v1v2 (latest)

How Does a Neural Network's Architecture Impact Its Robustness to Noisy Labels?

Neural Information Processing Systems (NeurIPS), 2020

23 December 2020

Jimmy Ba

Papers citing "How Does a Neural Network's Architecture Impact Its Robustness to Noisy Labels?"

10 / 10 papers shown

Revisiting Early-Learning Regularization When Federated Learning Meets Noisy Labels

Taehyeon Kim

Donggyu Kim

SeYoung Yun

152

08 Feb 2024

DeTiME: Diffusion-Enhanced Topic Modeling using Encoder-decoder based LLMConference on Empirical Methods in Natural Language Processing (EMNLP), 2023

Weijie Xu

Wenxiang Hu

Fanyou Wu

Srinivasan H. Sengamedu

DiffM

301

23 Oct 2023

Quantifying and mitigating the impact of label errors on model disparity metricsInternational Conference on Learning Representations (ICLR), 2023

241

04 Oct 2023

Strong inductive biases provably prevent harmless interpolationInternational Conference on Learning Representations (ICLR), 2023

301

18 Jan 2023

Neighborhood-Regularized Self-Training for Learning with Few LabelsAAAI Conference on Artificial Intelligence (AAAI), 2023

Ran Xu

351

10 Jan 2023

Leveraging Unlabeled Data to Track MemorizationInternational Conference on Learning Representations (ICLR), 2022

245

08 Dec 2022

CTRL: Clustering Training Losses for Label Error DetectionIEEE Transactions on Artificial Intelligence (IEEE TAI), 2022

C. Yue

N. Jha

NoLa

353

17 Aug 2022

Graph Neural Networks are Dynamic ProgrammersNeural Information Processing Systems (NeurIPS), 2022

Andrew Dudzik

Petar Velickovic

402

29 Mar 2022

Detecting Corrupted Labels Without Training a Model to PredictInternational Conference on Machine Learning (ICML), 2021

Zhaowei Zhu

Zihao Dong

Yang Liu

NoLa

563

12 Oct 2021

What Neural Networks Memorize and Why: Discovering the Long Tail via Influence EstimationNeural Information Processing Systems (NeurIPS), 2020

Vitaly Feldman

Chiyuan Zhang

TDI

704

597

09 Aug 2020