Filters








2,046 Hits in 1.6 sec

On the Relationship Between Counterfactual Explainer and Recommender [article]

Gang Liu, Zhihan Zhang, Zheng Ning, Meng Jiang
2022 arXiv   pre-print
The community needs more fine-grained evaluation metrics to measure the quality of counterfactual explanations to recommender systems.  ...  To enable explainability, recent techniques such as ACCENT and FIA are looking for counterfactual explanations that are specific historical actions of a user, the removal of which leads to a change to  ...  Figure 1 : 1 Figure 1: Illustration of counterfactual explanation in neural recommender systems.  ... 
arXiv:2207.04317v2 fatcat:pocpg6ecergsxp2g3qjcginqsq

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.  ...  recommender systems without sacrificing their performance.  ...  Counterfactual Explanation In this section, we introduce the counterfactual neural recommendation model (CNR) in detail.  ... 
arXiv:2110.14844v1 fatcat:e3s7nbxivzhknidbckjek2hx2e

Reinforced Path Reasoning for Counterfactual Explainable Recommendation [article]

Xiangmeng Wang, Qian Li, Dianer Yu, Guandong Xu
2022 arXiv   pre-print
Moreover, counterfactual explanation could enhance recommendations by filtering out negative items.  ...  In this work, we propose a novel Counterfactual Explainable Recommendation (CERec) to generate item attribute-based counterfactual explanations meanwhile to boost recommendation performance.  ...  Finally, the learnt explanation policy generates attribute-based counterfactual explanations for recommendations.  ... 
arXiv:2207.06674v1 fatcat:cypcpzhxfrfbpaadfevc64un7u

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
Despite their effectiveness, counterfactuals are mainly designed for changing an undesired outcome of a prediction i.e. loan rejected.  ...  Counterfactuals, however, can be difficult to interpret, especially when a high number of features are involved in the explanation.  ...  We also observed that in general the average size of the counterfactual recommendations can vary dramatically for the same data given the underlying model.  ... 
arXiv:1811.05245v2 fatcat:rnvgsdfdlvb4reetsqwifdjhli

GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendations [article]

Ziheng Chen, Fabrizio Silvestri, Jia Wang, Yongfeng Zhang, Zhenhua Huang, Hongshik Ahn, Gabriele Tolomei
2022 arXiv   pre-print
Then, it generates both factual and counterfactual explanations by finding optimal adjacency matrix perturbations to capture the sufficient and necessary conditions for an item to be recommended, respectively  ...  Recently, graph neural networks (GNNs) have been widely used to develop successful recommender systems.  ...  In Algorithm 1, we describe how GREASE generates both factual or counterfactual explanations for a given recommended item i to a user u.  ... 
arXiv:2208.04222v1 fatcat:a3xkjlqhuvdibjzkgqfbkfn5ia

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.  ...  We thank the Center for Integrated Research Computing (CIRC) at the University of Rochester for providing computational resources and technical support. Notes and references  ...  Thus, one and two mutations combined are recommended in MMACE. Fig. S5 † illustrates the top counterfactual for a selected base molecule for 1,3,5 allowed mutations.  ... 
doi:10.1039/d1sc05259d pmid:35432902 pmcid:PMC8966631 fatcat:6enpcykw3zfajan3xmqwfwbjf4

Uncertainty Estimation and Out-of-Distribution Detection for Counterfactual Explanations: Pitfalls and Solutions [article]

Eoin Delaney, Derek Greene, Mark T. Keane
2021 arXiv   pre-print
Whilst an abundance of techniques have recently been proposed to generate counterfactual explanations for the predictions of opaque black-box systems, markedly less attention has been paid to exploring  ...  the uncertainty of these generated explanations.  ...  Acknowledgements This publication has emanated from research conducted with the financial support of (i) Science Foundation Ireland (SFI) to the Insight Centre for Data Analytics under Grant Number 12/  ... 
arXiv:2107.09734v1 fatcat:ungfgqe5ebe4nj6ngmwyd5in74

Causality Learning: A New Perspective for Interpretable Machine Learning [article]

Guandong Xu, Tri Dung Duong, Qian Li, Shaowu Liu, Xianzhi Wang
2021 arXiv   pre-print
Recent years have witnessed the rapid growth of machine learning in a wide range of fields such as image recognition, text classification, credit scoring prediction, recommendation system, etc.  ...  The evaluation techniques for assessing method quality, and open problems in causal interpretability are also discussed in this paper.  ...  Although recommendation system gains the immense popularity these days, there are not many studies working on counterfactual explanation for such system.  ... 
arXiv:2006.16789v2 fatcat:ole3dvpnjnfkflldd6to4nrrwq

Instance-based Counterfactual Explanations for Time Series Classification [article]

Eoin Delaney, Derek Greene, Mark T. Keane
2021 arXiv   pre-print
In this paper, we advance a novel model-agnostic, case-based technique – Native Guide – that generates counterfactual explanations for time series classifiers.  ...  Given a query time series, T_q, for which a black-box classification system predicts class, c, a counterfactual time series explanation shows how T_q could change, such that the system predicts an alternative  ...  We refer to T as a counterfactual explanation for T q such that b(T ) = c .  ... 
arXiv:2009.13211v2 fatcat:ir3hneg5dbe6bmlwh4w4o6k7ma

Editorial for the ICMR 2020 special issue

Michael S. Lew
2021 International Journal of Multimedia Information Retrieval  
In the paper, "Counterfactual Attribute-based Visual Explanations for Classification", the authors aim to explain how the deep neural networks make decisions.  ...  Diering, Maximilian Idahl, Sherzod Hakimov and Ralph Ewerth; and "Counterfactual Attribute-based Visual Explanations for Classification" by Sadaf Gulshad and Arnold Smeulders.  ... 
doi:10.1007/s13735-021-00211-8 fatcat:id5vzumk4rgvph56mysoyqwtxa

Robust Counterfactual Explanations on Graph Neural Networks [article]

Mohit Bajaj, Lingyang Chu, Zi Yu Xue, Jian Pei, Lanjun Wang, Peter Cho-Ho Lam, Yong Zhang
2022 arXiv   pre-print
Massive deployment of Graph Neural Networks (GNNs) in high-stake applications generates a strong demand for explanations that are robust to noise and align well with human intuition.  ...  These explanations are not robust to noise because independently optimizing the correlation for a single input can easily overfit noise.  ...  for a GNN built for recommendation systems [9, 44] .  ... 
arXiv:2107.04086v3 fatcat:3r35ia6jdveuxfjncfapbjba5u

Causal Inference in Recommender Systems: A Survey and Future Directions [article]

Chen Gao, Yu Zheng, Wenjie Wang, Fuli Feng, Xiangnan He, Yong Li
2022 arXiv   pre-print
For example, the recommender systems can recommend a battery charger to a user after buying a phone, in which the latter can serve as the cause of the former, and such a causal relation cannot be reversed  ...  Recently, to address it, researchers in recommender systems have begun to utilize causal inference to extract causality, enhancing the recommender system.  ...  [102] proposed to make use of a knowledge graph for an explainable recommendation. Actually, the paths in the knowledge graph are widely-used for generating explanations.  ... 
arXiv:2208.12397v1 fatcat:jpjp5sjunvczhmikx5gfjvc3qq

Benchmarking Counterfactual Algorithms for XAI: From White Box to Black Box [article]

Catarina Moreira and Yu-Liang Chou and Chihcheng Hsieh and Chun Ouyang and Joaquim Jorge and João Madeiras Pereira
2022 arXiv   pre-print
Our findings indicate that: (1) Different machine learning models have no impact on the generation of counterfactual explanations; (2) Counterfactual algorithms based uniquely on proximity loss functions  ...  (together with a quantitative analysis) to ensure a robust analysis of counterfactual explanations and the potential identification of biases.  ...  This work was also partially supported by Queensland University of Technology (QUT) Centre for Data Science First Byte Funding Program  ... 
arXiv:2203.02399v2 fatcat:rt5xwsjwbbaall2gynt2v7t4vq

"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
A technological approach for generating such feedback might be a playful and low-key starting point for job interview training.  ...  This feedback can be helpful concerning the improvement of behavioral skills needed for job interviews.  ...  As described in Section 1, the recommendations that we aim for can be seen as counterfactual explanations for the engagement model presented in Section 3.2.  ... 
arXiv:2206.03869v1 fatcat:qprb3vrscnelnf4mbbtxxgoubu

Counterfactual Explanations Can Be Manipulated [article]

Dylan Slack and Sophie Hilgard and Himabindu Lakkaraju and Sameer Singh
2021 arXiv   pre-print
Counterfactual explanations are emerging as an attractive option for providing recourse to individuals adversely impacted by algorithmic decisions.  ...  These results raise concerns regarding the dependability of current counterfactual explanation techniques, which we hope will inspire investigations in robust counterfactual explanations.  ...  Acknowledgments We would like to thank the anonymous reviewers for their insightful feedback.  ... 
arXiv:2106.02666v2 fatcat:twqf4amos5bo5p2npmft4z2pvi
« Previous Showing results 1 — 15 out of 2,046 results