Noisy Data

Noisy data, ubiquitous in real-world applications, poses a significant challenge to machine learning model accuracy and reliability. Current research focuses on developing robust algorithms and model architectures, such as deep learning networks (including CNNs and Transformers), that can effectively handle various types of noise (e.g., label noise, missing data, sensor noise) across diverse data modalities (e.g., images, text, time series). These advancements are crucial for improving the performance and trustworthiness of machine learning systems in fields ranging from medical imaging and financial prediction to environmental monitoring and natural language processing.

Papers

April 8, 2024

Fighting crime with Transformers: Empirical analysis of address parsing methods in payment data
Haitham Hammami, Louis Baligand, Bojan Petrovski
Transformer Megatron Decepticons Generative Large Language Model Noisy Data Empirical Analysis Generative LLM Crime Story E Commerce Platform Address Matching

March 21, 2024

SoftPatch: Unsupervised Anomaly Detection with Noisy Data
Xi Jiang, Ying Chen, Qiang Nie, Yong Liu, Jianlin Liu, Bin-Bin Gao, Jun Liu, Chengjie Wang, Feng Zheng
Anomaly Detection Unsupervised Anomaly Detection Noisy Data Single Simple Patch

March 20, 2024

February 27, 2024

Prioritizing Informative Features and Examples for Deep Learning from Noisy Data
Dongmin Park
Deep Learning Active Learning Noisy Data Feature Learning Fewer Example Labeling Model

February 21, 2024

Motion Code: Robust Time series Classification and Forecasting via Sparse Variational Multi-Stochastic Processes Learning
Chandrajit Bajaj, Minh Nguyen
Time Series Time Series Classification State of the Art Forecasting Noisy Data Temporal Shift Sparse Variational Motion Code

February 19, 2024

Understanding the Effects of Noise in Text-to-SQL: An Examination of the BIRD-Bench Benchmark
Niklas Wretblad, Fredrik Gordh Riseby, Rahul Biswas, Amin Ahmadi, Oskar Holmström
Mixed Effect Industrial Disturbing Noise Text to SQL Noisy Data Exam Document Query Language

February 2, 2024

Ambient-Pix2PixGAN for Translating Medical Images from Noisy Data
Wentao Chen, Xichen Xu, Jie Luo, Weimin Zhou
Medical Image Conditional Generative Adversarial Network Noisy Data GAN Architecture Ambient Sound Based Augmentation Medical Image Translation

February 1, 2024

Multiclass Learning from Noisy Labels for Non-decomposable Performance Measures
Mingyuan Zhang, Shivani Agarwal
Noisy Label Label Noise Noisy Data Class Conditional Multiclass Learning Non Decomposable Performance Measure

January 30, 2024

Bayesian Optimization with Noise-Free Observations: Improved Regret Bounds via Random Exploration
Hwanwoo Kim, Daniel Sanz-Alonso
Bayesian Optimization Regret Bound Noisy Data UCB Algorithm New Algorithm Random Exploration

January 21, 2024

Squared Wasserstein-2 Distance for Efficient Reconstruction of Stochastic Differential Equations
Mingtao Xia, Xiangting Li, Qijing Shen, Tom Chou
Wasserstein Distance Noisy Data Stochastic Differential Equation Numerical Experiment Efficient Reconstruction Metric Learning Loss

January 16, 2024

Weighted Spectral Filters for Kernel Interpolation on Spheres: Estimates of Prediction Accuracy for Noisy Data
Xiaotong Liu, Jinxin Wang, Di Wang, Shao-Bo Lin
Noisy Data Prediction Accuracy Spherical Surface Kernel Interpolation Spherical Data Quadrature Rule

December 23, 2023

Optimal Decision Tree with Noisy Outcomes
Su Jia, Fatemeh Navidi, Viswanath Nagarajan, R. Ravi
Decision Tree Noisy Data Linear Classifier Pool Based Active Learning Optimal Decision Tree

December 12, 2023

Analyze the Robustness of Classifiers under Label Noise
Cheng Zeng, Yixuan Xu, Jiaqi Tian
Native Robustness Label Noise Simple Classifier Noisy Data Training Label Analyse Text

November 27, 2023

Bayesian Formulations for Graph Spectral Denoising
Sam Leone, Xingzhi Sun, Michael Perlmutter, Smita Krishnaswamy
Noisy Data Single Cell Gaussian Noise Graph Signal Processing Single Cell RNA Graph Signal Denoising Bayesian Formulation

November 8, 2023

Algorithms for Non-Negative Matrix Factorization on Noisy Data With Negative Values
Dylan Green, Stephen Bailey
Practical Algorithm Matrix Factorization Noisy Data Abnormal Signal Non Negative Matrix Factorization Negative Matrix Factorization

October 25, 2023

Improving a Named Entity Recognizer Trained on Noisy Data with a Few Clean Instances
Zhendong Chu, Ruiyi Zhang, Tong Yu, Rajiv Jain, Vlad I Morariu, Jiuxiang Gu, Ani Nenkova
Entity Recognition Noisy Label MAESTRO Dataset Noisy Data Discriminative Model Distant Supervision

October 20, 2023

Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space
Yufei Gu, Xiaoqing Zheng, Tomaso Aste
Deep Learning Camera Lens Noisy Data Feature Space Implicit Regularization Double Descent Depth Analysis Enigma 51 Weak Model

October 18, 2023

Conservative Predictions on Noisy Financial Data
Omkar Nabar, Gautam Shroff
Machine Learning Algorithm Noisy Data Market Data Stock Market Prediction Conservative Prediction Differentiable Decision Tree

October 16, 2023

SoTTA: Robust Test-Time Adaptation on Noisy Data Streams
Taesik Gong, Yewon Kim, Taeckyung Lee, Sorn Chottananurak, Sung-Ju Lee
Test Time Adaptation Noisy Data Continual Adaptation Time Adaptation Parameter Aware Robustness

Noisy Data

Papers

Fighting crime with Transformers: Empirical analysis of address parsing methods in payment data

SoftPatch: Unsupervised Anomaly Detection with Noisy Data

Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data

Tackling Noisy Labels with Network Parameter Additive Decomposition

Prioritizing Informative Features and Examples for Deep Learning from Noisy Data

Motion Code: Robust Time series Classification and Forecasting via Sparse Variational Multi-Stochastic Processes Learning

Understanding the Effects of Noise in Text-to-SQL: An Examination of the BIRD-Bench Benchmark

Ambient-Pix2PixGAN for Translating Medical Images from Noisy Data

Multiclass Learning from Noisy Labels for Non-decomposable Performance Measures

Bayesian Optimization with Noise-Free Observations: Improved Regret Bounds via Random Exploration

Squared Wasserstein-2 Distance for Efficient Reconstruction of Stochastic Differential Equations

Weighted Spectral Filters for Kernel Interpolation on Spheres: Estimates of Prediction Accuracy for Noisy Data

Optimal Decision Tree with Noisy Outcomes

Analyze the Robustness of Classifiers under Label Noise

Bayesian Formulations for Graph Spectral Denoising

Algorithms for Non-Negative Matrix Factorization on Noisy Data With Negative Values

Improving a Named Entity Recognizer Trained on Noisy Data with a Few Clean Instances

Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space

Conservative Predictions on Noisy Financial Data

SoTTA: Robust Test-Time Adaptation on Noisy Data Streams