paper-with-me

홈 › Papers

Exploring the Robustness of In-Context Learning with Noisy Labels

2024-04-28 · Chen Cheng, Xinzhi Yu, Haodong Wen, Jingsong Sun, Guanzhang Yue, Yihao Zhang, Zeming Wei

Recently, the mysterious In-Context Learning (ICL) ability exhibited by Transformer architectures, especially in large language models (LLMs), has sparked significant research interest. However, the resilience of Transformers' in-context learning capabilities in the presence of noisy samples, prevalent in both training corpora and prompt demonstrations, remains underexplored. In this paper, inspired by prior research that studies ICL ability using simple function classes, we take a closer look at this problem by investigating the robustness of Transformers against noisy labels. Specifically, we first conduct a thorough evaluation and analysis of the robustness of Transformers against noisy labels during in-context learning and show that they exhibit notable resilience against diverse types of noise in demonstration labels. Furthermore, we delve deeper into this problem by exploring whether introducing noise into the training set, akin to a form of data augmentation, enhances such robustness during inference, and find that such noise can indeed improve the robustness of ICL. Overall, our fruitful analysis and findings provide a comprehensive understanding of the resilience of Transformer models against label noises during ICL and provide valuable insights into the research on Transformers in natural language processing. Our code is available at https://github.com/InezYu0928/in-context-learning.

📄 PDF Abstract BibTeX arXiv:2404.18191

Code (1)

inezyu0928/in-context-learning 공식 구현 pytorch

Tasks

Data AugmentationIn-Context LearningLearning with noisy labels

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Position-Wise Feed-Forward Layer 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

Exploring Loss Design Techniques For Decision Tree Robustness To Label Noise

2024-05-27 · Lukasz Sztukiewicz, Jack Henry Good, Artur Dubrawski

In the real world, data is often noisy, affecting not only the quality of features but also the accuracy of labels. Current research on mitigating label errors stems primarily from advances in deep learning, and a gap ex…

Deep Learning

Exploring the Role of Diversity in Example Selection for In-Context Learning

2025-05-03 · Janak Kapuriya, Manit Kaushik, Debasis Ganguly, Sumit Bhatia

In-Context Learning (ICL) has gained prominence due to its ability to perform tasks without requiring extensive training data and its robustness to noisy labels. A typical ICL workflow involves selecting localized exampl…

DiversityIn-Context LearningReranking

Graph Neural Networks with Coarse- and Fine-Grained Division for Mitigating Label Sparsity and Noise

2024-11-06 · Shuangjie Li, Baoming Zhang, Jianqing Song, Gaoli Ruan 외

Graph Neural Networks (GNNs) have gained considerable prominence in semi-supervised learning tasks in processing graph-structured data, primarily owing to their message-passing mechanism, which largely relies on the avai…

Graph ReconstructionNode Classification

Annot-Mix: Learning with Noisy Class Labels from Multiple Annotators via a Mixup Extension

2024-05-06 · Marek Herde, Lukas Lührs, Denis Huseljic, Bernhard Sick

Training with noisy class labels impairs neural networks' generalization performance. In this context, mixup is a popular regularization technique to improve training robustness by making memorizing false class labels mo…

How does self-supervised pretraining improve robustness against noisy labels across various medical image classification datasets?

2024-01-15 · Bidur Khanal, Binod Bhattarai, Bishesh Khanal, Cristian Linte

Noisy labels can significantly impact medical image classification, particularly in deep learning, by corrupting learned features. Self-supervised pretraining, which doesn't rely on labeled data, can enhance robustness a…

Contrastive Learningimage-classificationImage ClassificationMedical Image Classification+1