insights on how to improve model fairness to decision makers. Fortunately, with the rapid development of Explainable AI, we can use model explainability to gain insights into model (un)fairness. In this paper, we study the problem of explainable fairness, which helps to gain insights about why a system is fair or unfair, and guides the design of fair recommender systems with a more informed and unified methodology. Particularly, we focus on a common setting with feature-aware recommendation and exposure unfairness, but the proposed explainable fairness framework is general and can be applied to other recommendation settings and fairness definitions. We propose a Counterfactual Explainable Fairness framework, called CEF, which generates explanations about model fairness that can improve the fairness without significantly hurting the performance. The CEF framework formulates an optimization problem to learn the "minimal" change of the input features that changes the recommendation results to a certain level of fairness. Based on the counterfactual recommendation result of each feature, we calculate an explainability score in terms of the fairness-utility trade-off to rank all the feature-based explanations, and select the top ones as fairness explanations. Experimental results on several real-world datasets validate that our method is able to effectively provide explanations to the model disparities and these explanations can achieve better fairness-utility trade-off when using them for recommendation than all the baselines. CCS CONCEPTS• Computing methodologies → Artificial intelligence.

show abstract

Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning

Cited by 57 publications

References 18 publications

Trustworthy Graph Neural Networks: Aspects, Methods and Trends

Trustworthy Graph Neural Networks: Aspects, Methods and Trends

Fairness in Recommendation: A Survey

Explainable Fairness in Recommendation

Contact Info

Product

Resources

About