NetEffect: Discovery and Exploitation of Generalized Network Effects

TL;DR

NetEffect is a scalable graph mining method that detects, explains, and exploits generalized network effects like homophily and heterophily, significantly improving node classification performance on large real-world graphs.

Contribution

It introduces a principled statistical test and a closed-form solution for identifying and estimating GNE, enabling more accurate and explainable analysis of complex networks.

Findings

NetEffect detects the absence of GNE in many graphs with heterophily.

Incorporating GNE improves node classification accuracy.

Achieves over 7 times speedup on large graphs compared to competitors.

Abstract

Given a large graph with few node labels, how can we (a) identify whether there is generalized network-effects (GNE) or not, (b) estimate GNE to explain the interrelations among node classes, and (c) exploit GNE efficiently to improve the performance on downstream tasks? The knowledge of GNE is valuable for various tasks like node classification, and targeted advertising. However, identifying GNE such as homophily, heterophily or their combination is challenging in real-world graphs due to limited availability of node labels and noisy edges. We propose NetEffect, a graph mining approach to address the above issues, enjoying the following properties: (i) Principled: a statistical test to determine the presence of GNE in a graph with few node labels; (ii) General and Explainable: a closed-form solution to estimate the specific type of GNE observed; and (iii) Accurate and Scalable: the integration of GNE for accurate and fast node classification. Applied on real-world graphs, NetEffect discovers the unexpected absence of GNE in numerous graphs, which were recognized to exhibit heterophily. Further, we show that incorporating GNE is effective on node classification. On a million-scale real-world graph, NetEffect achieves over 7 times speedup (14 minutes vs. 2 hours) compared to most competitors.