{"type":"ScholarlyArticle","title":"Counterfactual Interpolation Augmentation (CIA): A Unified Approach to Enhance Fairness and Explainability of DNN","authors":[{"name":"Yao Qiang","slug":"yao-qiang","given":"Yao","family":"Qiang","affiliation":"Department of Computer Science , Wayne State University , USA"},{"name":"Chengyin Li","slug":"chengyin-li","given":"Chengyin","family":"Li","affiliation":"Department of Computer Science , Wayne State University , USA"},{"name":"Marco Brocanelli","slug":"marco-brocanelli","given":"Marco","family":"Brocanelli","affiliation":"Department of Computer Science , Wayne State University , USA"},{"name":"Dongxiao Zhu","slug":"dongxiao-zhu","given":"Dongxiao","family":"Zhu","affiliation":"Department of Computer Science , Wayne State University , USA"}],"abstract":"Bias in the training data can jeopardize fairness and explainability of deep neural network prediction on test data. We propose a novel bias-tailored data augmentation approach, Counterfactual Interpolation Augmentation (CIA), attempting to debias the training data by d-separating the spurious correlation between the target variable and the sensitive attribute. CIA generates counterfactual interpolations along a path simulating the distribution transitions between the input and its counterfactual example. CIA as a pre-processing approach enjoys two advantages: First, it couples with either plain training or debiasing training to markedly increase fairness over the sensitive attribute. Second, it enhances the explainability of deep neural networks by generating attribution maps via integrating counterfactual gradients. We demonstrate the superior performance of the CIA-trained deep neural network models using qualitative and quantitative experimental results. Our code is available at: https://github.com/qiangyao1988/CIA","doi":"10.24963/ijcai.2022/103","url":"https://ijcai.org/proceedings/2022/103","pdf":"https://ijcai.org/proceedings/2022/0103.pdf","markdown":"https://ijcai.org/proceedings/2022/103.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/103","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"AI Ethics, Trust, Fairness","track":"Main Track","number":103,"pages":{"first":732,"last":739},"keywords":["AI Ethics, Trust, Fairness: Fairness & Diversity","AI Ethics, Trust, Fairness: Explainability and Interpretability"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986572","length_sec":87,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984715","length_sec":333,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Arjovsky et al., 2019] Martin Arjovsky, Léon Bottou, Ishaan Gulrajani, and David Lopez-Paz. Invariant risk minimization. arXiv preprint arXiv:1907.02893, 2019.","title":"Invariant risk minimization","authors":"Martin Arjovsky, Léon Bottou, Ishaan Gulrajani, David Lopez-Paz","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Buolamwini and Gebru, 2018] Joy Buolamwini and Timnit Gebru. Gender shades: Intersectional accuracy dispari- ties in commercial gender classification. In Conference on fairness, accountability and transparency, pages 77- 91. PMLR, 2018.","title":"Joy Buolamwini and Timnit Gebru. Gender shades: Intersectional accuracy disparities in commercial gender classification","authors":"Gebru Buolamwini","year":"2018","venue":"Conference on fairness, accountability and transparency","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chuang and Mroueh, 2021] Ching-Yao Chuang and Youssef Mroueh. Fair mixup: Fairness via interpolation. arXiv preprint arXiv:2103.06503, 2021.","title":"Fair mixup: Fairness via interpolation","authors":"Ching-Yao Chuang, Youssef Mroueh","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Erion et al., 2021] Gabriel Erion, Joseph D Janizek, Pascal Sturmfels, Scott M Lundberg, and Su-In Lee. Improving performance of deep learning models with axiomatic at- tribution priors and expected gradients. Nature Machine Intelligence, pages 1-12, 2021.","title":"Improving performance of deep learning models with axiomatic attribution priors and expected gradients","authors":"Joseph D Gabriel Erion, Pascal Janizek, Scott M Sturmfels, Su-In Lundberg, Lee","year":"2021","venue":"Nature Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Geirhos et al., 2020] Robert Geirhos, Jörn-Henrik Jacob- sen, et al. Shortcut learning in deep neural networks. Na- ture Machine Intelligence, 2(11):665-673, 2020.","title":"Shortcut learning in deep neural networks","authors":"Robert Geirhos, Jörn-Henrik Jacobsen","year":"2020","venue":"Nature Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Hardt et al., 2016] Moritz Hardt, Eric Price, and Nati Sre- bro. Equality of opportunity in supervised learn- ing. Advances in neural information processing systems, 29:3315-3323, 2016.","title":"Equality of opportunity in supervised learning","authors":"Moritz Hardt, Eric Price, Nati Srebro","year":"2016","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Haug et al., 2021] Johannes Haug, Stefan Zürn, Peter El- Jiz, and Gjergji Kasneci. On baselines for local feature attributions. arXiv preprint arXiv:2101.00905, 2021.","title":"On baselines for local feature attributions","authors":"Johannes Haug, Stefan Zürn, Peter El-Jiz, Gjergji Kasneci","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hong and Yang, 2021] Youngkyu Hong and Eunho Yang. Unbiased classification through bias-contrastive and bias- balanced learning. Advances in Neural Information Pro- cessing Systems, 34, 2021.","title":"Unbiased classification through bias-contrastive and biasbalanced learning","authors":"Yang ; Hong, Youngkyu Hong, Eunho Yang","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Izzo et al., 2020] Cosimo Izzo, Aldo Lipani, Ramin Okhrati, and Francesca Medda. A baseline for shapley values in mlps: from missingness to neutrality. arXiv preprint arXiv:2006.04896, 2020.","title":"A baseline for shapley values in mlps: from missingness to neutrality","authors":"Cosimo Izzo, Aldo Lipani, Ramin Okhrati, Francesca Medda","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kapishnikov et al., 2021] Andrei Kapishnikov, Subhashini Venugopalan, Besim Avci, Ben Wedin, Michael Terry, and Tolga Bolukbasi. Guided integrated gradients: An adap- tive path method for removing noise. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition, pages 5050-5058, 2021.","title":"Guided integrated gradients: An adaptive path method for removing noise","authors":"Andrei Kapishnikov, Subhashini Venugopalan, Besim Avci, Ben Wedin, Michael Terry, Tolga Bolukbasi","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kim et al., 2019] Byungju Kim, Hyunwoo Kim, Kyungsu Kim, Sungjin Kim, and Junmo Kim. Learning not to learn: Training deep neural networks with biased data. In Pro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9012-9020, 2019.","title":"Learning not to learn: Training deep neural networks with biased data","authors":"Kim","year":"2019","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kim et al., 2021] Eungyeup Kim, Jihyeon Lee, and Jaegul Choo. Biaswap: Removing dataset bias with bias- tailored swapping augmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 14992-15001, 2021.","title":"Biaswap: Removing dataset bias with biastailored swapping augmentation","authors":"Kim","year":"2021","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kusner et al., 2017] Matt J Kusner, Joshua R Loftus, Chris Russell, and Ricardo Silva. Counterfactual fairness. arXiv preprint arXiv:1703.06856, 2017.","title":"Counterfactual fairness","authors":"Matt J Kusner, Joshua R Loftus, Chris Russell, Ricardo Silva","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Li et al., 2020] Xin Li, Xiangrui Li, Deng Pan, and Dongx- iao Zhu. Improving adversarial robustness via probabilis- tically compact loss with logit constraints. arXiv preprint arXiv:2012.07688, 2020.","title":"Improving adversarial robustness via probabilistically compact loss with logit constraints","authors":"Xin Li, Xiangrui Li, Deng Pan, Dongxiao Zhu","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Madras et al., 2018] David Madras, Elliot Creager, Toniann Pitassi, and Richard Zemel. Learning adversarially fair and transferable representations. In International Con- ference on Machine Learning, pages 3384-3393. PMLR, 2018.","title":"Learning adversarially fair and transferable representations","authors":"David Madras, Elliot Creager, Toniann Pitassi, Richard Zemel","year":"2018","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Madras et al., 2019] David Madras, Elliot Creager, Toni- ann Pitassi, and Richard Zemel. Fairness through causal awareness: Learning causal latent-variable models for bi- ased data. In FaCCT, pages 349-358, 2019.","title":"Fairness through causal awareness: Learning causal latent-variable models for biased data","authors":"David Madras, Elliot Creager, Toniann Pitassi, Richard Zemel","year":"2019","venue":"FaCCT","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Miglani et al., 2020] Vivek Miglani, Narine Kokhlikyan, Bilal Alsallakh, Miguel Martin, and Orion Reblitz- Richardson. Investigating saturation effects in integrated gradients. arXiv preprint arXiv:2010.12697, 2020.","title":"Investigating saturation effects in integrated gradients","authors":"Vivek Miglani, Narine Kokhlikyan, Bilal Alsallakh, Miguel Martin, Orion Reblitz-Richardson","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Nam et al., 2020] Junhyun Nam, Hyuntak Cha, Sungsoo Ahn, Jaeho Lee, and Jinwoo Shin. Learning from failure: Training debiased classifier from biased classifier. arXiv preprint arXiv:2007.02561, 2020.","title":"Learning from failure: Training debiased classifier from biased classifier","authors":"Nam","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Pan et al., 2020] Deng Pan, Xiangrui Li, Xin Li, and Dongxiao Zhu. Explainable recommendation via inter- pretable feature mapping and evaluation of explainability. arXiv preprint arXiv:2007.06133, 2020.","title":"Explainable recommendation via interpretable feature mapping and evaluation of explainability","authors":"Xiangrui Deng Pan, Xin Li, Dongxiao Li, Zhu","year":"2020","venue":null,"doi":null,"url":null,"internal_url":"/proceedings/2020/373"},{"position":20,"raw":"[Pan et al., 2021] Deng Pan, Xin Li, and Dongxiao Zhu. Ex- plaining deep neural network models with adversarial gra- dient integration. In Thirtieth International Joint Confer- ence on Artificial Intelligence (IJCAI), 2021.","title":"Explaining deep neural network models with adversarial gra-dient integration","authors":"Xin Deng Pan, Dongxiao Li, Zhu","year":"2021","venue":"Thirtieth International Joint Conference on Artificial Intelligence (IJCAI)","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Petsiuk et al., 2018] Vitali Petsiuk, Abir Das, and Kate Saenko. Rise: Randomized input sampling for explanation of black-box models. arXiv preprint arXiv:1806.07421, 2018.","title":"Rise: Randomized input sampling for explanation of black-box models","authors":"Abir Vitali Petsiuk, Kate Das, Saenko","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Pfohl et al., 2019] Stephen R Pfohl, Tony Duan, Daisy Yi Ding, and Nigam H Shah. Counterfactual reasoning for fair clinical risk prediction. In Machine Learning for Healthcare Conference, 2019.","title":"Counterfactual reasoning for fair clinical risk prediction","authors":"Tony Stephen R Pfohl, Daisy Duan, Yi Ding, H Nigam, Shah","year":"2019","venue":"Machine Learning for Healthcare Conference","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Qiang et al., 2020] Yao Qiang, Xin Li, and Dongxiao Zhu. Toward tag-free aspect based sentiment analysis: A mul- tiple attention network approach. In 2020 International Joint Conference on Neural Networks (IJCNN), pages 1- 8. IEEE, 2020.","title":"Toward tag-free aspect based sentiment analysis: A multiple attention network approach","authors":"Yao Qiang, Xin Li, Dongxiao Zhu","year":"2020","venue":"2020 International Joint Conference on Neural Networks (IJCNN)","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Sagawa et al., 2019] Shiori Sagawa, Pang Wei Koh, Tat- sunori B Hashimoto, and Percy Liang. Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization. arXiv preprint arXiv:1911.08731, 2019.","title":"Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization","authors":"Shiori Sagawa, Pang Wei Koh, Tatsunori B Hashimoto, Percy Liang","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Sohn et al., 2015] Kihyuk Sohn, Honglak Lee, and Xinchen Yan. Learning structured output representation using deep conditional generative models. Advances in neural infor- mation processing systems, 28:3483-3491, 2015.","title":"Learning structured output representation using deep conditional generative models","authors":"Sohn","year":"2015","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Sturmfels et al., 2020] Pascal Sturmfels, Scott Lundberg, and Su-In Lee. Visualizing the impact of feature attribu- tion baselines. Distill, 5(1):e22, 2020.","title":"Visualizing the impact of feature attribution baselines","authors":"Pascal Sturmfels, Scott Lundberg, Su-In Lee","year":"2020","venue":"Distill","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Sundararajan et al., 2017] Mukund Sundararajan, Ankur Taly, and Qiqi Yan. Axiomatic attribution for deep net- works. In International Conference on Machine Learning, pages 3319-3328. PMLR, 2017.","title":"Axiomatic attribution for deep networks","authors":"Mukund Sundararajan, Ankur Taly, Qiqi Yan","year":"2017","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Tong and Kagal, 2020] Schrasing Tong and Lalana Kagal. Investigating bias in image classification using model ex- planations. arXiv preprint arXiv:2012.05463, 2020.","title":"Investigating bias in image classification using model explanations","authors":"Kagal Tong, Schrasing Tong, Lalana Kagal","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Wachter et al., 2017] Sandra Wachter, Brent Mittelstadt, and Chris Russell. Counterfactual explanations without opening the black box: Automated decisions and the gdpr. Harv. JL & Tech., 31:841, 2017.","title":"Counterfactual explanations without opening the black box: Automated decisions and the gdpr","authors":"Sandra Wachter, Brent Mittelstadt, Chris Russell","year":"2017","venue":"Harv. JL & Tech","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Wang et al., 2021] Tianhao Wang, Zana Buc ¸inca, and Zilin Ma. Learning interpretable fair representations. Technical report, Technical report, Harvard University, 2021.","title":"Learning interpretable fair representations","authors":"Tianhao Wang, Zana Buc, Zilin Ma","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Xu et al., 2020] Shawn Xu, Subhashini Venugopalan, and Mukund Sundararajan. Attribution in scale and space. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9680-9689, 2020.","title":"Attribution in scale and space","authors":"Shawn Xu, Subhashini Venugopalan, Mukund Sundararajan","year":"2020","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhang and Sang, 2020] Yi Zhang and Jitao Sang. Towards accuracy-fairness paradox: Adversarial example-based data augmentation for visual debiasing. In Proceedings of the 28th ACM International Conference on Multimedia, pages 4346-4354, 2020.","title":"Towards accuracy-fairness paradox: Adversarial example-based data augmentation for visual debiasing","authors":"Sang ; Zhang, Yi Zhang, Jitao Sang","year":"2020","venue":"Proceedings of the 28th ACM International Conference on Multimedia","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Zhou et al., 2021] Yilun Zhou, Serena Booth, Marco Tulio Ribeiro, and Julie Shah. Do feature attribution meth- ods correctly attribute features? arXiv preprint arXiv:2104.14403, 2021.","title":"Do feature attribution methods correctly attribute features","authors":"Yilun Zhou, Serena Booth, Marco Tulio Ribeiro, Julie Shah","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}