Gradient-aware learning for joint biases: Label noise and class imbalance.

Data biases such as class imbalance and label noise always exist in large-scale datasets in real-world. These problems bring huge challenges to deep learning methods. Some previous works adopted loss re-weighting, sample re-weighting, or data-dependent regularization to mitigate the influence of these training biases. But these methods usually pay more attention to class imbalance problem when both the class imbalance and label noise exist in training set simultaneously. These methods may overfit noisy labels, which leads to a great degradation in performance. In this paper, we propose a gradient-aware learning method for the combination of the two biases. During the training process, we update only a part of crucial parameters regularly and rectify the update direction of the rest redundant parameters. This update rule is conducted both in the encoder and classifier of the deep network to decouple label noise and class imbalance implicitly. The experimental results verify the effectiveness of the proposed method on synthetic and real-world data biases.

Advances in Phenazines over the Past Decade: Review of Their Pharmacological Activities, Mechanisms of Action, Biosynthetic Pathways and Synthetic Strategies.

Phenazines are a large group of nitrogen-containing heterocycles, providing diverse chemical structures and various biological activities. Natural phenazines are mainly isolated from marine and terrestrial microorganisms. So far, more than 100 different natural compounds and over 6000 synthetic derivatives have been found and investigated. Many phenazines show great pharmacological activity in various fields, such as antimicrobial, antiparasitic, neuroprotective, insecticidal, anti-inflammatory and anticancer activity. Researchers continued to investigate these compounds and hope to develop them as medicines. Cimmino et al. published a significant review about anticancer activity of phenazines, containing articles from 2000 to 2011. Here, we mainly summarize articles from 2012 to 2021. According to sources of compounds, phenazines were categorized into natural phenazines and synthetic phenazine derivatives in this review. Their pharmacological activities, mechanisms of action, biosynthetic pathways and synthetic strategies were summarized. These may provide guidance for the investigation on phenazines in the future.