• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.11
• /
• pp.2903-2923
• /
• 2023

Knowledge recommendation is a type of recommendation system that recommends knowledge content to users in order to satisfy their needs. Although using graph neural networks to extract data features is an effective method for solving the recommendation problem, there is information loss when modeling real-world problems because an edge in a graph structure can only be associated with two nodes. Because one super-edge in the hypergraph structure can be connected with several nodes and the effectiveness of knowledge graph for knowledge expression, a dual-channel hypergraph convolutional neural network model (DCHC) based on hypergraph structure and knowledge graph is proposed. The model divides user data and knowledge data into user subhypergraph and knowledge subhypergraph, respectively, and extracts user data features by dual-channel hypergraph convolution and knowledge data features by combining with knowledge graph technology, and finally generates recommendation results based on the obtained user embedding and knowledge embedding. The performance of DCHC model is higher than the comparative model under AUC and F1 evaluation indicators, comparative experiments with the baseline also demonstrate the validity of DCHC model.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.31A no.1
• /
• pp.84-92
• /
• 1994

In this paper, we present a novel scheduling algorithm using the weighted interval graph. An interval graph is constructed, where an interval is a time frame of each operation. And for each operation type, we look for the maximum clique of the interval graph: the number of nodes of the maximum clique represents the number of operation that are executed concurrently. In order to minimize resource cost. we select the operation type to reduce the number of nodes of a maximum clique. For the selected operation type, an operation selected by selection rule is moved to decrease the number of nodes of a maximum clique. A selected operation among unscheduled operations is moved repeatly and assigned to a control step consequently. The proposed algorithm is applied to the pipeline and the nonpipeline data path synthesis. The experiment for examples shows the efficiency of the proposed scheduling algorithm.

• Genomics & Informatics
• /
• v.15 no.1
• /
• pp.19-27
• /
• 2017

Understanding complex relationships among heterogeneous biological data is one of the fundamental goals in biology. In most cases, diverse biological data are stored in relational databases, such as MySQL and Oracle, which store data in multiple tables and then infer relationships by multiple-join statements. Recently, a new type of database, called the graph-based database, was developed to natively represent various kinds of complex relationships, and it is widely used among computer science communities and IT industries. Here, we demonstrate the feasibility of using a graph-based database for complex biological relationships by comparing the performance between MySQL and Neo4j, one of the most widely used graph databases. We collected various biological data (protein-protein interaction, drug-target, gene-disease, etc.) from several existing sources, removed duplicate and redundant data, and finally constructed a graph database containing 114,550 nodes and 82,674,321 relationships. When we tested the query execution performance of MySQL versus Neo4j, we found that Neo4j outperformed MySQL in all cases. While Neo4j exhibited a very fast response for various queries, MySQL exhibited latent or unfinished responses for complex queries with multiple-join statements. These results show that using graph-based databases, such as Neo4j, is an efficient way to store complex biological relationships. Moreover, querying a graph database in diverse ways has the potential to reveal novel relationships among heterogeneous biological data.

• Research in Mathematical Education
• /
• v.10 no.4 s.28
• /
• pp.259-288
• /
• 2006

This study considers the performance of students in Grades 5 to 10 on four tasks assessing students' ability to evaluate data presented in numerical form, for example, in a list or table, or in graphical form, for example, in a frequency graph or scatter graph. The ability to tell a story from data or a graph is an important aspect of statistical literacy. The samples provide the opportunity to consider the association of two pairs of items, one from each type of interpretation, numerical and graphical. Educational implications for the outcomes and the classroom use of the items are considered.

• The KIPS Transactions:PartD
• /
• v.9D no.3
• /
• pp.337-344
• /
• 2002

Recently, there has been a lot of research on graph-type data because it can model seamless the application domains such as GIS, network, WWW, multimedia presentations etc., and domain in which the data sequence is important. In this paper, an efficient code system, called node code system, is proposed to evaluate paths of DAG in a multimedia presentation graph. The node code system assigns a unique binary string to each node of a graph. The comparison of node codes of two nodes tells the connectivity between the nodes without actual traversal of a graph. The method using the property of the node code system allows us to construct the paths between two nodes more efficiently than the method using conventional graph traversals. The algorithms to construct paths using the node code system are provided.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.5
• /
• pp.429-437
• /
• 2022

Recently, the demand for a QA (Question Answering) system for human-machine communication has increased. Among the QA systems, a closed domain QA system that can handle spatial-related questions is called GeoQA. In this study, a new type of graph database, LPG (Labeled Property Graph) was used to overcome the limitations of the RDF (Resource Description Framework) based database, which was mainly used in the GeoQA field. In addition, GraphQL (Graph Query Language), an API-type query language, is introduced to address the fact that the LPG query language is not standardized and the GeoQA system may depend on specific products. In this study, database was built so that answers could be retrieved when spatial-related questions were entered. Each data was obtained from the national spatial information portal and local data open service. The spatial relationships between each spatial objects were calculated in advance and stored in edge form. The user's questions were first converted to GraphQL through FOL (First Order Logic) format and delivered to the database through the GraphQL server. The LPG used in the experiment is Neo4j, the graph database that currently has the highest market share, and some of the built-in functions and QGIS were used for spatial calculations. As a result of building the system, it was confirmed that the user's question could be transformed, processed through the Apollo GraphQL server, and an appropriate answer could be obtained from the database.

• Journal of Internet Computing and Services
• /
• v.2 no.4
• /
• pp.69-81
• /
• 2001

This paper describes a parallel programming environment to help programmer to write parallel programs. Parallel program must be write according to the character of the various hardware or program. So it is difficult for the programs to write the parallel programmer. In this paper, we propose and implement a parallel programming environment using graph type intermediate representation form, and graph user interface is provided for programmer to get parallel programs easily, This parallel environment supports special functions using graph type intermediate representation form. The special functions involve program editing. data dependence analysis, loop transformation. CFG, PDG, HTG. This parallel environment helps users make parallelism and optimization easy through showing the intermediate code with graph.

• Journal of The Korean Association For Science Education
• /
• v.39 no.5
• /
• pp.655-668
• /
• 2019

In this study, we investigated the middle school students' processes of scientific graph construction from the perspective of the problem solving process. Ten 9th graders participated in this study. They constructed a scientific graph based on pictorial data depicting precipitation reaction. The think-aloud method was used in order to investigate their thinking processes deeply. Their activities were videotaped, and semi-structured interviews were also conducted. The analysis of the results revealed that their processes of scientific graph construction could be classified into four types according to the problem solving strategy and the level of representations utilized. Students using the structural strategy succeeded in constructing scientific graph regardless of the level of representation utilized, by analyzing the data and identifying the trend based on the propositional knowledge about the target concept of the graph. Students of random strategy-higher order representation type were able to succeed in constructing scientific graph by systematically analyzing the characteristics of the data using various representations, and considering the meaning of the graph constructed in terms of the scientific context. On the other hand, students of random strategy-lower order representation type failed to construct correct scientific graph by constructing graph in a way of simply connecting points, and checking the processes of graph construction only without considering the scientific context. On the bases of the results, effective methods for improving students' ability to construct scientific graphs are discussed.

• Journal of the Korean Mathematical Society
• /
• v.60 no.5
• /
• pp.959-986
• /
• 2023

Zhai and Lin recently proved that if G is an n-vertex connected 𝜃(1, 2, r + 1)-free graph, then for odd r and n ⩾ 10r, or for even r and n ⩾ 7r, one has ${\rho}(G){\leq}{\sqrt{{\lfloor}{\frac{n^2}{4}}{\rfloor}}}$, and equality holds if and only if G is $K_{{\lceil}{\frac{n}{2}}{\rceil},{\lfloor}{\frac{n}{2}}{\rfloor}}$. In this paper, for large enough n, we prove a sharp upper bound for the spectral radius in an n-vertex H-free non-bipartite graph, where H is 𝜃(1, 2, 3) or 𝜃(1, 2, 4), and we characterize all the extremal graphs. Furthermore, for n ⩾ 137, we determine the maximum number of edges in an n-vertex 𝜃(1, 2, 4)-free non-bipartite graph and characterize the unique extremal graph.