Graph-based Approach Research Articles

Graph-Based Semi-Supervised Deep Learning for Indonesian Aspect-Based Sentiment Analysis

Product reviews on the marketplace are interesting to research. Aspect-based sentiment analysis (ABSA) can be used to find in-depth information from a review. In one review, there can be several aspects with a polarity of sentiment. Previous research has developed ABSA, but it still has limitations in detecting aspects and sentiment classification and requires labeled data, but obtaining labeled data is very difficult. This research used a graph-based and semi-supervised approach to improve ABSA. GCN and GRN methods are used to detect aspect and opinion relationships. CNN and RNN methods are used to improve sentiment classification. A semi-supervised model was used to overcome the limitations of labeled data. The dataset used is an Indonesian-language review taken from the marketplace. A small part is labeled manually, and most are labeled automatically. The experiment results for the aspect classification by comparing the GCN and GRN methods obtained the best model using the GRN method with an F1 score = 0.97144. The experiment for sentiment classification by comparing the CNN and RNN methods obtained the best model using the CNN method with an F1 score = 0.94020. Our model can label most unlabeled data automatically and outperforms existing advanced models.

Declarative Data Flow in a Graph-Based Distributed Memory Runtime System

Runtime systems can significantly reduce the cognitive complexity of scientific applications, narrowing the gap between systems engineering and domain science in HPC. One of the most important angles in this is automating data migration in a cluster. Traditional approaches require the application developer to model communication explicitly, for example through MPI primitives. Celerity, a runtime system for accelerator clusters heavily inspired by the SYCL programming model, instead provides a purely declarative approach focused around access patterns. In addition to eliminating the need for explicit data transfer operations, it provides a basis for efficient and dynamic scheduling at runtime. However, it is currently only suitable for accessing array-like data from runtime-controlled tasks, while real programs often need to interact with opaque data local to each host, such as handles or database connections, and also need a defined way of transporting data into and out of the virtualised buffers of the runtime. In this paper, we introduce a graph-based approach and declarative API for expressing side-effect dependencies between tasks and moving data from the runtime context to the application space.

MetaGC-MC: A graph-based meta-learning approach to cold-start recommendation with/without auxiliary information

Collaborative filtering-based methods have achieved distinctive performance in ordinary recommendation tasks. However, they suffer from a cold-start problem when historical interaction is sparse. To carry out cold-start recommendations, many methods assume auxiliary data, such as user/item information and heterogeneous network information, being available. However, considering auxiliary data are not always available in practice, we explore a novel approach, MetaGC-MC, to alleviate cold-start recommendation issues, which can provide more effective cold-start recommendations, regardless of whether auxiliary data is available. MetaGC-MC is based on two emerging techniques, namely, graph convolutional network and meta-learning. In MetaGC-MC, a mechanism of stochastic enclosing subgraph sampling is introduced to randomly sample h-hop enclosing subgraphs as the meta-learning tasks for new users or new items. According to the γ-decaying theory, low-hop enclosing subgraphs contain enough information to learn good high-order graph structure information. Without relying on auxiliary data, MetaGC-MC can capture various subgraph structure information under a meta-learning framework, and encode learned information as a meta-prior that makes rapid adaptions in new subgraphs. MetaGC-MC can also take advantage of auxiliary data to enhance model performance. Extensive experimental results in three real-world datasets illustrate that MetaGC-MC is competitive with other state-of-the-art methods for user and item cold-start scenarios.

Social media content classification and community detection using deep learning and graph analytics

Social cybermedia has greatly changed the world’s perspective on information sharing and propagation. These platforms build virtual user communities in the form of followings or followers that can spread positive or negative content. These virtual communities play a vital role in the spread of hate content, which may create a severe law-and-order situation and social unrest in any country. Hate content can include offensive, anti-state, anti-religion, sexist, and racist posts. Classifying such content and identifying influential individuals who participate in these communities are challenging tasks for law enforcement agencies. This study proposes novel deep learning and graph-based approaches to identifying hate content, followed by approaches to detecting communities and exploring social media to detect hate content. Twitter is used as a case study, and tweets are extracted and annotated by linguistic experts to develop a dataset for experimentation and validation. The proposed customized LSTM-GRU model is used to classify hate content into six categories. The developed model offers an accuracy of 98.14% on the obtained dataset. The Girvan–Newman algorithm is employed for Twitter community detection and successfully identifies the most influential individuals. Moreover, the proposed approach precisely detects intraclass communities and highly influential persons. The developed model effectively identifies hate tweets and communities and can be used to monitor social media to identify any potential threat of unrest.

Enhancing the classification metrics of spectroscopy spectrums using neural network based low dimensional space.

Spectroscopy is a methodology for gaining knowledge of particles, especially biomolecules, by quantifying the interactions between matter and light. By examining the level of light absorbed, reflected or released by a specimen, its constituents, properties, and volume can be determined. Spectra obtained through spectroscopy procedures are quick, harmless and contactless; hence nowadays preferred in chemometrics. Due to the high dimensional nature of the spectra, it is challenging to build a robust classifier with good performance metrics. Many linear and nonlinear dimensionality reduction-based classification models have been previously implemented to overcome this issue. However, they lack in capturing the subtle details of the spectra into the low dimension space or cannot efficiently handle the nonlinearity present in the spectral data. We propose a graph-based neural network embedding approach to extract appropriate features into latent space and circumvent the spectrums' nonlinearity problem. Our approach performs dimensionality reduction into two phases: constructing a nearest neighbor graph and producing almost linear embedding using a fully connected neural network. Further, the low dimensional embedding is subjected to classification using the Random Forest algorithm. In this paper, we have implemented and compared our technique with four nonlinear dimensionality techniques widely used for spectral data analysis. In this study, we have considered five different spectral datasets belonging to specific applications. The various classification performance metrics of all the techniques are evaluated. The proposed approach is able to perform competitively well on six different low-dimensional spaces for each dataset with an accuracy score above 95% and Matthew's correlation coefficient value close to 1. The trustworthiness score of almost 1 show that the presented dimensionality reduction approach preserves the closest neighbor structure of high dimensional spectral inputs into latent space.

Grape Leaves Segmentation Using an Improved Graph-Based Approach

Grape Leaves Segmentation Using an Improved Graph-Based Approach

GraphIC: A graph-based approach for identifying complaints from code-mixed product reviews

Enterprises and online merchants can benefit from automatically detecting complaints from social media platforms and shopping websites. Prior studies on automatically identifying complaints on social media have relied chiefly on analyzing complaints in English, with little consideration for code-mixed complaints. We manually annotated the emotion and sentiment classes in the Product Review dataset, a code-mixed language complaint corpus. The extended corpus consists of 3711 instances annotated with the complaint, sentiment, and emotion labels. We present a Graph Attention Network (GAT) based multi-task framework that intends to simultaneously learn three closely related tasks, complaint detection (primary task), sentiment classification, and emotion recognition (auxiliary task). Based on a quantitative and qualitative study on the extended version of the Product Review corpus, the proposed approach attains an accuracy of 72.82% and a macro-F1 of 71% for the intended task of recognizing complaints, outperforming several single-task, multi-task baselines.11Resources are available at: https://github.com/appy1608/ESWA2022_GraphIC.

Graph-based pangenomics maximizes genotyping density and reveals structural impacts on fungal resistance in melon

The genomic sequences segregating in experimental populations are often highly divergent from the community reference and from one another. Such divergence is problematic under various short-read-based genotyping strategies. In addition, large structural differences are often invisible despite being strong candidates for causal variation. These issues are exacerbated in specialty crop breeding programs with fewer, lower-quality sequence resources. Here, we examine the benefits of complete genomic information, based on long-read assemblies, in a biparental mapping experiment segregating at numerous disease resistance loci in the non-model crop, melon (Cucumis melo). We find that a graph-based approach, which uses both parental genomes, results in 19% more variants callable across the population and raw allele calls with a 2 to 3-fold error-rate reduction, even relative to single reference approaches using a parent genome. We show that structural variation has played a substantial role in shaping two Fusarium wilt resistance loci with known causal genes. We also report on the genetics of powdery mildew resistance, where copy number variation and local recombination suppression are directly interpretable via parental genome alignments. Benefits observed, even in this low-resolution biparental experiment, will inevitably be amplified in more complex populations.

Comparison of two different types of reduced graph-based reservoir models: Interwell networks (GPSNet) versus aggregated coarse-grid networks (CGNet)

Computerized solutions for field management optimization often require reduced-order models to be computationally tractable. The purpose of this paper is to compare two different graph-based approaches for building such models. The first approach represents the reservoir as a graph of 1D numerical flow models that each connects an injector to a producer. One thus builds a network in which the topology is primarily determined by “well nodes” to which “non-well nodes” can be connected if need be. The second approach aims at building richer models so that the connectivity graph mimics the intercell connections in a conventional, coarse 3D grid model. One thus builds a network with topology defined by a mesh-like placement of “non-well nodes”, to which wells can be subsequently connected. The two approaches thus can be seen as graph-based analogues of traditional streamline and finite-volume simulation models. Both model types can be trained to match well responses obtained from underlying fine-scale simulations using standard misfit minimization methods; herein we rely on adjoint-based gradient optimization. Our comparisons show that graph models having a connectivity graph that mimics the intercell connectivity in coarse 3D models can represent a wider range of fluid connections and are generally more robust and easier to train than graph models built upon 1D subgridded interwell connections between injectors and producers only.

Pathfinder─Navigating and Analyzing Chemical Reaction Networks with an Efficient Graph-Based Approach.

While the field of first-principles explorations into chemical reaction space has been continuously growing, the development of strategies for analyzing resulting chemical reaction networks (CRNs) is lagging behind. A CRN consists of compounds linked by reactions. Analyzing how these compounds are transformed into one another based on kinetic modeling is a nontrivial task. Here, we present the graph-optimization-driven algorithm and program Pathfinder to allow for such an analysis of a CRN. The CRN for this work has been obtained with our open-source Chemoton reaction network exploration software. Chemoton probes reactive combinations of compounds for elementary steps and sorts them into reactions. By encoding these reactions of the CRN as a graph consisting of compound and reaction vertices and adding information about activation barriers as well as required reagents to the edges of the graph yields a complete graph-theoretical representation of the CRN. Since the probabilities of the formation of compounds depend on the starting conditions, the consumption of any compound during a reaction must be accounted for to reflect the availability of reagents. To account for this, we introduce compound costs to reflect compound availability. Simultaneously, the determined compound costs rank the compounds in the CRN in terms of their probability to be formed. This ranking then allows us to probe easily accessible compounds in the CRN first for further explorations into yet unexplored terrain. We first illustrate the working principle on an abstract small CRN. Afterward, Pathfinder is demonstrated in the example of the disproportionation of iodine with water and the comproportionation of iodic acid and hydrogen iodide. Both processes are analyzed within the same CRN, which we construct with our autonomous first-principles CRN exploration software Chemoton [Unsleber, J. P.; J. Chem. Theory Comput. 2022, 18, 5393-5409] guided by Pathfinder.

A proof-of-concept meaning discrimination experiment to compile a word-in-context dataset for adjectives – A graph-based distributional approach

AbstractThe Word-in-Context corpus, which forms part of the SuperGLUE benchmark dataset, focuses on a specific sense disambiguation task: it has to be decided whether two occurrences of a given target word in two different contexts convey the same meaning or not. Unfortunately, the WiC database exhibits a relatively low consistency in terms of inter-annotator agreement, which implies that the meaning discrimination task is not well defined even for humans. The present paper aims at tackling this problem through anchoring semantic information to observable surface data. For doing so, we have experimented with a graph-based distributional approach, where both sparse and dense adjectival vector representations served as input. According to our expectations the algorithm is able to anchor the semantic information to contextual data, and therefore it is able to provide clear and explicit criteria as to when the same meaning should be assigned to the occurrences. Moreover, since this method does not rely on any external knowledge base, it should be suitable for any low- or medium-resourced language.

Graph Spring Network and Informative Anchor Selection for session-based recommendation

Session-based recommendation (SBR) aims at predicting the next item for an ongoing anonymous session. The major challenge of SBR is how to capture richer relations in between items and learn ID-based item embeddings to capture such relations. Recent studies propose to first construct an item graph from sessions and employ a Graph Neural Network (GNN) to encode item embedding from the graph. Although such graph-based approaches have achieved performance improvements, their GNNs are not suitable for ID-based embedding learning for the SBR task. In this paper, we argue that the objective of such ID-based embedding learning is to capture a kind of neighborhood affinity in that the embedding of a node is similar to that of its neighbors’ in the embedding space. We propose a new graph neural network, called Graph Spring Network (GSN), for learning ID-based item embedding on an item graph to optimize neighborhood affinity in the embedding space. Furthermore, we argue that even stacking multiple GNN layers may not be enough to encode potential relations for two item nodes far-apart in a graph. In this paper, we propose a strategy that first selects some informative item anchors and then encode items’ potential relations to such anchors. In summary, we propose a GSN-IAS model (Graph Spring Network and Informative Anchor Selection) for the SBR task. We first construct an item graph to describe items’ co-occurrences in all sessions. We design the GSN for ID-based item embedding learning and propose an item entropy measure to select informative anchors. We then design an unsupervised learning mechanism to encode items’ relations to anchors. We next employ a shared gated recurrent unit (GRU) network to learn two session representations and make two next item predictions. Finally, we design an adaptive decision fusion strategy to fuse two predictions to make the final recommendation. Extensive experiments on three public datasets demonstrate the superiority of our GSN-IAS model over the state-of-the-art models.

A Graph-Based Blocking Approach for Entity Matching Using Contrastively Learned Embeddings

Data integration is considered a crucial task in the entity matching process. In this process, redundant and cunning entries must be identified and eliminated to improve the data quality. To archive this, a comparison between all entities is performed. However, this has quadratic computational complexity. To avoid this, `blocking' limits comparisons to probable matches. This paper presents a k-nearest neighbor graph-based blocking approach utilizing state-of-the-art context-aware sentence embeddings from pre-trained transformers. Our approach maps each database tuple to a node and generates a graph where nodes are connected by edges if they are related. We then invoke unsupervised community detection techniques over this graph and treat blocking as a graph clustering problem. Our work is motivated by the scarcity of training data for entity matching in real-world scenarios and the limited scalability of blocking schemes in the presence of proliferating data. Additionally, we investigate the impact of contrastively trained embeddings on the above system and test its capabilities on four data sets exhibiting more than 6 million comparisons. We show that our block processing times on the target benchmarks vary owing to the efficient data structure of the k-nearest neighbor graph. Our results also show that our method achieves better performance in terms of F1 score when compared to current deep learning-based blocking solutions.

Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis

Point cloud completion is a generation and estimation issue derived from the partial point clouds, which plays a vital role in the applications in 3D computer vision. The progress of deep learning (DL) has impressively improved the capability and robustness of point cloud completion. However, the quality of completed point clouds is still needed to be further enhanced to meet the practical utilization. Therefore, this work aims to conduct a comprehensive survey on various methods, including point-based, convolution-based, graph-based, and generative model-based approaches, etc. And this survey summarizes the comparisons among these methods to provoke further research insights. Besides, this review sums up the commonly used datasets and illustrates the applications of point cloud completion. Eventually, we also discussed possible research trends in this promptly expanding field.

Graph-based decision making for varying complexity multicriteria problems

In the modern world in various spheres of activity, the number of problems that need multi-criteria decision-making (MCDM) is constantly increasing. Researchers and experts offer a number of approaches to MCDM process in such tasks; in particular, most of them are based on expert methods. However, in practice, these methods require significant intellectual effort of experts and organizational and technical workload during the expert survey, and also usually take a long time. At the same time, it is not always possible for experts to use certain characteristics of alternatives, which also carries the risk of making decisions based on unfounded expert opinions. Therefore, such methods and tools should be clear and informative and at the same time easy to use to ensure the efficiency and effectiveness of their use. We offer a graph-based approach to expert decision-making and information visualization processes that meets these requirements and can significantly improve the efficiency of decision-making in multi-criteria selection tasks.

Graph-based data management system for efficient information storage, retrieval and processing

Data management systems rely on a correct design of data representation and software components. The data representation scheme plays a vital role in how the data are stored, which influences the efficiency of its processing and retrieval. The system components design realizes software engineering concepts to enable performance metrics such as scalability, efficiency, flexibility, maintainability, and extendibility. This paper presents a data management system that uses a graph-based data representation scheme to achieve an efficient data retrieval when using graph-based databases. Input data are transformed into vertices, edges, and labels while inserting them into the database. The proposed system consists of three layers which are: system beans layer, data access layer, and the database engine. Healthcare data are used to evaluate the system in comparison with resource description framework (RDF) semantics. Extensive experiments are conducted to compare different scenarios of data storage and retrieval using Neo4J, OrientDB, and RDF4J. Experimental results show that the performance of the proposed graph-based approach outperforms RDF4J framework in terms of insertion and retrieval time.

A design support tool based on building information modeling for design for deconstruction: A graph-based deconstructability assessment approach

Design for deconstruction (DfD) increases reusable components extracted from old structures by considering the ease of deconstruction from a construction project's early stage. However, due to a lack of tools and methods for evaluating DfD performance, quantifying the benefits of DfD for practical application is difficult. This study proposes a tool based on building information modeling for DfD to provide automated DfD performance evaluation results that include the mathematical evaluation score, CO2 emission, and cost. To validate the tool, we conducted a case study, assuming a steel structure design. Accordingly, it enables the development of deconstruction options and designs that reduce CO2 emissions and costs by up to 40.1% and 1.3%, respectively, when compared to initial alternatives. Reuse can reduce CO2 emissions and costs that increase per the deconstruction options. The study highlights the importance of analyzing the environmental load and cost of various deconstruction options that have been excluded from previous studies.

Knowledge Graph-Based Assembly Resource Knowledge Reuse towards Complex Product Assembly Process

Assembly process designers typically confront the challenge of seeking information out of large volumes of non-structured files with a view to supporting the decision-making to be made. It is a leading concern that embedding data in text documents can hardly be retrieved semantically in order to facilitate decision-making with timely support. For tackling this gap, we propose in this paper a knowledge graph-based approach used to merge and retrieve information decided to be relevant within an engineering context. The proposed approach is to establish a multidimensional integrated assembly resource knowledge graph (ARKG) based on the structure of function-structure-assembly procedure-assembly resource, and this multidimensional integrated structure can well accomplish the retrieval of related knowledge. The upper semantic framework of ARKG is established by the assembly resource ontology model, which is a semantic-type framework involving multiple domains of knowledge to create instantiated data reflecting the full profile of the assembly resource for obtaining structured data of ARKG while avoiding the data redundancy problem. The ARKG method is validated through assembly scenario of the aircraft, and the results show the effectiveness and accuracy of the ARKG used by the assembly process designer in the assembly process design phase for retrieving the target knowledge of the assembly resources.

A graph-based approach to client relationship management in fund administration

Ensuring effective and timely communication in the fund administration industry has become an essential element of client relationship management (CRM). A CRM team periodically evaluates asset managers perception of service quality using surveys, where it can be difficult to evaluate service quality objectively. Within the asset management industry, despite ongoing technological advances, the main channel of communication remains email. The sheer volume of email, and the industry’s reliance on it, can lead to practical problems that impact CRM. In this work we draw insights from the email communications between an operations team and two-sample clients to understand client relationships in a way not previously possible. The results are presented and we discuss how these can quantitatively support and improve service quality evaluations in CRM. For this application, we exploit the social relations in emails via a graph-based approach. A deep learning framework is described that allows a graph-based inspection of the email communications between asset managers and their fund administrators operations teams. The presented framework integrates a natural language processing model to transform email subject lines to embedding representations, a knowledge graph to transform the email communication links into a graph representation, and a graph neural network to process the embedding representations and classify the email communications. The classification of critical conversations via email is a demonstrative example of a scalable graph-based approach that allows the use of machine learning to process, learn, and explore the relations existing between the emails.

022 Using single-cell transcriptomics to characterise early mechanisms of disease remission in psoriasis

Biologic drugs have revolutionised outcomes in psoriasis, with a growing number of patients achieving clear skin (‘remission’). However, treatment involves expensive regular injections, and the long-term impact remains uncertain. An improved understanding of the early mechanisms underpinning biologics-induced remission may help inform strategies around drug withdrawal. This promises to overcome the burden of long-term continuous therapy. Here, we performed single-cell RNA sequencing on skin biopsies from 5 individuals with psoriasis who achieved remission upon treatment with the exemplar IL23p19 inhibitor risankizumab. We profiled whole skin at baseline, day-3, and -14 of treatment. Data was filtered, integrated, scaled, and normalized with the Seurat package, yielding a final dataset of 176,967 cells. A graph-based clustering approach identified 39 cell types, including keratinocyte, fibroblast, myeloid, and T cell subsets. Differential expression analysis demonstrated marked differences in transcript levels between day 0 and day 3, with the largest number of modulated genes observed among fibroblast and myeloid populations. Changes in the relative abundance of cell types became apparent at day 14, and could be verified by deconvolution of published bulk-RNA sequencing data. Finally, trajectory analysis suggested that the inflammatory cell states that characterise lesional skin are reversed soon after risankizumab treatment. Our high-resolution atlas indicates that myeloid and fibroblast populations are ‘early responders’ to risankizumab therapy, potentially driving biologic-induced remission.