Publication

Cross-Domain Few-Shot Graph Classification

AbstractWe study the problem of few-shot graph classification across domains with nonequivalent feature spaces by introducing three new cross-domain benchmarks constructed from publicly available datasets. We also propose an attention-based graph encoder that uses three congruent views of graphs, one contextual and two topological views, to learn representations of task specific information for fast adaptation, and task-agnostic information for knowledge transfer. We run exhaustive experiments to evaluate the performance of contrastive and meta-learning strategies. We show that when coupled with metric-based meta-learning frameworks, the proposed encoder achieves the best average meta-test classification accuracy across all benchmarks.

Download publication

Related Resources

See what’s new.

Publication

2013

Using Templates and Mapping Strategies to Support Analogical Transfer in Biomimetic Design

While biological phenomena can serve as meaningful analogies to…

Publication

1991

Issues in Combining Marking and Direct Manipulation Techniques

The direct manipulation paradigm has been effective in helping…

Publication

2010

Systemic computation using graphics processors

Previous work created the systemic computer – a model of computation…

Publication

2023

Assemble Them All: Physics-Based Planning for Generalizable Assembly by Disassembly

This work proposes a novel method to efficiently plan physically…

Get in touch

Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.

Contact us