Automatic Fault Detection for Deep Learning Programs Using Graph Transformations

• URL: http://arxiv.org/abs/2105.08095v2
• Date: Mon, 31 May 2021 02:17:12 GMT
• Title: Automatic Fault Detection for Deep Learning Programs Using Graph Transformations
• Authors: Amin Nikanjam, Houssem Ben Braiek, Mohammad Mehdi Morovati, Foutse Khomh
• Abstract summary: We propose NeuraLint, a model-based fault detection approach for Deep Learning programs. NeuraLint effectively detects faults and design issues in both synthesized and real-world examples with a recall of 70.5 % and a precision of 100 %. Although the proposed meta-model is designed for feedforward neural networks, it can be extended to support other neural network architectures.
• Score: 13.572917264310119
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Nowadays, we are witnessing an increasing demand in both corporates and academia for exploiting Deep Learning (DL) to solve complex real-world problems. A DL program encodes the network structure of a desirable DL model and the process by which the model learns from the training dataset. Like any software, a DL program can be faulty, which implies substantial challenges of software quality assurance, especially in safety-critical domains. It is therefore crucial to equip DL development teams with efficient fault detection techniques and tools. In this paper, we propose NeuraLint, a model-based fault detection approach for DL programs, using meta-modelling and graph transformations. First, we design a meta-model for DL programs that includes their base skeleton and fundamental properties. Then, we construct a graph-based verification process that covers 23 rules defined on top of the meta-model and implemented as graph transformations to detect faults and design inefficiencies in the generated models (i.e., instances of the meta-model). First, the proposed approach is evaluated by finding faults and design inefficiencies in 28 synthesized examples built from common problems reported in the literature. Then NeuraLint successfully finds 64 faults and design inefficiencies in 34 real-world DL programs extracted from Stack Overflow posts and GitHub repositories. The results show that NeuraLint effectively detects faults and design issues in both synthesized and real-world examples with a recall of 70.5 % and a precision of 100 %. Although the proposed meta-model is designed for feedforward neural networks, it can be extended to support other neural network architectures such as recurrent neural networks. Researchers can also expand our set of verification rules to cover more types of issues in DL programs.

Related papers

• DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback Alignment [57.62885438406724]
  Graph neural networks are recognized for their strong performance across various applications. BP has limitations that challenge its biological plausibility and affect the efficiency, scalability and parallelism of training neural networks for graph-based tasks. We propose DFA-GNN, a novel forward learning framework tailored for GNNs with a case study of semi-supervised learning.
  arXiv  Detail & Related papers  (2024-06-04T07:24:51Z)
• Sequential Graph Neural Networks for Source Code Vulnerability Identification [5.582101184758527]
  We present a properly curated C/C++ source code vulnerability dataset to aid in developing models. We also propose a learning framework based on graph neural networks, denoted SEquential Graph Neural Network (SEGNN) for learning a large number of code semantic representations. Our evaluations on two datasets and four baseline methods in a graph classification setting demonstrate state-of-the-art results.
  arXiv  Detail & Related papers  (2023-05-23T17:25:51Z)
• Deep Graph Reprogramming [112.34663053130073]
  "Deep graph reprogramming" is a model reusing task tailored for graph neural networks (GNNs) We propose an innovative Data Reprogramming paradigm alongside a Model Reprogramming paradigm.
  arXiv  Detail & Related papers  (2023-04-28T02:04:29Z)
• NeuRI: Diversifying DNN Generation via Inductive Rule Inference [16.463237407360594]
  NeuRI is a fully automated approach for generating valid and diverse Deep Learning models. NeuRI improves branch coverage of PyTorch by 24% and 15% over the state-of-the-art model-level fuzzers.
  arXiv  Detail & Related papers  (2023-02-04T23:42:07Z)
• Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks [52.566735716983956]
  We propose a graph gradual pruning framework termed CGP to dynamically prune GNNs. Unlike LTH-based methods, the proposed CGP approach requires no re-training, which significantly reduces the computation costs. Our proposed strategy greatly improves both training and inference efficiency while matching or even exceeding the accuracy of existing methods.
  arXiv  Detail & Related papers  (2022-07-18T14:23:31Z)
• CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning [92.36705236706678]
  "CodeRL" is a new framework for program synthesis tasks through pretrained LMs and deep reinforcement learning. During inference, we introduce a new generation procedure with a critical sampling strategy. For the model backbones, we extended the encoder-decoder architecture of CodeT5 with enhanced learning objectives.
  arXiv  Detail & Related papers  (2022-07-05T02:42:15Z)
• Precise Learning of Source Code Contextual Semantics via Hierarchical Dependence Structure and Graph Attention Networks [28.212889828892664]
  We propose a novel source code model embedded with hierarchical dependencies. We introduce the syntactic structural of the basic block, i.e., its corresponding AST, in source code model to provide sufficient information. The results show that our model reduces the scale of parameters by 50% and achieves 4% improvement on accuracy on program classification task.
  arXiv  Detail & Related papers  (2021-11-20T04:03:42Z)
• Software Vulnerability Detection via Deep Learning over Disaggregated Code Graph Representation [57.92972327649165]
  This work explores a deep learning approach to automatically learn the insecure patterns from code corpora. Because code naturally admits graph structures with parsing, we develop a novel graph neural network (GNN) to exploit both the semantic context and structural regularity of a program.
  arXiv  Detail & Related papers  (2021-09-07T21:24:36Z)
• Design Smells in Deep Learning Programs: An Empirical Study [9.112172220055431]
  Design smells in Deep Learning (DL) programs are poor design and-or configuration decisions taken during the development of DL components. We present a catalogue of 8 design smells for a popular DL architecture, namely deep Feedforward Neural Networks.
  arXiv  Detail & Related papers  (2021-07-05T21:26:05Z)
• An Introduction to Robust Graph Convolutional Networks [71.68610791161355]
  We propose a novel Robust Graph Convolutional Neural Networks for possible erroneous single-view or multi-view data. By incorporating an extra layers via Autoencoders into traditional graph convolutional networks, we characterize and handle typical error models explicitly.
  arXiv  Detail & Related papers  (2021-03-27T04:47:59Z)
• Learning Variational Data Assimilation Models and Solvers [34.22350850350653]
  We introduce end-to-end neural network architectures for data assimilation. A key feature of the proposed end-to-end learning architecture is that we may train the NN models using both supervised and unsupervised strategies.
  arXiv  Detail & Related papers  (2020-07-25T14:28:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.