In this paper, the task of cross-network node classification, which leverages the abundant labeled nodes from a source network to help classify unlabeled nodes in a target network, is studied. The existing domain adaptation algorithms generally fail to model the network structural information, and the current network embedding models mainly focus on single-network applications. Thus, both of them cannot be directly applied to solve the cross-network node classification problem. This motivates us to propose an adversarial cross-network deep network embedding (ACDNE) model to integrate adversarial domain adaptation with deep network embedding so as to learn network-invariant node representations that can also well preserve the network structural information. In ACDNE, the deep network embedding module utilizes two feature extractors to jointly preserve attributed affinity and topological proximities between nodes. In addition, a node classifier is incorporated to make node representations label-discriminative. Moreover, an adversarial domain adaptation technique is employed to make node representations network-invariant. Extensive experimental results demonstrate that the proposed ACDNE model achieves the state-of-the-art performance in cross-network node classification.

Mining user behavior features is an essential part of recommender systems. As user preferences change dynamically, long-term interest features are very useful for predicting users' future behavior. Hence, the accuracy of temporal prediction will be greatly improved, if we can combine user behavior regularities with the item features. In this paper, we propose a long short-term memory (LSTM) variant, named Multi-type Feature Mining and Fusion (MFMF) model, to mine the long-term dynamic user behavior pattern and the potential relationships between items. We combine these features with user and item attributes to predict which items users will click next. Experiments on two real-world datasets, LastFM dataset and movie dataset, demonstrate the effectiveness of the proposed approach comparing to both traditional and state-of-the- art methods.

Domain adaptation is the situation for supervised learning in which the training data are sampled from the source domain while the test data are sampled from the target domain that follows a different distribution. The key to solving such a problem is to reduce effects of the discrepancy between the training data and test data. Recently, deep learning methods that employ stacked denoising auto-encoders (SDAs) to learn new representations for both domains have been successfully applied in domain adaptation. And, remarkable performance on multi-domain sentiment analysis datasets has been reported, making deep learning a promising approach to domain adaptation problems. In this paper, a deep learning method called Stacked Robust Adaptively Regularized Auto-regressions (SRARAs) is proposed to learn useful representations for domain adaptation problems. Each layer of SRARAs contains two steps: a linear transformation step, which is based on robust adaptively regularized auto-regression, and a non-linear squashing transformation step. The first step aims at reducing the discrepancy between the training data and test data, and the second step is to introduce non-linearity and control the range of the elements in the outputs. The experimental results on text and image datasets demonstrate that the proposed method is very effective.

With the availability of abundant online multi-relational video information, recommender systems that can effectively exploit these sorts of data and suggest creatively interesting items will become increasingly important. Recent research illustrates that tensor models offer effective approaches for complex multi-relational data learning and missing element completion. So far, most tensor-based user clustering models have focused on the accuracy of recommendation. Given the dynamic nature of online media, recommendation in this setting is more challenging as it is difficult to capture the users’ dynamic topic distributions in sparse data settings as well as to identify unseen items as candidates of recommendation. Targeting at constructing a recommender system that can encourage more creativity, a deep Bayesian probabilistic tensor framework for tag and item recommendation is proposed. During the score ranking processes, a metric called Bayesian surprise is incorporated to increase the creativity of the recommended candidates. The new algorithm, called Deep Canonical PARAFAC Factorization (DCPF), is evaluated on both synthetic and large-scale real-world problems. An empirical study for video recommendation demonstrates the superiority of the proposed model and indicates that it can better capture the latent patterns of interactions and generates interesting recommendations based on creative tag combinations.

Deep architectures can now be well trained on massive labeled data. However, there exist many application scenarios where labeled data are sparse or absent. Domain adaptation and multi-task transfer learning provide attractive options when related labeled data or tasks are abundant from different domains. In this paper, a new graphical modeling approach to multi-layer factorization based domain adaptation is explored to address the scenarios that insufficient labeled data are available for supervised learning. A deep convolutional factorization based transfer learning (DCFTL) algorithm is proposed to facilitate layer-wise transfer learning between domains. Completely based on graphical model representation, the proposed framework can seamlessly merge inference and learning, and has clear interpretability of conditional independence. The empirical performances on image classification tasks in both supervised and semi-supervised adaptation settings illustrate the effectiveness and generalization of the proposed deep layered knowledge transfer framework.

Recommendation for user generated content sites has gained significant attention nowadays. To satisfy the niche tastes of users, product recommendation poses more challenges due to the data sparsity issue. This work is motivated by a real world online video recommendation problem, where the click records database suffers from sparseness of video inventory and video tags. Targeting the long tail phenomena of user behavior and sparsity of item features, we propose a personalized compound recommendation framework for online video recommendation called Dirichlet mixture probit model for information scarcity (DPIS). Assuming that each record is generated from a representation of user preferences, DPIS is a probit classifier utilizing record topical clustering on the user part for recommendation. As demonstrated by the real-world application, the proposed DPIS achieves better performance than traditional methods.

It is now a fact as well as a trend that people are increasingly relying on online social networks to work, study, and share with others. Thus, it is unavoidable for us to be influenced by others through online social networking. Studying social influence and information diffusion in online social networks can be remarkably useful in various real-life applications, notably influencer marketing and viral marketing. The Topical Affinity Propagation (TAP) model has been demonstrated with success to analyze the social influence on topic level. It manages to identify the most influential nodes on a given topic in social networks successfully. While TAP mainly focuses on the topic factor, it considers little about the complex relationship between individuals, which is crucial in calculating the influence probabilities between nodes. In this paper, the idea of quantitatively estimating the peer influence probability from a social persuasion perspective in sociology is exploited and consequently a persuasion-driven social influence analysis model is presented. Based on the TAP model and the social persuasion influence propagation measures, both the topical information and the persuasion influences between individuals are taken into consideration such that a social persuasion-driven influence analysis model is proposed. The experimental results on different data sets show that the social influences on a given topic can be discovered effectively by the proposed approach, especially under consideration of authority, the accuracy in identifying the most influential nodes can be significantly improved as compared with an existing work.

Computational creativity, as an emerging domain of application, emphasizes the use of big data to automatically design new knowledge. Based on the availability of complex multi-relational data, one aspect of computational creativity is to infer unexplored regions of feature space and novel learning paradigm, which is particularly useful for online recommendation. Tensor models offer effective approaches for complex multi-relational data learning and missing element completion. Targeting at constructing a recommender system that can compromise between accuracy and creativity for users, a deep Bayesian probabilistic tensor framework for tag and item recommending is adopted. Empirical results demonstrate the superiority of the proposed method and indicate that it can better capture latent patterns of interaction relationships and generate interesting recommendations based on creative tag combinations.