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

11/20/2019
by   Junjie Wang, et al.
12

Generalized zero-shot learning (GZSL) tackles the problem of learning to classify instances involving both seen classes and unseen ones. The key issue is how to effectively transfer the model learned from seen classes to unseen classes. Existing works in GZSL usually assume that some prior information about unseen classes are available. However, such an assumption is unrealistic when new unseen classes appear dynamically. To this end, we propose a novel heterogeneous graph-based knowledge transfer method (HGKT) for GZSL, agnostic to unseen classes and instances, by leveraging graph neural network. Specifically, a structured heterogeneous graph is constructed with high-level representative nodes for seen classes, which are chosen through Wasserstein barycenter in order to simultaneously capture inter-class and intra-class relationship. The aggregation and embedding functions can be learned through graph neural network, which can be used to compute the embeddings of unseen classes by transferring the knowledge from their neighbors. Extensive experiments on public benchmark datasets show that our method achieves state-of-the-art results.

READ FULL TEXT
research
06/27/2017

A Unified approach for Conventional Zero-shot, Generalized Zero-shot and Few-shot Learning

Prevalent techniques in zero-shot learning do not generalize well to oth...
research
07/22/2019

Relational Generalized Few-Shot Learning

Transferring learned models to novel tasks is a challenging problem, par...
research
12/10/2018

Learning Embedding Adaptation for Few-Shot Learning

Learning with limited data is a key challenge for visual recognition. Fe...
research
06/15/2021

Zero-shot Node Classification with Decomposed Graph Prototype Network

Node classification is a central task in graph data analysis. Scarce or ...
research
08/10/2023

Cross-heterogeneity Graph Few-shot Learning

In recent years, heterogeneous graph few-shot learning has been proposed...
research
01/06/2022

Balancing Generalization and Specialization in Zero-shot Learning

Zero-Shot Learning (ZSL) aims to transfer classification capability from...
research
10/06/2020

Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detection

Few-shot Intent Detection is challenging due to the scarcity of availabl...

Please sign up or login with your details

Forgot password? Click here to reset