Catálogo de publicaciones - revistas

<jats:title>Abstract</jats:title><jats:p>Nowadays recording and sharing personal lives using mobile devices on the Internet is becoming increasingly popular, and successive POI recommendation is gaining growing attention from academia and industry. In mobile scenarios, multiple influencing factors including the diversity of user preferences, the changeability of user behavior and the dynamic of spatiotemporal context bring great challenges to the POI recommender system. In order to accurately capture both the stable and the contextual preferences of mobile users in dynamic contexts, we propose a fusion framework JANICP (Joint Attention Networks with Inherent and Contextual Preferences) for successive POI recommendation by jointly training an offline/nearline user inherent interest perception model and an online user contextual interest prediction model. The offline model is trained based on the global historical behavior data to achieve stable interest representation, while the online model is trained based on the instantly selected context-sensitive data to achieve dynamic interest perception. An attention aggregation and matching module is used to fully connect the two kinds of preference representations and generate the final POI recommendation. Extensive experiments were conducted on three real datasets and experimental results show that the proposed JANICP outperforms existing state-of-the-art methods.</jats:p>

<jats:title>Abstract</jats:title><jats:p>Visual question answering is a complex multimodal task involving images and text, with broad application prospects in human–computer interaction and medical assistance. Therefore, how to deal with the feature interaction and multimodal feature fusion between the critical regions in the image and the keywords in the question is an important issue. To this end, we propose a neural network based on the encoder–decoder structure of the transformer architecture. Specifically, in the encoder, we use multi-head self-attention to mine word–word connections within question features and stack multiple layers of attention to obtain multi-level question features. We propose a mutual attention module to perform information exchange between modalities for better question features and image features representation on the decoder side. Besides, we connect the encoder and decoder in a meshed manner, perform mutual attention operations with multi-level question features, and aggregate information in an adaptive way. We propose a multi-scale fusion module in the fusion stage, which utilizes feature information at different scales to complete modal fusion. We test and validate the model effectiveness on VQA v1 and VQA v2 datasets. Our model achieves better results than state-of-the-art methods.</jats:p>

<jats:title>Abstract</jats:title><jats:p>Large-scale distributed training mainly consists of sub-model parallel training and parameter synchronization. With the expansion of training workers, the efficiency of parameter synchronization will be affected. To tackle this problem, we first propose 2D-TGA, a <jats:bold>g</jats:bold>rouping <jats:bold>A</jats:bold>llReduce method based on the two-dimensional <jats:bold>t</jats:bold>orus topology. This method synchronizes the model parameters by grouping and makes full use of bandwidth. Secondly, we propose a distributed algorithm, 2D-TGA-ADMM, which combines the 2D-TGA with the alternating direction method of multipliers (ADMM). It focuses on sub-model training and reduces the wait time among workers in the synchronization process. Finally, experimental results on the Tianhe-2 supercomputing platform show that compared with the <jats:inline-formula><jats:alternatives><jats:tex-math>$${\mathtt {MPI\_Allreduce}}$$</jats:tex-math><mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mi>MPI</mml:mi> <mml:mi>_</mml:mi> <mml:mi>Allreduce</mml:mi> </mml:mrow> </mml:math></jats:alternatives></jats:inline-formula>, the 2D-TGA could shorten the synchronization wait time by <jats:inline-formula><jats:alternatives><jats:tex-math>$$33\%$$</jats:tex-math><mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mn>33</mml:mn> <mml:mo>%</mml:mo> </mml:mrow> </mml:math></jats:alternatives></jats:inline-formula>.</jats:p>

<jats:title>Abstract</jats:title><jats:p>In recent years, Coronavirus disease 2019 (COVID-19) has become a global epidemic, and some efforts have been devoted to tracking and controlling its spread. Extracting structured knowledge from involved epidemic case reports can inform the surveillance system, which is important for controlling the spread of outbreaks. Therefore, in this paper, we focus on the task of Chinese epidemic event extraction (EE), which is defined as the detection of epidemic-related events and corresponding arguments in the texts of epidemic case reports. To facilitate the research of this task, we first define the epidemic-related event types and argument roles. Then we manually annotate a Chinese COVID-19 epidemic dataset, named COVID-19 Case Report (CCR). We also propose a novel hierarchical EE architecture, named <jats:italic>m</jats:italic>ulti-model <jats:italic>f</jats:italic>usion-based <jats:italic>h</jats:italic>ierarchical <jats:italic>e</jats:italic>vent <jats:italic>e</jats:italic>xtraction (MFHEE). In MFHEE, we introduce a multi-model fusion strategy to tackle the issue of recognition bias of previous EE models. The experimental results on CCR dataset show that our method can effectively extract epidemic events and outperforms other baselines on this dataset. The comparative experiments results on other generic datasets show that our method has good scalability and portability. The ablation studies also show that the proposed hierarchical structure and multi-model fusion strategy contribute to the precision of our model.</jats:p>

<jats:title>Abstract</jats:title><jats:p>Currently, most researchers only utilize the network information or node characteristics to calculate the connection probability between unconnected node pairs. Therefore, we attempt to project the problem of connection probability between unconnected pairs into the physical space calculating it. Firstly, the definition of gravitation is introduced in this paper, and the concept of gravitation is used to measure the strength of the relationship between nodes in complex networks. It is generally known that the gravitational value is related to the mass of objects and the distance between objects. In complex networks, the interrelationship between nodes is related to the characteristics, degree, betweenness, and importance of the nodes themselves, as well as the distance between nodes, which is very similar to the gravitational relationship between objects. Therefore, the importance of nodes is used to measure the mass property in the universal gravitational equation and the similarity between nodes is used to measure the distance property in the universal gravitational equation, and then a complex network model is constructed from physical space. Secondly, the direct and indirect gravitational values between nodes are considered, and a novel link prediction framework based on the gravitational field, abbreviated as LPFGF, is proposed, as well as the node similarity framework equation. Then, the framework is extended to various link prediction algorithms such as Common Neighbors (CN), Adamic-Adar (AA), Preferential Attachment (PA), and Local Random Walk (LRW), resulting in the proposed link prediction algorithms LPFGF-CN, LPFGF-AA, LPFGF-PA, LPFGF-LRW, and so on. Finally, four real datasets are used to compare prediction performance, and the results demonstrate that the proposed algorithmic framework can successfully improve the prediction performance of other link prediction algorithms, with a maximum improvement of 15%.</jats:p>

<jats:title>Abstract</jats:title><jats:p>With the rapid development of social networks, academic social networks have attracted increasing attention. In particular, providing personalized recommendations for learners considering data sparseness and cold-start scenarios is a challenging task. An important research topic is to accurately discover potential friends of learners to build implicit learning groups and obtain personalized collaborative recommendations of similar learners according to the learning content. This paper proposes a personalized explainable learner implicit friend recommendation method (PELIRM). Methodologically, PELIRM utilizes the learner's multidimensional interaction behavior in social networks to calculate the degrees of trust between learners and applies the three-degree influence theory to mine the implicit friends of learners. The similarity of research interests between learners is calculated by cosine and term frequency–inverse document frequency. To solve the recommendation problem for cold-start learners, the learner's common check-in IP is used to obtain the learner's location information. Finally, the degree of trust, similarity of research interests, and geographic distance between learners are combined as ranking indicators to recommend potential friends for learners and give multiple interpretations of the recommendation results. By verifying and evaluating the proposed method on real data from Scholar.com, the experimental results show that the proposed method is reliable and effective in terms of personalized recommendation and explainability.</jats:p>

<jats:title>Abstract</jats:title><jats:p>Temporal heterogeneous graphs can model lots of complex systems in the real world, such as social networks and e-commerce applications, which are naturally time-varying and heterogeneous. As most existing graph representation learning methods cannot efficiently handle both of these characteristics, we propose a Transformer-like representation learning model, named THAN, to learn low-dimensional node embeddings preserving the topological structure features, heterogeneous semantics, and dynamic patterns of temporal heterogeneous graphs, simultaneously. Specifically, THAN first samples heterogeneous neighbors with temporal constraints and projects node features into the same vector space, then encodes time information and aggregates the neighborhood influence in different weights via type-aware self-attention. To capture long-term dependencies and evolutionary patterns, we design an optional memory module for storing and evolving dynamic node representations. Experiments on three real-world datasets demonstrate that THAN outperforms the state-of-the-arts in terms of effectiveness with respect to the temporal link prediction task.</jats:p>

<jats:title>Abstract</jats:title><jats:p>We study the problem of multimodal embedding-based entity alignment (EA) between different knowledge graphs. Recent works have attempted to incorporate images (visual context) to address EA in a multimodal view. While the benefits of multimodal information have been observed, its negative impacts are non-negligible as injecting images without constraints brings much noise. It also remains unknown under what circumstances or to what extent visual context is truly helpful to the task. In this work, we propose to learn entity representations from graph structures and visual context, and combine feature similarities to find alignments at the output level. On top of this, we explore a mechanism which utilizes classification techniques and entity types to remove potentially un-helpful images (visual noises) during alignment learning and inference. We conduct extensive experiments to examine this mechanism and provide thorough analysis about impacts of the visual modality on EA.</jats:p>

<jats:title>Abstract</jats:title><jats:p>The ever-increasing number of systems based on semantic text analysis is making natural language understanding a fundamental task: embedding-based language models are used for a variety of applications, such as resume parsing or improving web search results. At the same time, despite their popularity and widespread use, concern is rapidly growing due to their display of social bias and lack of transparency. In particular, they exhibit a large amount of gender bias, favouring the consolidation of social stereotypes. Recently, sentence embeddings have been introduced as a novel and powerful technique to represent entire sentences as vectors. We propose a new metric to estimate gender bias in sentence embeddings, named <jats:italic>bias score</jats:italic>. Our solution leverages semantic importance of words and previous research on bias in word embeddings, and it is able to discern between neutral and biased gender information at sentence level. Experiments on a real-world dataset demonstrate that our novel metric can identify gender stereotyped sentences. Furthermore, we employ <jats:italic>bias score</jats:italic> to detect and then remove or compensate for the more stereotyped entries in text corpora used to train sentence encoders, improving their degree of fairness. Finally, we prove that models retrained on fairer corpora are less prone to make stereotypical associations compared to their original counterpart, while preserving accuracy in natural language understanding tasks. Additionally, we compare our experiments with traditional methods for reducing bias in embedding-based language models.</jats:p>

<jats:title>Abstract</jats:title><jats:p>The success of blockchain technology in cryptocurrencies reveals its potential in the data management field. Recently, there is a trend in the database community to integrate blockchains and traditional databases to obtain security, efficiency, and privacy from the two distinctive but related systems. In this survey, we discuss the use of blockchain technology in the data management field and focus on the fusion system of blockchains and databases. We first classify existing blockchain-related data management technologies by their locations on the blockchain-database spectrum. Based on the taxonomy, we discuss three types of fusion systems and analyze their design spaces and trade-offs. Then, by further investigating the typical systems and techniques of each type of fusion system and comparing the solutions, we provide insights of each fusion model. Finally, we outline the unsolved challenges and promising directions in this field and believe that fusion systems will take a more important role in data management tasks. We hope this survey can help both academia and industry to better understand the advantages and limitations of blockchain-related data management systems and develop fusion systems that meet various requirements in practice.</jats:p>