skip to main content


This content will become publicly available on April 12, 2025

Title: Inferring Data Preconditions from Deep Learning Models for Trustworthy Prediction in Deployment
Deep learning models are trained with certain assumptions about the data during the development stage and then used for prediction in the deployment stage. It is important to reason about the trustworthiness of the model's predictions with unseen data during deployment. Existing methods for specifying and verifying traditional software are insufficient for this task, as they cannot handle the complexity of DNN model architecture and expected outcomes. In this work, we propose a novel technique that uses rules derived from neural network computations to infer data preconditions for a DNN model to determine the trustworthiness of its predictions. Our approach, DeepInfer involves introducing a novel abstraction for a trained DNN model that enables weakest precondition reasoning using Dijkstra's Predicate Transformer Semantics. By deriving rules over the inductive type of neural network abstract representation, we can overcome the matrix dimensionality issues that arise from the backward non-linear computation from the output layer to the input layer. We utilize the weakest precondition computation using rules of each kind of activation function to compute layer-wise precondition from the given postcondition on the final output of a deep neural network. We extensively evaluated DeepInfer on 29 real-world DNN models using four different datasets collected from five different sources and demonstrated the utility, effectiveness, and performance improvement over closely related work. DeepInfer efficiently detects correct and incorrect predictions of high-accuracy models with high recall (0.98) and high F-1 score (0.84) and has significantly improved over the prior technique, SelfChecker. The average runtime overhead of DeepInfer is low, 0.22 sec for all the unseen datasets. We also compared runtime overhead using the same hardware settings and found that DeepInfer is 3.27 times faster than SelfChecker, the state-of- the-art in this area.  more » « less
Award ID(s):
2223812 2120448
PAR ID:
10540741
Author(s) / Creator(s):
; ;
Publisher / Repository:
Association for Computing Machinery
Date Published:
ISBN:
9798400702174
Subject(s) / Keyword(s):
deep neural networks, weakest precondition, trustworthiness
Format(s):
Medium: X Size: 2.2MB Other: .pdf
Size(s):
2.2MB
Location:
ICSE '24: Proceedings of the IEEE/ACM 46th International Conference on Software Engineering, Lisbon, Portugal
Sponsoring Org:
National Science Foundation
More Like this
  1. Deep neural network (DNN) models have achieved state‐of‐the‐art predictive accuracy in a wide range of applications. However, it remains a challenging task to accurately quantify the uncertainty in DNN predictions, especially those of continuous outcomes. To this end, we propose the Bayesian deep noise neural network (B‐DeepNoise), which generalizes standard Bayesian DNNs by extending the random noise variable from the output layer to all hidden layers. Our model is capable of approximating highly complex predictive density functions and fully learn the possible random variation in the outcome variables. For posterior computation, we provide a closed‐form Gibbs sampling algorithm that circumvents tuning‐intensive Metropolis–Hastings methods. We establish a recursive representation of the predictive density and perform theoretical analysis on the predictive variance. Through extensive experiments, we demonstrate the superiority of B‐DeepNoise over existing methods in terms of density estimation and uncertainty quantification accuracy. A neuroimaging application is included to show our model's usefulness in scientific studies.

     
    more » « less
  2. We present NeurASP, a simple extension of answer set programs by embracing neural networks. By treating the neural network output as the probability distribution over atomic facts in answer set programs, NeurASP provides a simple and effective way to integrate sub-symbolic and symbolic computation. We demonstrate how NeurASP can make use of a pre-trained neural network in symbolic computation and how it can improve the neural network's perception result by applying symbolic reasoning in answer set programming. Also, NeurASP can make use of ASP rules to train a neural network better so that a neural network not only learns from implicit correlations from the data but also from the explicit complex semantic constraints expressed by the rules.

     
    more » « less
  3. A deep neural network (DNN)-based adaptive controller with a real-time and concurrent learning (CL)-based adaptive update law is developed for a class of uncertain, nonlinear dynamic systems. The DNN in the control law is used to approximate the uncertain nonlinear dynamic model. The inner-layer weights of the DNN are updated offline using data collected in real-time; whereas, the output-layer DNN weights are updated online (i.e., in real-time) using the Lyapunov- and CL-based adaptation law. Specifically, the inner-layer weights of the DNN are trained offline (concurrent to real-time execution) after a sufficient amount of data is collected in real-time to improve the performance of the system, and after training is completed the inner-layer DNN weights are updated in batch-updates. The key development in this work is that the output-layer DNN update law is augmented with CL-based terms to ensure that the output-layer DNN weight estimates converge to within a ball of their optimal values. A Lyapunov-based stability analysis is performed to ensure semi-global exponential convergence to an ultimate bound for the trajectory tracking errors and the output-layer DNN weight estimation errors. 
    more » « less
  4. With the success of deep neural networks (DNN), many recent works have been focusing on developing hardware accelerator for power and resource-limited embedded system via model compression techniques, such as quantization, pruning, low-rank approximation, etc. However, almost all existing DNN structure is fixed after deployment, which lacks runtime adaptive DNN structure to adapt to its dynamic hardware resource, power budget, throughput requirement, as well as dynamic workload. Correspondingly, there is no runtime adaptive hardware platform to support dynamic DNN structure. To address this problem, we first propose a dynamic channel-adaptive deep neural network (CA-DNN) which can adjust the involved convolution channel (i.e. model size, computing load) at run-time (i.e. at inference stage without retraining) to dynamically trade off between power, speed, computing load and accuracy. Further, we utilize knowledge distillation method to optimize the model and quantize the model to 8-bits and 16-bits, respectively, for hardware friendly mapping. We test the proposed model on CIFAR-10 and ImageNet dataset by using ResNet. Comparing with the same model size of individual model, our CA-DNN achieves better accuracy. Moreover, as far as we know, we are the first to propose a Processing-in-Memory accelerator for such adaptive neural networks structure based on Spin Orbit Torque Magnetic Random Access Memory(SOT-MRAM) computational adaptive sub-arrays. Then, we comprehensively analyze the trade-off of the model with different channel-width between the accuracy and the hardware parameters, eg., energy, memory, and area overhead. 
    more » « less
  5. This paper describes a novel framework for executing a network of trained deep neural network (DNN) models on commercial-off-the-shelf devices that are deployed in an IoT environment. The scenario consists of two devices connected by a wireless network: a user-end device (U), which is a low-end, energy and performance-limited processor, and a cloudlet (C), which is a substantially higher performance and energy-unconstrained processor. The goal is to distribute the computation of the DNN models between U and C to minimize the energy consumption of U while taking into account the variability in the wireless channel delay and the performance overhead of executing models in parallel. The proposed framework was implemented using an NVIDIA Jetson Nano for U and a Dell workstation with Titan Xp GPU as C. Experiments demonstrate significant improvements both in terms of energy consumption of U and processing delay. 
    more » « less