Differentiated Information Mining: A Semi-supervised Learning Framework for GNNs

TL;DR

This paper introduces DiFac, a semi-supervised learning framework for GNNs that derives and enforces consistency among differentiated factors from a single source, improving robustness and generalization.

Contribution

The paper proposes a novel framework, DiFac, which extracts and enforces consistency among differentiated factors from one source, and incorporates large multimodal models for auxiliary decision factors.

Findings

DiFac improves robustness and generalization in low-label regimes.

It outperforms baseline methods on multiple benchmark datasets.

Incorporating auxiliary information sources enhances decision-making.

Abstract

In semi-supervised learning (SSL) for enhancing the performance of graph neural networks (GNNs) with unlabeled data, introducing mutually independent decision factors for cross-validation is regarded as an effective strategy to alleviate pseudo-label confirmation bias and training collapse. However, obtaining such factors is challenging in practice: additional and valid information sources are inherently scarce, and even when such sources are available, their independence from the original source cannot be guaranteed. To address this challenge, In this paper we propose a Differentiated Factor Consistency Semi-supervised Framework (DiFac), which derives differentiated factors from a single information source and enforces their consistency. During pre-training, the model learns to extract these factors; in training, it iteratively removes samples with conflicting factors and ranks pseudo-labels based on the shortest stave principle, selecting the top candidate samples to reduce overconfidence commonly observed in confidence-based or ensemble-based methods. Our framework can also incorporate additional information sources. In this work, we leverage the large multimodal language model to introduce latent textual knowledge as auxiliary decision factors, and we design a accountability scoring mechanism to mitigate additional erroneous judgments introduced by these auxiliary factors. Experiments on multiple benchmark datasets demonstrate that DiFac consistently improves robustness and generalization in low-label regimes, outperforming other baseline methods.