Decentralized Semi-Supervised Learning for Stochastic Configuration Networks Based on the Mean Teacher Method

The aim of this paper is to broaden the application of Stochastic Configuration Network (SCN) in the semi-supervised domain by utilizing common unlabeled data in daily life. It can enhance the classification accuracy of decentralized SCN algorithms while effectively protecting user privacy. To this end, we propose a decentralized semi-supervised learning algorithm for SCN, called DMT-SCN, which introduces teacher and student models by combining the idea of consistency regularization to improve the response speed of model iterations. In order to reduce the possible negative impact of unsupervised data on the model, we purposely change the way of adding noise to the unlabeled data. Simulation results show that the algorithm can effectively utilize unlabeled data to improve the classification accuracy of SCN training and is robust under different ground simulation environments.

Attentive Neighborhood Feature Augmentation for Semi-supervised Learning

Recent state-of-the-art semi-supervised learning(SSL)methods usually use data augmentations as core components.Such methods,however,are limited to simple transformations such as the augmentations under the instance’s naive representations or the augmentations under the instance’s semantic representations.To tackle this problem,we offer a unique insight into data augmentations and propose a novel data-augmentation-based semi-supervised learning method,called Attentive Neighborhood Feature Aug-mentation(ANFA).The motivation of our method lies in the observation that the relationship between the given feature and its neighborhood may contribute to constructing more reliable transformations for the data,and further facilitating the classifier to distinguish the ambiguous features from the low-dense regions.Specially,we first project the labeled and unlabeled data points into an embedding space and then construct a neighbor graph that serves as a similarity measure based on the similar representations in the embedding space.Then,we employ an attention mechanism to transform the target features into augmented ones based on the neighbor graph.Finally,we formulate a novel semi-supervised loss by encouraging the predictions of the interpolations of augmented features to be consistent with the corresponding interpolations of the predictions of the target features.We carried out exper-iments on SVHN and CIFAR-10 benchmark datasets and the experimental results demonstrate that our method outperforms the state-of-the-art methods when the number of labeled examples is limited.

A New Kind of Conjugate-nested Central Configurations in Consisted of One Regular Tetrahedron and One Regular Octahedron

A new case configuration in R^3, the conjugate-nest consisted of one regular tetrahedron and one regular octahedron is discussed. If the configuration is a central configuration, then all masses of outside layer are equivalent, the masses of inside layer are also equivalent. At the same time the following relation between ρ（r =√3/3ρ is the radius ratio of the sizes） and mass ratio τ=~↑m/m must be satisfied τ=~↑m/m=ρ（ρ＋3）（3＋2ρ＋ρ^2）^-3/2＋ρ（-ρ＋3）（3-2ρ＋ρ^2）^-3/2-4.2^-3/2ρ^-2-^-1ρ^-2/2（1＋ρ）（3＋2ρ＋ρ^2）^-3/2＋2（ρ-1）（3-2ρ＋ρ^2）^-3/2-4（2√2）^-3ρ, and for any mass ratio τ, when mass ratio r is in the open interval （0, 0.03871633950 ... ）, there exist three central configuration solutions（the initial configuration conditions who imply hamagraphic solutions） corresponding radius ratios are r1, r2, and r3, two of them in the interval （2.639300779… , ＋∞） and one is in the interval （0.7379549890…, 1.490942703… ）. when mass ratio τ is in the open interval （130.8164950… , ＋∞）, in the same way there have three corresponding radius ratios, two of them in the interval （0, 0.4211584789... ） and one is in the interval （0.7379549890…, 1.490942703…）. When mass ratio τ is in the open interval （0.03871633950…, 130.8164950…）, there has only one solution r in the interval （0.7379549890…, 1.490942703… ）.

A Deep Model for Partial Multi-label Image Classification with Curriculum-based Disambiguation

In this paper,we study the partial multi-label(PML)image classification problem,where each image is annotated with a candidate label set consisting of multiple relevant labels and other noisy labels.Existing PML methods typically design a disambiguation strategy to filter out noisy labels by utilizing prior knowledge with extra assumptions,which unfortunately is unavailable in many real tasks.Furthermore,because the objective function for disambiguation is usually elaborately designed on the whole training set,it can hardly be optimized in a deep model with stochastic gradient descent(SGD)on mini-batches.In this paper,for the first time,we propose a deep model for PML to enhance the representation and discrimination ability.On the one hand,we propose a novel curriculum-based disambiguation strategy to progressively identify ground-truth labels by incorporating the varied difficulties of different classes.On the other hand,consistency regularization is introduced for model training to balance fitting identified easy labels and exploiting potential relevant labels.Extensive experimental results on the commonly used benchmark datasets show that the proposed method significantlyoutperforms the SOTA methods.