• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권1호
• /
• pp.147-169
• /
• 2024

In pace with the development of network technology at lightning speed, social networks have been extensively applied in our lives. However, as social networks retain a large number of users' sensitive information, the openness of this information makes social networks vulnerable to attacks by malicious attackers. To preserve the link privacy of individuals in social networks, an uncertain graph method based on node random response is devised, which satisfies differential privacy while maintaining expected data utility. In this method, to achieve privacy preserving, the random response is applied on nodes to achieve edge modification on an original graph and node differential privacy is introduced to inject uncertainty on the edges. Simultaneously, to keep data utility, a divide and conquer strategy is adopted to decompose the original graph into many sub-graphs and each sub-graph is dealt with separately. In particular, only some larger sub-graphs selected by the exponent mechanism are modified, which further reduces the perturbation to the original graph. The presented method is proven to satisfy differential privacy. The performances of experiments demonstrate that this uncertain graph method can effectively provide a strict privacy guarantee and maintain data utility.

• Journal of Information Processing Systems
• /
• 제19권6호
• /
• 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.

• Journal of Information Processing Systems
• /
• 제20권4호
• /
• pp.501-513
• /
• 2024

In recent years, graph neural networks (GNNs) have been extensively used to analyze graph data across various domains because of their powerful capabilities in learning complex graph-structured data. However, recent research has focused on improving the performance of a single GNN with only two or three layers. This is because stacking layers deeply causes the over-smoothing problem of GNNs, which degrades the performance of GNNs significantly. On the other hand, ensemble methods combine individual weak models to obtain better generalization performance. Among them, gradient boosting is a powerful supervised learning algorithm that adds new weak models in the direction of reducing the errors of the previously created weak models. After repeating this process, gradient boosting combines the weak models to produce a strong model with better performance. Until now, most studies on GNNs have focused on improving the performance of a single GNN. In contrast, improving the performance of GNNs using multiple GNNs has not been studied much yet. In this paper, we propose gradient boosted graph neural networks (GBGNN) that combine multiple shallow GNNs with gradient boosting. We use shallow GNNs as weak models and create new weak models using the proposed gradient boosting-based loss function. Our empirical evaluations on three real-world datasets demonstrate that GBGNN performs much better than a single GNN. Specifically, in our experiments using graph convolutional network (GCN) and graph attention network (GAT) as weak models on the Cora dataset, GBGNN achieves performance improvements of 12.3%p and 6.1%p in node classification accuracy compared to a single GCN and a single GAT, respectively.

• 농촌계획
• /
• 제6권2호
• /
• pp.12-19
• /
• 2000

Irrigation pipeline networks consist mainly of buried pipes and are therefore relatively free from topographic constraints. Installation of irrigation pipeline systems is increasing since the systems have several advantages compared to open channel systems. To achieve economic design of pipeline networks, the layout should meet several conditions such as shortest path, maximum flow, and least cost. Graph theory is mathematical tool which enable to find out optimum layout for complicated network systems. In this study, applicability of graph theory to figure out optimum layout of irrigation pipeline networks was evaluated.

• Journal of applied mathematics & informatics
• /
• 제42권4호
• /
• pp.761-775
• /
• 2024

A cycle in a graph G that contains all of its vertices is said to be the Hamiltonian cycle of that graph. A Hamiltonian graph is one that has a Hamiltonian cycle. This article discusses how to create a new network from an existing one, such as the Enhanced Honeycomb Network EHC(n), which is created by adding six new edges to each layer of the Honeycomb Network HC(n). Enhanced honeycomb networks have 9n² + 3n - 6 edges and 6n² vertices. For every perfect sub-Honeycombe topology, this new network features six edge disjoint Hamiltonian cycles, which is an advantage over Honeycomb. Its diameter is (2n + 1), which is nearly 50% lesser than that of the Honeycomb network. Using 3-bit grey code, we demonstrated that the Enhanced Honeycomb Network EHC(n) is Hamiltonian.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권8호
• /
• pp.3216-3230
• /
• 2015

A hot-issued research topic in the workflow intelligence arena is the emerging topic of "workflow-supported organizational social networks." These specialized social networks have been proposed to primarily represent the process-driven work-sharing and work-collaborating relationships among the workflow-performers fulfilling a series of workflow-related operations in a workflow-supported organization. We can discover those organizational social networks, and visualize its analysis results as organizational knowledge. In this paper, we are particularly interested in how to visualize the degrees of closeness centralities among workflow-performers by proposing a graphical representation schema based on the Graph Markup Language, which is named to ccWSSN-GraphML. Additionally, we expatiate on the functional expansion of the closeness centralization formulas so as for the visualization framework to handle a group of workflow procedures (or a workflow package) with organizational workflow-performers.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2007년도 정기학술대회
• /
• pp.321-329
• /
• 2007

This paper reports on the application of network analysis approaches to investigate the characteristics of graph representations of Japanese word associations. Two semantic networks are constructed from two separate Japanese word association databases. The basic statistical features of the networks indicate that they have scale-free and small-world properties and that they exhibit hierarchical organization. A graph clustering method is also applied to the networks with the objective of generating hierarchical structures within the semantic networks. The method is shown to be an efficient tool for analyzing large-scale structures within corpora. As a utilization of the network clustering results, we briefly introduce two web-based applications: the first is a search system that highlights various possible relations between words according to association type, while the second is to present the hierarchical architecture of a semantic network. The systems realize dynamic representations of network structures based on the relationships between words and concepts.

• 충청수학회지
• /
• 제35권3호
• /
• pp.205-225
• /
• 2022

In this paper, we derive analytical closed results for the first (a, b)-KA index, the Sombor index, the modified Sombor index, the first reduced (a, b)-KA index, the reduced Sombor index, the reduced modified Sombor index, the second reduced (a, b)-KA index and the mean Sombor index mSO_α for the OTIS biswapped networks by considering basis graphs as path, wheel graph, complete bipartite graph and r-regular graphs. Network theory plays a significant role in electronic and electrical engineering, such as signal processing, networking, communication theory, and so on. A topological index (TI) is a real number associated with graph networks that correlates chemical networks with a variety of physical and chemical properties as well as chemical reactivity. The Optical Transpose Interconnection System (OTIS) network has recently received increased interest due to its potential uses in parallel and distributed systems.

• 한국정보과학회논문지:시스템및이론
• /
• 제29권2호
• /
• pp.65-74
• /
• 2002

병렬 처리 시스템의 상호연결 네트워크로써 스타 그래프 구조간 그간 널리 사용되어 왔던 하이퍼규브에 비해 지름 및 차수 등의 특성에 우수한 성능을 보임으로 인해 최근 많은 연구자들의 관심을 받고 있다. 스타 그래프 네트워크에서 여러가지 통신문제들이 연구되어 지고 있는데 그러한 통신 문제 중 에 가장 기본이 될수있는 문제 중의 하나가 브로드캐스팅이다. 본 논문에서는 윕홀라우팅을 지원하는 스타 그래프 네트워크 시스템에서의 브로드캐스팅 문제를 다룬다. 윔홀라우팅을 사용하는 네트워크에서는 전송 노드간의 거리보다 전송 시 링크 충돌을 최소화하는 것이 전체 통신 시간을 줄이는 중요한 요소가 되는 데 본 논문에서는 스타 그래프 네트워크에서의 해밀 토니안 경로를 이용하여 링크 충돌이 없이 n 차원 스타 네트워크$([long_n n!]+1)$ 통신스텝이 전체 브로드캐스팅이 완료되는 알고리즘을 제시한다. 이는 이론 절 하한값 $([long_n n!]+1)$ 에 근접한 결과로 기존의 n-1 통신 스텝이 걸리는 알고리즘 보다 향상된 결과이다.

• 문화기술의 융합
• /
• 제9권1호
• /
• pp.649-654
• /
• 2023

본 논문은 그래프 합성곱 신경망을 이용한 신경망 구조 탐색 모델 설계를 제안한다. 딥 러닝은 블랙박스로 학습이 진행되는 특성으로 인해 설계한 모델이 최적화된 성능을 가지는 구조인지 검증하지 못하는 문제점이 존재한다. 신경망 구조 탐색 모델은 모델을 생성하는 순환 신경망과 생성된 네트워크인 합성곱 신경망으로 구성되어있다. 통상의 신경망 구조 탐색 모델은 순환신경망 계열을 사용하지만 우리는 본 논문에서 순환신경망 대신 그래프 합성곱 신경망을 사용하여 합성곱 신경망 모델을 생성하는 GC-NAS를 제안한다. 제안하는 GC-NAS는 Layer Extraction Block을 이용하여 Depth를 탐색하며 Hyper Parameter Prediction Block을 이용하여 Depth 정보를 기반으로 한 spatial, temporal 정보(hyper parameter)를 병렬적으로 탐색합니다. 따라서 Depth 정보를 반영하기 때문에 탐색 영역이 더 넓으며 Depth 정보와 병렬적 탐색을 진행함으로 모델의 탐색 영역의 목적성이 분명하기 때문에 GC-NAS대비 이론적 구조에 있어서 우위에 있다고 판단된다. GC-NAS는 그래프 합성곱 신경망 블록 및 그래프 생성 알고리즘을 통하여 기존 신경망 구조 탐색 모델에서 순환 신경망이 가지는 고차원 시간 축의 문제와 공간적 탐색의 범위 문제를 해결할 것으로 기대한다. 또한 우리는 본 논문이 제안하는 GC-NAS를 통하여 신경망 구조 탐색에 그래프 합성곱 신경망을 적용하는 연구가 활발히 이루어질 수 있는 계기가 될 수 있기를 기대한다.