CCMN: A General Framework for Learning With Class-Conditional Multi-Label Noise.

Class-conditional noise commonly exists in machine learning tasks, where the class label is corrupted with a probability depending on its ground-truth. Many research efforts have been made to improve the model robustness against the class-conditional noise. However, they typically focus on the single label case by assuming that only one label is corrupted. In real applications, an instance is usually associated with multiple labels, which could be corrupted simultaneously with their respective conditional probabilities. In this paper, we formalize this problem as a general framework of learning with Class-Conditional Multi-label Noise (CCMN for short). We establish two unbiased estimators with error bounds for solving the CCMN problems, and further prove that they are consistent with commonly used multi-label loss functions. Finally, a new method for partial multi-label learning is implemented with the unbiased estimator under the CCMN framework. Empirical studies on multiple datasets and various evaluation metrics validate the effectiveness of the proposed method.

Partial Multi-Label Learning With Noisy Label Identification.

Partial multi-label learning (PML) deals with problems where each instance is assigned with a candidate label set, which contains multiple relevant labels and some noisy labels. Recent studies usually solve PML problems with the disambiguation strategy, which recovers ground-truth labels from the candidate label set by simply assuming that the noisy labels are generated randomly. In real applications, however, noisy labels are usually caused by some ambiguous contents of the example. Based on this observation, we propose a partial multi-label learning approach to simultaneously recover the ground-truth information and identify the noisy labels. The two objectives are formalized in a unified framework with trace norm and l1 norm regularizers. Under the supervision of the observed noise-corrupted label matrix, the multi-label classifier and noisy label identifier are jointly optimized by incorporating the label correlation exploitation and feature-induced noise model. Furthermore, by mapping each bag to a feature vector, we extend PML-NI method into multi-instance multi-label learning by identifying noisy labels based on ambiguous instances. A theoretical analysis of generalization bound and extensive experiments on multiple data sets from various real-world tasks demonstrate the effectiveness of the proposed approach.

Association between Ocular Axial Length-Related Genes and High Myopia in a Han Chinese Population.

AIMS: A previous genome-wide association study of high myopia identified five genome-wide loci for ocular axial length (C3orf26, ZC3H11B, RSPO1, GJD2, and ZNRF3). The aim of our study was to investigate the association between high myopia and genetic variants in the five loci in Han Chinese subjects. METHODS: Five single nucleotide polymorphisms were genotyped in 296 unrelated high-myopia subjects and 300 matched emmetropic controls by the SNaPshot method. The distribution of genotypes in the cases and controls was compared in codominant, dominant, and recessive genetic models by using SNPStats online software. RESULTS: Significant associations between rs994767 near ZC3H11B (p = 0.001), rs4074961 in RSPO1 (p < 0.001), and rs11073058 in GJD2 (p = 0.029) and high myopia were observed. Odds ratios (95% confidence intervals) were 1.532 (1.200-1.955), 1.603 (1.267-2.029), and 1.290 (1.027-1.621) for the rs994767 T allele, rs4074961 T allele, and rs11073058 T allele, respectively. But rs9811920 in C3orf26 and rs12321 in ZNRF3 were not associated with high myopia. CONCLUSION: Our findings suggested that genetic variants in ZC3H11B, RSPO1, and GJD2 are associated with susceptibility to the development of high myopia in a Han Chinese population. Functional roles of ZC3H11B, RSPO1, and GJD2 in the pathology of high myopia need to be further investigated.

DNA profiling in peripheral blood, buccal swabs, hair follicles and semen from a patient following allogeneic hematopoietic stem cells transplantation.

Allogeneic peripheral blood stem cells transplantation (allo-PBSCT) or allogeneic bone marrow transplantation (allo-BMT) have been widely used to treat patients exhibiting certain severe illnesses. However, previous studies have shown that the biological materials of allo-PBSCT or allo-BMT recipients may not constitute credible materials for personal identification. In the present study, four types of commonly used samples were collected from a male individual following gender-matched allo-BMT. Autosomal short tandem repeat (STR) and Y-STR markers analysis, based on polymerase chain reaction, were used to evaluate the chimerism status. The results showed that the blood sample were all donor type, the buccal swab sample were mixed chimerism, and the sperm and hair follicle samples maintained a recipient origin of 100%. In conclusion, identical results were obtained by the two methods and it was confirmed that DNA extracted from hair follicles and sperm can be used as a reference for the pre-transplant genotype DNA profile of the recipient in the gender-match allo-BMT or -PBSCT.