paper-with-me

홈 › Papers

DUEL: Duplicate Elimination on Active Memory for Self-Supervised Class-Imbalanced Learning

2024-02-14 · Won-Seok Choi, Hyundo Lee, Dong-Sig Han, Junseok Park, Heeyeon Koo, Byoung-Tak Zhang

Recent machine learning algorithms have been developed using well-curated datasets, which often require substantial cost and resources. On the other hand, the direct use of raw data often leads to overfitting towards frequently occurring class information. To address class imbalances cost-efficiently, we propose an active data filtering process during self-supervised pre-training in our novel framework, Duplicate Elimination (DUEL). This framework integrates an active memory inspired by human working memory and introduces distinctiveness information, which measures the diversity of the data in the memory, to optimize both the feature extractor and the memory. The DUEL policy, which replaces the most duplicated data with new samples, aims to enhance the distinctiveness information in the memory and thereby mitigate class imbalances. We validate the effectiveness of the DUEL framework in class-imbalanced environments, demonstrating its robustness and providing reliable results in downstream tasks. We also analyze the role of the DUEL policy in the training process through various metrics and visualizations.

📄 PDF Abstract BibTeX arXiv:2402.08963

Code (0)

등록된 구현이 없습니다.

Tasks

Diversity

Similar Papers 제목 키워드 기반

DUEL: Adaptive Duplicate Elimination on Working Memory for Self-Supervised Learning

2022-10-31 · Won-Seok Choi, Dong-Sig Han, Hyundo Lee, Junseok Park 외

In Self-Supervised Learning (SSL), it is known that frequent occurrences of the collision in which target data and its negative samples share the same class can decrease performance. Especially in real-world data such as…

Self-Supervised Learning

An End-to-End Geometric Deficiency Elimination Algorithm for 3D Meshes

2020-03-14 · Bingtao Ma, Hongsen Liu, Liangliang Nan, Yang Cong

The 3D mesh is an important representation of geometric data. In the generation of mesh data, geometric deficiencies (e.g., duplicate elements, degenerate faces, isolated vertices, self-intersection, and inner faces) are…

Lipschitz Dueling Bandits over Continuous Action Spaces

2026-04-01 · Mudit Sharma, Shweta Jain, Vaneet Aggarwal, Ganesh Ghalme arxiv

We study for the first time, stochastic dueling bandits over continuous action spaces with Lipschitz structure, where feedback is purely comparative. While dueling bandits and Lipschitz bandits have been studied separate…

Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering

2023-06-11 · Hai Ye, Qizhe Xie, Hwee Tou Ng

In this work, we study multi-source test-time model adaptation from user feedback, where K distinct models are established for adaptation. To allow efficient adaptation, we cast the problem as a stochastic decision-makin…

Decision MakingExtractive Question-AnsweringQuestion AnsweringTest-time Adaptation

ANACONDA: An Improved Dynamic Regret Algorithm for Adaptive Non-Stationary Dueling Bandits

2022-10-25 · Thomas Kleine Buening, Aadirupa Saha

We study the problem of non-stationary dueling bandits and provide the first adaptive dynamic regret algorithm for this problem. The only two existing attempts in this line of work fall short across multiple dimensions, …