2020

Model Agnostic Multilevel Explanations

Ramamurthy, Karthikeyan Natesan, Vinzamuri, Bhanukiran, Zhang, Yunfeng et al.

Understand

In recent years, post-hoc local instance-level and global dataset-level explainability of black-box models has received a lot of attention.

Much less attention has been given to obtaining insights at intermediate or group levels, which is a need outlined in recent works that study the challenges in realizing the guidelines in the General Data Protection Regulation (GDPR).
In this paper, we propose a meta-method that, given a typical local explainability method, can build a multilevel explanation tree.
The leaves of this tree correspond to the local explanations, the root corresponds to the global explanation, and intermediate levels correspond to explanations for groups of data points that it automatically clusters.

Built on

V. Arya, R. K. E. Bellamy, P.-Y. Chen, A. Dhurandhar, M. Hind, S. C. Hoffman, S. Houde, Q. V. Liao, R. Luss, A. Mojsilović, S. Mourad, P. Pedemonte, R. Raghavendra, J. Richards, P. Sattigeri, K. Shanmugam, M. Singh, K. R. Varshney, D. Wei, and Y. Zhang, “One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques,” Sept. 2019. [Online]. Available:
Original
1909
Earlier work this paper cites.
R. T. Rockafellar,
1970
Earlier work this paper cites.
R. M. Joseph Grenny, Al Switzler,
2001
Earlier work this paper cites.
P. Lipton, “What Good is an Explanation?”
2001
Earlier work this paper cites.
T. Pettinger, “10 Tips for Effective Conversation,” in
2008
Earlier work this paper cites.
S. Boyd, N. Parikh, E. Chu, B. Peleato, J. Eckstein
2011
Earlier work this paper cites.
F. Wang and C. Rudin, “Falling rule lists,” in
2015
Earlier work this paper cites.
G. K. Chen, E. C. Chi, J. M. O. Ranola, and K. Lange, “Convex clustering: An attractive alternative to hierarchical clustering,”
2015
Earlier work this paper cites.
M. Ribeiro, S. Singh, and C. Guestrin, “"Why Should I Trust You?" Explaining the Predictions of Any Classifier,” in
2016
Earlier work this paper cites.
G. Su, D. Wei, K. Varshney, and D. Malioutov, “Interpretable Two-level Boolean Rule Learning for Classification,” in
Original
2016
Earlier work this paper cites.

Similar

Been Kim and Rajiv Khanna and Oluwasanmi Koyejo, “Examples are not enough, learn to criticize! criticism for interpretability,” in
2016
Cited alongside, same era.
G. Montavon, W. Samek, and K.-R. Müller, “Methods for interpreting and understanding deep neural networks,”
2017
Cited alongside, same era.
S. Lundberg and S.-I. Lee, “Unified framework for interpretable methods,” in
2017
Cited alongside, same era.
M. Yu, A. M. Thompson, K. N. Ramamurthy, E. Yang, and A. C. Lozano, “Multitask Learning using Task Clustering with Applications to Predictive Modeling and GWAS of Plant Varieties,”
Original
2017
Cited alongside, same era.
D. Dheeru and E. Karra Taniskidou, “UCI machine learning repository,” 2017. [Online]. Available:
2017
Cited alongside, same era.
M. Hong and Z.-Q. Luo, “On the linear convergence of the alternating direction method of multipliers,”
2017
Cited alongside, same era.
P. N. Yannella and O. Kagan, “Analysis: Article 29 Working Party Guidelines on Automated Decision Making Under GDPR,” 2018, https://www.cyberadviserblog.com/2018/01/analysis-article-29-working-party-guidelines-on-automated-decision-making-under-gdpr/
2018
Cited alongside, same era.
FICO, “Explainable Machine Learning Challenge,”
2018
Cited alongside, same era.
A. Dhurandhar, P.-Y. Chen, R. Luss, C.-C. Tu, P. Ting, K. Shanmugam, and P. Das, “Explanations based on the missing: Towards contrastive explanations with pertinent negatives,” in
2018
Cited alongside, same era.

Then

G. Plumb, D. Molitor, and A. S. Talwalkar, “Model agnostic supervised local explanations,” in
2018
Later among the works it cites.
M. Tsang, Y. Sun, D. Ren, and Y. Liu, “Can I trust you more? Model-agnostic hierarchical explanations,”
Original
2018
Later among the works it cites.
K. Gurumoorthy, A. Dhurandhar, G. Cecchi, and C. Aggarwal, “Efficient Data Representation by Selecting Prototypes with Importance Weights,”
2019
Later among the works it cites.
D. Pedreschi, F. Giannotti, R. Guidotti, A. Monreale, S. Ruggieri, and F. Turini, “Meaningful explanations of Black Box AI decision systems,” in
2019
Later among the works it cites.
M. Weylandt, J. Nagorski, and G. I. Allen, “Dynamic Visualization and Fast Computation for Convex Clustering via Algorithmic Regularization,”
2019
Later among the works it cites.
M. Yu, K. N. Ramamurthy, A. Thompson, and A. Lozano, “Simultaneous Parameter Learning and Bi-Clustering for Multi-Response Models,”
2019
Later among the works it cites.
M. E. Kaminski and G. Malgieri, “Multi-layered explanations from algorithmic impact assessments in the GDPR,” in
2020
Closest in time.
S. Lundberg, G. Erion, H. Chen, D. A, J. M. Prutkin, B. Nair, R. Katz, J. Himmelfarb, N. Bansal, and S. I. Lee, “From local explanations to global understanding with explainable AI for trees,” in
2020
Closest in time.
U. Bhatt, A. Xiang, S. Sharma, A. Weller, Y. J. Ankur Taly, J. Ghosh, R. Puri, J. M. F. Moura, and P. Eckersley, “Efficient Data Representation by Selecting Prototypes with Importance Weights,” in
2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…