Robust Meta-Representation Learning via Global Label Inference and Classification

• URL: http://arxiv.org/abs/2212.11702v2
• Date: Sun, 5 Nov 2023 14:18:58 GMT
• Title: Robust Meta-Representation Learning via Global Label Inference and Classification
• Authors: Ruohan Wang, Isak Falk, Massimiliano Pontil, Carlo Ciliberto
• Abstract summary: We introduce Meta Label Learning (MeLa), a novel meta-learning algorithm that learns task relations by inferring global labels across tasks. MeLa outperforms existing methods across a diverse range of benchmarks, in particular under a more challenging setting where the number of training tasks is limited and labels are task-specific.
• Score: 42.81340522184904
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Few-shot learning (FSL) is a central problem in meta-learning, where learners must efficiently learn from few labeled examples. Within FSL, feature pre-training has recently become an increasingly popular strategy to significantly improve generalization performance. However, the contribution of pre-training is often overlooked and understudied, with limited theoretical understanding of its impact on meta-learning performance. Further, pre-training requires a consistent set of global labels shared across training tasks, which may be unavailable in practice. In this work, we address the above issues by first showing the connection between pre-training and meta-learning. We discuss why pre-training yields more robust meta-representation and connect the theoretical analysis to existing works and empirical results. Secondly, we introduce Meta Label Learning (MeLa), a novel meta-learning algorithm that learns task relations by inferring global labels across tasks. This allows us to exploit pre-training for FSL even when global labels are unavailable or ill-defined. Lastly, we introduce an augmented pre-training procedure that further improves the learned meta-representation. Empirically, MeLa outperforms existing methods across a diverse range of benchmarks, in particular under a more challenging setting where the number of training tasks is limited and labels are task-specific. We also provide extensive ablation study to highlight its key properties.

Related papers

• CPT: Competence-progressive Training Strategy for Few-shot Node Classification [11.17199104891692]
  Graph Neural Networks (GNNs) have made significant advancements in node classification, but their success relies on sufficient labeled nodes per class in the training data. Traditional episodic meta-learning approaches have shown promise in this domain, but they face an inherent limitation. We introduce CPT, a novel two-stage curriculum learning method that aligns task difficulty with the meta-learner's progressive competence.
  arXiv  Detail & Related papers  (2024-02-01T09:36:56Z)
• Learning to Learn for Few-shot Continual Active Learning [9.283518682371756]
  Continual learning strives to ensure stability in solving previously seen tasks while demonstrating plasticity in a novel domain. Recent advances in continual learning are mostly confined to a supervised learning setting, especially in NLP domain. We exploit meta-learning and propose a method, called Meta-Continual Active Learning.
  arXiv  Detail & Related papers  (2023-11-07T05:22:11Z)
• Contrastive Knowledge-Augmented Meta-Learning for Few-Shot Classification [28.38744876121834]
  We introduce CAML (Contrastive Knowledge-Augmented Meta Learning), a novel approach for knowledge-enhanced few-shot learning. We evaluate the performance of CAML in different few-shot learning scenarios.
  arXiv  Detail & Related papers  (2022-07-25T17:01:29Z)
• MetaICL: Learning to Learn In Context [87.23056864536613]
  We introduce MetaICL, a new meta-training framework for few-shot learning where a pretrained language model is tuned to do in-context learn-ing on a large set of training tasks. We show that MetaICL approaches (and sometimes beats) the performance of models fully finetuned on the target task training data, and outperforms much bigger models with nearly 8x parameters.
  arXiv  Detail & Related papers  (2021-10-29T17:42:08Z)
• Active Refinement for Multi-Label Learning: A Pseudo-Label Approach [84.52793080276048]
  Multi-label learning (MLL) aims to associate a given instance with its relevant labels from a set of concepts. Previous works of MLL mainly focused on the setting where the concept set is assumed to be fixed. Many real-world applications require introducing new concepts into the set to meet new demands.
  arXiv  Detail & Related papers  (2021-09-29T19:17:05Z)
• The Role of Global Labels in Few-Shot Classification and How to Infer Them [55.64429518100676]
  Few-shot learning is a central problem in meta-learning, where learners must quickly adapt to new tasks. We propose Meta Label Learning (MeLa), a novel algorithm that infers global labels and obtains robust few-shot models via standard classification.
  arXiv  Detail & Related papers  (2021-08-09T14:07:46Z)
• A Channel Coding Benchmark for Meta-Learning [21.2424398453955]
  Several important issues in meta-learning have proven hard to study thus far. We propose the channel coding problem as a benchmark for meta-learning. Going forward, this benchmark provides a tool for the community to study the capabilities and limitations of meta-learning.
  arXiv  Detail & Related papers  (2021-07-15T19:37:43Z)
• Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning [79.25478727351604]
  We explore a simple process: meta-learning over a whole-classification pre-trained model on its evaluation metric. We observe this simple method achieves competitive performance to state-of-the-art methods on standard benchmarks.
  arXiv  Detail & Related papers  (2020-03-09T20:06:36Z)
• Incremental Meta-Learning via Indirect Discriminant Alignment [118.61152684795178]
  We develop a notion of incremental learning during the meta-training phase of meta-learning. Our approach performs favorably at test time as compared to training a model with the full meta-training set.
  arXiv  Detail & Related papers  (2020-02-11T01:39:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.