Approximate graph mining with label costs

Anchuri, Pranay; Zaki, Mohammed J.; Barkol, Omer; Golan, Shahar; Shamy, Moshe

doi:10.1145/2487575.2487602

Cited by 24 publications

(15 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chemical Compound Categorization is important in biomedical research for testing whether a compound is active to a specific cancer, such as melanoma. For melanoma cancer, determining activities of a molecule is expensive as it requires time, efforts, and expensive resources [19] to conduct biological assay. In reality, some similar bioassay tasks 1 , such as an anti-cancer test for prostate, may be available.…”

Section: A Multi-task Graph Classification: Motivationmentioning

confidence: 99%

Task Sensitive Feature Exploration and Learning for Multitask Graph Classification

Pan

Zhu

et al. 2017

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Multitask learning (MTL) is commonly used for jointly optimizing multiple learning tasks. To date, all existing MTL methods have been designed for tasks with feature-vector represented instances, but cannot be applied to structure data, such as graphs. More importantly, when carrying out MTL, existing methods mainly focus on exploring overall commonality or disparity between tasks for learning, but cannot explicitly capture task relationships in the feature space, so they are unable to answer important questions, such as what exactly is shared between tasks and what is the uniqueness of one task differing from others? In this paper, we formulate a new multitask graph learning problem, and propose a task sensitive feature exploration and learning algorithm for multitask graph classification. Because graphs do not have features available, we advocate a task sensitive feature exploration and learning paradigm to jointly discover discriminative subgraph features across different tasks. In addition, a feature learning process is carried out to categorize each subgraph feature into one of three categories: (1) common feature; (2) task auxiliary feature; and (3) task specific feature, indicating whether the feature is shared by all tasks, by a subset of tasks, or by only one specific task, respectively. The feature learning and the multiple task learning are iteratively optimized to form a multitask graph classification model with a global optimization goal. Experiments on real-world functional brain analysis and chemical compound categorization demonstrate the algorithm's performance. Results confirm that our method can be used to explicitly capture task correlations and uniqueness in the feature space, and explicitly answer what are shared between tasks and what is the uniqueness of a specific task.

show abstract

Section: A Multi-task Graph Classification: Motivationmentioning

confidence: 99%

Task Sensitive Feature Exploration and Learning for Multitask Graph Classification

Pan

Zhu

et al. 2017

IEEE Trans. Cybern.

View full text Add to dashboard Cite

show abstract

“…The work in [25] detects clones in UML models such as class diagrams, but structure similarity is not considered when comparing two fragments. For subgraph detection, there are various methods considering frequent subgraph mining [26,27] and subgraph isomorphism [28], but the objective of these methods is significant different from this paper. These methods aim to discover arbitrary connected subgraphs instead of fragments, so many of them are useless for reference sub-process extraction which makes them not suitable for our purpose.…”

Section: Related Workmentioning

confidence: 99%

Generating Hierarchical Reference Process Model Using Fragments Clustering

Ling

Zhang

2015

2015 Asia-Pacific Software Engineering Conference (APSEC)

View full text Add to dashboard Cite

Process models are becoming more and more widespread in contemporary organizations. For the purpose of reducing cost and improve model quality, the ability to rapidly tailor a reference process to satisfy the changing of business requirements is necessary for organizations. In this context, how to provide a suitable reference process model for a specific domain becomes a challenging question. This paper proposes a method to automatically generate a hierarchical reference process model using fragments clustering from existing process variants. Similar fragments in process variants are detected and clustered firstly. Then an improved reference sub-process is discovered for each cluster of fragments based on a heuristic search. After fragments are replaced by reference sub-processes hierarchically, the refactored process variants are merged into the final reference process model. The quality and usability of the generated reference model are demonstrated by a case study and user experiment from a real industry scenario.

show abstract

“…The investigation of the proteins' spatial shape may provide important functional and structural insights (Clark et al, 1991;Cootes et al, 2003). Indeed, protein structures have been interpreted as graphs of amino acids and studied based on graph theory concepts (Borgwardt et al, 2005;Anchuri et al, 2013;Dhifli et al, 2014;Dhifli and Nguifo, 2015;Dhifli et al, 2017;Saha et al, 2017;Mrzic et al, 2018;Sugiyama et al, 2018). In this regard, some works were interested in the study of protein structures based on their graph properties and involved the use of topological classifications as in Bartoli et al (2007), where it has been shown that proteins can be considered as small-world networks of amino acids.…”

Section: Introductionmentioning

confidence: 99%

Efficiently Mining Recurrent Substructures from Protein Three-Dimensional Structure Graphs

Saidi

Dhifli

Maddouri

et al. 2019

Journal of Computational Biology

View full text Add to dashboard Cite

Studying protein structures is a major asset for understanding the molecular mechanisms of life. The number of publicly available protein structures has increasingly become extremely large. Yet, the classification of a protein structure remains a difficult, costly, and time-consuming task. Exploring spatial information on protein structures can provide important functional and structural insights. In this context, spatial motifs may correspond to relevant fragments, which might be very useful for a better understanding of proteins. In this article, we propose AntMot, a fast algorithm, to find spatial motifs from protein three-dimensional structures by extending the Karp-Miller-Rosenberg repetition finder, originally dedicated to sequences. The extracted motifs, termed ant-motifs, follow an ant-like shape that is composed of a backbone fragment from the primary structure, enriched with spatial refinements. We show that these motifs are biologically sound, and we used them as descriptors in the classification of several benchmark datasets. Experimental results show that our approach presents a trade-off between sequential motifs and subgraph motifs in terms of the number of extracted substructures, while providing a significant enhancement in the classification accuracy over sequential and frequent-subgraph motifs as well as alignment-based approaches.

show abstract

Approximate graph mining with label costs

Cited by 24 publications

References 21 publications

Task Sensitive Feature Exploration and Learning for Multitask Graph Classification

Task Sensitive Feature Exploration and Learning for Multitask Graph Classification

Generating Hierarchical Reference Process Model Using Fragments Clustering

Efficiently Mining Recurrent Substructures from Protein Three-Dimensional Structure Graphs

Contact Info

Product

Resources

About