1. An L1-and-L2-Norm-Oriented Latent Factor Model for Recommender Systems
Di Wu, Mingsheng Shang, Xin Luo, Zidong Wang IEEE Trans Neural Netw Learn Syst. 2022 Oct;33(10):5775-5788. doi: 10.1109/TNNLS.2021.3071392. Epub 2022 Oct 5.
A recommender system (RS) is highly efficient in filtering people's desired information from high-dimensional and sparse (HiDS) data. To date, a latent factor (LF)-based approach becomes highly popular when implementing a RS. However, current LF models mostly adopt single distance-oriented Loss like an L2 norm-oriented one, which ignores target data's characteristics described by other metrics like an L1 norm-oriented one. To investigate this issue, this article proposes an L1 -and- L2 -norm-oriented LF ( [Formula: see text]) model. It adopts twofold ideas: 1) aggregating L1 norm's robustness and L2 norm's stability to form its Loss and 2) adaptively adjusting weights of L1 and L2 norms in its Loss. By doing so, it achieves fine aggregation effects with L1 norm-oriented Loss 's robustness and L2 norm-oriented Loss 's stability to precisely describe HiDS data with outliers. Experimental results on nine HiDS datasets generated by real systems show that an [Formula: see text] model significantly outperforms state-of-the-art models in prediction accuracy for missing data of an HiDS dataset. Its computational efficiency is also comparable with the most efficient LF models. Hence, it has good potential for addressing HiDS data from real applications.
2. Minimizing L 1 over L 2 norms on the gradient
Chao Wang, Min Tao, Chen-Nee Chuah, James Nagy, Yifei Lou Inverse Probl. 2022 Jun;38(6):065011. Epub 2022 May 6.
In this paper, we study the L 1 /L 2 minimization on the gradient for imaging applications. Several recent works have demonstrated that L 1 /L 2 is better than the L 1 norm when approximating the L 0 norm to promote sparsity. Consequently, we postulate that applying L 1 /L 2 on the gradient is better than the classic total variation (the L 1 norm on the gradient) to enforce the sparsity of the image gradient. Numerically, we design a specific splitting scheme, under which we can prove subsequential and global convergence for the alternating direction method of multipliers (ADMM) under certain conditions. Experimentally, we demonstrate visible improvements of L 1 /L 2 over L 1 and other nonconvex regularizations for image recovery from low-frequency measurements and two medical applications of MRI and CT reconstruction. Finally, we reveal some empirical evidence on the superiority of L 1 /L 2 over L 1 when recovering piecewise constant signals from low-frequency measurements to shed light on future works.
3. An L-2-hydroxyglutarate biosensor based on specific transcriptional regulator LhgR
Zhaoqi Kang, Manman Zhang, Kaiyu Gao, Wen Zhang, Wensi Meng, Yidong Liu, Dan Xiao, Shiting Guo, Cuiqing Ma, Chao Gao, Ping Xu Nat Commun. 2021 Jun 15;12(1):3619. doi: 10.1038/s41467-021-23723-7.
L-2-Hydroxyglutarate (L-2-HG) plays important roles in diverse physiological processes, such as carbon starvation response, tumorigenesis, and hypoxic adaptation. Despite its importance and intensively studied metabolism, regulation of L-2-HG metabolism remains poorly understood and none of regulator specifically responded to L-2-HG has been identified. Based on bacterial genomic neighborhood analysis of the gene encoding L-2-HG oxidase (LhgO), LhgR, which represses the transcription of lhgO in Pseudomonas putida W619, is identified in this study. LhgR is demonstrated to recognize L-2-HG as its specific effector molecule, and this allosteric transcription factor is then used as a biorecognition element to construct an L-2-HG-sensing FRET sensor. The L-2-HG sensor is able to conveniently monitor the concentrations of L-2-HG in various biological samples. In addition to bacterial L-2-HG generation during carbon starvation, biological function of the L-2-HG dehydrogenase and hypoxia induced L-2-HG accumulation are also revealed by using the L-2-HG sensor in human cells.
