Feature Relationships Learning Incorporated Age Estimation Assisted by Cumulative Attribute Encoding

The research of human facial age estimation(AE)has attracted increasing attention for its wide applications.Up to date,a number of models have been constructed or employed to perform AE.Although the goal of AE can be achieved by either classification or regression,the latter based methods generally yield more promising results because the continuity and gradualness of human aging can naturally be preserved in age regression.However,the neighbor-similarity and ordinality of age labels are not taken into account yet.To overcome this issue,the cumulative attribute(CA)coding was introduced.Although such age label relationships can be parameterized via CA coding,the potential relationships behind age features are not incorporated to estimate age.To this end,in this paper we propose to perform AE by encoding the potential age feature relationships with CA coding via an implicit modeling strategy.Besides that,we further extend our model to gender-aware AE by taking into account gender variance in aging process.Finally,we experimentally validate the superiority of the proposed methodology.

Feature Selection with a Local Search Strategy Based on the Forest Optimization Algorithm

Feature selection has been widely used in data mining and machine learning.Its objective is to select a minimal subset of features according to some reasonable criteria so as to solve the original task more quickly.In this article,a feature selection algorithm with local search strategy based on the forest optimization algorithm,namely FSLSFOA,is proposed.The novel local search strategy in local seeding process guarantees the quality of the feature subset in the forest.Next,the fitness function is improved,which not only considers the classification accuracy,but also considers the size of the feature subset.To avoid falling into local optimum,a novel global seeding method is attempted,which selects trees on the bottom of candidate set and gives the algorithm more diversities.Finally,FSLSFOA is compared with four feature selection methods to verify its effectiveness.Most of the results are superior to these comparative methods.

Access Control Policy Based on Friend Circle

Nowadays,the scale of the user’s personal social network(personal network,a network of the user and their friends,where the user we call“center user”)is becoming larger and more complex.It is difficult to find a suitable way to manage them automatically.In order to solve this problem,we propose an access control model for social network to protect the privacy of the central users,which achieves the access control accurately and automatically.Based on the hybrid friend circle detection algorithm,we consider the aspects of direct judgment,indirect trust judgment and malicious users,a set of multi-angle control method which could be adapted to the social network environment is proposed.Finally,we propose the solution to the possible conflict of rights in the right control,and assign the rights reasonably in the case of guaranteeing the privacy of the users.

Self-adaptive label filtering learning for unsupervised domain adaptation

1 Introduction As an emerging machine learning paradigm,unsupervised domain adaptation(UDA)aims to train an effective model for unlabeled target domain by leveraging knowledge from related but distribution-inconsistent source domain.Most of the existing UDA methods[2]align class-wise distributions resorting to target domain pseudo-labels,for which hard labels may be misguided by misclassifications while soft labels are confusing with trivial noises so that both of them tend to cause frustrating performance.To overcome such drawbacks,as shown in Fig.1,we propose to achieve UDA by performing self-adaptive label filtering learning(SALFL)from both the statistical and the geometrical perspectives,which filters out the misclassified pseudo-labels to reduce negative transfer.Specifically,the proposed SALFL firstly predicts labels for the target domain instances by graph-based random walking and then filters out those noise labels by self-adaptive learning strategy.