Zero-shot Node Classification with Decomposed Graph Prototype Network

Abstract

Node classification is a central task in graph data analysis. Scarce or even no labeled data of emerging classes is a big challenge for existing methods. A natural question arises: can we classify the nodes from those classes that have never been seen? In this paper, we study this zero-shot node classification (ZNC) problem which has a two-stage nature: (1) acquiring high-quality class semantic descriptions (CSDs) for knowledge transfer, and (2) designing a well generalized graph-based learning model. For the first stage, we give a novel quantitative CSDs evaluation strategy based on estimating the real class relationships, so as to get the "best" CSDs in a completely automatic way. For the second stage, we propose a novel Decomposed Graph Prototype Network (DGPN) method, following the principles of locality and compositionality for zero-shot model generalization. Finally, we conduct extensive experiments to demonstrate the effectiveness of our solutions.

Accepted by KDD 2021

References in corpus (6)

• Semi-Supervised Classification with Graph Convolutional Networks
• Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
• Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
• Measuring Compositionality in Representation Learning
• Locality and compositionality in zero-shot learning
• Equivalence between LINE and Matrix Factorization