ColdExpand: Semi-Supervised Graph Learning in Cold Start

Il-Jae Kwon, Kyoung-Woon On, Dong-Geon Lee, Byoung-Tak Zhang

Keywords: Graph Neural Networks, Cold Start, Semi-supervised Learning

Abstract: Most real-world graphs are dynamic and eventually face the cold start problem. A fundamental question is how the new cold nodes acquire initial information in order to be adapted into the existing graph. Here we postulates the cold start problem as a fundamental issue in graph learning and propose a new learning setting, "``Expanded Semi-supervised Learning." In expanded semi-supervised learning we extend the original semi-supervised learning setting even to new cold nodes that are disconnected from the graph. To this end, we propose ColdExpand model that classifies the cold nodes based on link prediction with multiple goals to tackle. We experimentally prove that by adding additional goal to existing link prediction method, our method outperforms the baseline in both expanded semi-supervised link prediction (at most 24\%) and node classification tasks (at most 15%). To the best of our knowledge this is the first study to address expansion of semi-supervised learning to unseen nodes.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: This paper draws attention to a new task Expanded Semi-Supervised Learning, and propose the ColdExpand method which uses multi-task strategy to overcome the lack of topological information in the cold start setting.

Reviewed Version (pdf): https://openreview.net/references/pdf?id=O_tsnYWP9