GAD-PVI: A General Accelerated Dynamic-Weight Particle-Based Variational Inference Framework.

Particle-based Variational Inference (ParVI) methods have been widely adopted in deep Bayesian inference tasks such as Bayesian neural networks or Gaussian Processes, owing to their efficiency in generating high-quality samples given the score of the target distribution. Typically, ParVI methods evolve a weighted-particle system by approximating the first-order Wasserstein gradient flow to reduce the dissimilarity between the particle system's empirical distribution and the target distribution. Recent advancements in ParVI have explored sophisticated gradient flows to obtain refined particle systems with either accelerated position updates or dynamic weight adjustments.

WITHDRAWN: ATRA regulates myoblast differentiation and fusion through the RARα/Pitx2 signaling pathway, causing abnormal development of PFMs in ARM fetal rats.

This article has been withdrawn at the request of the author(s) and/or editor. The Publisher apologizes for any inconvenience this may cause. The full Elsevier Policy on Article Withdrawal can be found at https://www.

Unsupervised Domain Adaptation With Class-Aware Memory Alignment.

Unsupervised domain adaptation (UDA) is to make predictions on unlabeled target domain by learning the knowledge from a label-rich source domain. In practice, existing UDA approaches mainly focus on minimizing the discrepancy between different domains by mini-batch training, where only a few instances are accessible at each iteration. Due to the randomness of sampling, such a batch-level alignment pattern is unstable and may lead to misalignment.

Seasonal variations in spatial distribution, mobilization kinetic and toxicity risk of arsenic in sediments of Lake Taihu, China.

This study investigated seasonal variations in spatial distribution, mobilization kinetic and toxicity risk of arsenic (As) in sediments of three representative ecological lakes in Lake Taihu. Results suggested that the bioavailability and mobility of As in sediments depended on the lake ecological types and seasonal changes. At the algal-type zones and macrophyte-type zones, elevated As concentrations were observed in April and July, while these occurred at the transition areas in July and October.

Epoch-Evolving Gaussian Process Guided Learning for Classification.

The conventional mini-batch gradient descent algorithms are usually trapped in the local batch-level distribution information, resulting in the ``zig-zag'' effect in the learning process. To characterize the correlation information between the batch-level distribution and the global data distribution, we propose a novel learning scheme called epoch-evolving Gaussian process guided learning (GPGL) to encode the global data distribution information in a non-parametric way. Upon a set of class-aware anchor samples, our GP model is built to estimate the class distribution for each sample in mini-batch through label propagation from the anchor samples to the batch samples.

Effect of remediation reagents on bacterial composition and ecological function in black-odorous water sediments.

Black-odorous urban water bodies and sediments pose a serious environmental problem. In this study, we conducted microcosm batch experiments to investigate the effect of remediation reagents (magnesium hydroxide and calcium nitrate) on native bacterial communities and their ecological functions in the black-odorous sediment of urban water. The dominant phyla (Proteobacteria, Actinobacteria, Chloroflexi, and Planctomycetes) and classes (Alphaproteobacteria, Betaproteobacteria, and Gammaproteobacteria, Actinobacteria, Anaerolineae, and Planctomycetia) were determined under calcium nitrate and magnesium hydroxide treatments.

Treatment of Children Trichobezoar a Retrospective Study of 11 Cases.

Purpose: The goal of this study to summarize the clinical features, treatment and prognosis of children trichobezoar, and to guide the clinical diagnosis and treatment.

Methods: The clinical manifestations, auxiliary examination results, diagnosis and treatment process and family relationship of 11 cases of children with trichobezoar in our hospital were analyzed retrospectively.

Results: 11 cases were female, 4 cases were divorced single parent family, and 2 case was left behind child.

MgSvF: Multi-Grained Slow versus Fast Framework for Few-Shot Class-Incremental Learning.

As a challenging problem, few-shot class-incremental learning (FSCIL) continually learns a sequence of tasks, confronting the dilemma between slow forgetting of old knowledge and fast adaptation to new knowledge. In this paper, we concentrate on this "slow versus fast" (SvF) dilemma to determine which knowledge components to be updated in a slow fashion or a fast fashion, and thereby balance old-knowledge preservation and new-knowledge adaptation. We propose a multi-grained SvF learning strategy to cope with the SvF dilemma from two different grains: intra-space (within the same feature space) and inter-space (between two different feature spaces).

Elastic Knowledge Distillation by Learning From Recollection.

Model performance can be further improved with the extra guidance apart from the one-hot ground truth. To achieve it, recently proposed recollection-based methods utilize the valuable information contained in the past training history and derive a "recollection" from it to provide data-driven prior to guide the training. In this article, we focus on two fundamental aspects of this method, i.

What and Where: Learn to Plug Adapters via NAS for Multidomain Learning.

As an important and challenging problem, multidomain learning (MDL) typically seeks a set of effective lightweight domain-specific adapter modules plugged into a common domain-agnostic network. Usually, existing ways of adapter plugging and structure design are handcrafted and fixed for all domains before model learning, resulting in learning inflexibility and computational intensiveness. With this motivation, we propose to learn a data-driven adapter plugging strategy with neural architecture search (NAS), which automatically determines where to plug for those adapter modules.

Memory-Efficient Class-Incremental Learning for Image Classification.

With the memory-resource-limited constraints, class-incremental learning (CIL) usually suffers from the "catastrophic forgetting" problem when updating the joint classification model on the arrival of newly added classes. To cope with the forgetting problem, many CIL methods transfer the knowledge of old classes by preserving some exemplar samples into the size-constrained memory buffer. To utilize the memory buffer more efficiently, we propose to keep more auxiliary low-fidelity exemplar samples, rather than the original real-high-fidelity exemplar samples.

Stress-responses of microbial population and activity in activated sludge under long-term ciprofloxacin exposure.

In this study, the effects of ciprofloxacin on activated sludge were evaluated based on the microbial community and metabolic characteristics. The results indicated that the metabolism of chemical oxygen demand (COD) and nitrogen were inhibited with ciprofloxacin at mg/L level compared to the control experiment, and the concentration of ciprofloxacin was slightly decreased. High-throughput sequencing (HTS) results showed that ciprofloxacin greatly shaped the microbial communities in activated sludge, especially for the Nitrospirae phylum and Nitrospira genus.

Compositional changes of sedimentary microbes in the Yangtze River Estuary and their roles in the biochemical cycle.

Due to the geographical circumstances, the Yangtze River Estuary (YRE) and the adjacent East China Sea are extensively influenced by both anthropogenic activities and environmental factors. To reveal the responses of microbes in surface sediment to environmental factors and their contributions to the biogeochemical cycle in this area, surface sediment and overlying water samples were collected at 21 stations from the estuary to the coastal region. Water and sediment parameters were determined, and 16S rRNA genes of microbes in sediment samples were sequenced using high throughput sequencing technology.

Insights into the long-term pollution trends and sources contributions in Lake Taihu, China using multi-statistic analyses models.

Eutrophication pollution seriously threatens the sustainable development of Lake Taihu, China. In order to identify the primary parameters of water quality and the potential pollution sources, the water quality dataset of Lake Taihu (2010-2014) was analyzed with the water quality index (WQI) and multivariate statistical analysis methods. Principle component analysis/factor analysis (PCA/FA) and correlation analysis screened out five significant water quality indicators, i.

Towards the comprehensive water quality control in Lake Taihu: Correlating chlorphyll a and water quality parameters with generalized additive model.

In this study, the generalized additive model (GAM) was used to analyze seasonal monitoring data from Lake Taihu, collected from 2010 to 2014, with the aim to explore the correlation between chlorophyll a (Chla) and other water quality parameters. The selected optimal multivariable GAM could effectively explain the concentration variation of Chla occurring during each season, and the interpretation degree followed the order: summer > autumn > spring > winter. The fitting results indicated that the concentration variation of Chla could reflect that of biochemical oxygen demand and chemical oxygen demand in all seasons.