paper-with-me

홈 › Papers

Disentangling Sampling and Labeling Bias for Learning in Large-Output Spaces

2021-05-12 · Ankit Singh Rawat, Aditya Krishna Menon, Wittawat Jitkrittum, Sadeep Jayasumana, Felix X. Yu, Sashank Reddi, Sanjiv Kumar

Negative sampling schemes enable efficient training given a large number of classes, by offering a means to approximate a computationally expensive loss function that takes all labels into account. In this paper, we present a new connection between these schemes and loss modification techniques for countering label imbalance. We show that different negative sampling schemes implicitly trade-off performance on dominant versus rare labels. Further, we provide a unified means to explicitly tackle both sampling bias, arising from working with a subset of all labels, and labeling bias, which is inherent to the data due to label imbalance. We empirically verify our findings on long-tail classification and retrieval benchmarks.

📄 PDF Abstract BibTeX arXiv:2105.05736

Code (0)

등록된 구현이 없습니다.

Tasks

Retrieval

Similar Papers 제목 키워드 기반

Efficient Sequence Labeling with Actor-Critic Training

2018-09-30 · Saeed Najafi, Colin Cherry, Grzegorz Kondrak

Neural approaches to sequence labeling often use a Conditional Random Field (CRF) to model their output dependencies, while Recurrent Neural Networks (RNN) are used for the same purpose in other tasks. We set out to esta…

Decision MakingNERSequential Decision MakingTransliteration

Maximizing Signal in Human-Model Preference Alignment

2025-03-06 · Kelsey Kraus, Margaret Kroll

The emergence of powerful LLMs has led to a paradigm shift in Natural Language Understanding and Natural Language Generation. The properties that make LLMs so valuable for these tasks -- creativity, ability to produce fl…

modelNatural Language UnderstandingText Generation

Data Feedback Loops: Model-driven Amplification of Dataset Biases

2022-09-08 · Rohan Taori, Tatsunori B. Hashimoto

Datasets scraped from the internet have been critical to the successes of large-scale machine learning. Yet, this very success puts the utility of future internet-derived datasets at potential risk, as model outputs begi…

image-classificationImage ClassificationText Generation

Clean Label Disentangling for Medical Image Segmentation with Noisy Labels

2023-11-28 · Zicheng Wang, Zhen Zhao, Erjian Guo, Luping Zhou

Current methods focusing on medical image segmentation suffer from incorrect annotations, which is known as the noisy label issue. Most medical image segmentation with noisy labels methods utilize either noise transition…

DisentanglementImage SegmentationMedical Image SegmentationSemantic Segmentation

Combining Self-labeling with Selective Sampling

2023-01-11 · Jędrzej Kozal, Michał Woźniak

Since data is the fuel that drives machine learning models, and access to labeled data is generally expensive, semi-supervised methods are constantly popular. They enable the acquisition of large datasets without the nee…

Active Learning