Wenping Chen

Influence maximization has recently gained substantial attention as a crucial aspect of scheduling online campaigns and advertisements on social network platforms. While existing methods have primarily focused on targeting influence, they tend to face challenges when dealing with frequent requests for different targeted advertisement instances. This results in a significant computational overhead when handling each Targeted Influence Maximization (TIM) instance separately. Motivated by this issue, we introduce a novel approach called the Pre-train and Fine-tune Framework. Our framework leverages prior data, specifically information from previously encountered TIM instances, to pre-train an initial solution set that can be rapidly adapted to new TIM instances with relatively low computational costs. This approach enables the generation of personalized solutions for each TIM instance, substantially reducing computational expenses when compared to optimizing the solution from scratch for every new TIM instance. The pre-training process involves solving a challenging discrete optimization problem, for which we introduce deterministic and probabilistic algorithms. Through extensive experiments conducted on real-world social networks, we demonstrate the effectiveness and efficiency of our proposed algorithms.

Live video commenting is popular on video media platforms, as it can create a chatting atmosphere and provide supplementary information for users while watching videos. Automatically generating live video comments can improve user experience and enable human-like generation for bot chatting. Existing works mostly focus on short video datasets while ignoring other important video types such as long videos like movies. In this work, we collect a new Movie Live Comments (MovieLC) dataset to support research on live video comment generation for long videos. We also propose a knowledge enhanced generation model inspired by the divergent and informative nature of live video comments. Our model adopts a pre-training encoder-decoder framework and incorporates external knowledge. Extensive experiments show that both objective metrics and human evaluation demonstrate the effectiveness of our proposed model. The MovieLC dataset and our code will be released.

Determining whether nodes can be uniquely localized, called localizability detection, is a concomitant problem in network localization. Localizability detection under the traditional Non-Linear Localization (NLL) schema has been well explored, whereas localizability under the emerging Barycentric coordinate-based Linear Localization (BLL) schema has not been well investigated. Non-awareness of the node localizability in BLL may cause theoretically localizable nodes to converge to wrong locations because their locations are impacted by the wrong locations of the unlocalizable nodes through the iterative location propagation. In this article, the deficiency of existing localizability theories and algorithms in BLL is firstly investigated and then a necessary condition and a sufficient condition for BLL node localizability detection are proposed. Based on these two conditions, an efficient Iterative Maximum Flow (IMF) algorithm is designed to identify BLL localizable nodes, and only localizable nodes are selected to enable a Localizability Aware Barycentric Linear Localization (LABLL) algorithm, which can guarantee the locations of the localizable nodes converging correctly. The proposed IMF and LABLL algorithms are validated by both theoretical analysis and experimental evaluations.

The barycentric linear localization (BLL) methods provide a lightweight, distributed way to calculate locations for resource-limited IoT devices. A crucial requirement for BLL is that the nodes participating in the iterative location propagation are localizable. Otherwise, the unlocalizable nodes will continuously pose error information in the location propagation process, making even the theoretically localizable nodes converge to the wrong locations. However, the research on node localizability in BLL is much lacked, greatly limiting the application scope of BLL. In specific, BLL node localizability is detected on a generated graph $\mathcal{G^A}$ . For any node, its neighbors appear in $\mathcal{G^A}$ only when the neighbors can form triangle(s), so that $\mathcal{G^A}$ is much sparser than the original $\mathcal G$ . Thus, the node localizability condition in BLL is harder to be satisfied than that in traditional localization methods. Moreover, the distributed algorithm to detect BLL localizable nodes is still open. This paper thoroughly investigates the node localizability conditions and distributed localizable node detection algorithms in BLL. At first, an efficient and fully distributed Negative Edge Inference (NEI) algorithm is proposed for each node to infer implicit edges in its neighborhood. NEI strengthens the distance graph by revealing more distance constraints so that enables more neighboring triangles. Then a new sufficient condition, i.e., the recursive three disjoint path condition (Recursive-3DP) on the strengthened distance graph is proposed to identify BLL localizable nodes much more accurately. Secondly, a distributed Path Extension and Pruning (PEP) algorithm is proposed for distributed localizable node detection. PEP is proved to detect all the theoretically Recursive-3DP nodes in the strengthened distance graph. A Fast-PEP algorithm is further proposed, which misses very limited Recursive-3DP nodes while bringing significant improvement in efficiency. PEP and Fast-PEP guarantee to identify BLL localizable nodes in $2H$ rounds, where $H$ is the maximum hop number of the node disjoint paths. Finally, by using NEI and PEP (Fast-PEP), a localizability-aware BLL (LABEL) method is proposed, which correctly identifies localizable nodes and guarantees their correct location convergence. Extensive analysis and experiments show the advantages in localizability and location accuracy of the proposed schemes over the state-of-the-art methods.