Cognition-Driven Structural Prior for Instance-Dependent Label Transition Matrix Estimation.

The label transition matrix has emerged as a widely accepted method for mitigating label noise in machine learning. In recent years, numerous studies have centered on leveraging deep neural networks to estimate the label transition matrix for individual instances within the context of instance-dependent noise. However, these methods suffer from low search efficiency due to the large space of feasible solutions. Behind this drawback, we have explored that the real murderer lies in the invalid class transitions, that is, the actual transition probability between certain classes is zero but is estimated to have a certain value. To mask the invalid class transitions, we introduced a human-cognition-assisted method with structural information from human cognition. Specifically, we introduce a structured transition matrix network (STMN) designed with an adversarial learning process to balance instance features and prior information from human cognition. The proposed method offers two advantages: 1) better estimation effectiveness is obtained by sparing the transition matrix and 2) better estimation accuracy is obtained with the assistance of human cognition. By exploiting these two advantages, our method parametrically estimates a sparse label transition matrix, effectively converting noisy labels into true labels. The efficiency and superiority of our proposed method are substantiated through comprehensive comparisons with state-of-the-art methods on three synthetic datasets and a real-world dataset. Our code will be available at https://github.com/WheatCao/STMN-Pytorch.

Biosynthesis of DHGA12 and its roles in Arabidopsis seedling establishment.

Seed germination and photoautotrophic establishment are controlled by the antagonistic activity of the phytohormones gibberellins (GAs) and abscisic acid (ABA). Here we show that Arabidopsis thaliana GAS2 (Gain of Function in ABA-modulated Seed Germination 2), a protein belonging to the Fe-dependent 2-oxoglutarate dioxygenase superfamily, catalyzes the stereospecific hydration of GA12 to produce GA12 16, 17-dihydro-16α-ol (DHGA12). We show that DHGA12, a C20-GA has an atypical structure compared to known active GAs but can bind to the GA receptor (GID1c). DHGA12 can promote seed germination, hypocotyl elongation and cotyledon greening. Silencing and over-expression of GAS2 alters the ABA/GA ratio and sensitivity to ABA during seed germination and photoautotrophic establishment. Hence, we propose that GAS2 acts to modulate hormonal balance during early seedling development.