• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.3
• /
• pp.91-100
• /
• 2020

Unlike the existing Visual Question Answering(VQA) problems, the new Visual Commonsense Reasoning(VCR) problems require deep common sense reasoning for answering questions: recognizing specific relationship between two objects in the image, presenting the rationale of the answer. In this paper, we propose a novel deep neural network model, KG_VCR, for VCR problems. In addition to make use of visual relations and contextual information between objects extracted from input data (images, natural language questions, and response lists), the KG_VCR also utilizes commonsense knowledge embedding extracted from an external knowledge base called ConceptNet. Specifically the proposed model employs a Graph Convolutional Neural Network(GCN) module to obtain commonsense knowledge embedding from the retrieved ConceptNet knowledge graph. By conducting a series of experiments with the VCR benchmark dataset, we show that the proposed KG_VCR model outperforms both the state of the art(SOTA) VQA model and the R2C VCR model.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.2
• /
• pp.162-170
• /
• 2015

Commute time embedding involves computing the spectral decomposition of the graph Laplacian. It requires the computational burden proportional to $o(n^3)$, not suitable for large scale dataset. Many methods have been proposed to accelerate the computational time, which usually employ the Nystr${\ddot{o}}$m methods to approximate the spectral decomposition of the reduced graph Laplacian. They suffer from the lost of information by dint of sampling process. This paper proposes to reduce the errors by approximating the spectral decomposition of the graph Laplacian using that of the affinity matrix. However, this can not be applied as the data size increases, because it also requires spectral decomposition. Another method called approximate commute time embedding is implemented, which does not require spectral decomposition. The performance of the proposed algorithms is analyzed by computing the commute time on the patch graph.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.1
• /
• pp.27-34
• /
• 2005

In this paper, we propose the Q-edge labeling method related to the graph embedding problem in binomial trees. This result is able to design a new reliable interconnection networks with maximum connectivity using Q-edge labels as jump sequence of circulant graph. The circulant graph is a generalization of Harary graph which is a solution of the optimal problem to design a maximum connectivity graph consists of n vertices End e edgies. And this topology has optimal broadcasting because of having binomial trees as spanning tree.

• Journal of KIISE:Computer Systems and Theory
• /
• v.26 no.1
• /
• pp.107-116
• /
• 1999

대칭성(symmetry)은 그래프의 구조와 특성을 시각적으로 표현할 때 중요한 미적 기준 중의 하나이다. 또한 대칭성을 보여주는 드로잉은 전체 그래프가 크기가 작은 부그래트들로부터 반복적으로 구성됨을 보여줌으로써 전체 그래프에 대한 이해를 쉽게 푸는 해주는 장점이 있다. 하지만 일반적인 그래프에서 기하하적 대칭성(geometric symmetry)을 탐지하는 문제는 이미 NP-complete 임이 증명되었으므로 이에 대한 연구는 평면 그래프(planar graph)의 극히 제한적인 부분집합인 트리, 외부 평면 그래프, 임베딩된 (embedded) 평면 그래프 등에 초점이 맞추어져 왔다. 본 논문에서는 평면 그래프에서의 기하학적 대칭성 문제를 연구하였다. 평면 그래프를 이중 연결 성분들로 분할한 다음 이를 각각 다시 삼중 연결 성분들로 분할하여 트리를 구성하고 축소(reduction)개념을 도입함으로써 기하학적 대칭성을 탐지하는 O(n2)시간 알고리즘을 제시하였다. 여기서 n은 그래프의 정점의 개수이다. 이 알고리즘은 평면 그래프를 최대한 대칭적으로 드로잉하는 알고리즘 개발에 이용될 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.05a
• /
• pp.601-604
• /
• 2008

전위그래프와 버블정렬그래프는 스타그래프가 갖는 노드대칭성, 재귀적구조, 최대 고장허용도 등 그래프이론 관점에서 좋은 성질을 갖는 상호연결망이다. 본 논문에서는 버블정렬(bubblesort)그래프 $B_n$와 버블정렬-스타(bubblesort star)그래프가 전위(Transposition) 그래프 $T_n$의 서브그래프임을 보인다. 또한, 전위(Transposition)그래프 $T_n$을 버블정렬(Bubblesort)그래프 $B_n$으로 임베딩하는 연장율이 O(n)임을 보인다.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.10
• /
• pp.2615-2626
• /
• 1998

In this paper, we propose a new interconnection network called RFM graph, whichis the merger of the directed rotator and Faber-Moore graph, and analyze fault tolerance, routing algorithm node disjoint cycles and broadcasting algorithm. We also describe methods to embed star graph, 2 dimesional torus and bubblesort graph into RFM graph with unit expasion and dilation 2.

• The KIPS Transactions:PartA
• /
• v.14A no.4
• /
• pp.249-254
• /
• 2007

In this paper, we consider the embedding problem of postorder Fibonacci circulant. We show that Fibonacci linear array, Fibonacci mesh, Fibonacci tree, Fibonacci cubes and Hypercube are a subgraph of postorder Fibonacci circulant.

• Journal of KIISE:Computer Systems and Theory
• /
• v.31 no.1_2
• /
• pp.86-94
• /
• 2004

In this paper, we show that $ G(2^m, 4), m{\geq}3$with at most m-2 faulty elements has a fault-free cycle of length 1 for every ${\leq}1{\leq}2^m-f_v$ is the number of faulty vertices. To achieve our purpose, we define a graph G to be k-fault hypohamiltonian-connected if for any set F of faulty elements, G- F has a fault-free path joining every pair of fault-free vertices whose length is shorter than a hamiltonian path by one, and then show that$ G(2^m, 4), m{\geq}3$ is m-3-fault hypohamiltonian-connected.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.5
• /
• pp.165-170
• /
• 2023

With the recent rise of blockchain technology, cryptocurrency platforms using it are increasing, and currency transactions are being actively conducted. However, crimes that abuse the characteristics of cryptocurrency are also increasing, which is a problem. In particular, phishing scams account for more than a majority of Ethereum cybercrime and are considered a major security threat. Therefore, effective phishing scams detection methods are urgently needed. However, it is difficult to provide sufficient data for supervised learning due to the problem of data imbalance caused by the lack of phishing addresses labeled in the Ethereum participating account address. To address this, this paper proposes a phishing scams detection method that uses both Trans2vec, an effective graph embedding techique considering Ethereum transaction networks, and semi-supervised learning model Tri-training to make the most of not only labeled data but also unlabeled data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.6
• /
• pp.1361-1368
• /
• 2014

In this paper, we analyze emddings among HFCube(n,n), HCN(n,n), HFN(n,n) with lower network cost than that of Hypercube. The results are as follows. We propose that $Q_{2n}$ can be embedded into HFCube(n,n) with dilation 5, congestion 2. HCN(n,n) and HFN(n,n) are subgraphs of HFCube(n,n). HFCube(n,n) can be embedded into HFN(n,n) with dilation 3. HFCube(n,n) can be embedded into HCN(n,n) with dilation O(n). The results will be helpful to analyze several efficient properties in each interconnection network.