paper-with-me

Papers

Dynamics of Meta-learning Representation in the Teacher-student Scenario

2024-08-22 · Hui Wang, Cho Tung Yip, Bo Li

Gradient-based meta-learning algorithms have gained popularity for their ability to train models on new tasks using limited data. Empirical observations indicate that such algorithms are able to learn a shared representation across tasks, which is regarded as a key factor in their success. However, the in-depth theoretical understanding of the learning dynamics and the origin of the shared representation remains underdeveloped. In this work, we investigate the meta-learning dynamics of nonlinear two-layer neural networks trained on streaming tasks in the teacher-student scenario. Through the lens of statistical physics analysis, we characterize the macroscopic behavior of the meta-training processes, the formation of the shared representation, and the generalization ability of the model on new tasks. The analysis also points to the importance of the choice of certain hyperparameters of the learning algorithms.

📄 PDF Abstract BibTeX arXiv:2408.12545

Code (0)

등록된 구현이 없습니다.

Tasks

Meta-Learning

Similar Papers 제목 키워드 기반

Learning Knowledge Representation with Meta Knowledge Distillation for Single Image Super-Resolution

2022-07-18 · Han Zhu, Zhenzhong Chen, Shan Liu

Knowledge distillation (KD), which can efficiently transfer knowledge from a cumbersome network (teacher) to a compact network (student), has demonstrated its advantages in some computer vision applications. The represen…

Image Super-ResolutionKnowledge DistillationMeta-LearningSuper-Resolution

A Metamorphic Testing Perspective on Knowledge Distillation for Language Models of Code: Does the Student Deeply Mimic the Teacher?

2025-11-07 · Md. Abdul Awal, Mrigank Rochan, Chanchal K. Roy arxiv

Transformer-based language models of code have achieved state-of-the-art performance across a wide range of software analytics tasks, but their practical deployment remains limited due to high computational costs, slow i…

Knowledge Distillation

Meta Pseudo Labels

2020-03-23 · CVPR 2021 1 · Hieu Pham, Zihang Dai, Qizhe Xie, Minh-Thang Luong 외

We present Meta Pseudo Labels, a semi-supervised learning method that achieves a new state-of-the-art top-1 accuracy of 90.2% on ImageNet, which is 1.6% better than the existing state-of-the-art. Like Pseudo Labels, Meta…

Image ClassificationMeta-LearningSemi-Supervised Image Classification

Meta-Learning Guided Label Noise Distillation for Robust Signal Modulation Classification

2024-08-09 · Xiaoyang Hao, Zhixi Feng, Tongqing Peng, Shuyuan Yang

Automatic modulation classification (AMC) is an effective way to deal with physical layer threats of the internet of things (IoT). However, there is often label mislabeling in practice, which significantly impacts the pe…

Meta-Learning

Less is More: Task-aware Layer-wise Distillation for Language Model Compression

2022-10-04 · Chen Liang, Simiao Zuo, Qingru Zhang, Pengcheng He 외

Layer-wise distillation is a powerful tool to compress large models (i.e. teacher models) into small ones (i.e., student models). The student distills knowledge from the teacher by mimicking the hidden representations of…

Language ModelingLanguage ModellingModel Compression