ProtoDash: Fast Interpretable Prototype Selection

By Karthik S. Gurumoorthy, Amit Dhurandhar, Guillermo A. Cecchi. 2017

22 citations recorded by the source corpus.

In this paper we propose an efficient algorithm ProtoDash for selecting prototypical examples from complex datasets. Our work builds on top of the learn to criticize (L2C) work by Kim et al. (2016) and generalizes it to not only select prototypes for a given sparsity level $m$ but also to associate non-negative weights with each of them indicative of the importance of each prototype. Unlike in the case of L2C, this extension provides a single coherent framework under which both prototypes and criticisms (i.e. lowest weighted prototypes) can be found. Furthermore, our framework works for any symmetric positive definite kernel thus addressing one of the open questions laid out in Kim et al. (2016). Our additional requirement of learning non-negative weights introduces technical challenges as the objective is no longer submodular as in the previous work. However, we show that the problem is weakly submodular and derive approximation guarantees for our fast ProtoDash algorithm. Moreover, ProtoDash can not only find prototypical examples for a dataset $X$, but it can also find (weighted) prototypical examples from $X^{(2)}$ that best represent another dataset $X^{(1)}$, where $X^{(1)}$ and $X^{(2)}$ belong to the same feature space. We demonstrate the efficacy of our method on diverse domains namely; retail, digit recognition (MNIST) and on the latest publicly available 40 health questionnaires obtained from the Center for Disease Control (CDC) website maintained by the US Dept. of Health. We validate the results quantitatively as well as qualitatively based on expert feedback and recently published scientific studies on public health.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) (2018, background): “Prototypes are a selection of representative instances from the data [133]–[135], thus item membership is determined by its similarity to the prototypes which leads to overgeneralization.”
A Survey on the Explainability of Supervised Machine Learning (2020, methodology): “ProtoDash (Gurumoorthy et al., 2017) is an approach for selecting prototypical examples from complex data sets that extends the work from Kim et al. (2016) by non-negative weights for the importance of each prototype.”
Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives (2018, methodology): “Examples include establishment for rule/decision lists [39, 36], prototype exploration [19, 13], developing methods inspired by psychometrics [17] and learning human-consumable models [6].”
Sequential Explanations with Mental Model-Based Policies (2020, methodology): “We compared three experimental policies in selecting explanations generated by prototype (Kim et al., 2016; Gurumoorthy et al., 2017) and deep Taylor decomposition saliency map (Montavon et al., 2017) explainers, relative to random selection baselines.”
Interpretable Counterfactual Explanations Guided by Prototypes (2019, background): “(Kim, Khanna, and Koyejo 2016; Gurumoorthy, Dhurandhar, and Cecchi 2017) use prototypes as example-based explanations to improve the interpretability of complex datasets.”
TIP: Typifying the Interpretability of Procedures (2017, methodology): “This setup is similar to the one in [25].”