ML Anthology

Adversarial Projections to Tackle Support-Query Shifts in Few-Shot Meta-Learning

Aroof Aimen, Bharat Ladrecha, Narayanan C. Krishnan
ECML-PKDD 2022 pp. 615-630
doi:10.1007/978-3-031-26409-2_37 /ecmlpkdd/2022/aimen2022ecmlpkdd-adversarial/

Abstract

Popular few-shot Meta-learning (ML) methods presume that a task’s support and query data are drawn from a common distribution. Recently, Bennequin et al. [ 4 ] relaxed this assumption to propose a few-shot setting where the support and query distributions differ, with disjoint yet related meta-train and meta-test support-query shifts (SQS). We relax this assumption further to a more pragmatic SQS setting (SQS+) where the meta-test SQS is anonymous and need not be related to the meta-train SQS. The state-of-the-art solution to address SQS is transductive, requiring unlabelled meta-test query data to bridge the support and query distribution gap. In contrast, we propose a theoretically grounded inductive solution - Adversarial Query Projection (AQP) for addressing SQS+ and SQS that is applicable when unlabeled meta-test query instances are unavailable. AQP can be easily integrated into the popular ML frameworks. Exhaustive empirical investigations on benchmark datasets and their extensions, different ML approaches, and architectures establish AQP’s efficacy in handling SQS+ and SQS.

PDF ECML-PKDD Semantic Scholar

Cite

Text

Aimen et al. "Adversarial Projections to Tackle Support-Query Shifts in Few-Shot Meta-Learning." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2022. doi:10.1007/978-3-031-26409-2_37

Markdown

[Aimen et al. "Adversarial Projections to Tackle Support-Query Shifts in Few-Shot Meta-Learning." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2022.](https://mlanthology.org/ecmlpkdd/2022/aimen2022ecmlpkdd-adversarial/) doi:10.1007/978-3-031-26409-2_37

BibTeX

@inproceedings{aimen2022ecmlpkdd-adversarial,
  title     = {{Adversarial Projections to Tackle Support-Query Shifts in Few-Shot Meta-Learning}},
  author    = {Aimen, Aroof and Ladrecha, Bharat and Krishnan, Narayanan C.},
  booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year      = {2022},
  pages     = {615-630},
  doi       = {10.1007/978-3-031-26409-2_37},
  url       = {https://mlanthology.org/ecmlpkdd/2022/aimen2022ecmlpkdd-adversarial/}
}