• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• pp.803-816
• /
• 2023

Explainable artificial intelligence is a method that explains how a complex model (e.g., a deep neural network) yields its output from a given input. Recently, graph-type data have been widely used in various fields, and diverse graph neural networks (GNNs) have been developed for graph-type data. However, methods to explain the behavior of GNNs have not been studied much, and only a limited understanding of GNNs is currently available. Therefore, in this paper, we propose an explanation method for node classification using graph convolutional networks (GCNs), which is a representative type of GNN. The proposed method finds out which features of each node have the greatest influence on the classification of that node using GCN. The proposed method identifies influential features by backtracking the layers of the GCN from the output layer to the input layer using the gradients. The experimental results on both synthetic and real datasets demonstrate that the proposed explanation method accurately identifies the features of each node that have the greatest influence on its classification.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.649-654
• /
• 2023

This paper proposes the design of a neural network structure search model using graph convolutional neural networks. Deep learning has a problem of not being able to verify whether the designed model has a structure with optimized performance due to the nature of learning as a black box. The neural network structure search model is composed of a recurrent neural network that creates a model and a convolutional neural network that is the generated network. Conventional neural network structure search models use recurrent neural networks, but in this paper, we propose GC-NAS, which uses graph convolutional neural networks instead of recurrent neural networks to create convolutional neural network models. The proposed GC-NAS uses the Layer Extraction Block to explore depth, and the Hyper Parameter Prediction Block to explore spatial and temporal information (hyper parameters) based on depth information in parallel. Therefore, since the depth information is reflected, the search area is wider, and the purpose of the search area of the model is clear by conducting a parallel search with depth information, so it is judged to be superior in theoretical structure compared to GC-NAS. GC-NAS is expected to solve the problem of the high-dimensional time axis and the range of spatial search of recurrent neural networks in the existing neural network structure search model through the graph convolutional neural network block and graph generation algorithm. In addition, we hope that the GC-NAS proposed in this paper will serve as an opportunity for active research on the application of graph convolutional neural networks to neural network structure search.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.4
• /
• pp.314-322
• /
• 2021

Skeleton-based action recognition has attracted considerable attention in human action recognition. Recent methods for skeleton-based action recognition employ spatiotemporal graph convolutional networks (GCNs) and have remarkable performance. However, most of them have heavy computational complexity for robust action recognition. To solve this problem, we propose a shuffle graph convolutional network (SGCN) which is a lightweight graph convolutional network using pointwise group convolution rather than pointwise convolution to reduce computational cost. Our SGCN is composed of spatial and temporal GCN. The spatial shuffle GCN contains pointwise group convolution and part shuffle module which enhances local and global information between correlated joints. In addition, the temporal shuffle GCN contains depthwise convolution to maintain a large receptive field. Our model achieves comparable performance with lowest computational cost and exceeds the performance of baseline at 0.3% and 1.2% on NTU RGB+D and NTU RGB+D 120 datasets, respectively.

• Journal of Korea Multimedia Society
• /
• v.25 no.11
• /
• pp.1643-1652
• /
• 2022

Most of the existing machine reading research has used Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN) algorithms as networks. Among them, RNN was slow in training, and Question Answering Network (QANet) was announced to improve training speed. QANet is a model composed of CNN and self-attention. CNN extracts semantic and syntactic information well from the local corpus, but there is a limit to extracting the corresponding information from the global corpus. Graph Convolutional Networks (GCN) extracts semantic and syntactic information relatively well from the global corpus. In this paper, to take advantage of this strength of GCN, we propose I-QANet, which changed the CNN of QANet to GCN. The proposed model performed 1.2 times faster than the baseline in the Stanford Question Answering Dataset (SQuAD) dataset and showed 0.2% higher performance in Exact Match (EM) and 0.7% higher in F1. Furthermore, in the Korean Question Answering Dataset (KorQuAD) dataset consisting only of Korean, the learning time was 1.1 times faster than the baseline, and the EM and F1 performance were also 0.9% and 0.7% higher, respectively.

• Journal of Korea Multimedia Society
• /
• v.24 no.3
• /
• pp.423-430
• /
• 2021

Aiming Graph convolutional networks (GCNs) have achieved outstanding performances on skeleton-based action recognition. However, several problems remain in existing GCN-based methods, and the problem of low recognition rate caused by single input data information has not been effectively solved. In this article, we propose a Dual-stream fusion method that combines video data and skeleton data. The two networks respectively identify skeleton data and video data and fuse the probabilities of the two outputs to achieve the effect of information fusion. Experiments on two large dataset, Kinetics and NTU-RGBC+D Human Action Dataset, illustrate that our proposed method achieves state-of-the-art. Compared with the traditional method, the recognition accuracy is improved better.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.4008-4023
• /
• 2022

Since machine learning was introduced into cross-site scripting (XSS) attack detection, many researchers have conducted related studies and achieved significant results, such as saving time and labor costs by not maintaining a rule database, which is required by traditional XSS attack detection methods. However, this topic came across some problems, such as poor generalization ability, significant false negative rate (FNR) and false positive rate (FPR). Moreover, the automatic clustering property of graph convolutional networks (GCN) has attracted the attention of researchers. In the field of natural language process (NLP), the results of graph embedding based on GCN are automatically clustered in space without any training, which means that text data can be classified just by the embedding process based on GCN. Previously, other methods required training with the help of labeled data after embedding to complete data classification. With the help of the GCN auto-clustering feature and labeled data, this research proposes an approach to detect XSS attacks (called GCNXSS) to mine the dependencies between the units that constitute an XSS payload. First, GCNXSS transforms a URL into a word homogeneous graph based on word co-occurrence relationships. Then, GCNXSS inputs the graph into the GCN model for graph embedding and gets the classification results. Experimental results show that GCNXSS achieved successful results with accuracy, precision, recall, F1-score, FNR, FPR, and predicted time scores of 99.97%, 99.75%, 99.97%, 99.86%, 0.03%, 0.03%, and 0.0461ms. Compared with existing methods, GCNXSS has a lower FNR and FPR with stronger generalization ability.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.3
• /
• pp.9-14
• /
• 2022

In the IoT(internet of things) where various devices can be connected, failure of essential devices may lead to a lot of economic and life losses. For reducing the losses, fault diagnosis techniques have been considered an essential part of IoT. In this paper, the method based on a graph neural network is proposed for determining fault and classifying types by extracting features from vibration data of systems. For training of the deep learning model, fault dataset are used as input data obtained from the CWRU(case western reserve university). To validate the classification performance of the proposed model, a conventional CNN(convolutional neural networks)-based fault classification model is compared with the proposed model. From the simulation results, it was confirmed that the classification performance of the proposed model outweighed the conventional model by up to 5% in the unevenly distributed data. The classification runtime can be improved by lightweight the proposed model in future works.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.170-172
• /
• 2019

개체명 연결이란 주어진 문장에 출현한 단어를 위키피디아와 같은 지식 기반 상의 하나의 개체에 연결하는 것을 의미한다. 문장에 나타나는 개체들은 주로 동일한 주제를 가지게 되는데 본 논문에서는 이러한 특징을 활용하기 위해서 개체들을 그래프상의 노드로 표현하고, 그래프 신경망을 이용하여 주변 노드의 정보를 통해 노드 표상을 업데이트한다. 한국어 위키피디아 링크 데이터를 사용하여 실험을 진행한 결과 개발 셋에서 82.09%, 평가 셋에서 81.87%의 성능을 보였다.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.752-759
• /
• 2022

The instantiation of spaces as a discrete entity allows users to utilize BIM models in a wide range of analyses. However, in practice, their utility has been limited as spaces are erroneously entered due to human error and often omitted entirely. Recent studies attempted to automate space allocation using artificial intelligence approaches. However, there has been limited success as most studies focused solely on the use of geometric features to distinguish spaces. In this study, in addition to geometric features, semantic relations between spaces and elements were modeled and used to improve space classification in BIM models. Graph Convolutional Networks (GCN), a deep learning algorithm specifically tailored for learning in graphs, was deployed to classify spaces via a similarity graph that represents the relationships between spaces and their surrounding elements. Results confirmed that accuracy (ACC) was +0.08 higher than the baseline model in which only geometric information was used. Most notably, GCN was able to correctly distinguish spaces with no apparent difference in geometry by discriminating the specific elements that were provided by the similarity graph.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.419-437
• /
• 2023

As the number of thin filers in Korea surpasses 12 million, there is a growing interest in enhancing the accuracy of assessing their credit default risk to generate additional revenue. Specifically, researchers are actively pursuing the development of default prediction models using machine learning and deep learning algorithms, in contrast to traditional statistical default prediction methods, which struggle to capture nonlinearity. Among these efforts, Graph Neural Network (GNN) architecture is noteworthy for predicting default in situations with limited data on thin filers. This is due to their ability to incorporate network information between borrowers alongside conventional credit-related data. However, prior research employing graph neural networks has faced limitations in effectively handling diverse categorical variables present in credit information. In this study, we introduce the Transformer embedded Graph Convolutional Network (TeGCN), which aims to address these limitations and enable effective default prediction for thin filers. TeGCN combines the TabTransformer, capable of extracting contextual information from categorical variables, with the Graph Convolutional Network, which captures network information between borrowers. Our TeGCN model surpasses the baseline model's performance across both the general borrower dataset and the thin filer dataset. Specially, our model performs outstanding results in thin filer default prediction. This study achieves high default prediction accuracy by a model structure tailored to characteristics of credit information containing numerous categorical variables, especially in the context of thin filers with limited data. Our study can contribute to resolving the financial exclusion issues faced by thin filers and facilitate additional revenue within the financial industry.