STR-GNN: stability-regularized graph neural networks for suppressing spurious temporal variations in dynamic
Daozheng Qu1,2, Yanfei Ma3, Yibo Wang4
1Department of Computer Science, Fairleigh Dickinson University, V6B 2P6, Vancouver, Canada. daozheng.qu@ieee.org.
Scientific Reports
|June 2, 2026
Summary
Temporal graph neural networks (GNNs) often struggle with unstable community assignments due to noise. This study introduces a method to stabilize community evolution in dynamic networks, improving reliability.
Area of Science:
- Graph Neural Networks
- Network Science
- Data Mining
Background:
- Temporal graphs exhibit spurious fluctuations, leading to unstable community assignments in dynamic networks.
- Existing graph neural networks (GNNs) can overreact to transient noise, hindering accurate community detection.
- Instability is particularly problematic in streaming or weakly supervised temporal GNN applications.
Purpose of the Study:
- To address spurious temporal variations in dynamic community detection using temporal GNNs.
- To enhance the temporal consistency and reliability of community structures identified by GNNs.
- To develop a framework that distinguishes genuine community evolution from transient perturbations.
Main Methods:
- Implemented stability-aware regularization techniques.
- Introduced consistency restrictions across successive graph snapshots.
- Developed a framework to promote coherent community structures over time.
Main Results:
- Mitigated false temporal fluctuations in community assignments.
- Enhanced the resilience and reliability of temporal GNNs for community identification.
- Improved the ability to adapt to authentic structural changes while maintaining stability.
Conclusions:
- The proposed method stabilizes community evolution, making temporal GNNs more suitable for real-world dynamic networks.
- The framework improves interpretability by reducing erratic fluctuations in community structures.
- This approach enhances the robustness of dynamic community recognition in noisy and partially observed data.
Related Concept Videos
01:14Stability of structures
In mechanical engineering, the stability of systems under various forces is critical for designing durable and efficient structures. One fundamental way to explore these concepts is by analyzing systems like two rods connected at a pivot point, O, with a torsional spring of spring constant k at the pivot point. This system is similar in appearance to a scissor jack used to change tires on a car. In this case, the arms of the linkage (equivalent to the rods in this system) are entirely vertical,...
01:19Survival Tree
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a survival tree begins...
Building a Survival Tree
Constructing a survival tree begins...
01:28Stability
The time response of a linear time-invariant (LTI) system can be divided into transient and steady-state responses. The transient response represents the system's initial reaction to a change in input and diminishes to zero over time. In contrast, the steady-state response is the behavior that persists after the transient effects have faded.
The stability of an LTI system is determined by the roots of its characteristic equation, known as poles. A system is stable if it produces a bounded...
The stability of an LTI system is determined by the roots of its characteristic equation, known as poles. A system is stable if it produces a bounded...
01:37Neural Regulation
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
01:24BIBO stability of continuous and discrete -time systems
System stability is a fundamental concept in signal processing, often assessed using convolution. For a system to be considered bounded-input bounded-output (BIBO) stable, any bounded input signal must produce a bounded output signal. A bounded input signal is one where the modulus does not exceed a certain constant at any point in time.
To determine the BIBO stability, the convolution integral is utilized when a bounded continuous-time input is applied to a Linear Time-Invariant (LTI) system.
To determine the BIBO stability, the convolution integral is utilized when a bounded continuous-time input is applied to a Linear Time-Invariant (LTI) system.
01:24Sequence Networks of Rotating Machines
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...
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...