6.0Impact Factor
9.9CiteScore
26 daysTime to First Decision

Machine Learning and Knowledge Extraction, Volume 4, Issue 3

September 2022 - 13 articles

Cover Story: Molecular descriptors essentially dictate the performance of quantitative structure–activity relationship (QSAR) models that uncover molecules with desired properties in the ever-expanding virtual and synthetically available chemical space. The Simplified Molecular Input Line Entry System (SMILES) is one of the most used descriptors, for which the importance of numerical encoding has recently been recognized. We propose a new variable-length-array SMILES (VLA-SMILES) descriptor that reduces the code size while preserving structural characteristics, where the tradeoff between training speed and accuracy is controlled through clustering of binary numbers. The method of statistical H₀ hypothesis testing based on the F_2,n-2 criteria was used for predictive ability validation of designed VLA-SMILES featuring QSAR models using prototypical ChEMBL datasets (n is a volume of the testing set). View this paper

Issues are regarded as officially published after their release is announced to the table of contents alert mailing list .
You may sign up for email alerts to receive table of contents of newly released issues.
PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.

Articles (13)

Select all

Article

8 Citations

4,332 Views

20 Pages

Semantic Image Segmentation Using Scant Pixel Annotations

Adithi D. Chakravarthy,
Dilanga Abeyrathna,
Mahadevan Subramaniam,
Parvathi Chundi and
Venkataramana Gadhamshetty

Mach. Learn. Knowl. Extr.2022, 4(3), 621-640;https://doi.org/10.3390/make4030029

1 July 2022

The success of deep networks for the semantic segmentation of images is limited by the availability of annotated training data. The manual annotation of images for segmentation is a tedious and time-consuming task that often requires sophisticated us...

Full Article

Article

11 Citations

4,451 Views

30 Pages

Certifiable Unlearning Pipelines for Logistic Regression: An Experimental Study

Ananth Mahadevan and
Michael Mathioudakis

Mach. Learn. Knowl. Extr.2022, 4(3), 591-620;https://doi.org/10.3390/make4030028

22 June 2022

Machine unlearning is the task of updating machine learning (ML) models after a subset of the training data they were trained on is deleted. Methods for the task are desired to combine effectiveness and efficiency (i.e., they should effectively &ldqu...

Full Article

Article

1 Citations

2,942 Views

11 Pages

Real Quadratic-Form-Based Graph Pooling for Graph Neural Networks

Youfa Liu and
Guo Chen

Mach. Learn. Knowl. Extr.2022, 4(3), 580-590;https://doi.org/10.3390/make4030027

21 June 2022

Graph neural networks (GNNs) have developed rapidly in recent years because they can work over non-Euclidean data and possess promising prediction power in many real-word applications. The graph classification problem is one of the central problems i...

Full Article

of 2

Get Alerted

Add your email address to receive forthcoming issues of this journal.

Mach. Learn. Knowl. Extr. - ISSN 2504-4990

Imprint

Download Flyer