Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Community-Aware Framework for Influence Maximization with Explicit Accounting for Inter-Community Influence

Eliot W. Robson, Abhishek K. Umrawal

TL;DR

The paper tackles Influence Maximization in networks with significant cross-community diffusion by introducing Community-IM++, a scalable framework that explicitly accounts for inter-community influence. It extends prior community-aware IM methods with a diffusion-degree (CDD) heuristic anchored in two-hop cross-community diffusion, integrated into a Leiden-based partitioning and progressive budgeting workflow to select seeds with high cross-community reach. Empirical results on real-world networks show that Community-IM++ achieves near-greedy influence with up to two orders of magnitude lower runtime than CELF, and outperforms baselines in highly modular structures. This approach offers a practical, efficient tool for large-scale diffusion tasks such as viral marketing, misinformation control, and public health campaigns where cross-community reach is crucial.

Abstract

Influence Maximization (IM) seeks to identify a small set of seed nodes in a social network to maximize expected information spread under a diffusion model. While community-based approaches improve scalability by exploiting modular structure, they typically assume independence between communities, overlooking inter-community influence$\unicode{x2014}$a limitation that reduces effectiveness in real-world networks. We introduce Community-IM++, a scalable framework that explicitly models cross-community diffusion through a principled heuristic based on community-based diffusion degree (CDD) and a progressive budgeting strategy. The algorithm partitions the network, computes CDD to prioritize bridging nodes, and allocates seeds adaptively across communities using lazy evaluation to minimize redundant computations. Experiments on large real-world social networks under different edge weight models show that Community-IM++ achieves near-greedy influence spread at up to 100 times lower runtime, while outperforming Community-IM and degree heuristics across budgets and structural conditions. These results demonstrate the practicality of Community-IM++ for large-scale applications such as viral marketing, misinformation control, and public health campaigns, where efficiency and cross-community reach are critical.

A Community-Aware Framework for Influence Maximization with Explicit Accounting for Inter-Community Influence

TL;DR

The paper tackles Influence Maximization in networks with significant cross-community diffusion by introducing Community-IM++, a scalable framework that explicitly accounts for inter-community influence. It extends prior community-aware IM methods with a diffusion-degree (CDD) heuristic anchored in two-hop cross-community diffusion, integrated into a Leiden-based partitioning and progressive budgeting workflow to select seeds with high cross-community reach. Empirical results on real-world networks show that Community-IM++ achieves near-greedy influence with up to two orders of magnitude lower runtime than CELF, and outperforms baselines in highly modular structures. This approach offers a practical, efficient tool for large-scale diffusion tasks such as viral marketing, misinformation control, and public health campaigns where cross-community reach is crucial.

Abstract

Influence Maximization (IM) seeks to identify a small set of seed nodes in a social network to maximize expected information spread under a diffusion model. While community-based approaches improve scalability by exploiting modular structure, they typically assume independence between communities, overlooking inter-community influencea limitation that reduces effectiveness in real-world networks. We introduce Community-IM++, a scalable framework that explicitly models cross-community diffusion through a principled heuristic based on community-based diffusion degree (CDD) and a progressive budgeting strategy. The algorithm partitions the network, computes CDD to prioritize bridging nodes, and allocates seeds adaptively across communities using lazy evaluation to minimize redundant computations. Experiments on large real-world social networks under different edge weight models show that Community-IM++ achieves near-greedy influence spread at up to 100 times lower runtime, while outperforming Community-IM and degree heuristics across budgets and structural conditions. These results demonstrate the practicality of Community-IM++ for large-scale applications such as viral marketing, misinformation control, and public health campaigns, where efficiency and cross-community reach are critical.
Paper Structure (28 sections, 2 theorems, 12 equations, 12 figures, 1 table, 1 algorithm)

This paper contains 28 sections, 2 theorems, 12 equations, 12 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Motivation
  3. Literature Review
  4. Contribution
  5. Organization
  6. Preliminaries and Problem Statement
  7. Diffusion Model
  8. Influence
  9. Problem Statement
  10. Estimating the Influence
  11. Influence Estimation
  12. Diffusion Degree
  13. The Proposed Framework
  14. Overview
  15. Community Structure
  16. ...and 13 more sections

Key Result

Lemma 3.2

For $u, v \in V$, let $\mathcal{P}_{v,u}^{(2)}$ be all paths from $v$ to $u$ of length at most two. Then: where $\operatorname{\mathbb{P}}\del{P}$ denotes the probability that all edges of path $P$ are active.

Figures (12)

  • Figure 1: Deezer network
  • Figure 2: DBLP network
  • Figure 3: Amazon network
  • Figure 5: Deezer network
  • Figure 6: DBLP network
  • ...and 7 more figures

Theorems & Definitions (7)

  • Definition 3.1
  • Lemma 3.2
  • proof
  • Remark 3.3
  • Remark 3.4
  • Lemma 4.1
  • proof