Relational Graph Research Articles

Graph Neural Networks with Multi-features for Predicting Cocrystals using APIs and Coformers Interactions.

Active pharmaceutical ingredients (APIs) have gained direct pharmaceutical interest, along with their in vitro properties, and thus utilized as auxiliary solid dosage forms upon FDA guidance and approval on pharmaceutical cocrystals when reacting with coformers, as a potential and attractive route for drug substance development. However, screening and selecting suitable and appropriate coformers that may potentially react with APIs to successfully form cocrystals is a time-consuming, inefficient, economically expensive, and labour-intensive task. In this study, we implemented GNNs to predict the formation of cocrystals using our introduced API-coformers relational graph data. We further compared our work with previous studies that implemented descriptor-based models (e.g., random forest, support vector machine, extreme gradient boosting, and artificial neural networks). All built graph-based models show compelling performance accuracies (i.e., 91.36, 94.60 and 95. 95% for GCN, GraphSAGE, and RGCN respectively). RGCN demonstrated effectiveness and prevailed among the built graph-based models due to its capability to capture intricate and learn nuanced relationships between entities such as non-ionic and non-covalent interactions or link information between APIs and coformers which are crucial for accurate predictions and representations. These capabilities allows the model to adeptly learn the topological structure inherent in the graph data.

Integrated Extraction of Entities and Relations via Attentive Graph Convolutional Networks

For information security, entity and relation extraction can be applied in sensitive information protection, data leakage detection, and other aspects. The current approaches to entity relation extraction not only ignore the relevance and dependency between name entity recognition and relation extraction but also may result in the cumulative propagation of errors. To solve this problem, it is proposed that an end-to-end joint entity and relation extraction model based on the Attention mechanism and Graph Convolutional Network (GCN) to simultaneously extract named entities and their relationships. The model includes three parts: the detection of entity span, the construction of an entity relation weighted graph, and the inference of entity relation type. Firstly, the detection of entity spans is viewed as a sequence labeling problem, and a multi-feature fusion approach for word embedding representation is designed to calculate all entity spans in a sentence to form an entity span matrix. Secondly, the entity span matrix is employed in the Multi-Head Attention mechanism for constructing the weighted adjacency matrix of the entity relation graph. Finally, for the inference of entity relation type, considering the interaction between entities and relations, the entity span matrix and relation connection matrix are simultaneously fed into the GCN for integrated extraction of entities and relations. Our model is evaluated on the public NYT dataset, attaining a precision of 66.4%, a recall of 63.1%, and an F1 score of 64.7% for joint entity and relation extraction, significantly outperforming other approaches. Experiments demonstrate that the proposed model is helpful for inferring entities and relations, considering the interaction between entities and relations through the Attention mechanism and GCN.

Large eddy simulation of soot formation in a turbulent lifted flame with a discretized population balance and a reduced kinetic mechanism

This article presents simulations of a turbulent lifted flame using the large eddy simulation-transport probability density function-discretized population balance equation approach. This approach takes into account the interaction between turbulent reacting flow and soot particle formation. A reduced chemical kinetics mechanism including a series of polycyclic aromatic hydrocarbons (PAHs) species linked to soot formation is generated employing the approach of the directed relation graph error propagation and is tested on a perfectly stirred reactor under varying equivalent ratio conditions and premixed flames. The soot kinetics model includes the PAH-based nucleation and surface condensation, the hydrogen abstraction acetylene addition surface growth and oxidation mechanism, and the size-dependent aggregation. The soot morphology considers the surface area and other geometrical properties for both spherical primary particles and fractal aggregates. The simulation results show, in general, reasonably good agreement with experimental measurements in terms of lifted height, flame shape, flow-field velocity, the hydroxyl radical, and soot volume fraction. A discussion of micromixing and its modeling in the context of the Interaction by Exchange with the Mean model is also presented. To investigate the effect of the soot micromixing frequency factor on soot particles, an additional simulation is conducted where this factor is reduced by a factor of 10 for the soot particles. The maximum soot volume fraction is observed to increase slightly. However, compared with the impact of kinetics on soot modeling, this effect is a minor one.

A framework for generating recommendations based on trust in an informal e-learning environment

Rapid advancement in information technology promotes the growth of new online learning communities in an e-learning environment that overloads information and data sharing. When a new learner asks a question, how a system recommends the answer is the problem of the learner’s cold start. In this article, our contributions are: (i) We proposed a Trust-aware Deep Neural Recommendation (TDNR) framework that addresses learner cold-start issues in informal e-learning by modeling complex nonlinear relationships. (ii) We utilized latent Dirichlet allocation for tag modeling, assigning tag categories to newly posted questions and ranking experts related to specific tags for active questioners based on hub and authority scores. (iii) We enhanced recommendation accuracy in the TDNR model by introducing a degree of trust between questioners and responders. (iv) We incorporated the questioner-responder relational graph, derived from structural preference information, into our proposed model. We evaluated the proposed model on the Stack Overflow dataset using mean absolute precision (MAP), root mean squared error (RMSE), and F-measure metrics. Our significant findings are that TDNR is a hybrid approach that provides more accurate recommendations compared to rating-based and social-trust-based approaches, the proposed model can facilitate the formation of informal e-learning communities, and experiments show that TDNR outperforms the competing methods by an improved margin. The model’s robustness, demonstrated by superior MAE, RMSE, and F-measure metrics, makes it a reliable solution for addressing information overload and user sparsity in Stack Overflow. By accurately modeling complex relationships and incorporating trust degrees, TDNR provides more relevant and personalized recommendations, even in cold-start scenarios. This enhances user experience by facilitating the formation of supportive learning communities and ensuring new learners receive accurate recommendations.

Edge computing task scheduling method based on user’s social relations: a construction and solution for Smart City Library

In the realm of the development of a Smart City Library, the integration of robust edge computing is vital. The research suggests a novel task-scheduling model for edge computing, leveraging user’s social relationships. Analyzing these connections involves constructing a user’s social relationship graph by implementing mathematical convolution and the Jaccard similarity ratio. This precise quantification of social ties ensures secure and reliable task scheduling. An equipment connection graph of a user equipment service is also crafted based on Euclidean distance, aligning task scheduling with device-to-device (D2D) communication conditions. Combining a user’s social relationship graph and a user’s device-service device connection graph creates a task-device bipartite graph. On the other hand, the calculation of a task execution cost and edge weight determination finalize a scheduling model. Implementing the proposed method for constructing a model for edge computing task scheduling based on utilizing the Kuhn–Munkres (KM) algorithm demonstrates positive impacts, which are few delays and less energy consumption, on edge computing task scheduling. For instance, when the social threshold score changes from 02. To 0.6, the total task execution delay time increases from 23 to 32, which is the best when compared with other algorithms. The approach strengthens security and reliability while decreasing task execution delays and energy consumption. This research advances edge computing for Smart City Libraries, promising transformative implications.

Concurrent Access Performance Comparison Between Relational Databases and Graph NoSQL Databases for Complex Algorithms

Databases are a fundamental element of contemporary software applications. The most widely used and recognized type in practice is the relational database, valued for its ability to store and organize data in tabular structures, its emphasis on data consistency and integrity, and its use of a standardized query language, SQL. However, with the rapid increase in both the volume and complexity of data, relational databases have recently encountered challenges in effectively modeling this expanding information. To address performance challenges, new database systems have emerged, offering alternative approaches to data modeling—these are known as NoSQL databases. In this paper, we present an indoor navigation application designed to operate on both a relational database, Microsoft SQL Server, and a graph-based NoSQL database, Neo4j. We describe the algorithms implemented for testing and the performance metrics analyzed to draw our conclusions. The results revealed Neo4j’s strength in managing data with complex relationships but also exposed its limitations in handling concurrent access, where SQL Server demonstrated significantly greater stability.

Fully exploring object relation interaction and hidden state attention for video captioning

Video Captioning (VC) is a challenging task of automatically generating natural language sentences for describing video contents. As a video often contains multiple objects, it is comprehensively crucial to identify multiple objects and model relationships between them. Previous models usually adopt Graph Convolutional Networks (GCN) to infer relational information via object nodes, but there exist uncertainty and over-smoothing issues of relational reasoning. To tackle these issues, we propose a Knowledge Graph based Video Captioning Network (KG-VCN) by fully exploring object relation interaction, hidden state and attention enhancement. In encoding stages, we present a Graph and Convolution Hybrid Encoder (GCHE), which uses an object detector to find visual objects with bounding boxes for Knowledge Graph (KG) and Convolutional Neural Network (CNN). To model intrinsic relations between detected objects, we propose a knowledge graph based Object Relation Graph Interaction (ORGI) module. In ORGI, we design triplets (head, relation, tail) to efficiently mine object relations, and create a global node to enable adequate information flow among all graph nodes for avoiding possibly missed relations. To produce accurate and rich captions, we propose a hidden State and Attention Enhanced Decoder (SAED) by integrating hidden states and dynamically updated attention features. Our SAED accepts both relational and visual features, adopts Long Short-Term Memory (LSTM) to produce hidden states, and dynamically update attention features. Unlike existing methods, we concatenate state and attention features to predict next word sequentially. To demonstrate the effectiveness of our model, we conduct experiments on three well-known datasets (MSVD, MSR-VTT, VaTeX), and our model achieves impressive results significantly outperforming existing state-of-the-art models.

Proposal Semantic Relationship Graph Network for Temporal Action Detection

Temporal action detection, a critical task in video activity understanding, is typically divided into two stages: proposal generation and classification. However, most existing methods overlook the importance of information transfer among proposals during classification, often treating each proposal in isolation, which hampers accurate label prediction. In this paper, we propose a novel method for inferring semantic relationships both within and between action proposals, guiding the fusion of action proposal features accordingly. Building on this approach, we introduce the Proposal Semantic Relationship Graph Network (PSRGN), an end-to-end model that leverages intra-proposal semantic relationship graphs to extract cross-scale temporal context and an inter-proposal semantic relationship graph to incorporate complementary neighboring information, significantly improving proposal feature quality and overall detection performance. This is the first method to apply graph structure learning in temporal action detection, adaptively constructing the inter-proposal semantic graph. Extensive experiments on two datasets demonstrate the effectiveness of our approach, achieving state-of-the-art results. Code and results are available at http://github.com/Riiick2011/PSRGN .

TRGCN: A Prediction Model for Information Diffusion Based on Transformer and Relational Graph Convolutional Network

In order to capture and integrate the structural features and temporal features contained in social graph and diffusion cascade more effectively, an information diffusion prediction model based on the Transformer and Relational Graph Convolutional Network (TRGCN) is proposed. Firstly, a dynamic heterogeneous graph composed of the social network graph and the diffusion cascade graph was constructed, and it was input into the Relational Graph Convolutional Network (RGCN) to extract the structural features of each node. Secondly, the time embedding of each node was reencoded using Bi-directional Long Short-Term Memory (Bi-LSTM). The time decay function was introduced to give different weights to nodes at different time positions, so as to obtain the temporal features of nodes. Finally, structural features and temporal features were input into Transformer and then merged. The spatiotemporal features are obtained for information diffusion prediction. The experimental results on three real datasets of X (formerly known as Twitter), Douban, and Memetracker show that compared with the optimal model in the comparison experiment, the TRGCN model has an average increase of 4.16% in Hits@100 metric and 13.26% in map@100 metric. The validity and rationality of the model are proved.

Graph-based stock prediction with multisource information and relational data fusion

With the application of multisource information in different fields, the combination of different types of information, such as numerical data and text information, has become a favourable choice for performing stock market analyses. Despite the rich information provided by multisource data, building structured relationships remains challenging. In addition, some market relationship-based analysis methods use a predefined graph structure as a stock relationship graph, which makes it impossible to sensitively aggregate attribute features, and these methods cannot dynamically update market relationships or relationship strengths. In this paper, we propose a novel dynamic attribute-driven graph attention network incorporating sentiment (AGATS) information, transaction data, and text data. Inspired by behavioural finance, we separately extract sentiment information as a factor of technical indicators, and further realize the early fusion of technical indicators and textual data through tensor fusion. In particular, real-time intramarket dependencies and key attribute information are captured with graph networks, enabling dynamic relationship and relationship strength updates. Experiments conducted on real datasets show that our model is capable of ourperforming previously developed methods in prediction and trading.

PTNS: patent citation trajectory prediction based on temporal network snapshots

With the rapid development of science and technology, the pace of development in the knowledge economy is accelerating. Intellectual property, especially patents, is a strategic resource for technological innovation and a crucial support for building an innovative country. Therefore, it is particularly important to predict patents with high value and strong impact from the numerous and uneven-quality patents. However, patent citation behavior involves many uncertainties, and it is difficult to capture its temporal variations effectively. Therefore, this paper proposes a patent citation trajectory prediction model (PTNS) based on temporal network snapshots. It adopts relational graph convolutional networks (R-GCN) to learn the complex relationships among multiple attributes of patents and utilizes bidirectional long short-term memory networks (BiLSTM) to aggregate the temporal evolution differences of patents. Subsequently, principal component analysis (PCA) is used to explore the evolution characteristics of patent citations in depth, thereby capturing the aging effect and the ‘sleeping beauty’ phenomenon. Compared with other baselines, the PTNS performs well. In predicting new, grown, and random patents, the RMSLE decreases by approximately 0.04, 0.14, and 0.18 respectively, while the MALE decreases by approximately 0.04, 0.12, and 0.16 respectively.

On Generalizations of Pairwise Compatibility Graphs

A graph $G$ is a pairwise compatibility graph (PCG) if there exists an edge-weighted tree and an interval $I$, such that each leaf of the tree is a vertex of the graph, and there is an edge $\{ x, y \}$ in $G$ if and only if the weight of the path in the tree connecting $x$ and $y$ lies within the interval $I$. Originating in phylogenetics, PCGs are closely connected to important graph classes like leaf-powers and multi-threshold graphs, widely applied in bioinformatics, especially in understanding evolutionary processes. In this paper we introduce two natural generalizations of the PCG class, namely $k$-OR-PCG and $k$-AND-PCG, which are the classes of graphs that can be expressed as union and intersection, respectively, of $k$ PCGs. These classes can be also described using the concepts of the covering number and the intersection dimension of a graph in relation to the PCG class. We investigate how the classes of OR-PCG and AND-PCG are related to PCGs, $k$-interval-PCGs and other graph classes known in the literature. In particular, we provide upper bounds on the minimum $k$ for which an arbitrary graph $G$ belongs to $k$-interval-PCGs, $k$-OR-PCG or $k$-AND-PCG classes. For particular graph classes we improve these general bounds. Moreover, we show that, for every integer $k$, there exists a bipartite graph that is not in the $k$-interval-PCGs class, proving that there is no finite $k$ for which the $k$-interval-PCG class contains all the graphs. This answers an open question of Ahmed and Rahman from 2017. Finally, using a Ramsey theory argument, we show that for any $k$, there exists graphs that are not in $k$-AND-PCG, and graphs that are not in $k$-OR-PCG.

Perfect Resolution of Strong Conflict-Free Colouring of Interval Hypergraphs

The \(k\) -Strong Conflict-Free ( \(k\) -SCF, in short) colouring problem seeks to find a colouring of the vertices of a hypergraph \(H\) using minimum number of colours so that in every hyperedge \(e\) of \(H\) , there are at least \(\min\{|e|,k\}\) vertices whose colours are different from that of all other vertices in \(e\) . In the case of interval hypergraphs, we present an exact \({\mathsf{P}}\) -time algorithm for the \(k\) -SCF problem thus solving an open problem posed by Cheilaris et al. (2014). We achieve our results by showing that for any hypergraph, a \(k\) -SCF colouring is a proper colouring of a related simple graph which we refer to as a co-occurrence graph . We then show that a co-occurrence graph is obtained by identifying an induced subgraph of a second simple graph that we introduce, which we refer to as the conflict graph . For interval hypergraphs, we show that each co-occurrence graph and the conflict graph are perfect graphs. This property plays a crucial role in our polynomial time algorithm. Secondly, we show that for an interval hypergraph, the \(1\) -SCF colouring number is the minimum partition of its intervals into sets such that each set has an exact hitting set (a hitting set in which each interval is hit exactly once).

Discovering API usage specifications for security detection using two-stage code mining

An application programming interface (API) usage specification, which includes the conditions, calling sequences, and semantic relationships of the API, is important for verifying its correct usage, which is in turn critical for ensuring the security and availability of the target program. However, existing techniques either mine the co-occurring relationships of multiple APIs without considering their semantic relationships, or they use data flow and control flow information to extract semantic beliefs on API pairs but difficult to incorporate when mining specifications for multiple APIs. Hence, we propose an API specification mining approach that efficiently extracts a relatively complete list of the API combinations and semantic relationships between APIs. This approach analyzes a target program in two stages. The first stage uses frequent API set mining based on frequent common API identification and filtration to extract the maximal set of frequent context-sensitive API sequences. In the second stage, the API relationship graph is constructed using three semantic relationships extracted from the symbolic path information, and the specifications containing semantic relationships for multiple APIs are mined. The experimental results on six popular open-source code bases of different scales show that the proposed two-stage approach not only yields better results than existing typical approaches, but also can effectively discover the specifications along with the semantic relationships for multiple APIs. Instance analysis shows that the analysis of security-related API call violations can assist in the cause analysis and patch of software vulnerabilities.

An Algorithm for Predicting Vehicle Behavior in High-Speed Scenes Using Visual and Dynamic Graphical Neural Network Inference

Accidents caused by vehicles changing lanes occur frequently on highways. Moreover, frequent lane changes can severely impact traffic flow during peak commuting hours and on busy roads. A novel framework based on a multi-relational graph convolutional network (MR-GCN) is herein proposed to address these challenges. First, a dynamic multilevel relational graph was designed to describe interactions between vehicles and road objects at different spatio-temporal granularities, with real-time updates to edge weights to enhance understanding of complex traffic scenarios. Second, an improved spatio-temporal interaction graph generation method was introduced, focusing on spatio-temporal variations and capturing complex interaction patterns to enhance prediction accuracy and adaptability. Finally, by integrating a dynamic multi-relational graph convolutional network (DMR-GCN) with dynamic scene sensing and interaction learning mechanisms, the framework enables real-time updates of complex vehicle relationships, thereby improving behavior prediction’s accuracy and real-time performance. Experimental validation on multiple benchmark datasets, including KITTI, Apollo, and Indian, showed that our algorithmic framework achieves significant performance improvements in vehicle behavior prediction tasks, with Map, Recall, and F1 scores reaching 90%, 88%, and 89%, respectively, outperforming existing algorithms. Additionally, the model achieved a Map of 91%, a Recall of 89%, and an F1 score of 90% under congested road conditions in a self-collected high-speed traffic scenario dataset, further demonstrating its robustness and adaptability in high-speed traffic conditions. These results show that the proposed model is highly practical and stable in real-world applications such as traffic control systems and self-driving vehicles, providing strong support for efficient vehicle behavior prediction.

CIRG-SL: Commonsense Inductive Relation Graph framework with Soft Labels for Empathetic Response Generation

Empathy, the ability to understand and respond to others’ emotions, is critical in dialogue systems, particularly for applications such as psychological counselling and casual conversation. However, existing approaches often struggle to accurately capture emotional transitions in user utterances and dialogue contexts across multiple levels of granularity. Additionally, the orthogonality of one-hot emotion representations overlooks the subtle relationships between emotion categories. To overcome these limitations, we propose a novel framework: the commonsense inductive relation graph with fine emotional soft labels for empathetic response generation. This framework refines the representation of user utterances by incorporating commonsense knowledge to derive external emotional cues, which are integrated into an adaptive inductive relation graph. This graph explicitly captures and models dynamic emotional trajectories throughout the dialogue. Additionally, we propose a fine-grained soft label construction method that more accurately reflects the nuanced distribution of emotions, replacing the rigid one-hot encoding with a continuous representation that better captures inter-emotion relationships. Our approach achieves strong performance on the benchmark EmpatheticDialogues dataset, with a perplexity score of 27.85, Dist-1 of 1.81, Dist-2 of 6.58, and a dialogue emotion accuracy of 55.65%. These results highlight the effectiveness of our framework in capturing subtle emotions and generating contextually rich, empathetic responses.

MCAP: Low-Pass GNNs with Matrix Completion for Academic Recommendations

Graph Neural Networks (GNNs) are commonly used and have shown promising performance in recommendation systems. A major branch, Heterogeneous GNNs, models heterogeneous information by leveraging side information for academic paper recommendations. These networks use message passing and high-order propagation to learn representations for users and items. However, existing recommendation methods perform high-order propagation, leading to suboptimal representation learning. To address this issue, this paper proposes a framework called MCAP, which uses relation-aware GNNs and executes low-pass propagation with matrix completion to enhance academic paper recommendations. The framework uses an attention mechanism to learn top- U relationships by constructing a user-user relation graph based on common authors and venues from interacted items. To efficiently and effectively capture semantic-aware similar items, MCAP builds an item-item relation graph by fusing side information of papers using text embedding models (e.g., Mistral) and large language models (e.g., GPT-3.5-Turbo, GLM-4). Finally, the relation-aware user-user and item-item graphs are incorporated into existing GNN-based models to generate representations of users and papers to enhance academic paper recommendations. The effectiveness of the MCAP is validated using four academic datasets, AMiner-PC, AMiner-WeChat, CiteULike, and DBLP, with user-item interactions and side information of papers. Comprehensive experiments show that the MCAP outperforms state-of-the-art models in terms of Recall@5, NDCG@5, and HR@5 with 69.2%, 70.5%, and 77.6% on the AMiner-WeChat dataset. The code for MCAP is available at https://github.com/THUDM/MCAP .

A Controllability Reinforcement Learning Method for Pancreatic Cancer Biomarker Identification.

Pancreatic cancer is one of the most malignant cancers with rapid progression and poor prognosis. The use of transcriptional data can be effective in finding new biomarkers for pancreatic cancer. Many network-based methods used to identify cancer biomarkers are proposed, among which the combination of network controllability appears. However, most of the existing methods do not study RNA, rely on priori and mutations information, or can only achieve classification tasks. In this study, we propose a method combined Relational Graph Convolutional Network and Deep Q-Network called RDDriver to identify pancreatic cancer biomarkers based on multi-layer heterogeneous transcriptional regulation network. Firstly, we construct a regulation network containing long non-coding RNA, microRNA, and messenger RNA. Secondly, Relational Graph Convolutional Network is used to learn the node representation. Finally, we use the idea of Deep Q-Network to build a model, which score and prioritize each RNA with the Popov-Belevitch-Hautus criterion. We train RDDriver on three small simulated networks, and calculate the average score after applying the model parameters to the regulation networks separately. To demonstrate the effectiveness of the method, we perform experiments for comparison between RDDriver and other eight methods based on the approximate benchmark of three types cancer drivers RNAs.

Hub Cover Pebbling Number

The hub cover pebbling number, h ∗ ( G ) , of a graph $G$, is the least non-negative integer such that from all distributions of h ∗ ( G ) pebbles over the vertices of G , it is possible to place at least one pebble each on every vertex of a set of vertices of a hub set for G using a sequence of pebbling move operations, each pebbling move operation removes two pebbles from a vertex and places one pebble on an adjacent vertex. Here we compute the hub cover pebbling number for wheel related graphs.

Knowledge graph construction in hyperbolic space for automatic image annotation

Automatic image annotation (AIA) is a fundamental and challenging task in computer vision. Considering the correlations between tags can lead to more accurate image understanding, benefiting various applications, including image retrieval and visual search. While many attempts have been made to incorporate tag correlations in annotation models, the method of constructing a knowledge graph based on external knowledge sources and hyperbolic space has not been explored. In this paper, we create an attributed knowledge graph based on vocabulary, integrate external knowledge sources such as WordNet, and utilize hyperbolic word embeddings for the tag representations. These embeddings provide a sophisticated tag representation that captures hierarchical and complex correlations more effectively, enhancing the image annotation results. In addition, leveraging external knowledge sources enhances contextuality and significantly enriches existing AIA datasets. We exploit two deep learning-based models, the Relational Graph Convolutional Network (R-GCN) and the Vision Transformer (ViT), to extract the input features. We apply two R-GCN operations to obtain word descriptors and fuse them with the extracted visual features. We evaluate the proposed approach using three public benchmark datasets. Our experimental results demonstrate that the proposed architecture achieves state-of-the-art performance across most metrics on Corel5k, ESP Game, and IAPRTC-12.