Exploring the Similarity of Representations in Model-Agnostic Meta-Learning

2021-05-12 · ICLR Workshop Learning_to_Learn 2021 5 · Thomas Goerttler, Klaus Obermayer

In past years model-agnostic meta-learning (MAML) has been one of the most promising approaches in meta-learning. It can be applied to different kinds of problems, e.g., reinforcement learning, but also shows good results on few-shot learning tasks. Besides their tremendous success in these tasks, it has still not been fully revealed yet, why it works so well. Recent work proposes that MAML rather reuses features than rapidly learns. In this paper, we want to inspire a deeper understanding of this question by analyzing MAML's representation. We apply representation similarity analysis (RSA), a well-established method in neuroscience, to the few-shot learning instantiation of MAML. Although some part of our analysis supports their general results that feature reuse is predominant, we also reveal arguments against their conclusion. The similarity-increase of layers closer to the input layers arises from the learning task itself and not from the model. In addition, the representations after inner gradient steps make a broader change to the representation than the changes during meta-training.

📄 PDF Abstract BibTeX arXiv:2105.05757

Code (1)

ThomasGoerttler/similarity-analysis-of-maml 공식 구현 tf

Tasks

Few-Shot Learning Meta-Learning

Methods 이 논문이 사용한 방법론

MAML 설명 없음

EMBEDDIA at SemEval-2022 Task 8: Investigating Sentence, Image, and Knowledge Graph Representations for Multilingual News Article Similarity

2022-07-01 · SemEval (NAACL) 2022 7 · Elaine Zosa, Emanuela Boros, Boshko Koloski, Lidia Pivovarova

In this paper, we present the participation of the EMBEDDIA team in the SemEval-2022 Task 8 (Multilingual News Article Similarity). We cover several techniques and propose different methods for finding the multilingual n…

Articles Semantic Similarity Semantic Textual Similarity Sentence

Transfer Learning for Bayesian HPO with End-to-End Meta-Features

2021-09-29 · Hadi Samer Jomaa, Sebastian Pineda Arango, Lars Schmidt-Thieme, Josif Grabocka

Hyperparameter optimization (HPO) is a crucial component of deploying machine learning models, however, it remains an open problem due to the resource-constrained number of possible hyperparameter evaluations. As a resul…

Hyperparameter Optimization Transfer Learning

BOIL: Towards Representation Change for Few-shot Learning

2020-08-20 · ICLR 2021 1 · Jaehoon Oh, Hyungjun Yoo, ChangHwan Kim, Se-Young Yun

Model Agnostic Meta-Learning (MAML) is one of the most representative of gradient-based meta-learning algorithms. MAML learns new tasks with a few data samples using inner updates from a meta-initialization point and lea…

Few-Shot Learning Meta-Learning

Learning Metadata-Agnostic Representations for Text-to-SQL In-Context Example Selection

2024-10-17 · Chuhong Mai, Ro-ee Tal, Thahir Mohamed

In-context learning (ICL) is a powerful paradigm where large language models (LLMs) benefit from task demonstrations added to the prompt. Yet, selecting optimal demonstrations is not trivial, especially for complex or mu…

In-Context Learning Question Similarity Representation Learning Text to SQL+1

Task-similarity Aware Meta-learning through Nonparametric Kernel Regression

2020-06-12 · Arun Venkitaraman, Anders Hansson, Bo Wahlberg

This paper investigates the use of nonparametric kernel-regression to obtain a tasksimilarity aware meta-learning algorithm. Our hypothesis is that the use of tasksimilarity helps meta-learning when the available tasks a…

Meta-Learning regression