首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献，搜索用时 15 毫秒
1.
Nowadays, signed network has become an important research topic because it can reflect more complex relationships in reality than traditional network, especially in social networks. However, most signed network methods that achieve excellent performance through structure information learning always neglect neutral links, which have unique information in social networks. At the same time, previous approach for neutral links cannot utilize the graph structure information, which has been proved to be useful in node embedding field. Thus, in this paper, we proposed the Signed Graph Convolutional Network with Neutral Links (NL-SGCN) to address the structure information learning problem of neutral links in signed network, which shed new insight on signed network embedding. In NL-SGCN, we learn two representations for each node in each layer from both inner character and outward attitude aspects and propagate their information by balance theory. Among these three types of links, information of neutral links will be limited propagated by the learned coefficient matrix. To verify the performance of the proposed model, we choose several classical datasets in this field to perform empirical experiment. The experimental result shows that NL-SGCN significantly outperforms the existing state-of-the-art baseline methods for link prediction in signed network with neutral links, which supports the efficacy of structure information learning in neutral links.  相似文献   

2.
Graph convolutional network (GCN) is a powerful tool to process the graph data and has achieved satisfactory performance in the task of node classification. In general, GCN uses a fixed graph to guide the graph convolutional operation. However, the fixed graph from the original feature space may contain noises or outliers, which may degrade the effectiveness of GCN. To address this issue, in this paper, we propose a robust graph learning convolutional network (RGLCN). Specifically, we design a robust graph learning model based on the sparse constraint and strong connectivity constraint to achieve the smoothness of the graph learning. In addition, we introduce graph learning model into GCN to explore the representative information, aiming to learning a high-quality graph for the downstream task. Experiments on citation network datasets show that the proposed RGLCN outperforms the existing comparison methods with respect to the task of node classification.  相似文献   

3.
Learning latent representations for users and points of interests (POIs) is an important task in location-based social networks (LBSN), which could largely benefit multiple location-based services, such as POI recommendation and social link prediction. Many contextual factors, like geographical influence, user social relationship and temporal information, are available in LBSN and would be useful for this task. However, incorporating all these contextual factors for user and POI representation learning in LBSN remains challenging, due to their heterogeneous nature. Although the encouraging performance of POI recommendation and social link prediction are delivered, most of the existing representation learning methods for LBSN incorporate only one or two of these contextual factors. In this paper, we propose a novel joint representation learning framework for users and POIs in LBSN, named UP2VEC. In UP2VEC, we present a heterogeneous LBSN graph to incorporate all these aforementioned factors. Specifically, the transition probabilities between nodes inside the heterogeneous graph are derived by jointly considering these contextual factors. The latent representations of users and POIs are then learnt by matching the topological structure of the heterogeneous graph. For evaluating the effectiveness of UP2VEC, a series of experiments are conducted with two real-world datasets (Foursquare and Gowalla) in terms of POI recommendation and social link prediction. Experimental results demonstrate that the proposed UP2VEC significantly outperforms the existing state-of-the-art alternatives. Further experiment shows the superiority of UP2VEC in handling cold-start problem for POI recommendation.  相似文献   

4.
Graph neural networks (GNN) have emerged as a new state-of-the-art for learning knowledge graph representations. Although they have shown impressive performance in recent studies, how to efficiently and effectively aggregate neighboring features is not well designed. To tackle this challenge, we propose the simplifying heterogeneous graph neural network (SHGNet), a generic framework that discards the two standard operations in GNN, including the transformation matrix and nonlinear activation. SHGNet, in particular, adopts only the essential component of neighborhood aggregation in GNN and incorporates relation features into feature propagation. Furthermore, to capture complex structures, SHGNet utilizes a hierarchical aggregation architecture, including node aggregation and relation weighting. Thus, the proposed model can treat each relation differently and selectively aggregate informative features. SHGNet has been evaluated for link prediction tasks on three real-world benchmark datasets. The experimental results show that SHGNet significantly promotes efficiency while maintaining superior performance, outperforming all the existing models in 3 out of 4 metrics on NELL-995 and in 4 out of 4 metrics on FB15k-237 dataset.  相似文献   

5.
As a prevalent problem in online advertising, CTR prediction has attracted plentiful attention from both academia and industry. Recent studies have been reported to establish CTR prediction models in the graph neural networks (GNNs) framework. However, most of GNNs-based models handle feature interactions in a complete graph, while ignoring causal relationships among features, which results in a huge drop in the performance on out-of-distribution data. This paper is dedicated to developing a causality-based CTR prediction model in the GNNs framework (Causal-GNN) integrating representations of feature graph, user graph and ad graph in the context of online advertising. In our model, a structured representation learning method (GraphFwFM) is designed to capture high-order representations on feature graph based on causal discovery among field features in gated graph neural networks (GGNNs), and GraphSAGE is employed to obtain graph representations of users and ads. Experiments conducted on three public datasets demonstrate the superiority of Causal-GNN in AUC and Logloss and the effectiveness of GraphFwFM in capturing high-order representations on causal feature graph.  相似文献   

6.
As an emerging task in opinion mining, End-to-End Multimodal Aspect-Based Sentiment Analysis (MABSA) aims to extract all the aspect-sentiment pairs mentioned in a pair of sentence and image. Most existing methods of MABSA do not explicitly incorporate aspect and sentiment information in their textual and visual representations and fail to consider the different contributions of visual representations to each word or aspect in the text. To tackle these limitations, we propose a multi-task learning framework named Cross-Modal Multitask Transformer (CMMT), which incorporates two auxiliary tasks to learn the aspect/sentiment-aware intra-modal representations and introduces a Text-Guided Cross-Modal Interaction Module to dynamically control the contributions of the visual information to the representation of each word in the inter-modal interaction. Experimental results demonstrate that CMMT consistently outperforms the state-of-the-art approach JML by 3.1, 3.3, and 4.1 absolute percentage points on three Twitter datasets for the End-to-End MABSA task, respectively. Moreover, further analysis shows that CMMT is superior to comparison systems in both aspect extraction (AE) and sentiment classification (SC), which would move the development of multimodal AE and SC algorithms forward with improved performance.  相似文献   

7.
Text classification is an important research topic in natural language processing (NLP), and Graph Neural Networks (GNNs) have recently been applied in this task. However, in existing graph-based models, text graphs constructed by rules are not real graph data and introduce massive noise. More importantly, for fixed corpus-level graph structure, these models cannot sufficiently exploit the labeled and unlabeled information of nodes. Meanwhile, contrastive learning has been developed as an effective method in graph domain to fully utilize the information of nodes. Therefore, we propose a new graph-based model for text classification named CGA2TC, which introduces contrastive learning with an adaptive augmentation strategy into obtaining more robust node representation. First, we explore word co-occurrence and document word relationships to construct a text graph. Then, we design an adaptive augmentation strategy for the text graph with noise to generate two contrastive views that effectively solve the noise problem and preserve essential structure. Specifically, we design noise-based and centrality-based augmentation strategies on the topological structure of text graph to disturb the unimportant connections and thus highlight the relatively important edges. As for the labeled nodes, we take the nodes with same label as multiple positive samples and assign them to anchor node, while we employ consistency training on unlabeled nodes to constrain model predictions. Finally, to reduce the resource consumption of contrastive learning, we adopt a random sample method to select some nodes to calculate contrastive loss. The experimental results on several benchmark datasets can demonstrate the effectiveness of CGA2TC on the text classification task.  相似文献   

8.
Transfer learning utilizes labeled data available from some related domain (source domain) for achieving effective knowledge transformation to the target domain. However, most state-of-the-art cross-domain classification methods treat documents as plain text and ignore the hyperlink (or citation) relationship existing among the documents. In this paper, we propose a novel cross-domain document classification approach called Link-Bridged Topic model (LBT). LBT consists of two key steps. Firstly, LBT utilizes an auxiliary link network to discover the direct or indirect co-citation relationship among documents by embedding the background knowledge into a graph kernel. The mined co-citation relationship is leveraged to bridge the gap across different domains. Secondly, LBT simultaneously combines the content information and link structures into a unified latent topic model. The model is based on an assumption that the documents of source and target domains share some common topics from the point of view of both content information and link structure. By mapping both domains data into the latent topic spaces, LBT encodes the knowledge about domain commonality and difference as the shared topics with associated differential probabilities. The learned latent topics must be consistent with the source and target data, as well as content and link statistics. Then the shared topics act as the bridge to facilitate knowledge transfer from the source to the target domains. Experiments on different types of datasets show that our algorithm significantly improves the generalization performance of cross-domain document classification.  相似文献   

9.
Knowledge graphs are sizeable graph-structured knowledge with both abstract and concrete concepts in the form of entities and relations. Recently, convolutional neural networks have achieved outstanding results for more expressive representations of knowledge graphs. However, existing deep learning-based models exploit semantic information from single-level feature interaction, potentially limiting expressiveness. We propose a knowledge graph embedding model with an attention-based high-low level features interaction convolutional network called ConvHLE to alleviate this issue. This model effectively harvests richer semantic information and generates more expressive representations. Concretely, the multilayer convolutional neural network is utilized to fuse high-low level features. Then, features in fused feature maps interact with other informative neighbors through the criss-cross attention mechanism, which expands the receptive fields and boosts the quality of interactions. Finally, a plausibility score function is proposed for the evaluation of our model. The performance of ConvHLE is experimentally investigated on six benchmark datasets with individual characteristics. Extensive experimental results prove that ConvHLE learns more expressive and discriminative feature representations and has outperformed other state-of-the-art baselines over most metrics when addressing link prediction tasks. Comparing MRR and Hits@1 on FB15K-237, our model outperforms the baseline ConvE by 13.5% and 16.0%, respectively.  相似文献   

10.
Previous studies have confirmed that citation mention and location reveal different contributions of the cited articles, and that both are significant in scientific research evaluation. However, traditional citation count prediction only focuses on predicting citation frequency. In this paper, we propose a novel fine-grained citation count prediction task (FGCCP), which aims to predict in-text citation count from each structural function of a paper separately. Specifically, we treated this task as a “sequence to sequence” issue and a multi-task learning job, in which both the inputs and the outputs are based on the sequence pattern of citations from different structural functions. To fulfill FGCCP, we proposed a transformer-based model (i.e. MTAT) in which a novel among-attention mechanism is employed. Based on an empirical study of full-text documents from PubMed Central Open Access Subset, our model achieves satisfactory prediction accuracy, and surpasses common machine learning and deep learning models on FGCCP. Moreover, we also discuss the potential role of the among-attention mechanism and the reason why our proposed model outperforms state-of-the-art strategies. FGCCP may provide more detailed decision-making evidence and evaluation basis for researchers in scientific research evaluation. In addition, MTAT is a general model which can be easily deployed in other multi-task learning jobs.  相似文献   

11.
文本分类是处理和组织大量文本数据的关键技术之一。为了更加有效地实现文本分类,本文提出了一种基于图模型的文本特征提取方法。该方法利用类别信息在训练数据集上构造邻接带权图及其补图,使得属于同一个类别的样本点的投影尽可能近,不属于同一个类别的样本点的投影尽可能远。这种方法既能够获得文本空间的全局结构信息又可以保留局部结构信息。最后,采用K近邻分类器在20Newsgroups标准数据集上进行训练和测试,并且与基于潜在语义索引的文本分类方法做了比较,文本分类的性能得到很大提高。实验结果表明,本文所提出的方法能够有效地提高文本分类的性能。  相似文献   

12.
Recently, phishing scams have become one of the most serious types of crime involved in Ethereum, the second-largest blockchain-based cryptocurrency platform. The existing phishing scams detection techniques for Ethereum mostly use traditional machine learning or network representation learning to mine the key information from the transaction network and identify phishing addresses. However, these methods typically crop the temporal transaction graph into snapshot sequences or construct temporal random wanderings to model the dynamic evolution of the topology of the transaction graph. In this paper, we propose PDTGA, a method that applies graph representation learning based on temporal graphs attention to improve the effectiveness of phishing scams detection in Ethereum. Specifically, we learn the functional representation of time directly and model the time signal through the interactions between the time encoding function and node features, edge features, and the topology of the graph. We collected a real-world Ethereum phishing scam dataset, containing over 250,000 transaction records between more than 100,000 account addresses, and divided them into three datasets of different sizes. Through data analysis, we first summarized the periodic pattern of Ethereum phishing scam activities. Then we constructed 14 kinds of account node features and 3 kinds of transaction edge features. Experimental evaluations based on the above three datasets demonstrate that PDTGA with 94.78% AUC score and 88.76% recall score outperforms the state-of-the-art methods.  相似文献   

13.
张晓丹 《情报杂志》2021,(1):184-188
[目的/意义]随着互联网数字资源的剧增,如何从海量数据中挖掘出有价值的信息成为数据挖掘领域研究的热点问题。文本大数据分类是这一领域的关键问题之一。随着深度学习的发展,使得基于深度学习的文本大数据分类成为可能。[方法/过程]针对近年来出现的图神经网络文本分类效率低的问题,提出改进的方法。利用文本、句子及关键词构建拓扑关系图和拓扑关系矩阵,利用马尔科夫链采样算法对每一层的节点进行采样,再利用多级降维方法实现特征降维,最后采用归纳式推理的方式实现文本分类。[结果/结论]为了测试该文所提方法的性能,利用常用的公用语料库和自行构建的NSTL科技期刊文献语料库对本文提出的方法进行实验,与当前常用的文本分类模型进行准确率和推理时间的比较。实验结果表明,所提出的方法可在保证文本及文献大数据分类准确率的前提下,有效提高分类的效率。  相似文献   

14.
Deep multi-view clustering (MVC) is to mine and employ the complex relationships among views to learn the compact data clusters with deep neural networks in an unsupervised manner. The more recent deep contrastive learning (CL) methods have shown promising performance in MVC by learning cluster-oriented deep feature representations, which is realized by contrasting the positive and negative sample pairs. However, most existing deep contrastive MVC methods only focus on the one-side contrastive learning, such as feature-level or cluster-level contrast, failing to integrating the two sides together or bringing in more important aspects of contrast. Additionally, most of them work in a separate two-stage manner, i.e., first feature learning and then data clustering, failing to mutually benefit each other. To fix the above challenges, in this paper we propose a novel joint contrastive triple-learning framework to learn multi-view discriminative feature representation for deep clustering, which is threefold, i.e., feature-level alignment-oriented and commonality-oriented CL, and cluster-level consistency-oriented CL. The former two submodules aim to contrast the encoded feature representations of data samples in different feature levels, while the last contrasts the data samples in the cluster-level representations. Benefiting from the triple contrast, the more discriminative representations of views can be obtained. Meanwhile, a view weight learning module is designed to learn and exploit the quantitative complementary information across the learned discriminative features of each view. Thus, the contrastive triple-learning module, the view weight learning module and the data clustering module with these fused features are jointly performed, so that these modules are mutually beneficial. The extensive experiments on several challenging multi-view datasets show the superiority of the proposed method over many state-of-the-art methods, especially the large improvement of 15.5% and 8.1% on Caltech-4V and CCV in terms of accuracy. Due to the promising performance on visual datasets, the proposed method can be applied into many practical visual applications such as visual recognition and analysis. The source code of the proposed method is provided at https://github.com/ShizheHu/Joint-Contrastive-Triple-learning.  相似文献   

15.
Graph neural networks have been frequently applied in recommender systems due to their powerful representation abilities for irregular data. However, these methods still suffer from the difficulties such as the inflexible graph structure, sparse and highly imbalanced data, and relatively shallow networks, limiting rate prediction ability for recommendations. This paper presents a novel deep dynamic graph attention framework based on influence and preference relationship reconstruction (DGA-IPR) for recommender systems to learn optimal latent representations of users and items. The entire framework involves a user branch and an item branch. An influence-based dynamic graph attention (IDGA) module, a preference-based dynamic graph attention (PDGA) module, and an adaptive fine feature extraction (AFFE) module are respectively constructed for each branch. Concretely, the first two attention modules concentrate on reconstructing influence and preference relationship graphs, breaking imbalanced and fixed constraints of graph structures. Then a deep feature aggregation block and an adaptive feature fusion operation are built, improving the network depth and capturing potential high-order information expressions. Besides, AFFE is designed to acquire finer latent features for users and items. The DGA-IPR architecture is formed by integrating IDGA, PDGA, and AFFE for users and items, respectively. Experiments reveal the superiority of DGA-IPR over existing recommendation models.  相似文献   

16.
The literature has not fully and adequately explained why contextual (e.g., BERT-based) representations are so successful to improve the effectiveness of some Natural Language Processing tasks, especially Automatic Text Classifications (ATC). In this article, we evince that such representations, when properly tuned to a target domain, produce an extremely separable space that makes the classification task very effective, independently of the classifier employed for solving the ATC task. To demonstrate our hypothesis, we perform a thorough class separability analysis in order to visualize and measure how well BERT-based embeddings separate documents of different classes in comparison with other widely used representation approaches, e.g., TFIDF BoW, static embeddings (e.g., fastText) and zero-shot (non-tuned) contextual embeddings. We also analyze separability in the context of transfer learning and compare BERT-based representations with those obtained from other transformers (e.g., RoBERTa, XLNET). Our experiments covering sixteen datasets in topic and sentiment classification, eight classification methods and three class separability metrics show that the fine-tuned BERT embeddings are highly separable in the corresponding space (e.g., they are 67% more separable than the static embeddings). As a consequence, they allow the simplest classifiers to achieve similar effectiveness as the most complex methods. We also find moderate to high correlations between separability and effectiveness in all experimented scenarios. Overall, our main finding is that more discriminative (i.e., separable) textual representations constitute a critical part of the ATC solutions that, given the current state-of-the-art in classification algorithms, are more prominent than the algorithmic (classifier) method for solving the task.  相似文献   

17.
  相似文献   

18.
Finding structural and efficient ways of leveraging available data is not an easy task, especially when dealing with network data, as is the case in telco churn prediction. Several previous works have made advancements in this direction both from the perspective of churn prediction, by proposing augmented call graph architectures, and from the perspective of graph featurization, by proposing different graph representation learning methods, frequently exploiting random walks. However, both graph augmentation as well as representation learning-based featurization face drawbacks. In this work, we first shift the focus from a homogeneous to a heterogeneous perspective, by defining different probabilistic meta paths on augmented call graphs. Secondly, we focus on solutions for the usually significant number of random walks that graph representation learning methods require. To this end, we propose a sampling method for random walks based on a combination of most suitable random walk generation strategies, which we determine with the help of corresponding Markov models. In our experimental evaluation, we demonstrate the benefits of probabilistic meta path-based walk generation in terms of predictive power. In addition, this paper provides promising insights regarding the interplay of the type of meta path and the predictive outcome, as well as the potential of sampling random walks based on the meta path structure in order to alleviate the computational requirements of representation learning by reducing typically sizable required data input.  相似文献   

19.
Human collaborative relationship inference is a meaningful task for online social networks and is called link prediction in network science. Real-world networks contain multiple types of interacting components and can be modeled naturally as heterogeneous information networks (HINs). The current link prediction algorithms in HINs fail to effectively extract training samples from snapshots of HINs; moreover, they underutilise the differences between nodes and between meta-paths. Therefore, we propose a meta-circuit machine (MCM) that can learn and fuse node and meta-path features efficiently, and we use these features to inference the collaborative relationships in question-and-answer and bibliographic networks. We first utilise meta-circuit random walks to obtain training samples in which the basic idea is to perform biased meta-path random walks on the input and target network successively and then connect them. Then, a meta-circuit recurrent neural network (mcRNN) is designed for link prediction, which represents each node and meta-path by a dense vector and leverages an RNN to fuse the features of node sequences. Experiments on two real-world networks demonstrate the effectiveness of our framework. This study promotes the investigation of potential evolutionary mechanisms for collaborative relationships and offers practical guidance for designing more effective recommendation systems for online social networks.  相似文献   

20.
Many methods of multi-kernel clustering have a bias to power base kernels by ignoring other kernels. To address this issue, in this paper, we propose a new method of multi-kernel graph fusion based on min–max optimization (namely MKGF-MM) for spectral clustering by making full use of all base kernels. Specifically, the proposed method investigates a novel min–max weight strategy to capture the complementary information among all base kernels. As a result, every base kernel contributes to the construction of the fusion graph from all base kernels so that the quality of the fusion graph is guaranteed. In addition, we design an iterative optimization method to solve the proposed objective function. Furthermore, we theoretically prove that our optimization method achieves convergence. Experimental results on real medical datasets and scientific datasets demonstrate that the proposed method outperforms all comparison methods and the proposed optimization method achieves fast convergence.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号