paper-with-me

홈 › Papers

MAML is a Noisy Contrastive Learner in Classification

2021-06-29 · ICLR 2022 4 · Chia-Hsiang Kao, Wei-Chen Chiu, Pin-Yu Chen

Model-agnostic meta-learning (MAML) is one of the most popular and widely adopted meta-learning algorithms, achieving remarkable success in various learning problems. Yet, with the unique design of nested inner-loop and outer-loop updates, which govern the task-specific and meta-model-centric learning, respectively, the underlying learning objective of MAML remains implicit and thus impedes a more straightforward understanding of it. In this paper, we provide a new perspective of the working mechanism of MAML. We discover that MAML is analogous to a meta-learner using a supervised contrastive objective. The query features are pulled towards the support features of the same class and against those of different classes. Such contrastiveness is experimentally verified via an analysis based on the cosine similarity. Moreover, we reveal that vanilla MAML has an undesirable interference term originating from the random initialization and the cross-task interaction. We thus propose a simple but effective technique, zeroing trick, to alleviate the interference. Extensive experiments are conducted on both mini-ImageNet and Omniglot datasets to demonstrate the consistent improvement brought by our proposed method, validating its effectiveness.

📄 PDF Abstract BibTeX arXiv:2106.15367

Code (1)

iandrover/maml_noisy_contrasive_learner pytorch

Tasks

ClassificationFew-Shot LearningMeta-Learning

Methods 이 논문이 사용한 방법론

MAML 설명 없음

Similar Papers 제목 키워드 기반

BatMan-CLR: Making Few-shots Meta-Learners Resilient Against Label Noise

2023-09-12 · Jeroen M. Galjaard, Robert Birke, Juan Perez, Lydia Y. Chen

The negative impact of label noise is well studied in classical supervised learning yet remains an open research question in meta-learning. Meta-learners aim to adapt to unseen learning tasks by learning a good initial m…

Meta-Learning

Stateless Neural Meta-Learning using Second-Order Gradients

2021-04-21 · Mike Huisman, Aske Plaat, Jan N. van Rijn

Deep learning typically requires large data sets and much compute power for each new problem that is learned. Meta-learning can be used to learn a good prior that facilitates quick learning, thereby relaxing these requir…

image-classificationImage ClassificationMeta-Learning

A Nested Bi-level Optimization Framework for Robust Few Shot Learning

2020-11-13 · KrishnaTeja Killamsetty, Changbin Li, Chen Zhao, Rishabh Iyer 외

Model-Agnostic Meta-Learning (MAML), a popular gradient-based meta-learning framework, assumes that the contribution of each task or instance to the meta-learner is equal. Hence, it fails to address the domain shift betw…

Few-Shot LearningMeta-Learning

Q-MAML: Quantum Model-Agnostic Meta-Learning for Variational Quantum Algorithms

2025-01-10 · Junyong Lee, Jeihee Cho, Shiho Kim

In the Noisy Intermediate-Scale Quantum (NISQ) era, using variational quantum algorithms (VQAs) to solve optimization problems has become a key application. However, these algorithms face significant challenges, such as …

Meta-Learning

Auto-Meta: Automated Gradient Based Meta Learner Search

2018-06-11 · Jaehong Kim, Sangyeul Lee, Sungwan Kim, Moonsu Cha 외

Fully automating machine learning pipelines is one of the key challenges of current artificial intelligence research, since practical machine learning often requires costly and time-consuming human-powered processes such…

BIG-bench Machine LearningMeta-LearningNeural Architecture Search