• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제23권3호
• /
• pp.156-164
• /
• 2017

두 그래프의 유사도를 측정하는 문제는 다양한 응용분야에서 그래프 문제를 해결하기 위한 기본적인 도구 중 하나이다. 대부분 그래프 알고리즘들은 정점과 간선의 개수를 기반으로 한 시간 복잡도를 가진다. 최근 GPU는 낮은 가격 대비 높은 계산 능력을 제공하기 때문에 그래프 응용에서 수행 시간을 개선하기 위해 널리 활용되고 있다. 본 논문에서는 GPU 환경에서 CUDA를 사용하여 그래프의 유사도를 측정하기 위한 효율적인 병렬 알고리즘을 제안한다. 제안된 알고리즘의 평가를 위해 CPU 기반 알고리즘과 비교하였으며 실험적 결과를 통하여 제안된 방법이 성능과 효율성에서 상당한 개선이 있음을 보인다. 또한 그래프의 크기가 클수록 제안된 알고리즘의 성능이 더 개선됨을 보인다.

• 한국컴퓨터정보학회논문지
• /
• 제24권7호
• /
• pp.61-69
• /
• 2019

In this paper, a classification method of random graph models is proposed and it is based on centralities of the random graphs. Similarity between two random graphs is measured for the classification of random graph models. The similarity between two random graph models $G^{R_1}$ and $G^{R_2}$ is defined by the distance of $G^{R_1}$ and $G^{R_2}$, where $G^{R_2}$ is a set of random graph $G^{R_2}=\{G_1^{R_2},...,G_p^{R_2}\}$ that have the same number of nodes and edges as random graph $G^{R_1}$. The distance($G^{R_1},G^{R_2}$) is obtained by comparing centralities of $G^{R_1}$ and $G^{R_2}$. Through the computational experiments, we show that it is possible to compare random graph models regardless of the number of vertices or edges of the random graphs. Also, it is possible to identify and classify the properties of the random graph models by measuring and comparing similarities between random graph models.

• 반도체디스플레이기술학회지
• /
• 제20권3호
• /
• pp.113-116
• /
• 2021

As artificial intelligence technologies, including deep learning, develop, these technologies are being introduced to code similarity analysis. In the traditional analysis method of calculating the graph edit distance (GED) after converting the source code into a control flow graph (CFG), there are studies that calculate the GED through a trained graph neural network (GNN) with the converted CFG, Methods for analyzing code similarity through CNN by imaging CFG are also being studied. In this paper, to determine which approach will be effective and efficient in researching code similarity analysis methods using artificial intelligence in the future, code similarity is measured through funcGNN, which measures code similarity using GNN, and Siamese Network, which is an image similarity analysis model. The accuracy was compared and analyzed. As a result of the analysis, the error rate (0.0458) of the Siamese network was bigger than that of the funcGNN (0.0362).

• Architectural research
• /
• 제17권2호
• /
• pp.57-64
• /
• 2015

In architectural planning, previous cases of similar spatial program provide important data for architectural design. Case-based reasoning (CBR) paradigm in the field of architectural design is closely related to the designing behavior of a planner who makes use of similar architectural designs and spatial programs in the past. In CBR, spatial graph can be constituted with most fundamental data, which can provide a method of searching spatial program by using visual graphs. This study developed a system for CBR that can analyze the similarity through graph comparison and search for buildings. This is an integrated system that is able to compare space similarity of different buildings and analyze their types, in addition to the analysis on a space within a single structure.

• 한국컴퓨터정보학회논문지
• /
• 제23권12호
• /
• pp.57-64
• /
• 2018

In this paper, a method to measure similarity between two graphs is proposed, which is based on centralities of the graphs. The similarity between two graphs $G_1$ and $G_2$ is defined by the difference of distance($G_1$, $G_{R_1}$) and distance($G_2$, $G_{R_2}$), where $G_{R_1}$ and $G_{R_2}$ are set of random graphs that have the same number of nodes and edges as $G_1$ and $G_2$, respectively. Each distance ($G_*$, $G_{R_*}$) is obtained by comparing centralities of $G_*$ and $G_{R_*}$. Through the computational experiments, we show that it is possible to compare graphs regardless of the number of vertices or edges of the graphs. Also, it is possible to identify and classify the properties of the graphs by measuring and comparing similarities between two graphs.

• Journal of Multimedia Information System
• /
• 제3권3호
• /
• pp.53-61
• /
• 2016

This research proposes the index optimization as a classification task and application of the graph based KNN. We need the index optimization as an important task for maximizing the information retrieval performance. And we try to solve the problems in encoding words into numerical vectors, such as huge dimensionality and sparse distribution, by encoding them into graphs as the alternative representations to numerical vectors. In this research, the index optimization is viewed as a classification task, the similarity measure between graphs is defined, and the KNN is modified into the graph based version based on the similarity measure, and it is applied to the index optimization task. As the benefits from this research, by modifying the KNN so, we expect the improvement of classification performance, more graphical representations of words which is inherent in graphs, the ability to trace more easily results from classifying words. In this research, we will validate empirically the proposed version in optimizing index on the two text collections: NewsPage.com and 20NewsGroups.

• ETRI Journal
• /
• 제38권3호
• /
• pp.540-550
• /
• 2016

Spectral clustering is a powerful tool for exploratory data analysis. Many existing spectral clustering algorithms typically measure the similarity by using a Gaussian kernel function or an undirected k-nearest neighbor (kNN) graph, which cannot reveal the real clusters when the data are not well separated. In this paper, to improve the spectral clustering, we consider a robust similarity measure based on the shared nearest neighbors in a directed kNN graph. We propose two novel algorithms for spectral clustering: one based on the number of shared nearest neighbors, and one based on their closeness. The proposed algorithms are able to explore the underlying similarity relationships between data points, and are robust to datasets that are not well separated. Moreover, the proposed algorithms have only one parameter, k. We evaluated the proposed algorithms using synthetic and real-world datasets. The experimental results demonstrate that the proposed algorithms not only achieve a good level of performance, they also outperform the traditional spectral clustering algorithms.

• Journal of Information Processing Systems
• /
• 제16권6호
• /
• pp.1407-1423
• /
• 2020

A graph is a data structure consisting of nodes and edges between these nodes. Graph embedding is to generate a low dimensional vector for a given graph that best represents the characteristics of the graph. Recently, there have been studies on graph embedding, especially using deep learning techniques. However, until now, most deep learning-based graph embedding techniques have focused on unweighted graphs. Therefore, in this paper, we propose a graph embedding technique for weighted graphs based on long short-term memory (LSTM) autoencoders. Given weighted graphs, we traverse each graph to extract node-weight sequences from the graph. Each node-weight sequence represents a path in the graph consisting of nodes and the weights between these nodes. We then train an LSTM autoencoder on the extracted node-weight sequences and encode each nodeweight sequence into a fixed-length vector using the trained LSTM autoencoder. Finally, for each graph, we collect the encoding vectors obtained from the graph and combine them to generate the final embedding vector for the graph. These embedding vectors can be used to classify weighted graphs or to search for similar weighted graphs. The experiments on synthetic and real datasets show that the proposed method is effective in measuring the similarity between weighted graphs.

• 한국콘텐츠학회논문지
• /
• 제22권8호
• /
• pp.33-43
• /
• 2022

지식 그래프 및 단백질 상호 작용과 같은 실제 데이터에서 개체들과 개체들의 관계 및 구조를 나타내기 위해 레이블 그래프를 사용한다. IT의 급속한 발전과 데이터의 폭발적인 증가로 사용자에게 관심 있는 정보를 제공하기 위한 서브 그래프 매칭 기술이 필요하다. 본 논문은 레이블의 의미적 유사성과 그래프 구조 차이를 고려한 근사 Top-k 서브 그래프 매칭 기법을 제안한다. 제안하는 기법은 레이블 의미적 유사도를 고려하기 위하여 FastText을 활용한 학습 모델을 이용한다. 레이블 간 의미적 유사도를 미리 계산한 LSG(Label Similarity Graph)를 통해 처리 속도의 효율을 높인다. LSG를 통해 레이블이 정확하게 일치해야 확장이 가능한 기존 연구의 한계를 해결한다. 2-hop까지 탐색을 수행함으로써 질의 그래프에 대한 구조적 유사성을 지원한다. 매칭된 서브 그래프는 유사도 값 기반으로 Top-k 결과를 제공한다. 제안하는 기법의 우수성을 보이기 위하여 다양한 성능평가를 수행한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권7호
• /
• pp.2568-2584
• /
• 2015

Spectral clustering has become one of the most popular clustering approaches in recent years. Similarity graph constructed on the data is one of the key factors that influence the performance of spectral clustering. However, the similarity graphs constructed by existing methods usually contain some unreliable edges. To construct reliable similarity graph for spectral clustering, an efficient method based on Markov random walk (MRW) is proposed in this paper. In the proposed method, theMRW model is defined on the raw k-NN graph and the neighbors of each sample are determined by the probability of the MRW. Since the high order transition probabilities carry complex relationships among data, the neighbors in the graph determined by our proposed method are more reliable than those of the existing methods. Experiments are performed on the synthetic and real-world datasets for performance evaluation and comparison. The results show that the graph obtained by our proposed method reflects the structure of the data better than those of the state-of-the-art methods and can effectively improve the performance of spectral clustering.