非独立随机变量部分和的收敛定理(英文)

讨论了只与矩有关的非独立随机变量部分和序列的收敛性．这些结果推广了Ｓｔｏｕｔ在［１］的中定理，进一步对一些相依随机变量给出了相应的结果．

FedTC:A Personalized Federated LearningMethod with Two Classifiers

Centralized training of deep learning models poses privacy risks that hinder their deployment.Federated learning(FL)has emerged as a solution to address these risks,allowing multiple clients to train deep learning models collaborativelywithout sharing rawdata.However,FL is vulnerable to the impact of heterogeneous distributed data,which weakens convergence stability and suboptimal performance of the trained model on local data.This is due to the discarding of the old local model at each round of training,which results in the loss of personalized information in the model critical for maintaining model accuracy and ensuring robustness.In this paper,we propose FedTC,a personalized federated learning method with two classifiers that can retain personalized information in the local model and improve the model’s performance on local data.FedTC divides the model into two parts,namely,the extractor and the classifier,where the classifier is the last layer of the model,and the extractor consists of other layers.The classifier in the local model is always retained to ensure that the personalized information is not lost.After receiving the global model,the local extractor is overwritten by the globalmodel’s extractor,and the classifier of the globalmodel serves as anadditional classifier of the localmodel toguide local training.The FedTCintroduces a two-classifier training strategy to coordinate the two classifiers for local model updates.Experimental results on Cifar10 and Cifar100 datasets demonstrate that FedTC performs better on heterogeneous data than current studies,such as FedAvg,FedPer,and local training,achieving a maximum improvement of 27.95%in model classification test accuracy compared to FedAvg.

ASCFL:Accurate and Speedy Semi-Supervised Clustering Federated Learning

The influence of non-Independent Identically Distribution(non-IID)data on Federated Learning(FL)has been a serious concern.Clustered Federated Learning(CFL)is an emerging approach for reducing the impact of non-IID data,which employs the client similarity calculated by relevant metrics for clustering.Unfortunately,the existing CFL methods only pursue a single accuracy improvement,but ignore the convergence rate.Additionlly,the designed client selection strategy will affect the clustering results.Finally,traditional semi-supervised learning changes the distribution of data on clients,resulting in higher local costs and undesirable performance.In this paper,we propose a novel CFL method named ASCFL,which selects clients to participate in training and can dynamically adjust the balance between accuracy and convergence speed with datasets consisting of labeled and unlabeled data.To deal with unlabeled data,the prediction labels strategy predicts labels by encoders.The client selection strategy is to improve accuracy and reduce overhead by selecting clients with higher losses participating in the current round.What is more,the similarity-based clustering strategy uses a new indicator to measure the similarity between clients.Experimental results show that ASCFL has certain advantages in model accuracy and convergence speed over the three state-of-the-art methods with two popular datasets.

Predator-induced changes of male and female mating preferences: innate and learned components

While many mati ng pref ere nces have a genetic basis, the question remai ns as to whether and how learning/experience can modify individual mate choice decisions. We used wild-caught (predator-experienced) and Fi laboratory-reared (predator-naive) invasive Western mosquitofish Gambusia affinis from China to test whether mating preferences (assessed in a first mate choice test) would change under immediate predation threat. The same individuals were tested in a second mate choice test during which 1 of 3 types of animated predators was presented: 1) a co-occurring predator, 2) a co-evolved but not currently co-occurring predator, and 3) a non-piscivorous species as control. We compared preference scores derived from both mate choice tests to separate innate from experiential effects of predation. We also asked whether predator-induced changes in mating preferences would differ betwee n sexes or depend on the choosing individual's personality type and/or body size. Wild-caught fish altered their mate choice decisions most when exposed to the co-occurring predator whereas laboratory-reared individuals responded most to the co-evolved predator, suggesting that both innate mechanisms and learning effects are involved. This behavior likely reduces individuals' risk of falling victim to predation by temporarily moving away from high-quality (i.e., conspicuous) mating partners. Accordingly, effects were stronger in bolder than shyer, large- compared with small-bodied, and female compared with male focal individuals, likely because those phenotypes face an increased predation risk overall. Our study adds to the growing body of literature appreciating the complexity of the mate choice process, where an array of intrinsic and extrinsic factors interacts during decision-making.

A comparison of two methods to assess audience-induced changes in male mate choice

Multidirectional communicative interactions in social networks can have a profound effect on mate choice behavior. Male Atlantic molly Poecilia mexicana exhibit weaker mating preferences when an audience male is presented. This could be a male strategy to reduce sperm competition risk： interacting more equally with different females may be advantageous because ri- vals might copy mate choice decisions. In line with this hypothesis, a previous study found males to show a strong audience effect when being observed while exercising mate choice, but not when the rival was presented only before the choice tests. Audience effects on mate choice decisions have been quantified in poeciliid fishes using association preference designs, but it remains un- known if patterns found from measuring association times translate into actual mating behavior. Thus, we created five audience treatments simulating different forms of perceived sperm competition risk and determined focal males＇ mating preferences by scoring pre-mating （nipping） and mating behavior （gonopodial thrusting）. Nipping did not reflect the pattern that was found when association preferences were measured, while a very similar pattern was uncovered in thrusting behavior. The strongest response was observed when the audience could eavesdrop on the focal male＇s behavior. A reduction in the strength of focal males＇ preferences was also seen after the rival male had an opportunity to mate with the focal male＇s preferred mate. In comparison, the reduction of mating preferences in response to an audience was greater when measuring association times than actual mating behavior. While measuring direct sexual interactions between the focal male and both slimulus females not only the male＇s motivational state is reflected but also females＇ behavior such as avoidance of male sexual harassment [Current Zoology 58 （1）： 84-94, 2012].