ترغب بنشر مسار تعليمي؟ اضغط هنا

S-LIME: Stabilized-LIME for Model Explanation

270   0   0.0 ( 0 )
 نشر من قبل Zhengze Zhou
 تاريخ النشر 2021
والبحث باللغة English




اسأل ChatGPT حول البحث

An increasing number of machine learning models have been deployed in domains with high stakes such as finance and healthcare. Despite their superior performances, many models are black boxes in nature which are hard to explain. There are growing efforts for researchers to develop methods to interpret these black-box models. Post hoc explanations based on perturbations, such as LIME, are widely used approaches to interpret a machine learning model after it has been built. This class of methods has been shown to exhibit large instability, posing serious challenges to the effectiveness of the method itself and harming user trust. In this paper, we propose S-LIME, which utilizes a hypothesis testing framework based on central limit theorem for determining the number of perturbation points needed to guarantee stability of the resulting explanation. Experiments on both simulated and real world data sets are provided to demonstrate the effectiveness of our method.



قيم البحث

اقرأ أيضاً

Unintended radiated emissions arise during the use of electronic devices. Identifying and mitigating the effects of these emissions is a key element of modern power engineering and associated control systems. Signal processing of the electrical syste m can identify the sources of these emissions. A dataset known as Flaming Moes includes captured unintended radiated emissions from consumer electronics. This dataset was analyzed to construct next-generation methods for device identification. To this end, a neural network based on applying the ResNet-18 image classification architecture to the short time Fourier transforms of short segments of voltage signatures was constructed. Using this classifier, the 18 device classes and background class were identified with close to 100 percent accuracy. By applying LIME to this classifier and aggregating the results over many classifications for the same device, it was possible to determine the frequency bands used by the classifier to make decisions. Using ensembles of classifiers trained on very similar datasets from the same parent data distribution, it was possible to recover robust sets of features of device output useful for identification. The additional understanding provided by the application of LIME enhances the trainability, trustability, and transferability of URE analysis networks.
As machine learning black boxes are increasingly being deployed in domains such as healthcare and criminal justice, there is growing emphasis on building tools and techniques for explaining these black boxes in an interpretable manner. Such explanati ons are being leveraged by domain experts to diagnose systematic errors and underlying biases of black boxes. In this paper, we demonstrate that post hoc explanations techniques that rely on input perturbations, such as LIME and SHAP, are not reliable. Specifically, we propose a novel scaffolding technique that effectively hides the biases of any given classifier by allowing an adversarial entity to craft an arbitrary desired explanation. Our approach can be used to scaffold any biased classifier in such a way that its predictions on the input data distribution still remain biased, but the post hoc explanations of the scaffolded classifier look innocuous. Using extensive evaluation with multiple real-world datasets (including COMPAS), we demonstrate how extremely biased (racist) classifiers crafted by our framework can easily fool popular explanation techniques such as LIME and SHAP into generating innocuous explanations which do not reflect the underlying biases.
We present the first end to end approach for real time material estimation for general object shapes with uniform material that only requires a single color image as input. In addition to Lambertian surface properties, our approach fully automaticall y computes the specular albedo, material shininess, and a foreground segmentation. We tackle this challenging and ill posed inverse rendering problem using recent advances in image to image translation techniques based on deep convolutional encoder decoder architectures. The underlying core representations of our approach are specular shading, diffuse shading and mirror images, which allow to learn the effective and accurate separation of diffuse and specular albedo. In addition, we propose a novel highly efficient perceptual rendering loss that mimics real world image formation and obtains intermediate results even during run time. The estimation of material parameters at real time frame rates enables exciting mixed reality applications, such as seamless illumination consistent integration of virtual objects into real world scenes, and virtual material cloning. We demonstrate our approach in a live setup, compare it to the state of the art, and demonstrate its effectiveness through quantitative and qualitative evaluation.
While designing inductive bias in neural architectures has been widely studied, we hypothesize that transformer networks are flexible enough to learn inductive bias from suitable generic tasks. Here, we replace architecture engineering by encoding in ductive bias in the form of datasets. Inspired by Peirces view that deduction, induction, and abduction form an irreducible set of reasoning primitives, we design three synthetic tasks that are intended to require the model to have these three abilities. We specifically design these synthetic tasks in a way that they are devoid of mathematical knowledge to ensure that only the fundamental reasoning biases can be learned from these tasks. This defines a new pre-training methodology called LIME (Learning Inductive bias for Mathematical rEasoning). Models trained with LIME significantly outperform vanilla transformers on three very different large mathematical reasoning benchmarks. Unlike dominating the computation cost as traditional pre-training approaches, LIME requires only a small fraction of the computation cost of the typical downstream task.
The Shapley value has become a popular method to attribute the prediction of a machine-learning model on an input to its base features. The use of the Shapley value is justified by citing [16] showing that it is the emph{unique} method that satisfies certain good properties (emph{axioms}). There are, however, a multiplicity of ways in which the Shapley value is operationalized in the attribution problem. These differ in how they reference the model, the training data, and the explanation context. These give very different results, rendering the uniqueness result meaningless. Furthermore, we find that previously proposed approaches can produce counterintuitive attributions in theory and in practice---for instance, they can assign non-zero attributions to features that are not even referenced by the model. In this paper, we use the axiomatic approach to study the differences between some of the many operationalizations of the Shapley value for attribution, and propose a technique called Baseline Shapley (BShap) that is backed by a proper uniqueness result. We also contrast BShap with Integrated Gradients, another extension of Shapley value to the continuous setting.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا