Cross-Domain Few-Shot Graph Classification

01/20/2022
by   Kaveh Hassani, et al.
0

We 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. The source code and data will be released here: https://github.com/kavehhassani/metagrl

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/29/2021

Cross-Domain Few-Shot Classification via Adversarial Task Augmentation

Few-shot classification aims to recognize unseen classes with few labele...
research
07/01/2021

Improving Task Adaptation for Cross-domain Few-shot Learning

In this paper, we look at the problem of cross-domain few-shot classific...
research
05/21/2023

Many or Few Samples? Comparing Transfer, Contrastive and Meta-Learning in Encrypted Traffic Classification

The popularity of Deep Learning (DL), coupled with network traffic visib...
research
06/06/2021

DAMSL: Domain Agnostic Meta Score-based Learning

In this paper, we propose Domain Agnostic Meta Score-based Learning (DAM...
research
10/10/2022

Multi-Modal Fusion by Meta-Initialization

When experience is scarce, models may have insufficient information to a...
research
10/12/2022

The Devil is in the Details: On Models and Training Regimes for Few-Shot Intent Classification

Few-shot Intent Classification (FSIC) is one of the key challenges in mo...
research
03/13/2023

MetaTroll: Few-shot Detection of State-Sponsored Trolls with Transformer Adapters

State-sponsored trolls are the main actors of influence campaigns on soc...

Please sign up or login with your details

Forgot password? Click here to reset