Rethinking Knowledge Graph Propagation for Zero-Shot Learning

05/29/2018
by   Michael Kampffmeyer, et al.
0

The potential of graph convolutional neural networks for the task of zero-shot learning has been demonstrated recently. These models are highly sample efficient as related concepts in the graph structure share statistical strength allowing generalization to new classes when faced with a lack of data. However, knowledge from distant nodes can get diluted when propagating through intermediate nodes, because current approaches to zero-shot learning use graph propagation schemes that perform Laplacian smoothing at each layer. We show that extensive smoothing does not help the task of regressing classifier weights in zero-shot learning. In order to still incorporate information from distant nodes and utilize the graph structure, we propose an Attentive Dense Graph Propagation Module (ADGPM). ADGPM allows us to exploit the hierarchical graph structure of the knowledge graph through additional connections. These connections are added based on a node's relationship to its ancestors and descendants and an attention scheme is further used to weigh their contribution depending on the distance to the node. Finally, we illustrate that finetuning of the feature representation after training the ADGPM leads to considerable improvements. Our method achieves competitive results, outperforming previous zero-shot learning approaches.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/26/2022

Semantic Enhanced Knowledge Graph for Large-Scale Zero-Shot Learning

Zero-Shot Learning has been a highlighted research topic in both vision ...
research
03/13/2017

Zero-Shot Learning - The Good, the Bad and the Ugly

Due to the importance of zero-shot learning, the number of proposed appr...
research
03/15/2019

Zero Shot Learning with the Isoperimetric Loss

We introduce the isoperimetric loss as a regularization criterion for le...
research
09/21/2022

DeepGraphONet: A Deep Graph Operator Network to Learn and Zero-shot Transfer the Dynamic Response of Networked Systems

This paper develops a Deep Graph Operator Network (DeepGraphONet) framew...
research
02/26/2021

Knowledge-aware Zero-Shot Learning: Survey and Perspective

Zero-shot learning (ZSL) which aims at predicting classes that have neve...
research
06/11/2019

Task-Aware Deep Sampling for Feature Generation

The human ability to imagine the variety of appearances of novel objects...
research
05/26/2021

Zero-shot Medical Entity Retrieval without Annotation: Learning From Rich Knowledge Graph Semantics

Medical entity retrieval is an integral component for understanding and ...

Please sign up or login with your details

Forgot password? Click here to reset