共查询到20条相似文献，搜索用时 78 毫秒
1.
2.
《Information processing & management》2022,59(4):102946
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
3.
《Information processing & management》2023,60(3):103284
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
4.
5.
《Information processing & management》2022,59(5):103004
Although the Knowledge Graph (KG) has been successfully applied to various applications, there is still a large amount of incomplete knowledge in the KG. This study proposes a Knowledge Graph Completion (KGC) method based on the Graph Attention Faded Mechanism (GAFM) to solve the problem of incomplete knowledge in KG. GAFM introduces a graph attention network that incorporates the information in multi-hop neighborhood nodes to embed the target entities into low dimensional space. To generate a more expressive entity representation, GAFM gives different weights to the neighborhood nodes of the target entity by adjusting the attention value of neighborhood nodes according to the variation of the path length. The attention value is adjusted by the attention faded coefficient, which decreases with the increase of the distance between the neighborhood node and the target entity. Then, considering that the capsule network has the ability to fit features, GAFM introduces the capsule network as the decoder to extract feature information from triple representations. To verify the effectiveness of the proposed method, we conduct a series of comparative experiments on public datasets (WN18RR and FB15k-237). Experimental results show that the proposed method outperforms baseline methods. The Hits@10 metric is improved by 8% compared with the second-place KBGAT method. 相似文献
6.
《Information processing & management》2022,59(4):102967
Graph-based multi-view clustering aims to take advantage of multiple view graph information to provide clustering solutions. The consistency constraint of multiple views is the key of multi-view graph clustering. Most existing studies generate fusion graphs and constrain multi-view consistency by clustering loss. We argue that local pair-view consistency can achieve fine-modeling of consensus information in multiple views. Towards this end, we propose a novel Contrastive and Attentive Graph Learning framework for multi-view clustering (CAGL). Specifically, we design a contrastive fine-modeling in multi-view graph learning using maximizing the similarity of pair-view to guarantee the consistency of multiple views. Meanwhile, an Att-weighted refined fusion graph module based on attention networks to capture the capacity difference of different views dynamically and further facilitate the mutual reinforcement of single view and fusion view. Besides, our CAGL can learn a specialized representation for clustering via a self-training clustering module. Finally, we develop a joint optimization objective to balance every module and iteratively optimize the proposed CAGL in the framework of graph encoder–decoder. Experimental results on six benchmarks across different modalities and sizes demonstrate that our CAGL outperforms state-of-the-art baselines. 相似文献
7.
8.
9.
Science has greatly contributed to the advancement of technology and to the innovation of production processes and their applications. Cleaning products have become indispensable in today’s world, as personal and environmental hygiene is important to all societies worldwide. Such products are used in the home, in most work environments and in the industrial sectors. Most of the detergents on the market are synthesised from petrochemical products. However, the interest in reducing the use of products harmful to human health and the environment has led to the search for detergents formulated with natural, biodegradable surfactant components of biological (plant or microbiological) origin or chemically synthesised from natural raw materials usually referred to as green surfactants. This review addresses the different types, properties, and uses of surfactants, with a focus on green surfactants, and describes the current scenario as well as the projections for the future market economy related to the production of the different types of green surfactants marketed in the world.How to cite: Farias CBB, Almeida FCG, Silva IA, et al. Production of green surfactants: Market prospects. Electron J Biotechnol 2021;51. https://doi.org/10.1016/j.ejbt.2021.02.002 相似文献
10.
BackgroundMathematical modeling is useful in the analysis, prediction, and optimization of an enzymatic process. Unlike the conventional modeling methods, Monte Carlo method has special advantages in providing representations of the molecule’s spatial distribution. However, thus far, Monte Carlo modeling of enzymatic system is namely based on unimolecular basis, not suitable for practical applications. In this research, Monte Carlo modeling is performed for enzymatic hydrolysis of lactose for the purpose of real-time applications.ResultsThe enzyme hydrolysis of lactose, which is conformed to Michaelis–Menten kinetics, is modeled using the Monte Carlo modeling method, and the simulation results prove that the model predicts the reaction kinetics very well.ConclusionsMonte Carlo modeling method can be used to model enzymatic reactions in a simple way for real-time applications.How to cite: Gao L, Guo Q, Lin H, et al. Modeling of lactose enzymatic hydrolysis using Monte Carlo method. Electron J Biotechnol 2019;41.https://doi.org/10.1016/j.ejbt.2019.04.010 相似文献
11.
《Information processing & management》2023,60(4):103348
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
12.
《Information processing & management》2023,60(5):103416
Recently, graph neural network (GNN) has been widely used in sequential recommendation because of its powerful ability to capture high-order collaborative relations, greatly promoting recommendation performance. However, some existing GNN-based methods fail to make full use of multiple relevant features of nodes and ignore the impact of semantic association between nodes on extracting user preferences. To this end, we propose a multi-feature fused collaborative attention network MASR, which sufficiently learns the temporal and positional features of nodes, and innovatively measures the importance of these two features for analyzing the nodes’ dynamic patterns. In addition, we incorporate semantic-enriched contrastive learning into collaborative filtering to enhance the semantic association between nodes and reduce the noise from the structural neighborhood, which has a positive effect on the sequential recommendation. Compared with the baseline models, the performance of MASR on MovieLens, CDs and Beauty datasets is improved by 2.0%, 2.1% and 1.7% respectively, proving its effectiveness in the sequential recommendation. 相似文献
13.
BackgroundTP73 antisense RNA 1 (TP73-AS1), a newly discovered long non-coding RNA (lncRNA), has been reported to be upregulated in various kinds of tumors, and shows a variable influence on living quality and prognosis of patients. Thus, we conducted a meta-analysis to evaluate the overall prognostic value of the lncRNA TP73-AS1 in cancer patients.ResultsA systematic literature retrieval was carried out using the PubMed, Cochrane Library, EMBASE, and Web of Science databases. We calculated the pooled hazard ratio (HR) and odds ratio (OR) with 95% confidence intervals (CIs) to evaluate the association of TP73-AS1 expression with prognostic and clinicopathological parameters. A total of 15 studies including 1057 cancer patients were finally selected for the meta-analysis. The results demonstrated that high TP73-AS1 expression was significantly associated with shorter overall survival (OS) (HR = 1.97, 95% CI: 1.68–2.31, P < 0.001). According to a fixed-effects or random-effects model, elevated TP73-AS1 expression markedly predicted advanced clinical stage (OR = 3.30, 95% CI: 2.35–4.64, P < 0.001), larger tumor size (OR = 2.37, 95% CI: 1.75–3.22, P < 0.001), earlier lymph node metastasis (OR = 3.28, 95% CI: 1.59–6.76, P = 0.001), and distant metastasis (OR = 4.94, 95% CI: 2.61–9.37, P < 0.001).ConclusionsHigh lncRNA TP73-AS1 expression appears to be predictive of a worse OS and clinicopathologic features for patients with various types of malignant tumors. These results provide a basis for utilizing TP73-AS1 expression as an unfavorable indicator to predict survival outcomes.How to cite: Wang X, Shu K, Wang Z, et al. Prognostic value of long non-coding RNA TP73-AS1 expression in different types of cancer: A systematic review and meta-analysis. Electron J Biotechnol 2020;43. https://doi.org/10.1016/j.ejbt.2019.12.005. 相似文献
14.
Chloroplast biotechnology has emerged as a promissory platform for the development of modified plants to express products aimed mainly at the pharmaceutical, agricultural, and energy industries. This technology’s high value is due to its high capacity for the mass production of proteins. Moreover, the interest in chloroplasts has increased because of the possibility of expressing multiple genes in a single transformation event without the risk of epigenetic effects. Although this technology solves several problems caused by nuclear genetic engineering, such as turning plants into safe bio-factories, some issues must still be addressed in relation to the optimization of regulatory regions for efficient gene expression, cereal transformation, gene expression in non-green tissues, and low transformation efficiency. In this article, we provide information on the transformation of plastids and discuss the most recent achievements in chloroplast bioengineering and its impact on the biopharmaceutical and agricultural industries; we also discuss new tools that can be used to solve current challenges for their successful establishment in recalcitrant crops such as monocots.How to cite: Quintín Rascón-Cruz Q, González-Barriga CD, Iglesias-Figueroa BF, et al. Plastid transformation: Advances and challenges for its implementation in agricultural crops. Electron J Biotechnol 2021;51. https://doi.org/10.1016/j.ejbt.2021.03.005 相似文献
15.
16.
BackgroundThe intestinal bacterial community has an important role in maintaining human health. Dysbiosis is a key inducer of many chronic diseases including obesity and diabetes. Kunming mice are frequently used as a model of human disease and yet little is known about the bacterial microbiome resident to the gastrointestinal tract.ResultsWe undertook metagenomic sequencing of the luminal contents of the stomach, duodenum, jejunum, ileum, cecum, colon, and rectum of Kunming mice. Firmicutes was the dominant bacterial phylum of each intestinal tract and Lactobacillus the dominant genus. However, the bacterial composition differed among the seven intestinal tracts of Kunming mice. Compared with the small intestine, the large intestine bacterial community of Kunming mice is more stable and diverse.ConclusionsTo our knowledge, ours is the first study to systematically describe the gastrointestinal bacterial composition of Kunming mice. Our findings provide a better understanding of the bacterial composition of Kunming mice and serves as a foundation for the study of precision medicine.How to cite: Han X, Shao H, Wang Y, et al. Composition of the bacterial community in the gastrointestinal tract of Kunming mice. Electron J Biotechnol 2020;43. https://doi.org/10.1016/j.ejbt.2019.11.003 相似文献
17.
《Information processing & management》2022,59(3):102919
Similarity search with hashing has become one of the fundamental research topics in computer vision and multimedia. The current researches on semantic-preserving hashing mainly focus on exploring the semantic similarities between pointwise or pairwise samples in the visual space to generate discriminative hash codes. However, such learning schemes fail to explore the intrinsic latent features embedded in the high-dimensional feature space and they are difficult to capture the underlying topological structure of data, yielding low-quality hash codes for image retrieval. In this paper, we propose an ordinal-preserving latent graph hashing (OLGH) method, which derives the objective hash codes from the latent space and preserves the high-order locally topological structure of data into the learned hash codes. Specifically, we conceive a triplet constrained topology-preserving loss to uncover the ordinal-inferred local features in binary representation learning. By virtue of this, the learning system can implicitly capture the high-order similarities among samples during the feature learning process. Moreover, the well-designed latent subspace learning is built to acquire the noise-free latent features based on the sparse constrained supervised learning. As such, the latent under-explored characteristics of data are fully employed in subspace construction. Furthermore, the latent ordinal graph hashing is formulated by jointly exploiting latent space construction and ordinal graph learning. An efficient optimization algorithm is developed to solve the resulting problem to achieve the optimal solution. Extensive experiments conducted on diverse datasets show the effectiveness and superiority of the proposed method when compared to some advanced learning to hash algorithms for fast image retrieval. The source codes of this paper are available at https://github.com/DarrenZZhang/OLGH . 相似文献
18.
《Information processing & management》2023,60(5):103475
Effective passage retrieval is crucial for conversation question answering (QA) but challenging due to the ambiguity of questions. Current methods rely on the dual-encoder architecture to embed contextualized vectors of questions in conversations. However, this architecture is limited in the embedding bottleneck and the dot-product operation. To alleviate these limitations, we propose generative retrieval for conversational QA (GCoQA). GCoQA assigns distinctive identifiers for passages and retrieves passages by generating their identifiers token-by-token via the encoder–decoder architecture. In this generative way, GCoQA eliminates the need for a vector-style index and could attend to crucial tokens of the conversation context at every decoding step. We conduct experiments on three public datasets over a corpus containing about twenty million passages. The results show GCoQA achieves relative improvements of +13.6% in passage retrieval and +42.9% in document retrieval. GCoQA is also efficient in terms of memory usage and inference speed, which only consumes 1/10 of the memory and takes in less than 33% of the time. The code and data are released at https://github.com/liyongqi67/GCoQA. 相似文献
19.
Since more than twenty years ago, some species of bacteria and fungi have been used to produce protein biomass or single-cell protein (SCP), with inexpensive feedstock and wastes being used as their sources of carbon and energy. The role of SCP as a safe food and feed is being highlighted more because of the worldwide protein scarcity. Even though SCP has been successfully commercialized in the UK for decades, study of optimal fermentation conditions, various potential substrates, and a broad range of microorganisms is still being pursued by many researchers. In this article, commonly used methods for the production of SCP and different fermentation systems are briefly reviewed, with submerged fermentation being highlighted as a more commonly used method. Emphasis is given to the effect of influencing factors on the biomass yield and productivity in an effort to provide a comprehensive review for researchers in related fields of interest.How to cite: Reihani SFS, Khosravi-Darani K. Influencing factors on single cell protein production by submerged fermentation: A review. Electron J Biotechnol 2019;37. https://doi.org/10.1016/j.ejbt.2018.11.005. 相似文献
20.
We highlight the importance of the mixed genetic approaches (classical and currents) to improve the social perception related to the GMOs acceptance. We pointed out that CRISPR/Cas9 events could carry DNA variability/rearrangements related to somaclonal variations or epigenetic changes that are independent from the editing per se. The transformation of single cells, followed by plant regeneration, is used to generate modified plants, transgenic or genome editing (CRISPR/Cas9). The incidence of undesirable somaclonal variations and/or epigenetic changes that might have occurred during in vitro multiplication and regeneration processes, must be carefully analyzed in replicates in field trials. One remarkable challenge is related to the time lapse that selects the modified elite genotypes, because these strategies may spend a variable amount of time before the results are commercialized, where in all the cases it should be take into account the genotype × environment interactions. Furthermore, this combination of techniques can create an encouraging bridge between the public opinion and the community of geneticists who are concerned with plant genetic improvement. In this context, either transgenesis or genomic editing strategies become complementary modern tools to facing the challenges of plant genetic improvement. Their applications will depend on case-by-case analysis, and when possible will necessary associate them to the schemes and bases of classic plant genetic improvement.How to cite: Arencibia A, D’Afonseca V, Chakravarthi M, et al. Learning from transgenics: Advanced gene editing technologies should also bridge the gap with traditional genetic selection. Electron J Biotechnol 2019;41. https://doi.org/10.1016/j.ejbt.2019.06.001 相似文献