Explaining Synergistic Effects in Social Recommendations

TL;DR

This paper introduces SemExplainer, a novel method that explains how synergistic effects across multiple social networks influence recommendations by identifying subgraphs that maximize information gain, improving explainability.

Contribution

The paper extends the concept of information gain to graph data and develops SemExplainer, a method that explains synergistic effects in social recommendation systems through subgraph analysis.

Findings

SemExplainer outperforms baseline methods in explaining synergistic effects.

It effectively identifies subgraphs embodying synergistic effects.

Experiments demonstrate improved explanation quality on three datasets.

Abstract

In social recommenders, the inherent nonlinearity and opacity of synergistic effects across multiple social networks hinders users from understanding how diverse information is leveraged for recommendations, consequently diminishing explainability. However, existing explainers can only identify the topological information in social networks that significantly influences recommendations, failing to further explain the synergistic effects among this information. Inspired by existing findings that synergistic effects enhance mutual information between inputs and predictions to generate information gain, we extend this discovery to graph data. We quantify graph information gain to identify subgraphs embodying synergistic effects. Based on the theoretical insights, we propose SemExplainer, which explains synergistic effects by identifying subgraphs that embody them. SemExplainer first extracts explanatory subgraphs from multi-view social networks to generate preliminary importance explanations for recommendations. A conditional entropy optimization strategy to maximize information gain is developed, thereby further identifying subgraphs that embody synergistic effects from explanatory subgraphs. Finally, SemExplainer searches for paths from users to recommended items within the synergistic subgraphs to generate explanations for the recommendations. Extensive experiments on three datasets demonstrate the superiority of SemExplainer over baseline methods, providing superior explanations of synergistic effects.