Model-Agnostic Graph Regularization for Few-Shot Learning

by   Ethan Shen, et al.
University of Massachusetts Amherst
Stanford University

In many domains, relationships between categories are encoded in the knowledge graph. Recently, promising results have been achieved by incorporating knowledge graph as side information in hard classification tasks with severely limited data. However, prior models consist of highly complex architectures with many sub-components that all seem to impact performance. In this paper, we present a comprehensive empirical study on graph embedded few-shot learning. We introduce a graph regularization approach that allows a deeper understanding of the impact of incorporating graph information between labels. Our proposed regularization is widely applicable and model-agnostic, and boosts the performance of any few-shot learning model, including fine-tuning, metric-based, and optimization-based meta-learning. Our approach improves the performance of strong base learners by up to 2 and 6.7 Additional analyses reveal that graph regularizing models result in a lower loss for more difficult tasks, such as those with fewer shots and less informative support examples.


page 1

page 2

page 3

page 4


Looking back to lower-level information in few-shot learning

Humans are capable of learning new concepts from small numbers of exampl...

Combat Data Shift in Few-shot Learning with Knowledge Graph

Many few-shot learning approaches have been designed under the meta-lear...

On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning

Model-agnostic meta-learning (MAML) has emerged as one of the most succe...

L2AE-D: Learning to Aggregate Embeddings for Few-shot Learning with Meta-level Dropout

Few-shot learning focuses on learning a new visual concept with very lim...

Ontology-enhanced Prompt-tuning for Few-shot Learning

Few-shot Learning (FSL) is aimed to make predictions based on a limited ...

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

Zero-Shot Learning has been a highlighted research topic in both vision ...

Scalable Regularization of Scene Graph Generation Models using Symbolic Theories

Several techniques have recently aimed to improve the performance of dee...

Please sign up or login with your details

Forgot password? Click here to reset