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

Time-Series Graph00:54

Time-Series Graph

5.6K
A time-series graph is a line graph with repeated measurements taken at successive intervals of time. It is also called a time series chart. To construct a time-series graph, one must look at both pieces of a paired data set. The horizontal axis is used to plot the time increments, and the vertical axis is used to plot the values of the variable that one is measuring. By using the axes in this way, each point on the graph will correspond to time and a measured quantity. The points on the graph...
5.6K
Graphs of Equations in Two Variables01:30

Graphs of Equations in Two Variables

406
An equation with two variables, typically written in the form y = f(x) or Ax + By = C, describes a relationship between quantities represented by x and y. Each solution to such an equation is an ordered pair (x, y) that satisfies the equation when substituted. These pairs can be represented graphically to understand the variables' relationship visually.A common technique for constructing the graph of a two-variable equation is to create a value table. Begin by choosing several values for the...
406
Sequence Networks of Rotating Machines01:24

Sequence Networks of Rotating Machines

550
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
550
Entropy Changes Accompanying Specific Processes01:21

Entropy Changes Accompanying Specific Processes

135
Entropy, a measure of disorder in a system, changes during phase transitions like freezing or boiling. At the transition temperature Ttrs, where two phases are in equilibrium, the phase transition is a reversible process. The entropy change can be calculated from a substance's enthalpy of transition using the equation ΔStrs = ΔtrsH /Ttrs.When a perfect gas expands isothermally from one volume to another, entropy increases logarithmically with volume. Conversely, isothermal compression...
135
Drug Concentration Versus Time Correlation01:15

Drug Concentration Versus Time Correlation

3.1K
The plasma drug concentration-time curve is a crucial tool in pharmacokinetics, representing the drug's concentration in plasma at different time intervals post-administration. This curve illustrates the drug's journey from absorption into the systemic circulation, distribution to body tissues, and eventual elimination through excretion or biotransformation.
Two pivotal parameters are the minimum effective concentration (MEC) and the minimum toxic concentration (MTC). The MEC is the...
3.1K
Understanding Memory01:19

Understanding Memory

1.9K
Memory is the retention of information or experiences over time, facilitated through three main processes: encoding, storage, and retrieval. Encoding is the process of inputting information into the memory system. For instance, when listening to a lecture, watching a play, reading a book, or having a conversation, the brain is actively encoding information. This initial stage involves transforming sensory input into a form that can be processed and stored by the brain. Various factors, such as...
1.9K

You might also read

Related Articles

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

Sort by
Same author

Scaling Up Bayesian Neural Networks with Neural Networks.

Transactions on machine learning research·2026
Same author

SPOP-mediated nuclear ubiquitination degradation of p62/SQSTM1 contributes to HR repair.

Oncogene·2026
Same author

Neoadjuvant immunochemotherapy followed by definitive radiotherapy in locally advanced head and neck squamous cell carcinoma: two-year survival outcomes.

Cancer immunology, immunotherapy : CII·2026
Same author

Ultra-deep <i>vs</i>. standard swept-source optical coherence tomography for posterior vitreous detachment assessment: a retrospective comparative study.

Quantitative imaging in medicine and surgery·2026
Same author

Case Report: Diagnosis of Hyperthyroidism in a Preterm Infant With Concurrent Respiratory Distress Syndrome.

AACE endocrinology and diabetes·2026
Same author

YOLOv13 Steel Surface Defect Detection Method Based on Multi-Scale Denoising Enhanced A2C2f Module.

Materials (Basel, Switzerland)·2026
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

Related Experiment Video

Updated: Apr 21, 2026

Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients
09:32

Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients

Published on: December 18, 2016

13.1K

NEU: Continuous-time memory evolution for temporal interaction graph networks.

Yang Meng1, Yuting Liu2

  • 1School of Mathematics and Statistics, Beijing Jiaotong University, Beijing, 100044, China.

Neural Networks : the Official Journal of the International Neural Network Society
|April 19, 2026
PubMed
Summary
This summary is machine-generated.

Introducing the Natural Evolution Unit (NEU), this study enhances temporal graph neural networks (GNNs) by enabling continuous memory evolution. NEU mitigates memory aging in dynamic graphs, improving prediction accuracy and temporal consistency.

Keywords:
Continuous-time modelingMemory evolutionOrdinary differential equationsTemporal interaction graphs

More Related Videos

Temporal Ordering of Dynamic Expression Data from Detailed Spatial Expression Maps
11:52

Temporal Ordering of Dynamic Expression Data from Detailed Spatial Expression Maps

Published on: February 9, 2017

6.6K
Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
09:44

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

6.2K

Related Experiment Videos

Last Updated: Apr 21, 2026

Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients
09:32

Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients

Published on: December 18, 2016

13.1K
Temporal Ordering of Dynamic Expression Data from Detailed Spatial Expression Maps
11:52

Temporal Ordering of Dynamic Expression Data from Detailed Spatial Expression Maps

Published on: February 9, 2017

6.6K
Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
09:44

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

6.2K

Area of Science:

  • Machine Learning, Graph Neural Networks, Temporal Dynamics

Background:

  • Canonical Graph Neural Networks (GNNs) assume static graph topologies, limiting their application to dynamic, real-world interaction graphs.
  • Existing memory-augmented temporal GNNs update node memory discretely, neglecting natural decay and short-term drift, leading to stale memories for sparsely active nodes.
  • Current models cannot infer node states at arbitrary intermediate timestamps, hindering accuracy and temporal consistency.

Purpose of the Study:

  • To introduce a novel module, the Natural Evolution Unit (NEU), for continuous-time memory evolution in temporal graphs.
  • To address the limitations of discrete-update paradigms in temporal GNNs, specifically memory aging and lack of continuous time inferability.
  • To enhance the temporal modeling capabilities of GNNs by treating time differences as dynamic drivers rather than static inputs.

Main Methods:

  • Developed the Natural Evolution Unit (NEU) module, integrating a continuous-time memory evolution stage before embedding read-out.
  • NEU employs a learnable ordinary differential equation (ODE) to model smooth memory drift and decay between events.
  • Utilized fixed time encoding for training stability, enhancing experimental results.

Main Results:

  • NEU enables continuous queryability of node states at arbitrary timestamps, offering improved temporal inferability and interpretability.
  • The ODE-driven dynamics in NEU significantly enhance temporal modeling, reducing reliance on complex learnable time encodings.
  • Experiments on five datasets demonstrated consistent improvements in Area Under the Curve (AUC) and Average Precision (AP) over strong memory-based baselines.

Conclusions:

  • The Natural Evolution Unit (NEU) effectively mitigates memory aging in temporal GNNs, crucial for long-term prediction on dynamic graphs.
  • NEU provides a simple yet effective approach for representation learning on dynamic graphs, enhancing both accuracy and temporal consistency.
  • Continuous-time memory evolution offers a promising new perspective for modeling evolving relational data.