Observation of the out-of-plane orbital antidamping-like torque.

The out-of-plane antidamping-like orbital torque fosters great hope for high-efficiency spintronic devices. Here we report experimentally the observation of out-of-plane antidamping-like torque that could be generated by z-polarized orbital current in ferromagnetic-metal/oxidized Cu (CuOx) bilayers, which is presented unambiguously by the magnetic field angle dependence of the spin-torque ferromagnetic resonance signal. The CuOx thickness dependence of the orbital torque ratios highlights that the interfacial effect would be responsible for the generation of orbital current. Besides that, the CuOx thickness dependence of the damping parameter further proves the observation of antidamping-like torque. This result contributes to enriching the orbital-related theory of the generation mechanism of the orbital torque.

[Effect of aerobic exercise on AKT/GSK3ß mediated hepatocyte apoptosis in nonalcoholic fatty liver disease].

OBJECTIVE: To investigate the effect of aerobic exercise on AKT/GSK3ß pathway-mediated hepatocyte apoptosis in non-alcoholic fatty liver diseases(NAFLD). METHODS: A total of 30 6-week-old male C57BL/6J mice, and mice were fed adaptively for one week. The control group was fed with ordinary diet, and the model group and model exercise group were fed with high-fat diet until 18 weeks. At the 10th week of the experiment, the model exercise group received aerobic exercise intervention for 8 consecutive weeks until the end of the experiment at the 18th week. Automatic biochemical analyzer to detect serum total cholesterol(TC), triglycerides(TG), alanine aminotransferase(ALT), aspartate aminotransferase(AST), low-density lipoprotein(LDL-C) and high-density lipoprotein(HDL-C) levels. Liver pathological morphology was observed by staining with oil red O and HE. The expression changes of AKT, P-AKT~( Ser473), GSK3ß, P-GSK3ß~(Ser9) and Caspase-3 proteins were detected by western blot, and the apoptosis of hepatocytes was detected by in situ terminal transferase labeling(TUNEL). RESULTS: (1) After intervention, compared with control group, body weight, liver index, serum TC, TG, ALT, AST and LDL-C levels in model group were significantly increased(P<0.01 or P<0.05), while HDL-C level was significantly decreased(P<0.01). Compared with model group, body weight, liver index, serum TC, TG, ALT, AST and LDL-C levels in model exercise group were significantly decreased(P<0.01 or P<0.05), while HDL-C level was significantly increased(P<0.01). (2) Compared with the control group, hepatocyte steatosis and the number of lipid droplets in model group were significantly increased. Compared with the model group, the degree of hepatic adipose degeneration was significantly improved and the number of hepatic lipid droplets was significantly decreased in the model exercise group. (3) Compared with control group, the protein expression levels of P-AKT~(Ser473) and P-GSK3ß~(Ser9) in model group were significantly decreased(P<0.01 or P<0.05), the protein expression levels of Caspase-3 were significantly increased(P<0.05), and the number of hepatocyte apoptosis was significantly increased(P<0.05). Compared with model group, the expression of P-AKT~(Ser473) and P-GSK3ß~(Ser9) protein in model exercise group was significantly increased(P<0.01 or P<0.05), the expression of Caspase-3 protein was significantly decreased(P<0.05), and the number of hepatocyte apoptosis was significantly decreased(P<0.01). CONCLUSION: Aerobic exercise can effectively improve NAFLD, by activating AKT/GSK3ß pathway and increasing the expression of AKT/GSK3ß pathway related molecules, thereby reducing caspase-3 expression and hepatocyte apoptosis.

[Research progress on mechanism of exercise improving non-alcoholic fatty liver disease through regulating endoplasmic reticulum stress].

Non-alcoholic fatty liver disease (NAFLD) is one of the main diseases of metabolic syndrome. With the increasing popularity of NAFLD in the world, the prevention and therapy of NAFLD are facing great challenges. In recent years, scholars at home and abroad have carried out a large number of studies on NAFLD, but its pathogenesis is still unclear. Endoplasmic reticulum stress (ERS) is caused by the accumulation of unfolded or misfolded proteins. In response to ERS, cells help restore normal endoplasmic reticulum function by initiating a protective mechanism known as the unfolded protein response (UPR). Abnormal accumulation of lipids in hepatocytes, aggravated inflammatory response, increased apoptosis of hepatocytes and insulin resistance (IR) are the main pathogenic factors and characteristics of NAFLD, which are closely related to hepatic ERS. A large number of studies have shown that exercise, as a low-cost treatment, can prevent and improve NAFLD effectively, and its mechanism is related to exercise regulating the level of ERS. This paper reviews the research progress on the mechanism of exercise improving NAFLD from the point of view of ERS. The mechanism of exercise improving NAFLD is related to the regulation of hepatocyte lipid metabolism, alleviation of inflammatory reaction, reduction of hepatocyte apoptosis and improvement of IR through regulating ERS.

The mutuality of social emotions: How the victim's reactive attitude influences the transgressor's emotional responses.

Would a transgressor be guiltier or less after receiving the victim's forgiving or blaming attitude? Everyday intuitions and empirical evidence are mixed in this regard, leaving how interpersonal attitudes shape the transgressor's reactive social emotions an open question. We combined a social interactive game with multivariate pattern analysis of fMRI data to address this question. Participants played an interactive game in an fMRI scanner where their incorrect responses could cause either high or low pain stimulation to an anonymous co-player. Following incorrect responses, participants were presented with the co-player's (i.e., the victim's) attitude towards the harm (Blame, Forgive, or Neutral). Behaviorally, the victim's attitude and the severity of harm interactively modulated the transgressor's social emotions, with expectation violation serving as a mediator. While unexpected forgiveness following severe harm amplified the participants' guilt, unexpected blame following minor harm reduced the participants' guilt and increased their anger. This role of expectation violation was supported by multivariate pattern analysis of fMRI, revealing a shared neural representation in ventral striatum in the processing of victim's attitude-induced guilt and anger. Moreover, we identified a neural re-appraisal process of guilt in the transgressor, with the involvement of area related to self-conscious processing (i.e., perigenual anterior cingulate cortex) before knowing the victim's attitude transiting to the involvement of other-regarding related area (i.e., temporoparietal junction) after knowing the victim's attitude. These findings uncover the neurocognitive bases underlying the transgressor's social emotional responses, and highlight the importance of the mutuality of social emotions.

Draft genome sequence of Camellia sinensis var. sinensis provides insights into the evolution of the tea genome and tea quality.

Tea, one of the world's most important beverage crops, provides numerous secondary metabolites that account for its rich taste and health benefits. Here we present a high-quality sequence of the genome of tea, Camellia sinensis var. sinensis (CSS), using both Illumina and PacBio sequencing technologies. At least 64% of the 3.1-Gb genome assembly consists of repetitive sequences, and the rest yields 33,932 high-confidence predictions of encoded proteins. Divergence between two major lineages, CSS and Camellia sinensis var. assamica (CSA), is calculated to ∼0.38 to 1.54 million years ago (Mya). Analysis of genic collinearity reveals that the tea genome is the product of two rounds of whole-genome duplications (WGDs) that occurred ∼30 to 40 and ∼90 to 100 Mya. We provide evidence that these WGD events, and subsequent paralogous duplications, had major impacts on the copy numbers of secondary metabolite genes, particularly genes critical to producing three key quality compounds: catechins, theanine, and caffeine. Analyses of transcriptome and phytochemistry data show that amplification and transcriptional divergence of genes encoding a large acyltransferase family and leucoanthocyanidin reductases are associated with the characteristic young leaf accumulation of monomeric galloylated catechins in tea, while functional divergence of a single member of the glutamine synthetase gene family yielded theanine synthetase. This genome sequence will facilitate understanding of tea genome evolution and tea metabolite pathways, and will promote germplasm utilization for breeding improved tea varieties.

Immunogenicity and Safety of an F-Genotype Attenuated Mumps Vaccine in Healthy 8- to 24-Month-Old Children.

Background: Mumps vaccine immunizations have reduced the incidence of this disease. With the variation of mumps circulating strain, novel vaccine strains are always important. Methods: A 2-center parallel, randomized, double-blind noninferiority trial was performed to compare an F-genotype attenuated mumps vaccine (SP strain) to the A-genotype vaccine (S-79, Jeryl-Lynn strain) in 1080 healthy children aged 8-24 months in Hubei, China. Results: Participants were randomly assigned to receive a high or low dose of the SP or S79 vaccine and then assessed clinically at 30 minutes and 1-28 days postinoculation. No differences in local or systemic reactivity were observed. A similar incidence of severe adverse events associated with the vaccine was observed in the high-dose group and the positive control group. Based on throat swab collections, no viral shedding was present at the 4th and 10th days in any group. Neutralizing and hemagglutination-inhibiting antibody assays with the F- or A-genotype strains showed similar trends in geometric mean titers in the high-dose SP and S79 groups. Increased cytotoxic T lymphocyte responses were observed in all groups. Conclusions: The F-genotype attenuated mumps vaccine is safe, offers immunogenicity against a homologous virus, and is noninferior to the A-genotype vaccine in 8- to 24-month-old children.

Comparative transcriptomic analysis reveals gene expression associated with cold adaptation in the tea plant Camellia sinensis.

BACKGROUND: Low temperature restricts the planting range of all crops, but cold acclimation induces adaption to cold stress in many plants. Camellia sinensis, a perennial evergreen tree that is the source of tea, is mainly grown in warm areas. Camellia sinensis var. sinensis (CSS) has greater cold tolerance than Camellia sinensis var. assamica (CSA). To gain deep insight into the molecular mechanisms underlying cold adaptation, we investigated the physiological responses and transcriptome profiles by RNA-Seq in two tea varieties, cold resistant SCZ (classified as CSS) and cold susceptible YH9 (classified as CSA), during cold acclimation. RESULTS: Under freezing stress, lower relative electrical conductivity and higher chlorophyll fluorescence (Fv/Fm) values were detected in SCZ than in YH9 when subjected to freezing acclimation. During cold treatment, 6072 and 7749 DEGs were observed for SCZ and YH9, respectively. A total of 978 DEGs were common for both SCZ and YH9 during the entire cold acclimation process. DEGs were enriched in pathways of photosynthesis, hormone signal transduction, and transcriptional regulation of plant-pathogen interactions. Further analyses indicated that decreased expression of Lhca2 and higher expression of SnRK2.8 are correlated with cold tolerance in SCZ. CONCLUSIONS: Compared with CSA, CSS was significantly more resistant to freezing after cold acclimation, and this increased resistance was associated with an earlier expression of cold-induced genes. Because the greater transcriptional differentiation during cold acclimation in SCZ may contribute to its greater cold tolerance, our studies identify specific genes involved in photoinhibition, ABA signal conduction, and plant immunity that should be studied for understanding the processes involved in cold tolerance. Marker-assisted breeding focused on the allelic variation at these loci provides an avenue for the possible generation of CSA cultivars that have CSS-level cold tolerance.

Magnon-driven interfacial magnetoelectric coupling in Co/PMN-PT multiferroic heterostructures.

Magnon-driven interfacial magnetoelectric coupling in Co/PMN-PT multiferroic heterostructures is investigated at room temperature. The electric field controlled ferromagnetic resonance field possesses a loop-like curve, with a large resonance field shift between positive and negative remanent polarizations, which confirms a non-volatile strong magnetoelectric coupling. However, with a non-magnetic Ta layer inserted at the Co/PMN-PT interface, a piezostrain-induced butterfly-like curve of the resonance field versus applied electric field of the Co/Ta/PMN-PT multiferroic heterostructure is observed. Further, the non-volatile behavior of the resonance field changing with the applied electric field can be obtained, consistent with the result of polarization versus applied electric field curve, which can be attributed to the magnon-driven interfacial magnetoelectric coupling, showing a strong correlation of magnetization of Co thin film and the polarization of PMN-PT. The result is promising for the design of future multiferroic devices.

Transcriptome profiling of the fertile parent and sterile hybrid in tea plant flower buds.

BACKGROUND: The tea plant is a crucial economic crop. The floral organ development consumes a large amount of nutrients, which affects the leaf yield. To understand the mechanism by which the tea plant produces sterile floral buds, we obtained a sterile tea plant by artificial hybridization. RNA-sequencing based transcriptome analysis was implemented in three samples to determine the differentially expressed genes (DEGs) related to flower development. RESULTS: In this study, a total of 1991 DEGs were identified; 1057 genes were up-regulated and 934 genes were down-regulated in sterile hybrid floral buds. These were mainly distributed in the regulation of biological and metabolic processes. Significantly, auxin biosynthesis genes YUCCA, AUX1 and PIN were dramatically down-regulated, and ARF gene was up-regulated in the sterile hybrid floral buds, and flower development-related genes AP1, AP2 and SPL were changed. A total of 12 energy transfer-related genes were significantly decreased. Furthermore, the expression of 11 transcription factor genes was significantly different. CONCLUSION: The transcriptome analysis suggested that the production of sterile floral buds is a complex bioprocess, and that low auxin-related gene levels result in the formation of sterile floral buds in the tea plant.

Electric-field control of non-volatile 180° switching of the unidirectional anisotropy field in a multiferroic heterostructure.

We investigate the room-temperature, electric-field-mediated, non-volatile 180° switching of the unidirectional anisotropy field in an IrMn/CoFeB/Ta/Pb(Mg1/3Nb2/3)O3-PbTiO3 heterostructure. The variation in exchange bias under different electric fields appears clearly in the magnetic hysteresis loops. The remnant magnetization as a function of electric field, as determined by static magnetic measurements, exhibits a non-volatile behavior, which is consistent with the results of the ferromagnetic resonance field as a function of electric field. Moreover, the measured ferromagnetic resonance shows that the uniaxial magnetic anisotropy field is non-volatile and the unidirectional anisotropy field undergoes 180° switching that can be acquired and separated distinctly. This result is attributed to the piezo-strain effect. The electric-field-mediated non-volatile 180° switching of the unidirectional anisotropy field paves the way for sensors and other spintronic devices.

COMT Val158Met polymorphism influences the susceptibility to framing in decision-making: OFC-amygdala functional connectivity as a mediator.

Individuals tend to avoid risk in a gain frame, in which options are presented in a positive way, but seek risk in a loss frame, in which the same options are presented negatively. Previous studies suggest that emotional responses play a critical role in this "framing effect." Given that the Met allele of COMT Val158Met polymorphism (rs4680) is associated with the negativity bias during emotional processing, this study investigated whether this polymorphism is associated with individual susceptibility to framing and which brain areas mediate this gene-behavior association. Participants were genotyped, scanned in resting state, and completed a monetary gambling task with options (sure vs risky) presented as potential gains or losses. The Met allele carriers showed a greater framing effect than the Val/Val homozygotes as the former gambled more than the latter in the loss frame. Moreover, the gene-behavior association was mediated by resting-state functional connectivity (RSFC) between orbitofrontal cortex (OFC) and bilateral amygdala. Met allele carriers showed decreased RSFC, thereby demonstrating higher susceptibility to framing than Val allele carriers. These findings demonstrate the involvement of COMT Val158Met polymorphism in the framing effect in decision-making and suggest RSFC between OFC and amygdala as a neural mediator underlying this gene-behavior association. Hum Brain Mapp 37:1880-1892, 2016. © 2016 Wiley Periodicals, Inc.

Structural Phase Transition Effect on Resistive Switching Behavior of MoS2 -Polyvinylpyrrolidone Nanocomposites Films for Flexible Memory Devices.

The 2H phase and 1T phase coexisting in the same molybdenum disulfide (MoS2 ) nanosheets can influence the electronic properties of the materials. The 1T phase of MoS2 is introduced into the 2H-MoS2 nanosheets by two-step hydrothermal synthetic methods. Two types of nonvolatile memory effects, namely write-once read-many times memory and rewritable memory effect, are observed in the flexible memory devices with the configuration of Al/1T@2H-MoS2 -polyvinylpyrrolidone (PVP)/indium tin oxide (ITO)/polyethylene terephthalate (PET) and Al/2H-MoS2 -PVP/ITO/PET, respectively. It is observed that structural phase transition in MoS2 nanosheets plays an important role on the resistive switching behaviors of the MoS2 -based device. It is hoped that our results can offer a general route for the preparation of various promising nanocomposites based on 2D nanosheets of layered transition metal dichalcogenides for fabricating the high performance and flexible nonvolatile memory devices through regulating the phase structure in the 2D nanosheets.

Identifying cancer-related microRNAs based on gene expression data.

MOTIVATION: MicroRNAs (miRNAs) are short non-coding RNAs that play important roles in post-transcriptional regulations as well as other important biological processes. Recently, accumulating evidences indicate that miRNAs are extensively involved in cancer. However, it is a big challenge to identify which miRNAs are related to which cancer considering the complex processes involved in tumors, where one miRNA may target hundreds or even thousands of genes and one gene may regulate multiple miRNAs. Despite integrative analysis of matched gene and miRNA expression data can help identify cancer-associated miRNAs, such kind of data is not commonly available. On the other hand, there are huge amount of gene expression data that are publicly accessible. It will significantly improve the efficiency of characterizing miRNA's function in cancer if we can identify cancer miRNAs directly from gene expression data. RESULTS: We present a novel computational framework to identify the cancer-related miRNAs based solely on gene expression profiles without requiring either miRNA expression data or the matched gene and miRNA expression data. The results on multiple cancer datasets show that our proposed method can effectively identify cancer-related miRNAs with higher precision compared with other popular approaches. Furthermore, some of our novel predictions are validated by both differentially expressed miRNAs and evidences from literature, implying the predictive power of our proposed method. In addition, we construct a cancer-miRNA-pathway network, which can help explain how miRNAs are involved in cancer. AVAILABILITY AND IMPLEMENTATION: The R code and data files for the proposed method are available at http://comp-sysbio.org/miR_Path/ CONTACT: liukeq@gmail.com SUPPLEMENTARY INFORMATION: supplementary data are available at Bioinformatics online.

Reward breaks through center-surround inhibition via anterior insula.

Focusing attention on a target creates a center-surround inhibition such that distractors located close to the target do not capture attention. Recent research showed that a distractor can break through this surround inhibition when associated with reward. However, the brain basis for this reward-based attention is unclear. In this fMRI study, we presented a distractor associated with high or low reward at different distances from the target. Behaviorally the low-reward distractor did not capture attention and thus did not cause interference, whereas the high-reward distractor captured attention only when located near the target. Neural activity in extrastriate cortex mirrored the behavioral pattern. A comparison between the high-reward and the low-reward distractors presented near the target (i.e., reward-based attention) and a comparison between the high-reward distractors located near and far from the target (i.e., spatial attention) revealed a common frontoparietal network, including inferior frontal gyrus and inferior parietal sulcus as well as the visual cortex. Reward-based attention specifically activated the anterior insula (AI). Dynamic causal modelling showed that reward modulated the connectivity from AI to the frontoparietal network but not the connectivity from the frontoparietal network to the visual cortex. Across participants, the reward-based attentional effect could be predicted both by the activity in AI and by the changes of spontaneous functional connectivity between AI and ventral striatum before and after reward association. These results suggest that AI encodes reward-based salience and projects it to the stimulus-driven attentional network, which enables the reward-associated distractor to break through the surround inhibition in the visual cortex.

Graph Convolutional Networks With Adaptive Neighborhood Awareness.

Graph convolutional networks (GCNs) can quickly and accurately learn graph representations and have shown powerful performance in many graph learning domains. Despite their effectiveness, neighborhood awareness remains essential and challenging for GCNs. Existing methods usually perform neighborhood-aware steps only from the node or hop level, which leads to a lack of capability to learn the neighborhood information of nodes from both global and local perspectives. Moreover, most methods learn the nodes' neighborhood information from a single view, ignoring the importance of multiple views. To address the above issues, we propose a multi-view adaptive neighborhood-aware approach to learn graph representations efficiently. Specifically, we propose three random feature masking variants to perturb some neighbors' information to promote the robustness of graph convolution operators at node-level neighborhood awareness and exploit the attention mechanism to select important neighbors from the hop level adaptively. We also utilize the multi-channel technique and introduce a proposed multi-view loss to perceive neighborhood information from multiple perspectives. Extensive experiments show that our method can better obtain graph representation and has high accuracy.

Hybrid Residual Multiexpert Reinforcement Learning for Spatial Scheduling of High-Density Parking Lots.

Industries, such as manufacturing, are accelerating their embrace of the metaverse to achieve higher productivity, especially in complex industrial scheduling. In view of the growing parking challenges in large cities, high-density vehicle spatial scheduling is one of the potential solutions. Stack-based parking lots utilize parking robots to densely park vehicles in the vertical stacks like container stacking, which greatly reduces the aisle area in the parking lot, but requires complex scheduling algorithms to park and take out the vehicles. The existing high-density parking (HDP) scheduling algorithms are mainly heuristic methods, which only contain simple logic and are difficult to utilize information effectively. We propose a hybrid residual multiexpert (HIRE) reinforcement learning (RL) approach, a method for interactive learning in the digital industrial metaverse, which efficiently solves the HDP batch space scheduling problem. In our proposed framework, each heuristic scheduling method is considered as an expert. The neural network trained by RL assigns the expert strategy according to the current parking lot state. Furthermore, to avoid being limited by heuristic expert performance, the proposed hierarchical network framework also sets up a residual output channel. Experiments show that our proposed algorithm outperforms various advanced heuristic methods and the end-to-end RL method in the number of vehicle maneuvers, and has good robustness to the parking lot size and the estimation accuracy of vehicle exit time. We believe that the proposed HIRE RL method can be effectively and conveniently applied to practical application scenarios, which can be regarded as a key step for RL to enter the practical application stage of the industrial metaverse.

Scientization or parametrization? Which system is more advantageous to environmental conservation in the reform of China's state-owned forest farms?

Government leadership and grassroots participation are the most typical institutional arrangements in natural resource management, a topic which has been the subject of vigorous debate for a long time. Individually, these systems are referred to as scientization and parametrization. This paper takes the reform of China's state-owned forest farms (SSFs) as a pointcut, comparing the effects of the 2011 policy (representing scientization) and the 2015 policy (representing parametrization) on environmental conservation. For the period from 2006 to 2018, China's provinces are analyzed via difference-in-differences (DID) and principal components difference-in-differences (PCDID) empirical strategies. The results show that the 2015 policy increased new afforestation by an average of 0.903 units, but the 2011 policy had no significant impact. The influence path of the 2015 policy was to curb corruption, relieve fiscal stress, and stimulate innovation, playing mechanism effects of 20.49%, 14.17%, and 33.55%, respectively. However, the 2015 policy was not ideal in terms of its goal of incentivizing multi-agent participation in investments in conservation. Investors prefer to attempt afforestation projects with shorter payback periods, especially projects related to open forest land. Overall, this study supports the belief that parametric management is a better approach to natural resource management than scientific management, but the latter approach still has limitations. Therefore, we propose to prioritize the promotion of parametric management on the closed forest lands of SSFs, but there is no need to hastily mobilize grassroots participation in open forest land management projects.

CEModule: A Computation Efficient Module for Lightweight Convolutional Neural Networks.

Lightweight convolutional neural networks (CNNs) rely heavily on the design of lightweight convolutional modules (LCMs). For an LCM, lightweight design based on repetitive feature maps (LoR) is currently one of the most effective approaches. An LoR mainly involves an extraction of feature maps from convolutional layers (CE) and feature map regeneration through cheap operations (RO). However, existing LoR approaches carry out lightweight improvements only from the aspect of RO but ignore the problems of poor generalization, low stability, and high computation workload incurred in the CE part. To alleviate these problems, this article introduces the concept of key features from a CNN model interpretation perspective. Subsequently, it presents a novel LCM, namely CEModule, focusing on the CE part. CEModule increases the number of key features to maintain a high level of accuracy in classification. In the meantime, CEModule employs a group convolution strategy to reduce floating-point operations (FLOPs) incurred in the training process. Finally, this article brings forth a dynamic adaptation algorithm ( α -DAM) to enhance the generalization of CEModule-enabled lightweight CNN models, including the developed CENet in dealing with datasets of different scales. Compared with the state-of-the-art results, CEModule reduces FLOPs by up to 54% on CIFAR-10 while maintaining a similar level of accuracy in classification. On ImageNet, CENet increases accuracy by 1.2% following the same FLOPs and training strategies.

PSDC: A Prototype-Based Shared-Dummy Classifier Model for Open-Set Domain Adaptation.

Open-set domain adaptation (OSDA) aims to achieve knowledge transfer in the presence of both domain shift and label shift, which assumes that there exist additional unknown target classes not presented in the source domain. To solve the OSDA problem, most existing methods introduce an additional unknown class to the source classifier and represent the unknown target instances as a whole. However, it is unreasonable to treat all unknown target instances as a group since these unknown instances typically consist of distinct categories and distributions. It is challenging to identify all unknown instances with only one additional class. In addition, most existing methods directly introduce marginal distribution alignment to alleviate distribution shift between the source and target domains, failing to learn discriminative class boundaries in the target domain since they ignore categorical discriminative information in the adaptation. To address these problems, in this article, we propose a novel prototype-based shared-dummy classifier (PSDC) model for the OSDA. Specifically, our PSDC introduces an auxiliary dummy classifier to calibrate the source classifier and simultaneously develops a weighted adaptation procedure to align class-wise prototypes for adaptation. We further design a pseudo-unknown learning algorithm to reduce the open-set risk. Extensive experiments on Office-31, Office-Home, and VisDA datasets show that the proposed PSDC can outperform existing methods and achieve the new state-of-the-art performance. The code will be made public.

A Multichannel Convolutional Decoding Network for Graph Classification.

Graph convolutional networks (GCNs) have shown superior performance on graph classification tasks, and their structure can be considered as an encoder-decoder pair. However, most existing methods lack the comprehensive consideration of global and local in decoding, resulting in the loss of global information or ignoring some local information of large graphs. And the commonly used cross-entropy loss is essentially an encoder-decoder global loss, which cannot supervise the training states of the two local components (encoder and decoder). We propose a multichannel convolutional decoding network (MCCD) to solve the above-mentioned problems. MCCD first adopts a multichannel GCN encoder, which has better generalization than a single-channel GCN encoder since different channels can extract graph information from different perspectives. Then, we propose a novel decoder with a global-to-local learning pattern to decode graph information, and this decoder can better extract global and local information. We also introduce a balanced regularization loss to supervise the training states of the encoder and decoder so that they are sufficiently trained. Experiments on standard datasets demonstrate the effectiveness of our MCCD in terms of accuracy, runtime, and computational complexity.