ComplAI: Framework for Multi-factor Assessment of Black-Box Supervised Machine Learning Models
Authors: 
Arkadipta De, Satya Swaroop Gudipudi, Sourab Panchanan, Maunendra Sankar DesarkarAuthors Info & Claims
Arkadipta De, Satya Swaroop Gudipudi, Sourab Panchanan, Maunendra Sankar DesarkarAuthors Info & ClaimsPages 1096 - 1099
Abstract
In this paper, we present ComplAI, a unique framework to enable, observe, analyze and quantify explainability, robustness, performance, fairness, and model's behavior in drift scenarios, and to provide a single Trust Factor that evaluates different supervised ML models from an overall responsibility perspective. It helps users to (a) connect their models and enable explanations, (b) assess and visualize different aspects of the model and (c) compare different models from an overall perspective thereby facilitating actionable recourse for improvement of the models. ComplAI is model agnostic and works with different supervised machine learning scenarios and frameworks, seamlessly integrable with any ML life-cycle framework. Thus, this already deployed framework aims to unify critical aspects of Responsible AI systems for regulating the development process of such real systems. The theory version of the paper and a demo version is available in this link (use the Zip Password: Welcome2022!). An detailed version of the paper is available in Arxiv.
References
[1]
Black, E., Yeom, S., and Fredrikson, M. (2020). Fliptest: fairness testing via optimal transport. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, pages 111--121.
[2]
Brughmans, D. and Martens, D. (2021). Nice: An algorithm for nearest instance counterfactual explanations. arXiv preprint arXiv:2104.07411.
[3]
Carlini, N. and Wagner, D. (2017). Towards evaluating the robustness of neural networks. In 2017 IEE symposium on security and privacy (SP).
[4]
Feldman, M., Friedler, S. A., Moeller, J., Scheidegger, C., and Venkatasubramanian, S. (2015). Certifying and removing disparate impact. In ACM SIGKDD 2015.
[5]
Fernandez, C., Provost, F. J., and Han, X. (2020). Explaining data-driven decisions made by ai systems: The counterfactual approach. ArXiv, abs/2001.07417.
[6]
Guidotti, R., Monreale, A., Ruggieri, S., Pedreschi, D., Turini, F., and Giannotti, F. (2018). Local rule-based explanations of black box decision systems. arXiv preprint arXiv:1805.10820.
[7]
Hardt, M., Chen, X., Cheng, X., Donini, M., Gelman, J., Gollaprolu, S., He, J., Larroy, P., Liu, X., McCarthy, N., Rathi, A., Rees, S., Siva, A., Tsai, E., Vasist, K., Yilmaz, P., Zafar, M. B., Das, S., Haas, K., Hill, T., and Kenthapadi, K. (2021). Amazon sagemaker clarify: Machine learning bias detection and explainability in the cloud. In ACM SIGKDD 2021.
[8]
Lundberg, S., Erion, G., Chen, H., DeGrave, A., Prutkin, J., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., and Lee, S.-I. (2020). From local explanations to global understanding with explainable ai for trees. Nature Machine Intelligence, 2.
[9]
Martens, D. and Provost, F. (2014). Explaining data-driven document classifications. MIS Q., 38(1):73--100.
[10]
Ramon, Y., Martens, D., Provost, F. J., and Evgeniou, T. (2020). A comparison of instance-level counterfactual explanation algorithms for behavioral and textual data: Sedc, lime-c and shap-c. Advances in Data Analysis and Classification, 14:801--819.
[11]
Ribeiro, M. T., Singh, S., and Guestrin, C. (2016). "Why should I trust you?": Explaining the predictions of any classifier. In ACM SIGKDD 2016.
[12]
Russell, C. (2019). Efficient search for diverse coherent explanations. In FAT* '19.
[13]
Sharma, S., Henderson, J., and Ghosh, J. (2020). CERTIFAI: A common framework to provide explanations and analyse the fairness and robustness of black-box models. In AAAI/ACM AIES 2020.
[14]
Ustun, B., Spangher, A., and Liu, Y. (2019). Actionable recourse in linear classification. In Proceedings of the Conference on Fairness, Accountability, and Transparency, FAT* '19.
[15]
Wachter, S., Mittelstadt, B., and Russell, C. (2017). Counterfactual explanations without opening the black box: Automated decisions and the gdpr. Harv. JL & Tech., 31:841.
[16]
Weng, T.-W., Zhang, H., Chen, P.-Y., Yi, J., Su, D., Gao, Y., Hsieh, C.-J., and Daniel, L. (2018). Evaluating the robustness of neural networks: An extreme value theory approach. In International Conference on Learning Representations (ICLR).
[17]
Wexler, J., Pushkarna, M., Bolukbasi, T., Wattenberg, M., Viégas, F., and Wilson, J. (2019). The What-If tool: Interactive probing of machine learning models. IEEE transactions on visualization and computer graphics, 26(1):56--65.
Index Terms
- ComplAI: Framework for Multi-factor Assessment of Black-Box Supervised Machine Learning Models
Recommendations
Explainable machine learning in deployment
FAT* '20: Proceedings of the 2020 Conference on Fairness, Accountability, and TransparencyExplainable machine learning offers the potential to provide stakeholders with insights into model behavior by using various methods such as feature importance scores, counterfactual explanations, or influential training data. Yet there is little ...
Unlocking the Black Box: Towards Interactive Explainable Automated Machine Learning
Intelligent Data Engineering and Automated Learning – IDEAL 2023AbstractAutomated machine learning (AutoML) has transformed the process of selecting optimal machine learning (ML) models by autonomously searching for the most appropriate ones and fine-tuning associated hyperparameters. This eliminates the burdensome ...
Explaining Decisions of Black-Box Models Using BARBE
Database and Expert Systems ApplicationsAbstractMachine learning models are ubiquitous today in most application domains and are often taken for granted. While integrated into many systems, oftentimes even unnoticed by the user, these powerful models frequently remain as black-boxes. They are ...
Comments
Information & Contributors
Information
Published In
March 2023
1932 pages
ISBN:9781450395175
DOI:10.1145/3555776
- Conference Chairs:
- Jiman Hong,
- Maart Lanperne,
- Program Chairs:
- Juw Won Park,
- Tomas Cerny,
- Publication Chair:
- Hossain Shahriar
Copyright © 2023 Owner/Author(s).
Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s).
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 07 June 2023
Check for updates
Author Tags
Qualifiers
- Poster
Conference
SAC '23
Sponsor:
Acceptance Rates
Overall Acceptance Rate 1,650 of 6,669 submissions, 25%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 71Total Downloads
- Downloads (Last 12 months)59
- Downloads (Last 6 weeks)3
Reflects downloads up to 15 Sep 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in