62 citations · 244 across the 20 of their papers we have counts for
20 papers
Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models
Zhaowei Zhu, Jialu Wang, Hao Cheng +1
Language models have shown promise in various tasks but can be affected by undesired data during training, fine-tuning, or alignment. For example, if some unsafe conversations are…
Fairness Improves Learning from Noisily Labeled Long-Tailed Data
Jiaheng Wei, Zhaowei Zhu, Gang Niu +4
Both long-tailed and noisily labeled data frequently appear in real-world applications and impose significant challenges for learning. Most prior works treat either problem in an i…
To Aggregate or Not? Learning with Separate Noisy Labels
Jiaheng Wei, Zhaowei Zhu, Tianyi Luo +3
The rawly collected training data often comes with separate noisy labels collected from multiple imperfect annotators (e.g., via crowdsourcing). A typical way of using these separa…
Beyond Images: Label Noise Transition Matrix Estimation for Tasks with Lower-Quality Features
Zhaowei Zhu, Jialu Wang, Yang Liu
The label noise transition matrix, denoting the transition probabilities from clean labels to noisy labels, is crucial for designing statistically robust solutions. Existing estima…
Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations
Jiaheng Wei, Zhaowei Zhu, Hao Cheng +3
Existing research on learning with noisy labels mainly focuses on synthetic label noise. Synthetic noise, though has clean structures which greatly enabled statistical analyses, of…
Mitigating Memorization of Noisy Labels via Regularization between Representations
Hao Cheng, Zhaowei Zhu, Xing Sun +1
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).…
Detecting Corrupted Labels Without Training a Model to Predict
Zhaowei Zhu, Zihao Dong, Yang Liu
Label noise in real-world datasets encodes wrong correlation patterns and impairs the generalization of deep neural networks (DNNs). It is critical to find efficient ways to detect…
The Rich Get Richer: Disparate Impact of Semi-Supervised Learning
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 limite…
Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search
Jialu Wang, Yang Liu, Xin Eric Wang
Internet search affects people's cognition of the world, so mitigating biases in search results and learning fair models is imperative for social good. We study a unique gender bia…
Can Less be More? When Increasing-to-Balancing Label Noise Rates Considered Beneficial
Yang Liu, Jialu Wang
In this paper, we answer the question of when inserting label noise (less informative labels) can instead return us more accurate and fair models. We are primarily inspired by thre…
Assessing Multilingual Fairness in Pre-trained Multimodal Representations
Jialu Wang, Yang Liu, Xin Eric Wang
Recently pre-trained multimodal models, such as CLIP, have shown exceptional capabilities towards connecting images and natural language. The textual representations in English can…
To Smooth or Not? When Label Smoothing Meets Noisy Labels
Jiaheng Wei, Hangyu Liu, Tongliang Liu +3
Label smoothing (LS) is an arising learning paradigm that uses the positively weighted average of both the hard training labels and uniformly distributed soft labels. It was shown…
Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network
Shuo Yang, Erkun Yang, Bo Han +4
In label-noise learning, estimating the transition matrix is a hot topic as the matrix plays an important role in building statistically consistent classifiers. Traditionally, the…
Understanding Instance-Level Label Noise: Disparate Impacts and Treatments
Yang Liu
This paper aims to provide understandings for the effect of an over-parameterized model, e.g. a deep neural network, memorizing instance-dependent noisy labels. We first quantify t…
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels
Zhaowei Zhu, Yiwen Song, Yang Liu
The label noise transition matrix, characterizing the probabilities of a training instance being wrongly annotated, is crucial to designing popular solutions to learning with noisy…
A Second-Order Approach to Learning with Instance-Dependent Label Noise
Zhaowei Zhu, Tongliang Liu, Yang Liu
The presence of label noise often misleads the training of deep neural networks. Departing from the recent literature which largely assumes the label noise rate is only determined…
Linear Classifiers that Encourage Constructive Adaptation
Yatong Chen, Jialu Wang, Yang Liu
Machine learning systems are often used in settings where individuals adapt their features to obtain a desired outcome. In such settings, strategic behavior leads to a sharp loss i…
Federated Bandit: A Gossiping Approach
Zhaowei Zhu, Jingxuan Zhu, Ji Liu +1
In this paper, we study \emph{Federated Bandit}, a decentralized Multi-Armed Bandit problem with a set of agents, who can only communicate their local data with neighbors descr…
Learning with Instance-Dependent Label Noise: A Sample Sieve Approach
Hao Cheng, Zhaowei Zhu, Xingyu Li +3
Human-annotated labels are often prone to noise, and the presence of such noise will degrade the performance of the resulting deep neural network (DNN) models. Much of the literatu…
Policy Learning Using Weak Supervision
Jingkang Wang, Hongyi Guo, Zhaowei Zhu +1
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…