Data-Centric Learning from Unlabeled Graphs with Diffusion Model

TL;DR

This paper introduces a data-centric approach using diffusion models to leverage unlabeled graphs for property prediction, generating task-specific labeled examples that improve performance over traditional self-supervised methods.

Contribution

The paper proposes a novel diffusion-based method to extract and utilize knowledge from unlabeled graphs by generating labeled graph examples tailored to each prediction task.

Findings

Outperforms 15 existing methods on 15 tasks

Generated labeled examples improve prediction accuracy

Unlabeled data enhances performance beyond self-supervised learning

Abstract

Graph property prediction tasks are important and numerous. While each task offers a small size of labeled examples, unlabeled graphs have been collected from various sources and at a large scale. A conventional approach is training a model with the unlabeled graphs on self-supervised tasks and then fine-tuning the model on the prediction tasks. However, the self-supervised task knowledge could not be aligned or sometimes conflicted with what the predictions needed. In this paper, we propose to extract the knowledge underlying the large set of unlabeled graphs as a specific set of useful data points to augment each property prediction model. We use a diffusion model to fully utilize the unlabeled graphs and design two new objectives to guide the model's denoising process with each task's labeled data to generate task-specific graph examples and their labels. Experiments demonstrate that our data-centric approach performs significantly better than fifteen existing various methods on fifteen tasks. The performance improvement brought by unlabeled data is visible as the generated labeled examples unlike the self-supervised learning.