Identifying vital nodes is a significant issue for the study of network robustness, epidemic controlling and targeted destruction of networks. Previous studies on weak ties theory recovered that ties with weak strength usually act as the important bridges that connect different clusters and play important role in maintaining the network connectivity. In this paper, we quantify the strength of links based on local information of the network topology, and design a simple yet effective method to evaluate nodes' importance in terms of the number of their connections and overlap of their neighbors. Experimental analyses on synthetic and real networks demonstrate that the proposed algorithm identifies vital nodes leading to faster network collapse in target destruction than some well-known methods.

The topic of community detection in social networks has attracted a lot of attention in recent years. Existing methods always depict the relationship of two nodes using the snapshot of the network, but these snapshots cannot reveal the real relationships, especially when the connection history among nodes is considered. The problem of detecting the stable community in mobile social networks has been studied in this paper. Community cores are considered as stable subsets of the network in previous work. Based on these observations, this paper divides all nodes into a few of communities due to the community cores. Meanwhile, communities can be tracked through incremental computing. Experimental results based on real-world social networks demonstrate that our proposed method performs better than the well-known static community detection algorithm in mobile social networks.

Key node identification is one of the most fundamental and significant problems in complex network research. This article presents a novel approach called information-theory-based centrality $C_{H}$ to distinguish influential nodes in complex networks. From an information-theoretic perspective, nodes involved in many information channels will improve the quality of communication. Thus, the greater the number of information channels a node participates, the more the importance of this node during information transmission. With this motivation, the local and global connectivity are measured according to the resistance distance, which captures the characteristic that multiple available routes reduce the resistance of information transmission on networks. We further model the probability of information diffusion according to the local and global connectivity and put forward an information-theory-based centrality to identify influential nodes. Finally, extensive evaluations are implemented on real-world networks to verify the feasibility and effectiveness of the proposed method. According to the results, our proposed method outperforms classical methods in identifying influential nodes and also indicates the potential for analyzing the influence evolution of networks, which shows a positive and effective impact on locating influencers and predicting potential key players in the future.

Open domain relation prediction is an important task in triples extraction. When faced with the task of constructing large-scale knowledge graph systems, with the exception of structured data, it is necessary to automatically extract triples from a large amount of unstructured text to expand entities and relations. Although a large number of English open relation prediction methods have achieved good performance, the high-performance system for open domain Chinese triples extraction remains undeveloped due to the lack of large-scale Chinese annotation corpora and the difficulty of Chinese language processing. In this paper, we propose an integrated open domain Chinese triples hierarchical extraction method (CTHE) to solve this problem, considering the advantages of Bi-LSTM-CRF and Att-Bi-GRU models based on the pre-trained BERT encoding model. This method can recognize the named entities from Chinese sentences to establish entity pairs, and implement hierarchical extraction of specific and open relations based on the user-defined schema library and attention mechanism. The experimental results demonstrate the effectiveness of this method, which achieved stable performance on the test dataset, and better precision and F1-score in comparison with state-of-the-art Chinese open domain triples extraction methods. Furthermore, a large-scale annotated dataset for a Chinese named entity recognition (NER) task is established, which provides support for research on Chinese NER tasks.

Event argument extraction is a crucial subtask of event extraction, which aims at extracting arguments that correspond to argument roles when given event types. The majority of current document-level event argument extraction works focus on extracting information for only one event at a time without considering the association among events; this is known as document-level single-event extraction. However, the interrelationship among arguments can yield mutual gains in their extraction. Therefore, in this paper, we propose AssocKD, an Association-aware Knowledge Distillation Method for Document-level Event Argument Extraction, which enables the enhancement of document-level multi-event extraction with event association knowledge. Firstly, we introduce an association-aware training task to extract unknown arguments with the given privileged knowledge of relevant arguments, obtaining an association-aware model that can construct both intra-event and inter-event relationships. Secondly, we adopt multi-teacher knowledge distillation to transfer such event association knowledge from the association-aware teacher models to the event argument extraction student model. Our proposed method, AssocKD, is capable of explicitly modeling and efficiently leveraging event association to enhance the extraction of multi-event arguments at the document level. We conduct experiments on RAMS and WIKIEVENTS datasets and observe a significant improvement, thus demonstrating the effectiveness of our method.

Multimedia event extraction aims to jointly extract event structural knowledge from multiple modalities, thus improving the comprehension and utilization of events in the growing multimedia content (e.g., multimedia news). A key challenge in multimedia event extraction is to establish cross-modal correlations during training without multimedia event annotations. Considering the complexity and cost of annotation across modalities, the multimedia event extraction task only provides parallel annotated data for evaluation. Previous works attempt to learn implicit correlations directly from unlabeled image-text pairs, but do not yield substantially better performance for event-centric tasks. To address this problem, we propose a cross-modal multi-task learning framework X-MTL to establish cross-modal correlations at the task level, which can simultaneously address four key tasks of multimedia event extraction: trigger detection, argument extraction, verb classification, and role classification. Specifically, to process inputs from different modalities and tasks, we utilize two separate modality-specific encoders and a modality-shared encoder to learn joint task representations, and introduce textual and visual prompt learning methods to enrich and unify task inputs. To resolve task conflict in cross-modal multi-task learning, we propose a pseudo label based knowledge distillation method, combined with dynamic weight adjustment method, which can effectively lift the performance to surpass the separately-trained models. On the Multimedia Event Extraction benchmark M2E2, experimental results show that X-MTL surpasses the current state-of-the-art (SOTA) methods by 4.1% for multimedia event mention and 8.2% for multimedia argument role.