Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Pharmacodynamic Models: Logarithmic Concentration–Effect Model01:15

Pharmacodynamic Models: Logarithmic Concentration–Effect Model

The log-linear model is a pharmacological framework used to describe the relationship between drug concentration and its effect. This model is particularly relevant when the observed effects range between 20% and 80% of the drug’s maximum effect (Emax), where a near-linear relationship is observed between the log of drug concentration and the measured effect. However, the log-linear model does not predict the maximum possible effect (Emax) or the effect at zero drug concentration, limiting its...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Detection and recognition of metal surface corrosion based on CBG-YOLOv5s.

PloS one·2024
Same author

HDGFI: Hierarchical Dual-Level Graph Feature Interaction Model for Personalized Recommendation.

Entropy (Basel, Switzerland)·2022
See all related articles

Related Experiment Video

Updated: Jul 21, 2026

A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets
08:45

A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets

Published on: December 5, 2014

9.3K

A Dual Adaptive Interaction Click-Through Rate Prediction Based on Attention Logarithmic Interaction Network.

Shiqi Li1, Zhendong Cui1, Yongquan Pei1

  • 1School of Computer and Control Engineering, Yantai University, Yantai 264005, China.

Entropy (Basel, Switzerland)
|December 23, 2022
PubMed
Summary

The Attention Logarithmic Interaction Network (ALIN) improves click-through rate (CTR) prediction by adaptively modeling feature interactions. This novel approach enhances accuracy in advertising and recommender systems.

Keywords:
Newton’s identityattention mechanismfeature interactionlogarithmic networksrecommendation system

More Related Videos

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments
13:00

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments

Published on: January 23, 2017

10.0K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.0K

Related Experiment Videos

Last Updated: Jul 21, 2026

A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets
08:45

A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets

Published on: December 5, 2014

9.3K
Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments
13:00

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments

Published on: January 23, 2017

10.0K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.0K

Area of Science:

  • Computer Science
  • Machine Learning
  • Artificial Intelligence

Background:

  • Click-through rate (CTR) prediction is vital for advertising and recommender systems.
  • Accurately capturing user interests and managing vast datasets are key challenges.
  • Existing methods struggle to determine optimal feature interaction orders and identify useful interactions.

Purpose of the Study:

  • To introduce a novel network architecture for enhanced CTR prediction.
  • To effectively model feature interactions, including higher-order ones, adaptively.
  • To improve the accuracy and efficiency of CTR prediction models.

Main Methods:

  • The Attention Logarithmic Network (ALN) uses logarithmic neural networks (LNN) for feature interactions.
  • The Squeeze-and-Excitation (SE) mechanism adaptively weights higher-order feature interactions.
  • The Attention Logarithmic Interaction Network (ALIN) integrates Newton's identity into ALN to address information loss.

Main Results:

  • ALIN effectively models adaptive-order feature interactions using logarithmic and exponential transformations.
  • The SE mechanism adaptively prioritizes important higher-order feature interactions.
  • Experiments on two datasets demonstrate ALIN's efficiency and effectiveness in CTR prediction.

Conclusions:

  • ALIN offers a significant advancement in CTR prediction by intelligently handling feature interactions.
  • The proposed method addresses limitations of previous enumeration-filter approaches.
  • ALIN enhances prediction accuracy and system performance in advertising and recommendation contexts.