no code implementations • 25 Mar 2024 • Xinyuan Ji, Zhaowei Zhu, Wei Xi, Olga Gadyatskaya, Zilong Song, Yong Cai, Yang Liu
The high loss incurred by client-specific samples in heterogeneous label noise poses challenges for distinguishing between client-specific and noisy label samples, impacting the effectiveness of existing label noise learning approaches.
no code implementations • 20 Feb 2024 • Jinlong Pang, Jialu Wang, Zhaowei Zhu, Yuanshun Yao, Chen Qian, Yang Liu
A fair classifier should ensure the benefit of people from different groups, while the group information is often sensitive and unsuitable for model training.
1 code implementation • 19 Nov 2023 • Zhaowei Zhu, Jialu Wang, Hao Cheng, Yang Liu
Given the cost and difficulty of cleaning these datasets by humans, we introduce a systematic framework for evaluating the credibility of datasets, identifying label errors, and evaluating the influence of noisy labels in the curated language data, specifically focusing on unsafe comments and conversation classification.
no code implementations • 22 Mar 2023 • Jiaheng Wei, Zhaowei Zhu, Gang Niu, Tongliang Liu, Sijia Liu, Masashi Sugiyama, Yang Liu
Both long-tailed and noisily labeled data frequently appear in real-world applications and impose significant challenges for learning.
1 code implementation • 6 Oct 2022 • Zhaowei Zhu, Yuanshun Yao, Jiankai Sun, Hang Li, Yang Liu
Our theoretical analyses show that directly using proxy models can give a false sense of (un)fairness.
no code implementations • 14 Jun 2022 • Jiaheng Wei, Zhaowei Zhu, Tianyi Luo, Ehsan Amid, Abhishek Kumar, Yang Liu
The rawly collected training data often comes with separate noisy labels collected from multiple imperfect annotators (e. g., via crowdsourcing).
2 code implementations • 2 Feb 2022 • Zhaowei Zhu, Jialu Wang, Yang Liu
We observe that tasks with lower-quality features fail to meet the anchor-point or clusterability condition, due to the coexistence of both uninformative and informative representations.
2 code implementations • ICLR 2022 • Jiaheng Wei, Zhaowei Zhu, Hao Cheng, Tongliang Liu, Gang Niu, Yang Liu
These observations require us to rethink the treatment of noisy labels, and we hope the availability of these two datasets would facilitate the development and evaluation of future learning with noisy label solutions.
1 code implementation • 18 Oct 2021 • Hao Cheng, Zhaowei Zhu, Xing Sun, Yang Liu
Designing robust loss functions is popular in learning with noisy labels while existing designs did not explicitly consider the overfitting property of deep neural networks (DNNs).
1 code implementation • ICLR 2022 • Zhaowei Zhu, Tianyi Luo, Yang Liu
Semi-supervised learning (SSL) has demonstrated its potential to improve the model accuracy for a variety of learning tasks when the high-quality supervised data is severely limited.
2 code implementations • 12 Oct 2021 • Zhaowei Zhu, Zihao Dong, Yang Liu
In this paper, from a more data-centric perspective, we propose a training-free solution to detect corrupted labels.
no code implementations • 29 Sep 2021 • Zhaowei Zhu, Zihao Dong, Hao Cheng, Yang Liu
In this paper, given good representations, we propose a universally applicable and training-free solution to detect noisy labels.
2 code implementations • 10 Feb 2021 • Zhaowei Zhu, Yiwen Song, Yang Liu
Nonetheless, finding anchor points remains a non-trivial task, and the estimation accuracy is also often throttled by the number of available anchor points.
Image Classification with Human Noise Image Classification with Label Noise +1
1 code implementation • CVPR 2021 • Zhaowei Zhu, Tongliang Liu, Yang Liu
We first provide evidences that the heterogeneous instance-dependent label noise is effectively down-weighting the examples with higher noise rates in a non-uniform way and thus causes imbalances, rendering the strategy of directly applying methods for class-dependent label noise questionable.
no code implementations • 12 Dec 2020 • Zhaowei Zhu, Xiang Lan, Tingting Zhao, Yangming Guo, Pipin Kojodjojo, Zhuoyang Xu, Zhuo Liu, SiQi Liu, Han Wang, Xingzhi Sun, Mengling Feng
Cardiovascular disease is a major threat to health and one of the primary causes of death globally.
no code implementations • 24 Oct 2020 • Zhaowei Zhu, Jingxuan Zhu, Ji Liu, Yang Liu
Motivated by the proposal of federated learning, we aim for a solution with which agents will never share their local observations with a central entity, and will be allowed to only share a private copy of his/her own information with their neighbors.
1 code implementation • NeurIPS 2021 • Jingkang Wang, Hongyi Guo, Zhaowei Zhu, Yang Liu
Most existing policy learning solutions require the learning agents to receive high-quality supervision signals such as well-designed rewards in reinforcement learning (RL) or high-quality expert demonstrations in behavioral cloning (BC).
1 code implementation • ICLR 2021 • Hao Cheng, Zhaowei Zhu, Xingyu Li, Yifei Gong, Xing Sun, Yang Liu
This high-quality sample sieve allows us to treat clean examples and the corrupted ones separately in training a DNN solution, and such a separation is shown to be advantageous in the instance-dependent noise setting.
Image Classification with Label Noise Learning with noisy labels
no code implementations • 27 Jun 2018 • Shangshu Zhao, Zhaowei Zhu, Fuqian Yang, Xiliang Luo
In this paper, we investigate a stochastic task offloading model and propose a multi-armed bandit framework to formulate this model.
no code implementations • 20 Apr 2018 • Zhaowei Zhu, Ting Liu, Shengda Jin, Xiliang Luo
An effective task offloading strategy is needed to utilize the computational resources efficiently.