Abstract
Scientific computational models are crucial for analyzing and understanding complex real-life systems that are otherwise difficult for experimentation. However, the complex behavior and the vast input-output space of these models often make them opaque, slowing the discovery of novel phenomena. In this work, we present Hint (Hessian INTerestingness) - a new algorithm that can automatically and systematically explore black-box models and highlight local nonlinear interactions in the input-output space of the model. This tool aims to facilitate the discovery of interesting model behaviors that are unknown to the researchers. Using this simple yet powerful tool, we were able to correctly rank all pairwise interactions in known benchmark models and do so faster and with greater accuracy than state-of-the-art methods. We further applied Hint to existing computational neuroscience models, and were able to reproduce important scientific discoveries that were published years after the creation of those models. Finally, we ran Hint on two real-world models (in neuroscience and earth science) and found new behaviors of the model that were of value to domain experts.
| Original language | American English |
|---|---|
| Title of host publication | KDD 2019 - Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining |
| Publisher | Association for Computing Machinery |
| Pages | 425-435 |
| Number of pages | 11 |
| ISBN (Electronic) | 9781450362016 |
| DOIs | |
| State | Published - 25 Jul 2019 |
| Event | 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2019 - Anchorage, United States Duration: 4 Aug 2019 → 8 Aug 2019 |
Publication series
| Name | Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining |
|---|
Conference
| Conference | 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2019 |
|---|---|
| Country/Territory | United States |
| City | Anchorage |
| Period | 4/08/19 → 8/08/19 |
Bibliographical note
Funding Information:We thank the anonymous reviewers for their helpful comments. Dafna Shahaf is a Harry & Abe Sherman assistant professor. This work was supported by ISF grant 1764/15, the Drahi family foundation to IS, the Gatsby Charitable Foundation and the EPFL-Hebrew University Collaborative Grant and the EU Horizon 2020 program (720270, Human Brain Project).
Funding Information:
Finally, Hint highlights input-output regions that contrast a single heuristic assumption, namely that all features do not interact with one another with respect to the output. While this was sufficient to find previously unknown behaviors in models explored in this work, the actual priors modelers have while studying models might be different than our chosen heuristic. Similar to the work of De Bie [25], we would want users of Hint to be able to flexibly define priors that fit their beliefs, such that the highlighted samples will be as effective in updating said priors as possible. We believe that such automated tools to explore computational models can serve as a vehicle to accelerate scientific discoveries in many fields. Acknowledgements We thank the anonymous reviewers for their helpful comments. Dafna Shahaf is a Harry & Abe Sherman assistant professor. This work was supported by ISF grant 1764/15, the Drahi family foundation to IS, the Gatsby Charitable Foundation and the EPFL-Hebrew University Collaborative Grant and the EU Horizon 2020 program (720270, Human Brain Project).
Publisher Copyright:
© 2019 Association for Computing Machinery.
Keywords
- Computational models
- Interestingness
- Neuroscience
- Nonlinear interactions
- Simulation