Developing and Evaluating Graph Counterfactual Explanation with GRETEL

Prado-Romero, Mario Alfonso; Prenkaj, Bardh; Stilo, Giovanni

doi:10.1145/3539597.3573026

Cited by 5 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is a plethora of research works that deal with the automatic generation of counterfactual explanations for graphs [28]. Most of them try to generate the counterfactuals automatically, for example with the use of generative models [21], by just concentrating on edge deletion [20] or by a search driven by a Reinforcement Learning (RL) algorithm [25].…”

Section: Discussionmentioning

confidence: 99%

CLARUS: An Interactive Explainable AI Platform for Manual Counterfactuals in Graph Neural Networks

Beinecke

Saranti

Angerschmid

et al. 2022

Preprint

View full text Add to dashboard Cite

Lack of trust in artificial intelligence (AI) models in medicine is still the key blockage in the use of AI as clinical decision support systems (CDSS). Although AI models are already performing excellently in medicine, their black-box nature entails that it is often impossible to understand why a particular decision was made. In the field of explainable AI (XAI), many good tools have already been developed to "explain" to a human expert, for example, which input features influenced a prediction. However, in the clinical domain, it is essential that these explanations lead to some degree of causal understanding by the domain expert in the context of a specific application domain. For this reason, we have developed an interactive XAI platform that allows the domain expert to ask counterfactual ("what-if") questions. Our platform allows a domain expert to observe how changes based on their questions affect the AI decision and the XAI explanation.

show abstract

Section: Discussionmentioning

confidence: 99%

CLARUS: An Interactive Explainable AI Platform for Manual Counterfactuals in Graph Neural Networks

Beinecke

Saranti

Angerschmid

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…the number of edges. For more information on explaining black-box models for graphs, we remand the reader to the following survey (Prado-Romero et al 2022;Yuan et al 2020c).…”

Section: Explanations For Graphsmentioning

confidence: 99%

Benchmarking and survey of explanation methods for black box models

Bodria

Giannotti

Guidotti

et al. 2023

Data Min Knowl Disc

View full text Add to dashboard Cite

The rise of sophisticated black-box machine learning models in Artificial Intelligence systems has prompted the need for explanation methods that reveal how these models work in an understandable way to users and decision makers. Unsurprisingly, the state-of-the-art exhibits currently a plethora of explainers providing many different types of explanations. With the aim of providing a compass for researchers and practitioners, this paper proposes a categorization of explanation methods from the perspective of the type of explanation they return, also considering the different input data formats. The paper accounts for the most representative explainers to date, also discussing similarities and discrepancies of returned explanations through their visual appearance. A companion website to the paper is provided as a continuous update to new explainers as they appear. Moreover, a subset of the most robust and widely adopted explainers, are benchmarked with respect to a repertoire of quantitative metrics.

show abstract

“…Within the domain of recommender systems, several studies have been conducted with the objective of furnishing counterfactual explanations to explicate recommendations. These approaches may involve the utilization of methods such as heterogeneous information networks [31][32][33][34], perturbation models [9], or influence functions [35]. PRINCE [31] is a recommendation model that leverages a polynomial-time optimal algorithm to identify a minimal set of user actions from a search space that is exponential in size, achieved through the use of random walks over dynamic graphs.…”

Section: Counterfactual Explanationsmentioning

confidence: 99%

CETD: Counterfactual Explanations by Considering Temporal Dependencies in Sequential Recommendation

He,

An,

Wang

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Providing interpretable explanations can notably enhance users’ confidence and satisfaction with regard to recommender systems. Counterfactual explanations demonstrate remarkable performance in the realm of explainable sequential recommendation. However, current counterfactual explanation models designed for sequential recommendation overlook the temporal dependencies in a user’s past behavior sequence. Furthermore, counterfactual histories should be as similar to the real history as possible to avoid conflicting with the user’s genuine behavioral preferences. This paper presents counterfactual explanations by Considering temporal dependencies (CETD), a counterfactual explanation model that utilizes a variational autoencoder (VAE) for sequential recommendation and takes into account temporal dependencies. To improve explainability, CETD employs a recurrent neural network (RNN) when generating counterfactual histories, thereby capturing both the user’s long-term preferences and short-term behavior in their real behavioral history. Meanwhile, CETD fits the distribution of reconstructed data (i.e., the counterfactual sequences generated by VAE perturbation) in a latent space, and leverages learned variance to decrease the proximity of counterfactual histories by minimizing the distance between the counterfactual sequences and the original sequence. Thorough experiments conducted on two real-world datasets demonstrate that the proposed CETD consistently surpasses current state-of-the-art methods.

show abstract

Developing and Evaluating Graph Counterfactual Explanation with GRETEL

Cited by 5 publications

References 30 publications

CLARUS: An Interactive Explainable AI Platform for Manual Counterfactuals in Graph Neural Networks

CLARUS: An Interactive Explainable AI Platform for Manual Counterfactuals in Graph Neural Networks

Benchmarking and survey of explanation methods for black box models

CETD: Counterfactual Explanations by Considering Temporal Dependencies in Sequential Recommendation

Contact Info

Product

Resources

About