Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Identifying Key Nodes for the Influence Spread using a Machine Learning Approach

Mateusz Stolarski, Adam Piróg, Piotr Bródka

TL;DR

The paper tackles identifying influential seed nodes to maximize spread under the Independent Cascade diffusion model. It introduces an enhanced ML framework with Smart Bins discretization for robust ground-truth labeling, a 14-feature centrality embedding augmented by diffusion probabilities, and evaluation across multiple real networks using LightGBM. Key findings show that Smart Bins improve label quality and stability, and cross-network generalization is feasible, especially within network families; feature analysis highlights out-degree and related measures as primary predictors. The work offers practical pathways for rapid, generalizable seed selection in applications like marketing and epidemic control, with future directions including graph neural networks and network-similarity guided training set design.

Abstract

The identification of key nodes in complex networks is an important topic in many network science areas. It is vital to a variety of real-world applications, including viral marketing, epidemic spreading and influence maximization. In recent years, machine learning algorithms have proven to outperform the conventional, centrality-based methods in accuracy and consistency, but this approach still requires further refinement. What information about the influencers can be extracted from the network? How can we precisely obtain the labels required for training? Can these models generalize well? In this paper, we answer these questions by presenting an enhanced machine learning-based framework for the influence spread problem. We focus on identifying key nodes for the Independent Cascade model, which is a popular reference method. Our main contribution is an improved process of obtaining the labels required for training by introducing 'Smart Bins' and proving their advantage over known methods. Next, we show that our methodology allows ML models to not only predict the influence of a given node, but to also determine other characteristics of the spreading process-which is another novelty to the relevant literature. Finally, we extensively test our framework and its ability to generalize beyond complex networks of different types and sizes, gaining important insight into the properties of these methods.

Identifying Key Nodes for the Influence Spread using a Machine Learning Approach

TL;DR

The paper tackles identifying influential seed nodes to maximize spread under the Independent Cascade diffusion model. It introduces an enhanced ML framework with Smart Bins discretization for robust ground-truth labeling, a 14-feature centrality embedding augmented by diffusion probabilities, and evaluation across multiple real networks using LightGBM. Key findings show that Smart Bins improve label quality and stability, and cross-network generalization is feasible, especially within network families; feature analysis highlights out-degree and related measures as primary predictors. The work offers practical pathways for rapid, generalizable seed selection in applications like marketing and epidemic control, with future directions including graph neural networks and network-similarity guided training set design.

Abstract

The identification of key nodes in complex networks is an important topic in many network science areas. It is vital to a variety of real-world applications, including viral marketing, epidemic spreading and influence maximization. In recent years, machine learning algorithms have proven to outperform the conventional, centrality-based methods in accuracy and consistency, but this approach still requires further refinement. What information about the influencers can be extracted from the network? How can we precisely obtain the labels required for training? Can these models generalize well? In this paper, we answer these questions by presenting an enhanced machine learning-based framework for the influence spread problem. We focus on identifying key nodes for the Independent Cascade model, which is a popular reference method. Our main contribution is an improved process of obtaining the labels required for training by introducing 'Smart Bins' and proving their advantage over known methods. Next, we show that our methodology allows ML models to not only predict the influence of a given node, but to also determine other characteristics of the spreading process-which is another novelty to the relevant literature. Finally, we extensively test our framework and its ability to generalize beyond complex networks of different types and sizes, gaining important insight into the properties of these methods.

Paper Structure

This paper contains 12 sections, 3 equations, 7 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Framework Description
  4. Estimating Nodes' Influence
  5. Obtaining the Labels
  6. Selecting the Features for Machine Learning Algorithms
  7. Experiments
  8. Machine Learning Algorithm Evaluation
  9. Model Generalization
  10. Impact of Smart Binning
  11. The Importance of Features
  12. Discussion

Figures (7)

  • Figure S1: The framework for identifying influential nodes.
  • Figure S2: Smart bins---clustering discretization on the Facebook network. The dashed line marks the top 5% of the nodes. Nodes are colored according to the class they fit into, with the blue ones being top class (most influential nodes).
  • Figure S3: Machine learning algorithm comparison with mean values aggregated across all the experiments.
  • Figure S4: LightGBM performance in various tasks.
  • Figure S5: Model generalization.
  • ...and 2 more figures