Noisy Feedback

Noisy feedback, ubiquitous in machine learning applications from recommender systems to human-robot interaction, poses a significant challenge to algorithm performance. Current research focuses on developing robust algorithms and models that can effectively filter or mitigate the impact of noisy data, employing techniques like noise-filtering mechanisms, large language model integration for sample selection, and adaptive training strategies that adjust to varying noise levels. These advancements are crucial for improving the reliability and accuracy of various machine learning systems, particularly in scenarios where perfect feedback is unattainable or impractical. The resulting improvements in model robustness and efficiency have broad implications across diverse fields.

Papers

October 22, 2024

Navigating Noisy Feedback: Enhancing Reinforcement Learning with Error-Prone Language Models
Muhan Lin, Shuyang Shi, Yue Guo, Behdad Chalaki, Vaishnav Tadiparthi, Ehsan Moradi Pari, Simon Stepputtis, Joseph Campbell, Katia Sycara
Language Model Reinforcement Learning Reward Function Reward Model Noisy Feedback

September 23, 2024

CANDERE-COACH: Reinforcement Learning from Noisy Feedback
Yuxuan Li, Srijita Das, Matthew E. Taylor
Reinforcement Learning Imitation Learning Inverse Reinforcement Learning Noisy Feedback Human COACH AI Coach

September 16, 2024

Large Language Model Enhanced Hard Sample Identification for Denoising Recommendation
Tianrui Song, Wenshuo Chao, Hao Liu
Recommender System User Item Interaction Noisy Feedback Denoising Language Model Recommendation Denoising

June 24, 2024

Debiased Recommendation with Noisy Feedback
Haoxuan Li, Chunyuan Zheng, Wenjie Wang, Hao Wang, Fuli Feng, Xiao-Hua Zhou
Recommender System Unbiased Learning Debiased Recommendation Noisy Feedback Doubly Robust Missing Not at Random

April 30, 2024

Learning to Communicate Functional States with Nonverbal Expressions for Improved Human-Robot Collaboration
Liam Roy, Dana Kulic, Elizabeth Croft
Reinforcement Learning LeArning Abstract Human Robot Interaction Human Robot Collaboration Facial Behaviour Nonverbal Communication Noisy Feedback

March 1, 2024

Provably Robust DPO: Aligning Language Models with Noisy Feedback
Sayak Ray Chowdhury, Anush Kini, Nagarajan Natarajan
Language Model Direct Preference Optimization Preference Feedback Preference Change Noisy Feedback Noisy Preference Robust Preference

July 11, 2023

Selective Sampling and Imitation Learning via Online Regression
Ayush Sekhari, Karthik Sridharan, Wen Sun, Runzhe Wu
Imitation Learning Sample Selection Online Regression Noisy Feedback

August 21, 2022

Last-Iterate Convergence with Full and Noisy Feedback in Two-Player Zero-Sum Games
Kenshi Abe, Kaito Ariu, Mitsuki Sakamoto, Kentaro Toyoshima, Atsushi Iwasaki
Nash Equilibrium Two Player Zero Sum Last Iterate Convergence Normal Form Game Noisy Feedback Multiplicative Weight Update

August 2, 2022

Adapting Triplet Importance of Implicit Feedback for Personalized Recommendation
Haolun Wu, Chen Ma, Yingxue Zhang, Xue Liu, Ruiming Tang, Mark Coates
Matrix Factorization Recommendation Model Personalized Recommendation Implicit Feedback Importance Score Triplet Learning Noisy Feedback Triplet Recognition

June 13, 2022

No-Regret Learning in Games with Noisy Feedback: Faster Rates and Adaptivity via Learning Rate Separation
Yu-Guan Hsieh, Kimon Antonakopoulos, Volkan Cevher, Panayotis Mertikopoulos
Adaptive Importance Video Game Regret Minimization Regret Guarantee Regret Algorithm Noisy Feedback Continuous Game Monotone Game

May 6, 2022

Federated Learning with Noisy User Feedback
Rahul Sharma, Anil Ramakrishna, Ansel MacLaughlin, Anna Rumshisky, Jimit Majmudar, Clement Chung, Salman Avestimehr, Rahul Gupta
Machine Learning Machine Learning Model Training Model Label Supervision Noisy Feedback

January 28, 2022

Consistent Collaborative Filtering via Tensor Decomposition
Shiwen Zhao, Charles Crissman, Guillermo R Sapiro
Recommendation System Collaborative Filtering Recommendation Model Tensor Decomposition Noisy Feedback

December 2, 2021

Learning Robust Recommender from Noisy Implicit Feedback
Wenjie Wang, Fuli Feng, Xiangnan He, Liqiang Nie, Tat-Seng Chua
Implicit Feedback Noisy Feedback Robust Recommendation Learning Based Recommender System DeNoising Training

November 6, 2021

Learning equilibria with personalized incentives in a class of nonmonotone games
Filippo Fabiani, Andrea Simonetto, Paul J. Goulart
Nash Equilibrium True Class Equilibrium State Noisy Feedback Learning Policy Personalized Incentive Learning Equilibrium

Noisy Feedback

Papers

Navigating Noisy Feedback: Enhancing Reinforcement Learning with Error-Prone Language Models

CANDERE-COACH: Reinforcement Learning from Noisy Feedback

Large Language Model Enhanced Hard Sample Identification for Denoising Recommendation

Debiased Recommendation with Noisy Feedback

Learning to Communicate Functional States with Nonverbal Expressions for Improved Human-Robot Collaboration

Provably Robust DPO: Aligning Language Models with Noisy Feedback

Selective Sampling and Imitation Learning via Online Regression

Last-Iterate Convergence with Full and Noisy Feedback in Two-Player Zero-Sum Games

Adapting Triplet Importance of Implicit Feedback for Personalized Recommendation

No-Regret Learning in Games with Noisy Feedback: Faster Rates and Adaptivity via Learning Rate Separation

Federated Learning with Noisy User Feedback

Consistent Collaborative Filtering via Tensor Decomposition

Learning Robust Recommender from Noisy Implicit Feedback

Learning equilibria with personalized incentives in a class of nonmonotone games