Ribeiro, Marco Tulio, Singh, Sameer, Guestrin, Carlos

Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model. Such understanding also provides insights into the model, which can be used to transform an untrustworthy model or prediction into a trustworthy one. In this work, we propose LIME, a novel explanation technique that explains the predictions of any classifier in an interpretable and faithful manner, by learning an interpretable model locally around the prediction. We also propose a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem. We demonstrate the flexibility of these methods by explaining different models for text (e.g. random forests) and image classification (e.g. neural networks). We show the utility of explanations via novel experiments, both simulated and with human subjects, on various scenarios that require trust: deciding if one should trust a prediction, choosing between models, improving an untrustworthy classifier, and identifying why a classifier should not be trusted.

Eaton, Eric (Lockheed Martin Advanced Technology Laboratories) | Holness, Gary (Lockheed Martin Advanced Technology Laboratories) | McFarlane, Daniel (Lockheed Martin Advanced Technology Laboratories)

We present an interactive learning method that enables a user to iteratively refine a regression model. The user examines the output of the model, visualized as the vertical axis of a 2D scatterplot, and provides corrections by repositioning individual data instances to the correct output level. Each repositioned data instance acts as a control point for altering the learned model, using the geometry underlying the data. We capture the underlying structure of the data as a manifold, on which we compute a set of basis functions as the foundation for learning. Our results show that manifold-based interactive learning improves performance monotonically with each correction, outperforming alternative approaches.

Maratea, Marco, Pulina, Luca, Ricca, Francesco

Answer Set Programming (ASP) is a truly-declarative programming paradigm proposed in the area of non-monotonic reasoning and logic programming, that has been recently employed in many applications. The development of efficient ASP systems is, thus, crucial. Having in mind the task of improving the solving methods for ASP, there are two usual ways to reach this goal: $(i)$ extending state-of-the-art techniques and ASP solvers, or $(ii)$ designing a new ASP solver from scratch. An alternative to these trends is to build on top of state-of-the-art solvers, and to apply machine learning techniques for choosing automatically the "best" available solver on a per-instance basis. In this paper we pursue this latter direction. We first define a set of cheap-to-compute syntactic features that characterize several aspects of ASP programs. Then, we apply classification methods that, given the features of the instances in a {\sl training} set and the solvers' performance on these instances, inductively learn algorithm selection strategies to be applied to a {\sl test} set. We report the results of a number of experiments considering solvers and different training and test sets of instances taken from the ones submitted to the "System Track" of the 3rd ASP Competition. Our analysis shows that, by applying machine learning techniques to ASP solving, it is possible to obtain very robust performance: our approach can solve more instances compared with any solver that entered the 3rd ASP Competition. (To appear in Theory and Practice of Logic Programming (TPLP).)

With cloud computing environments such as Amazon EC2, users typically have a large number of choices in terms of the instance types and number of instances they can run their jobs on. Not surprisingly, the amount of memory per core, storage media, and the number of instances are crucial chocies that determine the running time and thus indirectly the cost of running a given job. Ernest takes on the challenge of predicting the most efficient configuration for large advanced analytics applications in a heterogeneous multi-tenant environments. It might be that you have a certain budget, and want to minimize the running time given that budget, or perhaps you have a time limit, and want to complete the job as cheaply as possible within that time limit. Either way, exhaustively trying all of the combinations to find out which work the best isn't really feasible.

Rahnama, Amir Hossein Akhavan, Boström, Henrik

LIME is a popular approach for explaining a black-box prediction through an interpretable model that is trained on instances in the vicinity of the predicted instance. To generate these instances, LIME randomly selects a subset of the non-zero features of the predicted instance. After that, the perturbed instances are fed into the black-box model to obtain labels for these, which are then used for training the interpretable model. In this study, we present a systematic evaluation of the interpretable models that are output by LIME on the two use-cases that were considered in the original paper introducing the approach; text classification and object detection. The investigation shows that the perturbation and labeling phases result in both data and label shift. In addition, we study the correlation between the shift and the fidelity of the interpretable model and show that in certain cases the shift negatively correlates with the fidelity. Based on these findings, it is argued that there is a need for a new sampling approach that mitigates the shift in the LIME's framework.