Zero-shot Node Classification with Decomposed Graph Prototype Network

06/15/2021
by   Zheng Wang, et al.
0

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.

READ FULL TEXT
research
08/15/2023

KMF: Knowledge-Aware Multi-Faceted Representation Learning for Zero-Shot Node Classification

Recently, Zero-Shot Node Classification (ZNC) has been an emerging and c...
research
03/29/2019

Integrating Semantic Knowledge to Tackle Zero-shot Text Classification

Insufficient or even unavailable training data of emerging classes is a ...
research
11/20/2019

Heterogeneous Graph-based Knowledge Transfer for Generalized Zero-shot Learning

Generalized zero-shot learning (GZSL) tackles the problem of learning to...
research
03/23/2021

Expanding Semantic Knowledge for Zero-shot Graph Embedding

Zero-shot graph embedding is a major challenge for supervised graph lear...
research
12/14/2019

Estimating Early Fundraising Performance of Innovations via Graph-based Market Environment Model

Well begun is half done. In the crowdfunding market, the early fundraisi...
research
09/28/2019

Generalized Zero-shot ICD Coding

The International Classification of Diseases (ICD) is a list of classifi...
research
01/26/2023

SemSup-XC: Semantic Supervision for Zero and Few-shot Extreme Classification

Extreme classification (XC) involves predicting over large numbers of cl...

Please sign up or login with your details

Forgot password? Click here to reset