Refutations on "Debunking the Myths of Influence Maximization: An In-Depth Benchmarking Study"

TL;DR

This paper critically examines and refutes the claims of a recent influence maximization benchmarking study, highlighting methodological flaws, experimental issues, and misleading conclusions about various algorithms.

Contribution

It provides a systematic critique of the previous study, correcting misconceptions and emphasizing proper evaluation practices in influence maximization research.

Findings

The original study's methodology is flawed and leads to incorrect conclusions.

The paper identifies experimental bugs and issues in the influence maximization algorithms.

It refutes 11 specific misclaims made in the previous benchmarking study.

Abstract

In a recent SIGMOD paper titled "Debunking the Myths of Influence Maximization: An In-Depth Benchmarking Study", Arora et al. [1] undertake a performance benchmarking study of several well-known algorithms for influence maximization. In the process, they contradict several published results, and claim to have unearthed and debunked several "myths" that existed around the research of influence maximization. It is the goal of this article to examine their claims objectively and critically, and refute the erroneous ones. Our investigation discovers that first, the overall experimental methodology in Arora et al. [1] is flawed and leads to scientifically incorrect conclusions. Second, the paper [1] is riddled with issues specific to a variety of influence maximization algorithms, including buggy experiments, and draws many misleading conclusions regarding those algorithms. Importantly, they fail to appreciate the trade-off between running time and solution quality, and did not incorporate it correctly in their experimental methodology. In this article, we systematically point out the issues present in [1] and refute 11 of their misclaims.