Recent decades have seen the rise of large-scale Deep Neural Networks (DNNs) to achieve human-competitive performance in a variety of AI tasks. Often consisting of hundreds of million, if not hundreds of billion, parameters, these DNNs are too large to be deployed to or efficiently run on resource-constrained devices such as mobile phones or Internet of Things microcontrollers. Systems relying on large-scale DNNs thus have to call the corresponding model over the network, leading to substantial costs for hosting and running the large-scale remote model, costs which are often charged on a per-use basis. In this article, we propose BiSupervised , a novel architecture, where, before relying on a large remote DNN, a system attempts to make a prediction on a small-scale local model. A DNN supervisor monitors said prediction process and identifies easy inputs for which the local prediction can be trusted. For these inputs, the remote model does not have to be invoked, thus saving costs while only marginally impacting the overall system accuracy. Our architecture furthermore foresees a second supervisor to monitor the remote predictions and identify inputs for which not even these can be trusted, allowing to raise an exception or run a fallback strategy instead. We evaluate the cost savings and the ability to detect incorrectly predicted inputs on four diverse case studies: IMDb movie review sentiment classification, GitHub issue triaging, ImageNet image classification, and SQuADv2 free-text question answering. In all four case studies, we find that BiSupervised allows to reduce cost by at least 30% while maintaining similar system-level prediction performance. In two case studies (IMDb and SQuADv2), we find that BiSupervised even achieves a higher system-level accuracy, at reduced cost, compared to a remote-only model. Furthermore, measurements taken on our setup indicate a large potential of BiSupervised to reduce average prediction latency.

This is the Replicated Computational Results (RCR) Report for our TOSEM paper “Adopting Two Supervisors for Efficient Use of Large-Scale Remote Deep Neural Networks”, where we propose a novel client-server architecture allowing to leverage the high accuracy of huge neural networks running on remote servers while reducing the economical and latency costs typically coming from using such models. As part of this RCR, we provide a replication package, which allows the full replication of all our results and is specifically designed to facilitate reuse.

Abstract Deep Neural Networks (DNNs) are becoming a crucial component of modern software systems, but they are prone to fail under conditions that are different from the ones observed during training (out-of-distribution inputs) or on inputs that are truly ambiguous, i.e., inputs that admit multiple classes with nonzero probability in their labels. Recent work proposed DNN supervisors to detect high-uncertainty inputs before their possible misclassification leads to any harm. To test and compare the capabilities of DNN supervisors, researchers proposed test generation techniques, to focus the testing effort on high-uncertainty inputs that should be recognized as anomalous by supervisors. However, existing test generators aim to produce out-of-distribution inputs. No existing model- and supervisor independent technique targets the generation of truly ambiguous test inputs, i.e., inputs that admit multiple classes according to expert human judgment. In this paper, we propose a novel way to generate ambiguous inputs to test DNN supervisors and used it to empirically compare several existing supervisor techniques. In particular, we propose AmbiGuess to generate ambiguous samples for image classification problems. AmbiGuess is based on gradient-guided sampling in the latent space of a regularized adversarial autoencoder. Moreover, we conducted what is $${-}$$ - to the best of our knowledge $${-}$$ - the most extensive comparative study of DNN supervisors, considering their capabilities to detect 4 distinct types of high-uncertainty inputs, including truly ambiguous ones. We find that the tested supervisors’ capabilities are complementary: Those best suited to detect true ambiguity perform worse on invalid, out-of-distribution and adversarial inputs and vice-versa.

Summary Deep neural networks (DNN) are increasingly used as components of larger software systems that need to process complex data, such as images, written texts, audio/video signals. DNN predictions cannot be assumed to be always correct for several reasons, amongst which the huge input space that is dealt with, the ambiguity of some inputs data, as well as the intrinsic properties of learning algorithms, which can provide only statistical warranties. Hence, developers have to cope with some residual error probability. An architectural pattern commonly adopted to manage failure prone components is the supervisor , an additional component that can estimate the reliability of the predictions made by untrusted (e.g., DNN) components and can activate an automated healing procedure when these are likely to fail, ensuring that the deep learning‐based system (DLS) does not cause damages, despite its main functionality being suspended. In this paper, we consider DLS that implement a supervisor by means of uncertainty estimation. After overviewing the main approaches to uncertainty estimation and discussing their pros and cons, we motivate the need for a specific empirical assessment method that can deal with the experimental setting in which supervisors are used, where accuracy of the DNN matters only as long as the supervisor lets the DLS continue to operate. Then we present a large empirical study conducted to compare the alternative approaches to uncertainty estimation. We distilled a set of guidelines for developers that are useful to incorporate a supervisor based on uncertainty monitoring into a DLS.

Test Input Prioritizers (TIP) for Deep Neural Networks (DNN) are an important technique to handle the typically very large test datasets efficiently, saving computation and labelling costs. This is particularly true for large scale, deployed systems, where inputs observed in production are recorded to serve as potential test or training data for next versions of the system. Feng et. al. propose DeepGini, a very fast and simple TIP and show that it outperforms more elaborate techniques such as neuron- and surprise coverage. In a large-scale study (4 case studies, 8 test datasets, 32’200 trained models) we verify their findings. However, we also find that other comparable or even simpler baselines from the field of uncertainty quantification, such as the predicted softmax likelihood or the entropy of the predicted softmax likelihoods perform equally well as DeepGini

On complex problems, state of the art prediction accuracy of Deep Neural Networks (DNN) can be achieved using very large-scale models, consisting of billions of parameters. Such models can only be run on dedicated servers, typically provided by a 3th party service, which leads to a substantial monetary cost for every prediction. We propose a new software architecture for client-side applications, where a small local DNN is used alongside a remote large-scale model, aiming to make easy predictions locally at negligible monetary cost, while still leveraging the benefits of a large model for challenging inputs. In a proof of concept we reduce prediction cost by up to 50% without negatively impacting system accuracy.

Modern software systems rely on Deep Neural Networks (DNN) when processing complex, unstructured inputs, such as images, videos, natural language texts or audio signals. Provided the intractably large size of such input spaces, the intrinsic limitations of learning algorithms and the ambiguity about the expected predictions for some of the inputs, not only there is no guarantee that DNN's predictions are always correct, but rather developers must safely assume a low, though not negligible, error probability. A fail-safe Deep Learning based System (DLS) is one equipped to handle DNN faults by means of a supervisor, capable of recognizing predictions that should not be trusted and that should activate a healing procedure bringing the DLS to a safe state.In this paper, we propose an approach to use DNN uncertainty estimators to implement such supervisor. We first discuss advantages and disadvantages of existing approaches to measure uncertainty for DNNs and propose novel metrics for the empirical assessment of the supervisor that rely on such approaches. We then describe our publicly available tool UNCERTAINTY-WIZARD, which allows transparent estimation of uncertainty for regular tf.keras DNNs. Lastly, we discuss a large-scale study conducted on four different subjects to empirically validate the approach, reporting the lessons-learned as guidance for software engineers who intend to monitor uncertainty for fail-safe execution of DLS.

Uncertainty and confidence have been shown to be useful metrics in a wide variety of techniques proposed for deep learning testing, including test data selection and system supervision. We present Uncertainty-Wizard, a tool that allows to quantify such uncertainty and confidence in artificial neural networks. It is built on top of the industry-leading TF.KERAS deep learning API and it provides a near-transparent and easy to understand interface. At the same time, it includes major performance optimizations that we benchmarked on two different machines and different configurations.

Deep Neural Networks (DNNs) are the core component of modern autonomous driving systems. To date, it is still unrealistic that a DNN will generalize correctly to all driving conditions. Current testing techniques consist of offline solutions that identify adversarial or corner cases for improving the training phase.

Abstract Context: A Machine Learning based System (MLS) is a software system including one or more components that learn how to perform a task from a given data set. The increasing adoption of MLSs in safety critical domains such as autonomous driving, healthcare, and finance has fostered much attention towards the quality assurance of such systems. Despite the advances in software testing, MLSs bring novel and unprecedented challenges, since their behaviour is defined jointly by the code that implements them and the data used for training them. Objective: To identify the existing solutions for functional testing of MLSs, and classify them from three different perspectives: (1) the context of the problem they address, (2) their features, and (3) their empirical evaluation. To report demographic information about the ongoing research. To identify open challenges for future research. Method: We conducted a systematic mapping study about testing techniques for MLSs driven by 33 research questions. We followed existing guidelines when defining our research protocol so as to increase the repeatability and reliability of our results. Results: We identified 70 relevant primary studies, mostly published in the last years. We identified 11 problems addressed in the literature. We investigated multiple aspects of the testing approaches, such as the used/proposed adequacy criteria, the algorithms for test input generation, and the test oracles. Conclusions: The most active research areas in MLS testing address automated scenario/input generation and test oracle creation. MLS testing is a rapidly growing and developing research area, with many open challenges, such as the generation of realistic inputs and the definition of reliable evaluation metrics and benchmarks.