Heterogeneous social networks, which are characterized by diverse interaction types, have resulted in new challenges for missing link prediction. Most deep learning models tend to capture type-specific features to maximize the prediction performances on specific link types. However, the types of missing links are uncertain in heterogeneous social networks; this restricts the prediction performances of existing deep learning models. To address this issue, we propose a multi-type transferable method ( MTTM ) for missing link prediction in heterogeneous social networks, which exploits adversarial neural networks to remain robust against type differences. It comprises a generative predictor and a discriminative classifier. The generative predictor can extract link representations and predict whether the unobserved link is a missing link. To generalize well for different link types to improve the prediction performance, it attempts to deceive the discriminative classifier by learning transferable feature representations among link types. In order not to be deceived, the discriminative classifier attempts to accurately distinguish link types, which indirectly helps the generative predictor judge whether the learned feature representations are transferable among link types. Finally, the integrated MTTM is constructed on this minimax two-player game between the generative predictor and discriminative classifier to predict missing links based on transferable feature representations among link types. Extensive experiments show that the proposed MTTM can outperform state-of-the-art baselines for missing link prediction in heterogeneous social networks.

Community partition is of great importance in social networks because of the rapid increasing network scale, data and applications. We consider the community partition problem under Linear Threshold (LT) model in social networks, which is a combinatorial optimization problem that divides the social network to disjoint $m$ communities. Our goal is to maximize the sum of influence propagation within each community. As the influence propagation function of community partition problem is supermodular under LT model, we use the method of Lov ${\acute{a}}$ sz Extension to relax the target influence function and transfer our goal to maximize the relaxed function over a matroid polytope. Next, we propose a continuous greedy algorithm using the properties of the relaxed function to solve our problem, which needs to be discretized in concrete implementation. Then, random rounding technique is used to convert the fractional solution to the integer solution. We present a theoretical analysis with $1-1/e$ approximation ratio for the proposed algorithms. Extensive experiments are conducted to evaluate the performance of the proposed continuous greedy algorithms on real-world online social networks datasets. The results demonstrate that continuous community partition method can improve influence spread and accuracy of the community partition effectively.

Community partition is an important problem in many areas, such as biology networks and social networks. The objective of this problem is to analyze the relationships among data via the network topology. In this article, we consider the community partition problem under the independent cascade (IC) model in social networks. We formulate the problem as a combinatorial optimization problem that aims at partitioning a given social network into disjoint m communities. The objective is to maximize the sum of influence propagation of a social network through maximizing it within each community. The existing work shows that the influence maximization for community partition problem (IMCPP) is NP-hard. We first prove that the objective function of IMCPP under the IC model is neither submodular nor supermodular. Then, both supermodular upper bound and submodular lower bound are constructed and proved so that the sandwich framework can be applied. A continuous greedy algorithm and a discrete implementation are devised for upper and lower bound problems. The algorithm for both of the two problems gets a 1-1/e approximation ratio. We also present a simple greedy algorithm to solve the original objective function and apply the sandwich approximation framework to it to guarantee a data-dependent approximation factor. Finally, our algorithms are evaluated on three real datasets, which clearly verifies the effectiveness of our method in the community partition problem, as well as the advantage of our method against the other methods.

Temporal sentence grounding (TSG) aims to locate a semantically related segment of an untrimmed video guided by a sentence query. Since the untrimmed videos are too long, almost all existing TSG works first sparsely down-sample each video into a shorter video of a fixed length and then conduct multimodal interactions with the query sentence for reasoning. However, this video down-sampling process may introduce a challenging issue that confuses the latter grounding process: Due to the video down-sampling, some query-related frames may be filtered out; this process may remove the specific boundary frames of the target segment and take the adjacent irrelevant frames as new boundaries, easily leading to cross-modal misalignment and introducing both boundary-bias and reasoning-bias. Therefore, it is important to keep the grounding consistency (both temporal annotations and boundary predictions) between the original and the sampled videos. To this end, in this paper, we propose a novel Conditional Video Diffusion Network (CVDN) for TSG to learn extra visual semantics to enrich and refine the biased new boundaries, which enables soft-label boundary prediction for fine-grained frame-query reasoning. Specifically, we first construct a conditional video diffusion model which is separately trained to recover the consecutive semantics of the filtered frames between the adjacent sampled frames. Through the designed stochastic interval sampling strategies in the training process, this diffusion model is able to generate absent coherent semantics between the sparsely sampled frames and in turn enrich and refine them, benefiting the integral activity understanding for TSG. In this manner, the incorrect new boundaries will be refined to be closely correlated to the original boundary frames and contain sufficient query-related information, which is crucial for accurate segment prediction. Extensive experiments on three challenging datasets demonstrate the effectiveness of CVDN.

Recently dynamic social networks witnessed a massive surge in popularity, especially in the area of anomaly detection. Although the text-based methods have achieved impressive detection performances, their applications are limited to the social text provided by users. This research focuses on graph-based methods and proposes a universal method for generalized social networks. Different from the existing graph-based methods that summarize a number of structural features, the proposed nodes' evolution diversity inspired method (NEDM) detects anomalies in dynamic social networks from the perspective of diverse evolution mechanisms. More specifically, NEDM applies link prediction algorithms at the micro-level to fit evolution mechanisms followed by the behaviors of nodes, and designs indices to evaluate their fitting degrees in edge removal and generation processes. In addition, the behavior of a node is represented as a quantum superposition state where such behavior follows different evolution mechanisms with uncertain probabilities. We propose a quantum mechanism based particle swarm optimization algorithm (QMPSO) in NEDM. QMPSO determines the optimal observation states of the behaviors of different nodes, and maximally reflects the evolutional fluctuations in the evolution processes of social networks. As a result, NEDM can quantify the evolutional fluctuations in different periods, and detect anomalies in dynamic social networks. Comparing with art-of-the-state methods and real social data in extensive experiments on disparate real-world social networks, we verify the outstanding performance of NEDM in terms of both accuracy and universality.