Graph Classification

Tsuda, Koji; Saigo, Hiroto

doi:10.1007/978-1-4419-6045-0_11

Cited by 20 publications

(9 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Graph Kernels: graph kernels express similarity measures [10] involved in both classification [11] and clustering algorithms. One of the first approaches required a preliminary embedding definition of topological description vectors extracted from the most frequent subgraphs within a graph database [12].…”

Section: Related Workmentioning

confidence: 99%

Probabilistic Trace Alignment

Bergami¹,

Maggi²,

Montali³

et al. 2021

Preprint

View full text Add to dashboard Cite

Alignments provide sophisticated diagnostics that pinpoint deviations in a trace with respect to a process model and their severity. However, approaches based on trace alignments use crisp process models as reference and recent probabilistic conformance checking approaches check the degree of conformance of an event log with respect to a stochastic process model instead of finding trace alignments. In this paper, for the first time, we provide a conformance checking approach based on trace alignments using stochastic Workflow nets. Conceptually, this requires to handle the two possibly contrasting forces of the cost of the alignment on the one hand and the likelihood of the model trace with respect to which the alignment is computed on the other.

show abstract

Section: Related Workmentioning

confidence: 99%

Probabilistic Trace Alignment

Bergami¹,

Maggi²,

Montali³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Thus, to classify the individuals in a knowledge graph, it is important to describe each of these individuals using a fixed size vector that holds the most valuable features that represent the individual, from the classifier's point of view. In (Parundekar, 2018), to classify the individuals in the knowledge graphs, the features are selected from the relations between the individual and other entities in the graphs, using random walk approach (Tsuda and Saigo, 2010). Using this approach, the features are extracted per an individual in the graph, by hopping over the four possible types of hops any individual can have, which are a relation to an attribute, incoming relation, outgoing relation or a step over the relation, which unlike the other three hops lands on a different individual.…”

Section: Machine Learning From Knowledge Graph Applicationsmentioning

confidence: 99%

A Review of Machine Learning Applications in Semantic Web

Albannai¹,

Gültepe²,

Najih³

2019

JSTR

View full text Add to dashboard Cite

In recent years, the rapid growth of the semantic web has encouraged the use of knowledge graphs to store and exchange data among computers. The change in data storage and retrieval has imposed the need to integrate other techniques that interact with these data. Machine Learning (ML) is the most important fields of study that interacts with data, to extract the patterns and relations that can be used in future applications. However, these techniques are implemented to be used with structured data, where each data instance is characterized using a set of predefined features. Thus, to apply machine learning techniques to knowledge graphs, it is important to convert the formation of the information in these graphs. The knowledge graph represents a collection of interconnected descriptions of entities (objects, events, situations, or abstract concepts in the real world). This work reviews the knowledge graphs and how they are structured and stored. Then, the techniques being used to employ machine learning technique to improve the knowledge graphs are illustrated. Additionally, the integration of the information in the knowledge graphs, so that, they can be used in machine learning techniques are also reviewed. This review can provide a rigid overview for future researchers to provide more attention on the main drawbacks in the existing techniques. Moreover, the review shows that the existing integration approaches limit the performance of the machine learning techniques, as the knowledge extracted from the knowledge graph is trimmed to match the requirements of the ML technique. In conclusion, new machine learning techniques that can extract knowledge directly from the knowledge graph can provide significantly better performance.

show abstract

“…We evaluated two leading GNN architectures-Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT) [16] [17]-against traditional models like SVM, KNN, RF, and DNN. Using a benchmark dataset comprising 310 proteins, split into 174 MPs and 136 non-MPs, we approach MP prediction as a graph classification task [18].…”

Section: Introductionmentioning

confidence: 99%

MP-GNN: Graph Neural Networks to Identify Moonlighting Proteins

Zhou,

Sarkar

2023

Preprint

View full text Add to dashboard Cite

Moonlighting proteins (MPs) play critical roles in cellular functions and disease, yet their complex nature challenges traditional identification methods. This research delves into the potential of Graph Machine Learning (GML) to effectively utilize Protein-Protein Interaction (PPI) networks and physicochemical properties for MP prediction. Our study focuses on two GML architectures: Graph Attention Networks (GAT) and Graph Convolutional Networks (GCN), which are augmented by integrating quasi-sequence-order (QSOrder) and amino acid composition (AAC) to enrich the feature representation. We evaluated these models on a dataset comprising 310 proteins, finding that GML substantially outperforms conventional methodologies such as Support Vector Machines (SVM), K-nearest neighbors (KNN), and Random Forest (RF), especially in scenarios with limited data where Deep Neural Networks (DNNs) typically struggle. Notably, the GAT model, when enhanced with QSOrder and PPI data, exhibited exceptional accuracy, and robustness in precision, F1-score, and ROC-AUC metrics. This indicates a significant edge in capturing the complex predictive signals embedded in PPI networks. Our findings strongly support the integration of GML in MP research and suggest a novel approach for exploring MPs through their interactive partners.

show abstract

Graph Classification

Cited by 20 publications

References 37 publications

Probabilistic Trace Alignment

Probabilistic Trace Alignment

A Review of Machine Learning Applications in Semantic Web

MP-GNN: Graph Neural Networks to Identify Moonlighting Proteins

Contact Info

Product

Resources

About