Jure Leskovec, Manzil Zaheer, Maria Brbić, Ethan Shen, Nicholas Monath, Jiaqi Zhai
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.
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 subcomponents 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 fewshot learning model, including fine-tuning, metric-based and optimization-based meta-learning. Our approach improves performance of strong base learners by up to 2% on Mini-ImageNet and 6.7% on ImageNet-FS, outperforming state-of-theart graph embedded methods. Additional analyses reveal that graph regularizing models results in a lower loss for more difficult tasks, such as those with fewer shots and less informative support examples.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2102.07077")
get_code_for_paper("2102.07077")
have("2102.07077")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2102.07077.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2102.07077)
Connect an agent — have() is free.