Graph Pattern Research Articles

Making It Tractable to Detect and Correct Errors in Graphs

This paper develops \(\mathsf {Hercules} \) , a system for entity resolution (ER), conflict resolution (CR), timeliness deduction (TD) and missing value/link imputation (MI) in graphs. It proposes \(\mathsf {GCR^{+}\!s} \) , a class of graph cleaning rules that support not only predicates for ER and CR, but also temporal orders to deduce timeliness and data extraction to impute missing data. As opposed to previous graph rules, \(\mathsf {GCR^{+}\!s} \) are defined with a dual graph pattern to accommodate irregular structures of schemaless graphs, and adopt patterns of a star form to reduce the complexity. We show that while the implication and satisfiability problems are intractable for \(\mathsf {GCR^{+}\!s} \) , it is in PTIME to detect and correct errors with \(\mathsf {GCR^{+}\!s} \) . Underlying \(\mathsf {Hercules} \) , we train a ranking model to predict the temporal orders on attributes, and embed it as a predicate of \(\mathsf {GCR^{+}\!s} \) . We provide an algorithm for discovering \(\mathsf {GCR^{+}\!s} \) by combining the generations of patterns and predicates. We also develop a method for conducting ER, CR, TD and MI in the same process to improve the overall quality of graphs, by leveraging their interactions and chasing with \(\mathsf {GCR^{+}\!s} \) ; we show that the method has the Church-Rosser property under certain conditions. Using real-life and synthetic graphs, we empirically verify that \(\mathsf {Hercules} \) is 53% more accurate than the state-of-the-art graph cleaning systems, and performs comparably in efficiency and scalability.

Algorithms and Turing Kernels for Detecting and Counting Small Patterns in Unit Disk Graphs

In this paper we investigate the parameterized complexity of counting and detecting small patterns in unit disk graphs: Given an n-vertex unit disk graph G with an embedding of ply p (i.e. G is an intersection graph of closed unit disks, and each point is contained in at most p disks) and a k-vertex unit disk graph P, count the number of (induced) copies of P in G. For general patterns P, we give an 2O(pk/log⁡k)nO(1) time algorithm for counting pattern occurrences. We show this is tight, even for ply p=2: any 2o(n/log⁡n)nO(1) time algorithm violates the Exponential Time Hypothesis (ETH). Our approach combines tools developed for planar subgraph isomorphism such as ‘efficient inclusion-exclusion’ from [Nederlof STOC'20], and ‘isomorphisms checks’ from [Bodlaender et al. ICALP'16] with a different separator hierarchy and a new bound on the number of non-isomorphic separations tailored for unit disk graphs.

Topological differentiation of vegetation of the Lublin-Volyn geobotanical district

The position of the Lublin and Volyn (Volhynian) uplands within the geobotanical zonation system is ambiguous and disputable. An analysis of the syntaxonomical diversity and landscape distribution of the egetation of the Lublin and Volyn uplands revealed their similarity, and we consider this whole territory as the Lublin-Volyn geobotanical district of hornbeam-oak, oak forests, and steppe meadows. This district differs from the adjacent territories and is classified within the Central European mixed forests ecoregion. Typical and diagnostic syntaxa have been identified, and ecological-coenotic profiles have been constructed to characterize the distribution patterns of shrub-forest and herbaceous vegetation within the landscape. Based on calculations of phytosociological indicators for the main ecological factors, graphical patterns of their variation were developed. It was determined that the characteristic forests of the district, Tilieto-Carpinetum (Carpinion betulis), are represented by four variants (T.-C. var. galeobdolosum; T.-C. var. hepaticosum; T.-C. var. caricosum pilosae; T.-C. var. isopyrosum). The district is also characterized by the presence of syntaxa associated with carbonate soils, both of the marsh type (Caricion davallianae) and the meadow-steppe type (Cirsio-Brachypodion, Festucion valesiacae), with the dominance of Carex humilis and Stipa capillata. Using DCA-analysis, the correlation between ecological factor indicators and the distribution of plant communities within the ecological space has been established, forming six fields distributed along three vectors: by moisture (aquatic and marsh communities), xerophytism, and chemical properties of soils (meadow-steppe communities), as well as the structure of coenoses with a specific ombroregime (forest communities).

Similarity joins and clustering for SPARQL

The SPARQL standard provides operators to retrieve exact matches on data, such as graph patterns, filters and grouping. This work proposes and evaluates two new algebraic operators for SPARQL 1.1 that return similarity-based results instead of exact results. First, a similarity join operator is presented, which brings together similar mappings from two sets of solution mappings. Second, a clustering solution modifier is introduced, which instead of grouping solution mappings according to exact values, brings them together by using similarity criteria. For both cases, a variety of algorithms are proposed and analysed, and use-case queries that showcase the relevance and usefulness of the novel operators are presented. For similarity joins, experimental results are provided by comparing different physical operators over a set of real world queries, as well as comparing our implementation to the closest work found in the literature, DBSimJoin, a PostgreSQL extension that supports similarity joins. For clustering, synthetic queries are designed in order to measure the performance of the different algorithms implemented.

Size-fixed group discovery via multi-constrained graph pattern matching

Multi-Constrained Graph Pattern Matching (MC-GPM) aims to match a pattern graph with multiple attribute constraints on its nodes and edges, and has garnered significant interest in various fields, including social-based e-commerce and trust-based group discovery. However, the existing MC-GPM methods do not consider situations where the number of each node in the pattern graph needs to be fixed, such as finding experts group with expert quantities and relations specified. In this paper, a Multi-Constrained Strong Simulation with the Fixed Number of Nodes (MCSS-FNN) matching model is proposed, and then a Trust-oriented Optimal Multi-constrained Path (TOMP) matching algorithm is designed for solving it. Additionally, two heuristic optimization strategies are designed, one for combinatorial testing and the other for edge matching, to enhance the efficiency of the TOMP algorithm. Empirical experiments are conducted on four real social network datasets, and the results demonstrate the effectiveness and efficiency of the proposed algorithm and optimization strategies.

CGG: Category-aware global graph contrastive learning for session-based recommendation

With the auxiliary role of category information in capturing user interests, employing category information to improve session-based recommendation (SBR) is getting an energetic research point. Recent studies organized the category-aware session as the graph structure and utilized the graph neural network to explore the session interest for SBR. However, existing studies only focused on the category information in the current session and failed to overcome inherent sparsity of session data, which resulted in suboptimal SBR performance. To overcome these deficiencies, we propose a Category-aware Global Graph contrastive learning method, namely CGG, for SBR. To be specific, we firstly construct the category-aware global graph based on global item-item transitions, item-category associations and global category-category transitions, which utilizes more sufficient category information across sessions to learn embeddings of categories and items. Furthermore, we design the hierarchical dual-pattern contrastive learning mechanism to model the information interaction of graphical and sequential patterns of a category-aware session, which overcomes the negative influence of sparse session data by injecting self-supervised signals. Extensive experiments on multiple real-world datasets verify that CGG outperforms seven mainstream SBR methods on different measurements.

Inserting colloidal quantum dots into GaN mesa-array subsurface porous structures through electrochemical etching for display color conversion application

High-efficiency photon color conversion is an approach of great potential for implementing color display. Inspired by the observation of emission enhancement in a nanoscale cavity, a novel technique to fabricate an array of color converter by mixing colloidal quantum dots (QDs) with the electrolyte of an electrochemical etching (ECE) process is demonstrated. In this process, QDs flow with the electrolyte into the etched subsurface nanoscale porous structure (PS) and settle inside. Since the PS formation and hence QD insertion are controlled by the flow path of the applied electric current in the ECE process, this technique can be used for fabricating any graphic pattern. The nanostructure of such a QD-inserted mesa is examined to confirm QD insertion. Although only single-color mesa arrays are demonstrated in this paper, this technique can be used for fabricating a multiple-color mesa array if a QD or a light-emitting nanoparticle of higher thermal stability is available.

MAKG: A maritime accident knowledge graph for intelligent accident analysis and management

With the increasing frequency of human activities at sea, maritime accidents are occurring more often. Analyzing and mining maritime accident cases can help uncover the causal mechanisms behind these incidents, thereby enhancing maritime safety. As an emerging technology for knowledge management and mining, knowledge graphs offer significant support for the storage, reasoning, and decision-making processes related to maritime accidents.In this study, we established a knowledge graph construction and application framework for maritime accidents to facilitates the extraction and management of maritime knowledge from unstructured texts. First, 581 accident reports released by the China Maritime Safety Administration over the past decade (2014–2023) were used as the data basis for analysis and construction of the maritime accident ontology structure using the seven-step method, which comprises 8 entity types, 8 relationship types, and 18 attribute entity types. Second, We proposed MBERT-BiLSTM-CRF-SF, a named entity recognition model based on domain pretraining and self-training, to reduce graph construction costs. This model achieved state-of-the-art performance in the maritime domain, with an F1 score of 0.910 ± 0.006, which is about 5% higher than the mainstream model. In addition, we proposed an entity alignment method based on font and semantics to refine knowledge further. On the basis of the proposed method, we constructed a large, high-quality maritime accident knowledge graph (MAKG) system that contains 16,099 entities and 20,809 relationship instances. Finally, we reduced the complexity of applying knowledge graphs by integrating the CRISPE prompt learning framework of the large language model, and experiments on graph traversal, pattern recognition, and aggregation analysis were conducted to assess the quality of MAKG. Results demonstrate that MAKG can effectively enhance the efficiency of querying and reasoning about maritime accident information, thus providing significant support for the prevention and management of maritime accidents.

Controllable Contact-Destructive Hydrogel Actuators.

Constructing hydrogels with spatially heterogeneous structures are crucial for unlocking novel applications. To this end, selectively removing a specific portion of hydrogels by facile and intricate destructive strategies is worth exploring. Herein, a "contact-destructive" hydrogel actuator is presented, composed of a dynamic hydrogel network doped with hydrophilic polyethylene glycol (PEG). The destructive behavior of the hydrogel actuator is attributed to the surface tension-induced spreading effect and the enhanced water absorption due to the additive PEG. Parameters that act on these mechanisms are used to control the destruction of the hydrogel. During the destructive process, the hydrogel actuator exhibits locomotion routes predetermined by the graphic pattern with the aid of 3D printing. Additionally, such self-destructive behavior can be terminated by UV light irradiation when PEG is replaced with poly(ethylene glycol) diacrylate (PEGDA). Significantly, diverse applications including controllable 3D structures collapse, self-erasing, and on-demand cell release, are realized with such self-destructive hydrogel. These results demonstrate that the present hydrogel has great values in soft robotics, anti-counterfeiting, controlled drug delivery, and other related fields.

AdaMotif: Graph Simplification via Adaptive Motif Design.

With the increase of graph size, it becomes difficult or even impossible to visualize graph structures clearly within the limited screen space. Consequently, it is crucial to design effective visual representations for large graphs. In this paper, we propose AdaMotif, a novel approach that can capture the essential structure patterns of large graphs and effectively reveal the overall structures via adaptive motif designs. Specifically, our approach involves partitioning a given large graph into multiple subgraphs, then clustering similar subgraphs and extracting similar structural information within each cluster. Subsequently, adaptive motifs representing each cluster are generated and utilized to replace the corresponding subgraphs, leading to a simplified visualization. Our approach aims to preserve as much information as possible from the subgraphs while simplifying the graph efficiently. Notably, our approach successfully visualizes crucial community information within a large graph. We conduct case studies and a user study using real-world graphs to validate the effectiveness of our proposed approach. The results demonstrate the capability of our approach in simplifying graphs while retaining important structural and community information.

LGCDA: Predicting CircRNA-Disease Association Based on Fusion of Local and Global Features.

CircRNA has been shown to be involved in the occurrence of many diseases. Several computational frameworks have been proposed to identify circRNA-disease associations. Despite the existing computational methods have obtained considerable successes, these methods still require to be improved as their performance may degrade due to the sparsity of the data and the problem of memory overflow. We develop a novel computational framework called LGCDA to predict circRNA-disease associations by fusing local and global features to solve the above mentioned problems. First, we construct closed local subgraphs by using k-hop closed subgraph and label the subgraphs to obtain rich graph pattern information. Then, the local features are extracted by using graph neural network (GNN). In addition, we fuse Gaussian interaction profile (GIP) kernel and cosine similarity to obtain global features. Finally, the score of circRNA-disease associations is predicted by using the multilayer perceptron (MLP) based on local and global features. We perform five-fold cross validation on five datasets for model evaluation and our model surpasses other advanced methods.

MoTion: A new declarative object matching approach in Pharo

Pattern matching is an expressive way of matching data and extracting pieces of information from it. The recent inclusion of pattern matching in the Java and Python languages highlights that such a facility is more and more adopted by developers for everyday development. Other main stream programming languages also offer pattern matching capabilities as part of the language (Rust, Scala, Haskell, and OCaml), with different degrees of expressivity in what can be matched. In the meantime, in graphs, pattern matching takes a slightly different turn; it enhances the expressivity of the patterns that can be defined. Smalltalk currently offers little pattern matching capability to find specific objects inside a large graph of objects using a declarative pattern. In Pharo, the closest library to classical pattern matching that exists is the RBParseTreeSearcher, which allows to express specialized patterns over a Pharo Abstract Syntax Tree to find some inner node. The question arises of what features a flexible pattern matching language should have. In this paper, we review the features found in different existing pattern matching languages, both in General Purpose Languages (like Java) and in declarative graph pattern matching languages. We then describe MoTion, a new pattern matching engine for Pharo smalltalk, combining all these features. We discuss some aspects of MoTion’s implementation and illustrate its use with real case examples.

Node ranking algorithm using Graph Convolutional Networks and mini-batch training

This paper presents a novel algorithm for ranking nodes in graph-structured data using Graph Convolutional Networks (GCNs) combined with mini-batch training. The proposed method integrates local and global structural information, enabling a comprehensive understanding of node importance within complex networks. By employing a multi-layer GCN architecture with residual connections and dropout regularization, our approach captures intricate graph patterns while mitigating common issues such as vanishing gradients and overfitting. The node importance scores are computed using a Multi-Layer Perceptron (MLP), with the entire model trained using Mean Squared Error (MSE) loss optimized via the Adam algorithm. We demonstrate the scalability and effectiveness of our method through extensive experiments on various benchmark datasets, showcasing its superior performance in node ranking tasks compared to existing approaches.

A High‐Scalability Graph Modification System for Large‐Scale Networks

AbstractModifying network results is the most intuitive way to inject domain knowledge into network detection algorithms to improve their performance. While advances in computation scalability have made detecting large‐scale networks possible, the human ability to modify such networks has not scaled accordingly, resulting in a huge ‘interaction gap’. Most existing works only support navigating and modifying edges one by one in a graph visualization, which causes a significant interaction burden when faced with large‐scale networks. In this work, we propose a novel graph pattern mining algorithm based on the minimum description length (MDL) principle to partition and summarize multi‐feature and isomorphic sub‐graph matches. The mined sub‐graph patterns can be utilized as mediums for modifying large‐scale networks. Combining two traditional approaches, we introduce a new coarse‐middle‐fine graph modification paradigm (i.e. query graph‐based modification sub‐graph pattern‐based modification raw edge‐based modification). We further present a graph modification system that supports the graph modification paradigm for improving the scalability of modifying detected large‐scale networks. We evaluate the performance of our graph pattern mining algorithm through an experimental study, demonstrate the usefulness of our system through a case study, and illustrate the efficiency of our graph modification paradigm through a user study.

KGFabric: A Scalable Knowledge Graph Warehouse for Enterprise Data Interconnection

Based on the diversified application scenarios at Ant Group, we built the Ant Knowledge Graph Platform (AKGP). It has constructed numerous domain-specific knowledge graphs related to merchants, companies, accounts, products, and more. AKGP manages trillions of structured knowledge graphs, serving search, recommendation, risk control and other businesses. However, as the demand increasing for various workloads such as graph pattern matching, graph representation learning, and cross-domain knowledge reuse, the existing warehouse systems based on relational DBMS or graph databases are unable to meet the requirements. To address these issues, we propose KGFabric, an industrial-scale knowledge graph management system built on the distributed file system (DFS). KGFabric offers a nearline knowledge storage engine that utilizes a Semantic-enhanced Programmable Graph (SPG) model, which is compatible with the Labeled Property Graph (LPG) model. The data is persistently stored in DFS, such as HDFS, which leverages the POSIX file system API, making it suitable for deployment in multi-cloud environment at low cost. KGFabric provides a native graph-based and hybrid storage format that can serve as a shared backend for parallel graph computing systems, significantly accelerating the analysis of multi-workload. Additionally, KGFabric includes a graph fabric framework that minimizes data duplication and guarantees data security. KGFabric is able to manage Peta-scale data and has supported graph fabric and analysis with over 100 billion relations at Ant Group. We conduct experiments on various datasets to evaluate the performance of KGFabric. Compared with popular relational DBMS and graph databases, the storage space for semantic relations is reduced by over 90%. The performance of graph fabric improves by 21× in real-world workloads. In multi-hop semantic graph analysis, KGFabric enhances performance by 100×.

Graph Association Analyses for Early Drug Discovery

We demonstrate MedHunter, a system for assisting the early stage of drug development. MedHunter builds a biomedical knowledge graph DDKG by integrating data from eleven biochemical libraries and data banks, and aligning entities from different data sources by means of heterogeneous entity resolution. It identifies drug-disease associations and protein-protein interactions in DDKG by employing graph association rules (GARs). GARs use graph patterns to extract relevant entities and embed ML models as predicates. MedHunter discovers GARs from DDKG and incrementally enriches DDKG with external data; it cleans DDKG with a special form of GARs. We demonstrate MedHunter for its (a) interfaces, (b) data enrichment/cleaning, and (c) applications in target identification, drug-drug interaction and protein-protein interaction.

COMPARATIVE STUDY OF TIME ECHO VARIATIONS IN THE METABOLITE VALUES MR BRAIN SPECTROSCOPY

Background: MR spectroscopy is an additional sequence to evaluate lesion characteristics in the brain. Time Echo (TE) is crucial for analyzing MR spectroscopy metabolite. Purpose: This study aims to evaluate the best TE variations during MR spectroscopy examinations in brain lesions. Method: This research is an experimental quantitative study. Researchers used five samples focusing on the results of head multi-voxel spectroscopy charts with clinical lesions or masses that had been taken twice using TE 35 and TE 144. At each TE in each sample, three voxel areas were measured, namely normal, perilesional, and lesion. Each spectroscopy data result is processed individually through READY View software, automatically producing a spectroscopy graph pattern. The required data in this study is the value of each head spectroscopy metabolism: N-Acetyl Aspartate (NAA), Choline (Cho), Creatine (Cr), Myo-Inositol (MI), Lipids Lactate (LL). All statistical tests used the SPSS v.26 application. Result: Based on Paired T test results, NAA, Cho, Cr, and MI metabolites have p-values that account for 0.779 > 0.05; 0.179 > 0.05; 0.581 > 0.05; and 0.057 > 0.05. Based on the Wilcoxon Sign Rank test, the LL metabolite showed a p-value of 0.460 > 0.05. Conclusion: There is no significant difference between TE 35 ms and TE 144 ms during MR spectroscopy examinations.

Tacking over-smoothing: Target-guide progressive dynamic graph learning for 3D skeleton-based human motion prediction

Graph Convolution Network-based (GCN-based) approaches show promising performance on 3D skeleton-based human motion prediction due to its natural graph representation and outstanding ability for spatial–temporal dependencies modeling for human motion. However, the existing GCN-based methods inherently have difficulties in designing deep GCN-based structures for human motion prediction due to the over-smoothing issue. Although the over-smoothing issue has been studied in many scenarios, few attempts focus on this problem in 3D human motion prediction tasks. Therefore, we propose a novel deep GCN architecture termed TPDGN (Target-guide Progressive Dynamic Graph Network) to solve this issue in a motion prediction context. The core of the proposed TPDGN is the progressive dynamic graph leaning block, which is developed to model the dynamic graph pattern. We claim that the key to solving the over-smoothing issue is to reduce the loss of motion features and boost graph representations. Accordingly, we further explore the progressive learning mode by the specific target guidance for the motion prediction task, which aims at learning rich motion dependencies to tackle over-smoothing. Empirical results show that our approach could improve the over-smoothing issue, achieving state-of-the-art results on three public datasets. The codes is available at https://github.com/1111szu/TPDGN.

A Secure Parallel Pattern Mining System for Medical Internet of Things.

In this paper, a new generic parallel pattern mining framework called multi-objective Decomposition for Parallel Pattern-Mining (MD-PPM) is developed to solve challenges in the Internet of Medical Things through big data exploration. MD-PPM discovers important patterns by using decomposition and parallel mining methods to explore connectivity between medical data. First, a new technique, the multi-objective k-means algorithm, is used to aggregate medical data. A parallel pattern mining approach based on GPU and MapReduce architectures is also used to create useful patterns. To ensure complete privacy and security of the medical data, blockchain technology has been integrated throughout the system. Several tests were conducted to demonstrate the high performance of two sequential and graph pattern mining problems on large medical data and to evaluate the developed MD-PPM framework. From our results, our proposed MD-PPM has achieved strong results in terms of memory usage and computation time in terms of efficiency. Moreover, MD-PPM performs well in terms of accuracy and feasibility compared to existing models.

Self-supervised BGP-graph reasoning enhanced complex KBQA via SPARQL generation

Knowledge base question answering aims to answer complex questions from large-scale knowledge bases. Although existing generative language models that translate questions into SPARQL queries have achieved promising results, there are still generation errors due to redundancies or errors in the knowledge fed to the generative models and difficulties in representing the implicit logic of knowledge as the specific syntax of SPARQL. To address above issues, we propose TrackerQA, a novel self-supervised reasoning framework based on basic graph patterns (BGP) to determine precise paths and enhance SPARQL generation. First, we develop a contrastive learning semantic matching model to reduce the large knowledge searching space. Then, we built a BGP parser that parses the recalled knowledge and constraints into BGP graphs, which can deconstruct complex knowledge into BGP triples and naturally obtain supervision from gold SPARQL. Next, we design a self-supervised BGP graph neural network that encodes knowledge through graph transformation layers with directed message-passing control and employs a question-aware attention mechanism to predict the exact BGP paths. Finally, a SPARQL generator integrates the paths into a pre-trained language model to improve the performance of SPARQL generation. Experiments on the KQA Pro dataset show that our model achieves state-of-the-art answering accuracy scores of 95.32%, being the closest to the human level at 97.5%, and reasons out KB paths with F1 scores of 0.98 for nodes and 0.99 for edges.