Recurrent Collective Classification

TL;DR

This paper introduces Recurrent Collective Classification (RCC), a novel training method for iterative network node classification that improves accuracy and robustness by directly minimizing the loss function, overcoming biases of previous methods.

Contribution

The paper presents RCC, a new variant of ICA that uses gradient-based optimization to better align relational features with true labels, enhancing performance on noisy network data.

Findings

RCC outperforms traditional ICA in accuracy.

RCC demonstrates increased robustness in noisy classification settings.

Direct loss minimization improves model training effectiveness.

Abstract

We propose a new method for training iterative collective classifiers for labeling nodes in network data. The iterative classification algorithm (ICA) is a canonical method for incorporating relational information into classification. Yet, existing methods for training ICA models rely on the assumption that relational features reflect the true labels of the nodes. This unrealistic assumption introduces a bias that is inconsistent with the actual prediction algorithm. In this paper, we introduce recurrent collective classification (RCC), a variant of ICA analogous to recurrent neural network prediction. RCC accommodates any differentiable local classifier and relational feature functions. We provide gradient-based strategies for optimizing over model parameters to more directly minimize the loss function. In our experiments, this direct loss minimization translates to improved accuracy and robustness on real network data. We demonstrate the robustness of RCC in settings where local classification is very noisy, settings that are particularly challenging for ICA.