Interactive online learning for graph matching using active strategies

Conte, Donatello; Serratosa, Francesc

doi:10.1016/j.knosys.2020.106275

Cited by 8 publications

(3 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(As previously commented, Table 3 and Table 4 show their edit cost proposal.) Nevertheless, there has been a tendency to automatically learn these costs since it has been seen that a proper tuning of them is crucial to achieve good classification ratios in virtual screening [ 35 ] and other applications [ 56 , 57 , 58 , 59 , 60 ]. In [ 35 ], authors presented a learning algorithm that is forced to learn only one edit cost at once due to runtime restrictions.…”

Section: Methodsmentioning

confidence: 99%

Ligand-Based Virtual Screening Based on the Graph Edit Distance

Rica

Álvarez

Serratosa

2021

IJMS

Self Cite

View full text Add to dashboard Cite

Chemical compounds can be represented as attributed graphs. An attributed graph is a mathematical model of an object composed of two types of representations: nodes and edges. Nodes are individual components, and edges are relations between these components. In this case, pharmacophore-type node descriptions are represented by nodes and chemical bounds by edges. If we want to obtain the bioactivity dissimilarity between two chemical compounds, a distance between attributed graphs can be used. The Graph Edit Distance allows computing this distance, and it is defined as the cost of transforming one graph into another. Nevertheless, to define this dissimilarity, the transformation cost must be properly tuned. The aim of this paper is to analyse the structural-based screening methods to verify the quality of the Harper transformation costs proposal and to present an algorithm to learn these transformation costs such that the bioactivity dissimilarity is properly defined in a ligand-based virtual screening application. The goodness of the dissimilarity is represented by the classification accuracy. Six publicly available datasets—CAPST, DUD-E, GLL&GDD, NRLiSt-BDB, MUV and ULS-UDS—have been used to validate our methodology and show that with our learned costs, we obtain the highest ratios in identifying the bioactivity similarity in a structurally diverse group of molecules.

show abstract

Section: Methodsmentioning

confidence: 99%

Ligand-Based Virtual Screening Based on the Graph Edit Distance

Rica

Álvarez

Serratosa

2021

IJMS

Self Cite

View full text Add to dashboard Cite

show abstract

“…Unlike offline-based learning, teachers must be capable of preparing various things to support online learning, one of which is by considering the suitable language learning strategies (LLSs) applied in EFL online mode (Conte & Serratosa, 2020). This is to encourage students and assist them to be autonomous and active in their daily language learning endeavours given that the dimensions of social presence in online learning are low (Tu, 2001).…”

Section: Introductionmentioning

confidence: 99%

An Investigation on The Use of Social Strategies in Online EFL Learning

Ismiatun

Suhartoyo

2022

EHDJ

View full text Add to dashboard Cite

This study aims to investigate the use of social strategies in English as A Foreign Language (EFL) learning. This was inspired by the learning condition that has been changing from face-to-face atmosphere to the online-based due to the Covid-19 pandemic. This changing situation requires teachers and students to be more aware of applying suitable strategies in online learning mode, especially social strategies. Using the descriptive qualitative approach, this study was conducted on the fourth semester EFL students in a private university. To elicit the required data, set of online questionnaires was disseminated to 50 participants to obtain information on social strategies use in online EFL learning. The result of the descriptive analysis showed that average students exhibited a high frequency of using social strategies in their learning processes. In asynchronous learning, students preferred doing ‘collaboration and discussion’ to assess their completed task. The strategies of ‘using tools to improve interaction and communication as well as asking for clarification’ were more influential in synchronous learning in which technology effected the use of social strategies in the online class participation. Therefore, it becomes crystal clear that social strategies are deemed effective to aid online EFL learning. Further suggestions regarding the use of social strategies are also accessible at the end of this article.

show abstract

“…This is because all these applications have an objective function to be maximized (or minimized), for instance, the maximization of the recognition ratio or classification accuracy, between others. Thus, it turns out that several machine learning methods have been presented [19][20][21][22][23] to automatically deduce the graph edit distance parameters and, frequently, the objective function of these methods is maximized where these properties do not hold. Due to the findings of this paper, we currently know that the automatically learned graph edit distance parameters makes the graph edit distance to be a metric.…”

Section: Introductionmentioning

confidence: 99%

Redefining the Graph Edit Distance

Serratosa

2021

SN COMPUT. SCI.

Self Cite

View full text Add to dashboard Cite

Graph edit distance has been used since 1983 to compare objects in machine learning when these objects are represented by attributed graphs instead of vectors. In these cases, the graph edit distance is usually applied to deduce a distance between attributed graphs. This distance is defined as the minimum amount of edit operations (deletion, insertion and substitution of nodes and edges) needed to transform a graph into another. Since now, it has been stated that the distance properties have to be applied [(1) non-negativity (2) symmetry (3) identity and (4) triangle inequality] to the involved edit operations in the process of computing the graph edit distance to make the graph edit distance a metric. In this paper, we show that there is no need to impose the triangle inequality in each edit operation. This is an important finding since in pattern recognition applications, the classification ratio usually maximizes in the edit operation combinations (deletion, insertion and substitution of nodes and edges) that the triangle inequality is not fulfilled.

show abstract

Interactive online learning for graph matching using active strategies

Cited by 8 publications

References 60 publications

Ligand-Based Virtual Screening Based on the Graph Edit Distance

Ligand-Based Virtual Screening Based on the Graph Edit Distance

An Investigation on The Use of Social Strategies in Online EFL Learning

Redefining the Graph Edit Distance

Contact Info

Product

Resources

About