i-Algebra: Towards Interactive Interpretability of Deep Neural Networks


  • Xinyang Zhang Pennsylvania State University
  • Ren Pang Pennsylvania State University
  • Shouling Ji Zhejiang University
  • Fenglong Ma Pennsylvania State University
  • Ting Wang Pennsylvania State University




Accountability, Interpretability & Explainability


Providing explanations for deep neural networks (DNNs) is essential for their use in domains wherein the interpretability of decisions is a critical prerequisite. Despite the plethora of work on interpreting DNNs, most existing solutions offer interpretability in an ad hoc, one-shot, and static manner, without accounting for the perception, understanding, or response of end-users, resulting in their poor usability in practice. In this paper, we argue that DNN interpretability should be implemented as the interactions between users and models. We present i-Algebra, a first-of-its-kind interactive framework for interpreting DNNs. At its core is a library of atomic, composable operators, which explain model behaviors at varying input granularity, during different inference stages, and from distinct interpretation perspectives. Leveraging a declarative query language, users are enabled to build various analysis tools (e.g., ``drill-down'', ``comparative'', ``what-if'' analysis) via flexibly composing such operators. We prototype i-Algebra and conduct user studies in a set of representative analysis tasks, including inspecting adversarial inputs, resolving model inconsistency, and cleansing contaminated data, all demonstrating its promising usability.




How to Cite

Zhang, X., Pang, R., Ji, S., Ma, F., & Wang, T. (2021). i-Algebra: Towards Interactive Interpretability of Deep Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 35(13), 11691-11698. https://doi.org/10.1609/aaai.v35i13.17390



AAAI Technical Track on Philosophy and Ethics of AI