Author name cluster

Songhua Wu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

2 author rows

CLeaR Conference 2022 Conference Paper

Fair Classification with Instance-dependent Label Noise

Songhua Wu
Mingming Gong
Bo Han
Yang Liu
Tongliang Liu

With the widespread use of machine learning systems in our daily lives, it is important to consider fairness as a basic requirement when designing these systems, especially when the systems make life-changing decisions, e. g. , \textitCOMPAS algorithm helps judges decide whether to release an offender. For another thing, due to the cheap but imperfect data collection methods, such as crowdsourcing and web crawling, label noise is ubiquitous, which unfortunately makes fairness-aware algorithms even more prejudiced than fairness-unaware ones, and thereby harmful. To tackle these problems, we provide general frameworks for learning fair classifiers with \textitinstance-dependent label noise. For statistical fairness notions, we rewrite the classification risk and the fairness metric in terms of noisy data and thereby build robust classifiers. For the causality-based fairness notion, we exploit the internal causal structure of data to model the label noise and \textitcounterfactual fairness simultaneously. Experimental results demonstrate the effectiveness of the proposed methods on real-world datasets with controllable synthetic label noise.

PDF Details

JMLR Journal 2022 Journal Article

Learning from Noisy Pairwise Similarity and Unlabeled Data

Songhua Wu
Tongliang Liu
Bo Han
Jun Yu
Gang Niu
Masashi Sugiyama

SU classification employs similar (S) data pairs (two examples belong to the same class) and unlabeled (U) data points to build a classifier, which can serve as an alternative to the standard supervised trained classifiers requiring data points with class labels. SU classification is advantageous because in the era of big data, more attention has been paid to data privacy. Datasets with specific class labels are often difficult to obtain in real-world classification applications regarding privacy-sensitive matters, such as politics and religion, which can be a bottleneck in supervised classification. Fortunately, similarity labels do not reveal the explicit information and inherently protect the privacy, e.g., collecting answers to “With whom do you share the same opinion on issue $\mathcal{I}$?" instead of “What is your opinion on issue $\mathcal{I}$?". Nevertheless, SU classification still has an obvious limitation: respondents might answer these questions in a manner that is viewed favorably by others instead of answering truthfully. Therefore, there exist some dissimilar data pairs labeled as similar, which significantly degenerates the performance of SU classification. In this paper, we study how to learn from noisy similar (nS) data pairs and unlabeled (U) data, which is called nSU classification. Specifically, we carefully model the similarity noise and estimate the noise rate by using the mixture proportion estimation technique. Then, a clean classifier can be learned by minimizing a denoised and unbiased classification risk estimator, which only involves the noisy data. Moreover, we further derive a theoretical generalization error bound for the proposed method. Experimental results demonstrate the effectiveness of the proposed algorithm on several benchmark datasets. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2022. ( edit, beta )

PDF Details

ICML Conference 2021 Conference Paper

Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels

Songhua Wu
Xiaobo Xia
Tongliang Liu
Bo Han 0003
Mingming Gong
Nannan Wang 0001
Haifeng Liu
Gang Niu 0001

Learning with noisy labels has attracted a lot of attention in recent years, where the mainstream approaches are in \emph{pointwise} manners. Meanwhile, \emph{pairwise} manners have shown great potential in supervised metric learning and unsupervised contrastive learning. Thus, a natural question is raised: does learning in a pairwise manner \emph{mitigate} label noise? To give an affirmative answer, in this paper, we propose a framework called \emph{Class2Simi}: it transforms data points with noisy \emph{class labels} to data pairs with noisy \emph{similarity labels}, where a similarity label denotes whether a pair shares the class label or not. Through this transformation, the \emph{reduction of the noise rate} is theoretically guaranteed, and hence it is in principle easier to handle noisy similarity labels. Amazingly, DNNs that predict the \emph{clean} class labels can be trained from noisy data pairs if they are first pretrained from noisy data points. Class2Simi is \emph{computationally efficient} because not only this transformation is on-the-fly in mini-batches, but also it just changes loss computation on top of model prediction into a pairwise manner. Its effectiveness is verified by extensive experiments.

Details