21,521 Hits in 2.1 sec

Reinforced Path Reasoning for Counterfactual Explainable Recommendation [article]

Xiangmeng Wang, Qian Li, Dianer Yu, Guandong Xu
2022 arXiv   pre-print
In this work, we propose a novel Counterfactual Explainable Recommendation (CERec) to generate item attribute-based counterfactual explanations meanwhile to boost recommendation performance.  ...  Counterfactual explanations interpret the recommendation mechanism via exploring how minimal alterations on items or users affect the recommendation decisions.  ...  Explainable Recommendation Explainable recommendation is proven to improve user satisfaction [23] and system transparency [24] .  ... 
arXiv:2207.06674v1 fatcat:cypcpzhxfrfbpaadfevc64un7u

From Intrinsic to Counterfactual: On the Explainability of Contextualized Recommender Systems [article]

Yao Zhou, Haonan Wang, Jingrui He, Haixun Wang
2021 arXiv   pre-print
Each strategy explains its ranking decisions via different mechanisms: attention weights, adversarial perturbations, and counterfactual perturbations.  ...  In this paper, we investigate the dilemma between recommendation and explainability, and show that by utilizing the contextual features (e.g., item reviews from users), we can design a series of explainable  ...  recommendation (CER) [36] : The latest counterfactual explainable recommendation model.  ... 
arXiv:2110.14844v1 fatcat:e3s7nbxivzhknidbckjek2hx2e

On the Relationship between Counterfactual Explainer and Recommender: A Framework and Preliminary Observations [article]

Gang Liu, Zhihan Zhang, Zheng Ning, Meng Jiang
2022 arXiv   pre-print
We analyze the relationship between the performance of the recommender and the quality of the explainer.  ...  With this framework, we are able to investigate the relationship between the explainers and recommenders.  ...  Therefore, the recommendation 𝑟𝑒𝑐 * can be counterfactually explained by 𝑟𝑒𝑐 * and I * 𝑢 .  ... 
arXiv:2207.04317v1 fatcat:25q42lwugfadxo42uinzmeihn4

Counterfactual Explainable Recommendation [article]

Juntao Tan, Shuyuan Xu, Yingqiang Ge, Yunqi Li, Xu Chen, Yongfeng Zhang
2021 pre-print
In this paper, we propose Counterfactual Explainable Recommendation (CountER), which takes the insights of counterfactual reasoning from causal inference for explainable recommendation.  ...  recommendation decision on the counterfactual item is reversed.  ...  Any opinions, findings, conclusions or recommendations expressed in this material are those of the authors and do not necessarily reflect those of the sponsors.  ... 
doi:10.1145/3459637.3482420 arXiv:2108.10539v1 fatcat:bdohmlnkdzacvmyecxbzqkvs4e

FIND:Explainable Framework for Meta-learning [article]

Xinyue Shao, Hongzhi Wang, Xiao Zhu, Feng Xiong
2022 arXiv   pre-print
This paper proposes FIND, an interpretable meta-learning framework that not only can explain the recommendation results of meta-learning algorithm selection, but also provide a more complete and accurate  ...  Since the traditional meta-learning technique lacks explainability, as well as shortcomings in terms of transparency and fairness, achieving explainability for meta-learning is crucial.  ...  On the other hand, recommendation explainability is the explainability of the leaning algorithm recommended by meta-learning.  ... 
arXiv:2205.10362v2 fatcat:2mo4kyd3onap5av4qyugz4f2ru

Interpretable Credit Application Predictions With Counterfactual Explanations [article]

Rory Mc Grath, Luca Costabello, Chan Le Van, Paul Sweeney, Farbod Kamiab, Zhao Shen, Freddy Lecue
2018 arXiv   pre-print
We predict credit applications with off-the-shelf, interchangeable black-box classifiers and we explain single predictions with counterfactual explanations.  ...  Our contribution is two-fold: i) we propose positive counterfactuals, i.e. we adapt counterfactual explanations to also explain accepted loan applications, and ii) we propose two weighting strategies to  ...  Recommending to change these types of features would be of little use.  ... 
arXiv:1811.05245v2 fatcat:rnvgsdfdlvb4reetsqwifdjhli

On Counterfactual Explanations under Predictive Multiplicity [article]

Martin Pawelczyk, Klaus Broelemann, Gjergji Kasneci
2020 arXiv   pre-print
In summary, our theoretical and empiricaln results challenge the commonly held view that counterfactual recommendations should be sparse in general.  ...  In this work, we derive a general upper bound for the costs of counterfactual explanations under predictive multiplicity.  ...  : Explaining the predictions of any classifier. In SIGKDD. ACM, 2016.  ... 
arXiv:2006.13132v1 fatcat:nkqjenm4lrdlnegecwlmuay5pi

A General Model for Fair and Explainable Recommendation in the Loan Domain (Short paper)

Giandomenico Cornacchia, Fedelucio Narducci, Azzurra Ragone
2021 ACM Conference on Recommender Systems  
To this end, in this paper, we propose a model for generating natural language and counterfactual explanations for a loan recommender system with the aim of providing fairer and more transparent suggestions  ...  Recommender systems have been widely used in the Financial Services domain and can play a crucial role in personal loan comparison platforms.  ...  Figure 1 represents our proposed workflow for generating an explanation and a counterfactual explanation in order to recommend also corrective actions to the user.  ... 
dblp:conf/recsys/CornacchiaNR21 fatcat:lbgytk2dazd23lc5ttupreb4oi

Counterfactual Explanations for Machine Learning: A Review [article]

Sahil Verma and John Dickerson and Keegan Hines
2020 arXiv   pre-print
We also identify gaps and discuss promising research directions in the space of counterfactual explainability.  ...  Modern approaches to counterfactual explainability in machine learning draw connections to the established legal doctrine in many countries, making them appealing to fielded systems in high-impact areas  ...  Therefore the recommended counterfactuals should be diverse, giving applicants the choice to choose the easiest one.  ... 
arXiv:2010.10596v1 fatcat:bhw56sorfbfrhm7y473wlizt24

Causal Collaborative Filtering [article]

Shuyuan Xu, Yingqiang Ge, Yunqi Li, Zuohui Fu, Xu Chen, Yongfeng Zhang
2021 arXiv   pre-print
Finally, we further propose a general counterfactual constrained learning framework for estimating the user-item preferences.  ...  Recommender systems are important and valuable tools for many personalized services.  ...  More details will be explained in Section 5.  ... 
arXiv:2102.01868v4 fatcat:ly4jyi4v6na25m3hgwn264d5wu

"GAN I hire you?" – A System for Personalized Virtual Job Interview Training [article]

Alexander Heimerl and Silvan Mertes and Tanja Schneeberger and Tobias Baur and Ailin Liu and Linda Becker and Nicolas Rohleder and Patrick Gebhard and Elisabeth André
2022 arXiv   pre-print
The new feedback extension employs an eXplainable AI (XAI) method based on counterfactual reasoning for generating verbal feedback about observed social behavior.  ...  There, we make use of counterfactual explanations, explaining to a user that a modified version of her/his social behavior would have led to a better behavior rating.  ... 
arXiv:2206.03869v1 fatcat:qprb3vrscnelnf4mbbtxxgoubu

Explanation Ontology in Action: A Clinical Use-Case [article]

Shruthi Chari, Oshani Seneviratne, Daniel M. Gruen, Morgan A. Foreman, Amar K. Das, Deborah L. McGuinness
2020 arXiv   pre-print
Such a representation is increasingly necessary as explainability has become an important problem in Artificial Intelligence with the emergence of complex methods and an uptake in high-precision and user-facing  ...  Additionally, there have been some promising machine learning (ML) model efforts in the explainability space [1, 6] that could be used to generate system recommendations to populate specific explanation  ...  With the alternate set of inputs and the corresponding recommendation in place, the counterfactual explanation components can now be populated as slots based on the sufficiency condition for this explanation  ... 
arXiv:2010.01478v1 fatcat:a7mqolaoejehja3i67fltvpnmm

Counterfactual Explanations as Interventions in Latent Space [article]

Riccardo Crupi, Alessandro Castelnovo, Daniele Regoli, Beatriz San Miguel Gonzalez
2021 arXiv   pre-print
from the data, and at the same time to provide feasible recommendations to reach the proposed profile.  ...  Explainable Artificial Intelligence (XAI) is a set of techniques that allows the understanding of both technical and non-technical aspects of Artificial Intelligence (AI) systems.  ...  generator of explanations; providing, besides counterfactual explanations, causal-aware recommendations for algorithmic recourse.  ... 
arXiv:2106.07754v2 fatcat:vgab6kv2qjhrrgeeiwzq47dulq

"If it didn't happen, why would I change my decision?": How Judges Respond to Counterfactual Explanations for the Public Safety Assessment [article]

Yaniv Yacoby, Ben Green, Christopher L. Griffin, Finale Doshi Velez
2022 arXiv   pre-print
We ran think-aloud trials with eight sitting US state court judges, providing them with recommendations from the PRAI as well as CFEs.  ...  At first, judges misinterpreted the counterfactuals as real -- rather than hypothetical -- changes to defendants.  ...  Indeed, the judges felt more comfortable asking questions, and when asked to explain the counterfactuals to us, nearly all of them did so well.  ... 
arXiv:2205.05424v2 fatcat:awajsm5eqrh2pogzttr27k3vpm

Model agnostic generation of counterfactual explanations for molecules

Geemi P. Wellawatte, Aditi Seshadri, Andrew D. White
2022 Chemical Science  
Generating model agnostic molecular counterfactual explanations to explain model predictions.  ...  are recommended (3) the basic alphabet with only B, C, N, O, S, F, Cl, Br, I atoms is recommended.  ...  These counterfactuals can be used to explain what functional groups are most important for solubility of the base molecule.  ... 
doi:10.1039/d1sc05259d pmid:35432902 pmcid:PMC8966631 fatcat:6enpcykw3zfajan3xmqwfwbjf4
« Previous Showing results 1 — 15 out of 21,521 results