The development of social networks has not only improved the online experience, but also stimulated the advances in knowledge mining so as to assist people in planning their offline social events. Users can explore their favorite events, such as celebrations and symposiums, through the pictures and the posts from their friends on social networks. An effective event recommendation can offer great convenience for both event organizers and participants, which yet remains extremely challenging due to a wide range of practical concerns. In this paper we propose a novel recommendation framework, which combines the information from multiple sources and establishes a connection between the online knowledge and the event participation.

Despite the ability to model many real world settings as a network, one major challenge in analyzing network data is that important and reliable links between objects are usually obscured by noisy information and hence not readily discernible. In this paper, we propose to detect these important and reliable links - significant edges, from a target network by using multiple auxiliary networks and a limited amount of labelled information. In this process, we first abstract the community knowledge learnt across target and auxiliary networks to detect significant patterns. The mined community knowledge captures the key profile of network relationships and thus can be used to determine whether an existing edge indicates a true or false relationship. Experiments on real world network data show that our two staged solution -- a joint matrix factorisation procedure followed by edge significance score ranking, accurately predicts significant edges in target network by jointly exploring the underlying knowledge embedded in both target and auxiliary networks.

Networks, which characterize object relationships, are ubiquitous in various domains. One very important problem is to detect the nodes of a specific function in these networks. For example, is a user normal or anomalous in an email network? Does a protein play a key role in a protein-protein interaction network? In many applications, the information we have about the networks usually includes both node characteristics and network structures. Both types of information can contribute to the task of learning functional nodes, and we call the collection of node and link information as linked data. However, existing methods only use a few subjectively selected topological features from network structures to detect functional nodes, thus fail to include highly discriminative and meaningful patterns hidden in linked data. To address this problem, a novel Feature Integration based Functional Node Detection (FIND) algorithm is presented. Specifically, FIND extracts the most discriminative information from both node characteristics and network structures in the form of a unified latent feature representation with the guidance of several labeled nodes. Experiments on two real world data sets validate that the proposed method significantly outperforms the baselines on the detection of three different types of functional nodes.

Nowadays the rapid development in the area of human-computer interaction has given birth to a growing interest on detecting different affective states through smart devices. By using the modern sensor equipment, we can easily collect electroencephalogram (EEG) signals, which capture the information from central nervous system and are closely related with our brain activities. Through the training on EEG signals, we can make reasonable analysis on people's affection, which is very promising in various areas. Unfortunately, the special properties of EEG dataset have brought difficulties for conventional machine learning methods. The main reasons lie in two aspects: the small set of labeled samples and the noisy channel problem. To overcome these difficulties and successfully identify the affective states, we come up with a novel semi-supervised deep structured framework. Compared with previous deep learning models, our method is more adapted to the EEG classification problem. We first adopt a two-level procedure, which involves both supervised label information and unsupervised structure information to jointly make decision on channel selection. And then, we add a generative Restricted Boltzmann Machine (RBM) model for the classification task, and use the training objectives of generative learning and unsupervised learning to jointly regularize the discriminative training. Finally, we extend it to the active learning scenario, which solves the costly labeling problem. The experiments conducted on real EEG dataset have shown both the convincing result on critical channel selection and the superiority of our method over multiple baselines for the affective state recognition.

Linked data consist of both node attributes, e.g., Preferences, posts and degrees, and links which describe the connections between nodes. They have been widely used to represent various network systems, such as social networks, biological networks and etc. Knowledge discovery on linked data is of great importance to many real applications. One of the major challenges of learning linked data is how to effectively and efficiently extract useful information from both node attributes and links in linked data. Current studies on this topic either use selected topological statistics to represent network structures, or linearly map node attributes and network structures to a shared latent feature space. However, while approaches based on statistics may miss critical patterns in network structure, approaches based on linear mappings may not be sufficient to capture the non-linear characteristics of nodes and links. To handle the challenge, we propose, to our knowledge, the first deep learning method to learn from linked data. A restricted Boltzmann machine model named LRBM is developed for representation learning on linked data. In LRBM, we aim to extract the latent feature representation of each node from both node attributes and network structures, non-linearly map each pair of nodes to the links, and use hidden units to control the mapping. The details of how to adapt LRBM for link prediction and node classification on linked data have also been presented. In the experiments, we test the performance of LRBM as well as other baselines on link prediction and node classification. Overall, the extensive experimental evaluations confirm the effectiveness of the proposed LRBM model in mining linked data.

Time varying problems usually have complex underlying structures represented as dynamic networks where entities and relationships appear and disappear over time. The problem of efficiently performing dynamic link inference is extremely challenging due to the dynamic nature in massive evolving networks especially when there exist sparse connectivities and nonlinear transitional patterns. In this paper, we propose a novel deep learning framework, i.e., Conditional Temporal Restricted Boltzmann Machine (ctRBM), which predicts links based on individual transition variance as well as influence introduced by local neighbors. The proposed model is robust to noise and have the exponential capability to capture nonlinear variance. We tackle the computational challenges by developing an efficient algorithm for learning and inference of the proposed model. To improve the efficiency of the approach, we give a faster approximated implementation based on a proposed Neighbor Influence Clustering algorithm. Extensive experiments on simulated as well as real-world dynamic networks show that the proposed method outperforms existing algorithms in link inference on dynamic networks.

With the ultimate intent of improving the quality of life, identification of human's affective states on the collected electroencephalogram (EEG) has attracted lots of attention recently. In this domain, the existing methods usually use only a few labeled samples to classify affective states consisting of over thousands of features. Therefore, important information may not be well utilized and performance is lowered due to the randomness caused by the small sample problem. However, this issue has rarely been discussed in the previous studies. Besides, many EEG channels are irrelevant to the specific learning tasks, which introduce lots of noise to the systems and further lower the performance in the recognition of affective states. To address these two challenges, in this paper, we propose a novel Deep Belief Networks (DBN) based model for affective state recognition from EEG signals. Specifically, signals from each EEG channel are firstly processed with a DBN for effectively extracting critical information from the over thousands of features. The extracted low dimensional characteristics are then utilized in the learning to avoid the small sample problem. For the noisy channel problem, a novel stimulus-response model is proposed. The optimal channel set is obtained according to the response rate of each channel. Finally, a supervised Restricted Boltzmann Machine (RBM) is applied on the combined low dimensional characteristics from the optimal EEG channels. To evaluate the performance of the proposed Supervised DBN based Affective State Recognition (SDA) model, we implement it on the Deap Dataset and compare it with five baselines. Extensive experimental results show that the proposed algorithm can successfully handle the aforementioned two challenges and significantly outperform the baselines by 11.5% to 24.4%, which validates the effectiveness of the proposed algorithm in the task of affective state recognition.

Critical node detection in dynamic networks is of great value in many areas, such as the evolving of friendship in social networks, the development of epidemics, molecular pathogenesis of diseases and so on. As for detecting critical nodes in dynamic Protein-Protein Interaction Networks (PPINs), there are mainly two challenges: the first is to construct the dynamic PPINs that are not available directly from biological experiments in laboratories; and the second is how to identify the most critical units that are responsible for the dynamic processes. This paper proposes effective framework to tackle these two problems. First of all, this paper proposes to construct the dynamic PPINs by simultaneously modeling the activity of proteins and assembling the dynamic co-regulation protein network at each time point. As result, more comprehensive dynamic PPINs are built. Besides, a novel critical protein detection method that integrates multiple PPI networks into a Deep Belief Network model (referred to as MIDBN) is developed. The integrated model is trained to get hierarchical common representations of multiple sources which are used to reconstruct the original data. The variabilities of the reconstruction errors across the time courses are ranked to finally get the top proteins that have significantly different evolving structural patterns than the other nodes in the dynamic networks. We evaluated our network construction method by comparing the functional representations of the derived networks with that of two other traditional construction methods, and our method achieved superior function analysis results. The ranking results of critical proteins from MIDBN were compared with results from two baseline methods and the comparison results showed that MIDBN had better reconstruction rate and identified more proteins of critical value to yeast cell cycle process.

Dynamic networks are structures with objects and links between the objects that vary in time. Temporal information in dynamic networks can be used to reveal many important phenomena such as bursts of activities in social networks and human communication patterns in email networks. In this area, one very important problem is to understand dynamic patterns of object roles. For instance, will a user become a peripheral node in a social network? Could a website become a hub on the Internet? Will a gene be highly expressed in gene-gene interaction networks in the later stage of a cancer? In this paper, we propose a novel approach that identifies the role of each object, tracks the changes of object roles over time, and predicts the evolving patterns of the object roles in dynamic networks. In particular, a probability model is proposed to extract latent features of object roles from dynamic networks. The extracted latent features are discriminative in learning object roles and are capable of characterizing network structures. The probability model is then extended to learn the dynamic patterns and make predictions on object roles. We assess our method on two data sets on the tasks of exploring how users' importance and political interests evolve as time progresses on dynamic networks. Overall, the extensive experimental evaluations confirm the effectiveness of our approach for identifying, analyzing and predicting object roles on dynamic networks.

Transfer learning has benefited many real-world applications where labeled data are abundant in source domains but scarce in the target domain. As there are usually multiple relevant domains where knowledge can be transferred, multiple source transfer learning (MSTL) has recently attracted much attention. However, we are facing two major challenges when applying MSTL. First, without knowledge about the difference between source and target domains, negative transfer occurs when knowledge is transferred from highly irrelevant sources. Second, existence of imbalanced distributions in classes, where examples in one class dominate, can lead to improper judgement on the source domains’ relevance to the target task. Since existing MSTL methods are usually designed to transfer from relevant sources with balanced distributions, they will fail in applications where these two challenges persist. In this paper, we propose a novel two-phase framework to effectively transfer knowledge from multiple sources even when there exist irrelevant sources and imbalanced class distributions. First, an effective Supervised Local Weight (SLW) scheme is proposed to assign a proper weight to each source domain's classifier based on its ability of predicting accurately on each local region of the target domain. The second phase then learns a classifier for the target domain by solving an optimization problem which concerns both training error minimization and consistency with weighted predictions gained from source domains. A theoretical analysis shows that as the number of source domains increases, the probability that the proposed approach has an error greater than a bound is becoming exponentially small. Extensive experiments on disease prediction, spam filtering and intrusion detection data sets demonstrate the significant improvement in classification performance gained by the proposed method over existing MSTL approaches.

Informative Gene Selection is the process of identifying relevant genes that are significantly and differentially expressed in biological procedures. The microarray experiments conducted for this purpose usually implement only less than a hundred of samples to rank the relevance of over thousands of genes. Many irrelevant genes thus may gain statistical importance due to the randomness caused by the small sample problem, while relevant genes may lose focus in the same way. Overcoming such a problem goes beyond what a single microarray dataset can offer and stresses the use of multiple experiment results, which is defined as rank aggregation. In this paper, we propose a novel link prediction based rank aggregation algorithm for the purpose of informative gene selection. Each rank is transferred into a fully connected and weighted network, in which the nodes represent genes and the weights of links stand for priorities between connected nodes (genes). The integration of multiple gene ranks is then formulated as an optimization problem of link prediction on multiple networks, with criterion function favoring the maximization of weighted consensus among each network. We solve the problem through iterative estimation of weights and maximization of consensus among them. In the experimental evaluation, we demonstrate our method on the Prostate Cancer Dataset and compare it with other baseline methods. The results show that our link prediction based rank aggregation method remarkably outperforms all the compared methods, which proves the effectiveness of our framework in finding informative genes from multiple microarray experimental results.

Identification of a critical location in complex structures is one of the most important issues that affects the quality of safety in human life. Specifically, finding high fracture spots of a bone microstructure in our body is a very important research topic; however, it is still not well understood. In this paper, we study on identifying critical locations in a bone microstructure with our bone network model. In fact, about 25 million people in the United States suffer from osteoporosis, which is a systemic skeletal disease characterized by low bone mass and micro-architectural deterioration of bone tissue leading to enhanced bone fragility and a consequent increase in fracture risk. However, currently available techniques for the diagnosis of osteoporosis and the identification of critical locations of bone microstructure are limited. We create a bone network model based on properties of a bone microstructure and we develop a method, called information propagation, to identify critical locations in a bone network. Our paper focuses on detecting important edges as critical locations for the strength of bone microstructure when there are external forces applied to the bone network. Then, we evaluate results of the method in comparison with existing methods including the weighted betweenness centrality and the weighted bridge coefficient. We conclude with the discussion on advantages and disadvantages among those methods.