• Journal of Information Processing Systems
• /
• v.16 no.6
• /
• pp.1250-1260
• /
• 2020

This study proposes a novel deep neural network model that can accurately detect objects and their relationships in an image and represent them as a scene graph. The proposed model utilizes several multimodal features, including linguistic features and visual context features, to accurately detect objects and relationships. In addition, in the proposed model, context features are embedded using graph neural networks to depict the dependencies between two related objects in the context feature vector. This study demonstrates the effectiveness of the proposed model through comparative experiments using the Visual Genome benchmark dataset.

• KIISE Transactions on Computing Practices
• /
• v.23 no.8
• /
• pp.473-480
• /
• 2017

In recent years, semiconductor-based storage devices such as flash memory (SSDs) have been developed to high performance. In addition, a trend has been observed of optimally utilizing resources such as the central processing unit (CPU) and memory of the internal controller in the storage device according to the needs of the application. This concept is called In-Storage Processing (ISP). In a storage device equipped with the ISP function, it is possible to process part of the operation executed on the host system, thus reducing the load on the host. Moreover, since the data is processed in the storage device, the data transferred to the host are reduced. In this paper, we propose a method to optimize graph query processing by utilizing these ISP functions, and show that the optimized graph processing method improves the performance of the graph 500 benchmark by up to 20%.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.53 no.4
• /
• pp.210-215
• /
• 2004

This paper proposes an implicit method for computing the minimum cost feedback vertex set for a graph. For an arbitrary graph, a Boolean function is derived, whose satisfying assignments directly correspond to feedback vertex sets of the graph. Importantly, cycles in the graph are never explicitly enumerated, but rather, are captured implicitly in this Boolean function. This function is then used to determine the minimum cost feedback vertex set. Even though computing the minimum cost satisfying assignment for a Boolean function remains an NP-hard problem, it is possible to exploit the advances made in the area of Boolean function representation in logic synthesis to tackle this problem efficiently in practice for even reasonably large sized graphs. The algorithm has obvious application in flip-flop selection for partial scan. The algorithm proposed in this paper is the first to obtain the MFVS solutions for many benchmark circuits.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.4
• /
• pp.85-91
• /
• 2023

In order to utilize KOSMOS, the performance evaluation results are presented in this paper with CloudSuite, an application service-based benchmark program in the cloud computing area. CloudSuite offers several distinct applications as cloud services in two parts: offline applications and online applications on containers. In comparison with other microservers which have similar hardware specifications of KOSMOS, it was observed that KOSMOS was superior in all CloudSuite benchmark applications. KOSMOS also showed higher performance than Intel Xeon CPU-based servers in an offline application. KOSMOS reduced completion time during executing Graph Analytics by 30.3% and 72.3% compared to two Intel Xeon CPU-based servers in an experimental configuration of multiple nodes in KOSMOS.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.33A no.2
• /
• pp.196-204
• /
• 1996

This paper presents a new scheduling algorithm, which is the most improtant subtask in the high level synthesis. The proposed algorithm performs scheduling in consideration of resource sharing concept based on characteristics of conditionsla bransches in the intermediate data structure. CDFG (control data flow graph) generated by a VHDL analyzer. This algorithm constructs a conditon graph based on time frame of each operation using both the ASAP and the ALAP scheduling algorithm. The conditon priority is obtained from the condition graph constructed from each conditional brance. The determined condition priority implies the sequential order of transforming the CDFG with conditonal branches into the CDFG without conditional branches. To minimize resource cost, the CDFG with conditional branches are transformed into the CDFG without conditonal brancehs according to the condition priority. Considering the data dependency, the hardware constraints, and the data execution time constraints, each operation in the transformed CDFG is assigned ot control steps. Such assigning of unscheduled operations into contorl steps implies the performance of the scheduling in the consecutive movement of operations. The effectiveness of this algorithm is hsown by the experiment for the benchmark circuits.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.12
• /
• pp.1096-1100
• /
• 2012

Most of previous genetic algorithms for solving graph problems have used a vertex-based encoding. We proposed an edge encoding based new genetic algorithm using a spanning tree. Contrary to general edge-based encoding, a spanning tree-based encoding represents only feasible partitions. As a target problem, we adopted the MAX CUT problem, which is well known as a representative NP-hard problem, and examined the performance of the proposed genetic algorithm. The experiments on benchmark graphs are executed and compared with vertex-based encoding. Performance improvements of the spanning tree-based encoding on sparse graphs was observed.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.6
• /
• pp.1646-1655
• /
• 1999

This thesis presents a new VHDL intermediate format CDDG(Control Dominated Data Graph) and a minimal constrained scheduling algorithm for an optimal control dominated ASIC design. CDDG is a control flow graph which represents conditional branches and loops efficiently. Also it represents data dependency and such constraints as hardware resource and timing. In the proposed scheduling algorithm, the constraints using the inclusion and overlap relation among subgraphs. The effectiveness of the proposed algorithm has been proven by the experiment with the benchmark examples.

• The KIPS Transactions:PartB
• /
• v.15B no.6
• /
• pp.609-612
• /
• 2008

Let G = (V, E) be a simple undirected graph. The Minimum Vertex Cover (MVC) problem is to find a minimum subset C of V such that for every edge, at least one of its endpoints should be included in C. Like many other graph theoretic problems this problem is also known to be NP-hard. In this paper, we propose a genetic algorithm called LeafGA for MVC problem and show the performance of the proposed algorithm by applying it to several published benchmark graphs.

• The Korean Journal of Applied Statistics
• /
• v.37 no.3
• /
• pp.355-380
• /
• 2024

In this paper, we compare the performance of graph-based deep learning models using OECD test guideline (TG) data. OECD TG are a unique tool for assessing the potential effects of chemicals on health and environment. but many guidelines include animal testing. Animal testing is time-consuming and expensive, and has ethical issues, so methods to find or minimize alternatives are being studied. Deep learning is used in various fields using chemicals including toxicity prediciton, and research on graph-based models is particularly active. Our goal is to compare the performance of graph-based deep learning models on OECD TG data to find the best performance model on there. We collected the results of OECD TG from the website eChemportal.org operated by the OECD, and chemicals that were impossible or inappropriate to learn were removed through pre-processing. The toxicity prediction performance of five graph-based models was compared using the collected OECD TG data and MoleculeNet data, a benchmark dataset for predicting chemical properties.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.8
• /
• pp.243-250
• /
• 2020

Knowledge graph-based question answering not only requires deep understanding of the given natural language questions, but it also needs effective reasoning to find the correct answers on a large knowledge graph. In this paper, we propose a deep neural network model for effective reasoning on a knowledge graph, which can find correct answers to complex questions requiring multi-hop inference. The proposed model makes use of highly expressive bilinear graph neural network (BGNN), which can utilize context information between a pair of neighboring nodes, as well as allows bidirectional feature propagation between each entity node and one of its neighboring nodes on a knowledge graph. Performing experiments with an open-domain knowledge base (Freebase) and two natural-language question answering benchmark datasets(WebQuestionsSP and MetaQA), we demonstrate the effectiveness and performance of the proposed model.