Oldie but Goodie: Re-illuminating Label Propagation on Graphs with Partially Observed Features

TL;DR

This paper introduces GOODIE, a hybrid framework combining Label Propagation and Feature Propagation with attention and contrastive learning, to improve node classification on graphs with missing features, outperforming existing methods.

Contribution

It presents a novel hybrid approach with a GNN-based decoder, Structure-Feature Attention, and pseudo-label contrastive learning for better performance with partial features.

Findings

GOODIE outperforms state-of-the-art methods with limited features.

GOODIE performs well even with abundant features.

The proposed model effectively leverages structure and feature information.

Abstract

In real-world graphs, we often encounter missing feature situations where a few or the majority of node features, e.g., sensitive information, are missed. In such scenarios, directly utilizing Graph Neural Networks (GNNs) would yield sub-optimal results in downstream tasks such as node classification. Despite the emergence of a few GNN-based methods attempting to mitigate its missing situation, when only a few features are available, they rather perform worse than traditional structure-based models. To this end, we propose a novel framework that further illuminates the potential of classical Label Propagation (Oldie), taking advantage of Feature Propagation, especially when only a partial feature is available. Now called by GOODIE, it takes a hybrid approach to obtain embeddings from the Label Propagation branch and Feature Propagation branch. To do so, we first design a GNN-based decoder that enables the Label Propagation branch to output hidden embeddings that align with those of the FP branch. Then, GOODIE automatically captures the significance of structure and feature information thanks to the newly designed Structure-Feature Attention. Followed by a novel Pseudo-Label contrastive learning that differentiates the contribution of each positive pair within pseudo-labels originating from the LP branch, GOODIE outputs the final prediction for the unlabeled nodes. Through extensive experiments, we demonstrate that our proposed model, GOODIE, outperforms the existing state-of-the-art methods not only when only a few features are available but also in abundantly available situations. Source code of GOODIE is available at: https://github.com/SukwonYun/GOODIE.