Relational Features Research Articles

ELPGPT: Large Language Models Enhancing Link Prediction in Electrical Knowledge Graph

Graphs provide essential means for organizing and analyzing complex equipment data. Although link prediction techniques have been widely applied to enhance knowledge graphs, existing methods still show room for improvement in accuracy, especially when dealing with sparse data. To address this, we introduce ELPGPT (Large Language Models Enhancing Link Prediction in Electrical Equipment Knowledge Graph), a novel approach that integrates large language models into link prediction to enhance the accuracy of relation prediction within electrical equipment knowledge graphs. The core of the ELPGPT method lies in the combination of large language models with traditional knowledge graph link prediction techniques. By leveraging the deep semantic understanding capabilities of large language models, this method effectively extracts relational features and enhances the handling of sparse data. Additionally, we employ a Retrieval-Augmented Generation (RAG) approach, which, by integrating external data sources, further enhances the precision and relevance of predictions. Experiments on the Electrical Equipment Knowledge Graph (EEKG) demonstrate that ELPGPT significantly improves performance across several metrics, including Hit@k, Mean Rank (MR), and Mean Reciprocal Rank (MRR). These results validate the effectiveness and potential applications of this method in the domain of link prediction for electrical equipment knowledge graphs.

Identifying Performance Issues in Cloud Service Systems Based on Relational-Temporal Features

Cloud systems, typically comprised of various components ( e.g. , microservices), are susceptible to performance issues, which may cause service-level agreement violations and financial losses. Identifying performance issues is thus of paramount importance for cloud vendors. In current practice, crucial metrics, i.e. , key performance indicators (KPIs), are monitored periodically to provide insight into the operational status of components. Identifying performance issues is often formulated as an anomaly detection problem, which is tackled by analyzing each metric independently. However, this approach overlooks the complex dependencies existing among cloud components. Some graph neural network-based methods take both temporal and relational information into account, however, the correlation violations in the metrics that serve as indicators of underlying performance issues are difficult for them to identify. Furthermore, a large volume of components in a cloud system results in a vast array of noisy metrics. This complexity renders it impractical for engineers to fully comprehend the correlations, making it challenging to identify performance issues accurately. To address these limitations, we propose Identifying Performance Issues based on Relational-Temporal Features (ISOLATE ), a learning-based approach that leverages both the relational and temporal features of metrics to identify performance issues. In particular, it adopts a graph neural network with attention to characterizing the relations among metrics and extracts long-term and multi-scale temporal patterns using a GRU and a convolution network, respectively. The learned graph attention weights can be further used to localize the correlation-violated metrics. Moreover, to relieve the impact of noisy data, ISOLATE utilizes a positive unlabeled learning strategy that tags pseudo labels based on a small portion of confirmed negative examples. Extensive evaluation on both public and industrial datasets shows that ISOLATE outperforms all baseline models with 0.945 F1-score and 0.920 Hit rate@3. The ablation study also proves the effectiveness of the relational-temporal features and the PU-learning strategy. Furthermore, we share the success stories of leveraging ISOLATE to identify performance issues in Huawei Cloud, which demonstrates its superiority in practice.

Node Importance Estimation for Knowledge Graphs Based on Multi-Perspectives Attention Fusion Mechanism

The advent of the Internet has led to the emergence of multi-source heterogeneous knowledge graphs, which have become a crucial means of storing and disseminating knowledge. Node importance estimation is a technique that is employed extensively in a number of fields, including recommender systems, intelligent search and resource allocation. This study introduces a Multi-perspective attention mechanism Fusion Algorithm for the mapping of multi-perspective features of knowledge graphs to Node Importance Estimation (MFA-NIE). First, structural embedding features, relational predicate features, and attribute features (both textual and quantitative) are established for the nodes. Subsequently, an enhanced attention mechanism is employed to extract, compress, and fuse these features. The fused hidden layer vector is employed in the design of a key-based attention mechanism, which enables the propagation of messages from neighboring nodes to the source node. This process results in the iterative updating of the source node’s hidden features. Finally, TOPSIS centrality, based on the topology of the source node, is employed to dynamically adjust the mapping between the fused features and node importance. Experiments were conducted on real-world, large-scale, multi-source, heterogeneous knowledge graphs, comparing the MFA-NIE algorithm with traditional and advanced baseline algorithms, including PR, PPR, GENI, RGTN, CLINE, MCRL, and others. The results demonstrate that the MFA-NIE algorithm significantly improves effectiveness and accuracy, showcasing its superiority, versatility, and practical application value.

Urban Land Use Classification Model Fusing Multimodal Deep Features

Urban land use classification plays a significant role in urban studies and provides key guidance for urban development. However, existing methods predominantly rely on either raster structure deep features through convolutional neural networks (CNNs) or topological structure deep features through graph neural networks (GNNs), making it challenging to comprehensively capture the rich semantic information in remote sensing images. To address this limitation, we propose a novel urban land use classification model by integrating both raster and topological structure deep features to enhance the accuracy and robustness of the classification model. First, we divide the urban area into block units based on road network data and further subdivide these units using the fractal network evolution algorithm (FNEA). Next, the K-nearest neighbors (KNN) graph construction method with adaptive fusion coefficients is employed to generate both global and local graphs of the blocks and sub-units. The spectral features and subgraph features are then constructed, and a graph convolutional network (GCN) is utilized to extract the node relational features from both the global and local graphs, forming the topological structure deep features while aggregating local features into global ones. Subsequently, VGG-16 (Visual Geometry Group 16) is used to extract the image convolutional features of the block units, obtaining the raster structure deep features. Finally, the transformer is used to fuse both topological and raster structure deep features, and land use classification is completed using the softmax function. Experiments were conducted using high-resolution Google images and Open Street Map (OSM) data, with study areas on the third ring road of Shenyang and the fourth ring road of Chengdu. The results demonstrate that the proposed method improves the overall accuracy and Kappa coefficient by 9.32% and 0.17, respectively, compared to single deep learning models. Incorporating subgraph structure features further enhances the overall accuracy and Kappa by 1.13% and 0.1. The adaptive KNN graph construction method achieves accuracy comparable to that of the empirical threshold method. This study enables accurate large-scale urban land use classification with reduced manual intervention, improving urban planning efficiency. The experimental results verify the effectiveness of the proposed method, particularly in terms of classification accuracy and feature representation completeness.

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.

Chronobridge: a novel framework for enhanced temporal and relational reasoning in temporal knowledge graphs

The task of predicting entities and relations in Temporal Knowledge Graph (TKG) extrapolation is crucial and has been studied extensively. Mainstream algorithms, such as Gated Recurrent Unit (GRU) models, primarily focus on encoding historical factual features within TKGs, often neglecting the importance of incorporating entities and relational features during decoding. This bias ultimately leads to loss of detail and inadequate prediction accuracy during the inference process. To address this issue, a novel ChronoBridge framework is proposed that features a dual mechanism of a chronological node encoder and a bridged feature fusion decoder. Specifically, the chronological node encoder employs an advanced recursive neural network with an enhanced GRU in an autoregressive manner to model historical KG sequences, thereby accurately capturing entity changes over time and significantly enhancing the model’s ability to identify and encode temporal patterns of facts across the timeline. Meanwhile, the bridged feature fusion decoder utilizes a new variant of GRU and a multilayer perception mechanism during the prediction phase to extract entity and relation features and fuse them for inference, thereby strengthening the reasoning capabilities of the model for future events. Testing on three standard datasets showed significant improvements, with a 25.21% increase in MRR accuracy and a 39.38% enhancement in relation inference. This advancement not only improves the understanding of temporal evolution in knowledge graphs but also sets a foundation for future research and applications of TKG reasoning.

Enhancing Real-Time Visual SLAM with Distant Landmarks in Large-Scale Environments

The efficacy of visual Simultaneous Localization and Mapping (SLAM) diminishes in large-scale environments due to challenges in identifying distant landmarks, leading to a limited perception range and trajectory drift. This paper presents a practical method to enhance the accuracy of feature-based real-time visual SLAM for compact unmanned vehicles by constructing distant map points. By tracking consecutive image features across multiple frames, remote map points are generated with sufficient parallax angles, extending the mapping scope to the theoretical maximum range. Observations of these landmarks from preceding keyframes are supplemented accordingly, improving back-end optimization and, consequently, localization accuracy. The effectiveness of this approach is ensured by the introduction of the virtual map point, a proposed data structure that links relational features to an imaginary map point, thereby maintaining the constrained size of local optimization during triangulation. Based on the ORB-SLAM3 code, a SLAM system incorporating the proposed method is implemented and tested. Experimental results on drone and vehicle datasets demonstrate that the proposed method outperforms ORB-SLAM3 in both accuracy and perception range with negligible additional processing time, thus preserving real-time performance. Field tests using a UGV further validate the efficacy of the proposed method.

Reinforcement learning-based portfolio optimization with deterministic state transition

Portfolio optimization has attracted substantial interest within the artificial intelligence community due to its significant impact on financial decision-making, risk management, and market analysis. Reinforcement learning fits well with portfolio optimization because their goal is to maximize cumulative returns. In reinforcement learning, state transition probabilities are often unknown and must be estimated. However, in portfolio backtesting experiments, these probabilities are deterministic, making the conventional reinforcement learning approach to estimating state transitions suboptimal for portfolio optimization. Addressing this issue, this study decomposes the portfolio optimization into two core tasks: prediction and profit policy optimization and proposes a novel reinforcement learning framework that assumes deterministic state transition probabilities, comprised of three main modules: feature extraction, prediction, and profit strategy optimization. To model assets more effectively and comprehensively, we capture their temporal features, relational features, and market state. We introduce a patch-wise correlation method and attribute based gate to enhance feature extraction. In the profit policy module, we utilize a deterministic strategy, employing a recursive reinforcement learning method based on Monte Carlo sampling to train the policy network. This enables dynamic adjustments of asset investment weights, ensuring the maximization of cumulative returns. Extensive experiments conducted on cryptocurrency datasets demonstrate the superior performance of our approach, and achieving 36.6%-75.6% improvements in main measurements on cryptocurrency datasets.

Integrating AI with medical industry chain data: enhancing clinical nutrition research through semantic knowledge graphs.

In clinical nutrition research, the medical industry chain generates a wealth of multidimensional spatial data across various formats, including text, images, and semi-structured tables. This data's inherent heterogeneity and diversity present significant challenges for processing and mining, which are further compounded by the data's diverse features, which are difficult to extract. To address these challenges, we propose an innovative integration of artificial intelligence (AI) with the medical industry chain data, focusing on constructing semantic knowledge graphs and extracting core features. These knowledge graphs are pivotal for efficiently acquiring insights from the vast and granular big data within the medical industry chain. Our study introduces the Clinical Feature Extraction Knowledge Mapping ( ) model, designed to augment the attributes of medical industry chain knowledge graphs through an entity extraction method grounded in syntactic dependency rules. The model is applied to real and large-scale datasets within the medical industry chain, demonstrating robust performance in relation extraction, data complementation, and feature extraction. It achieves superior results to several competitive baseline methods, highlighting its effectiveness in handling medical industry chain data complexities. By representing compact semantic knowledge in a structured knowledge graph, our model identifies knowledge gaps and enhances the decision-making process in clinical nutrition research.

Survival Analysis on Lung Cancer Patients in Damaturu-Nigeria

Cancer is one of the leading causes of death by lung cancer in particular, is the leading cause of cancer death in both men and women, accounting for 23% of all cancer deaths in 2019 according to the Centers for Disease Control and Prevention. One particular problem with lung cancer is that it usually has a poor prognosis. With such a deadly disease, it is crucial to predict the survival likelihood of cancer patients. However, this is not an easy task due to the many factors affecting the disease progression. Survival time has become an essential outcome of clinical trial, which began to emerge among the latter half of the 20th century. A present study was carried out on the survival analysis for patients with lung cancer. The data was obtained from Yobe State Specialist Hospital, Damaturu where each sample was collected from the recipients of the treatment of radical prostatectomy. The Kaplan Meier method was used to obtain and estimate the survival function and median. The log-rank test was used to test the differences in the survival curves. The cox proportional hazard (PH) model provided an effective covariate on the hazard function. As a result of cox PH model, the influence of standard clinical prognostic factors is based on the hazard rate of lung cancer patients. We performed rigorous cross-examination on each feature's relationship and the model for each feature type using data analysis information and survival analysis models. For each feature type, we used one representative survival analysis model from semi-parametric methods (Cox proportional hazards model), one from non-parametric methods (Kaplan-Meier estimator), and one from machine learning approaches (random survival forests). Using the results obtained from these different methods, we identified the best feature types and model combinations to get the top performance for various follow-up periods. The best model is Cox proportional hazards model based on the AIC and log-likelihood functions respectively.

Relational Persistent Homology for Multispecies Data with Application to the Tumor Microenvironment

Topological data analysis (TDA) is an active field of mathematics for quantifying shape in complex data. Standard methods in TDA such as persistent homology (PH) are typically focused on the analysis of data consisting of a single entity (e.g., cells or molecular species). However, state-of-the-art data collection techniques now generate exquisitely detailed multispecies data, prompting a need for methods that can examine and quantify the relations among them. Such heterogeneous data types arise in many contexts, ranging from biomedical imaging, geospatial analysis, to species ecology. Here, we propose two methods for encoding spatial relations among different data types that are based on Dowker complexes and Witness complexes. We apply the methods to synthetic multispecies data of a tumor microenvironment and analyze topological features that capture relations between different cell types, e.g., blood vessels, macrophages, tumor cells, and necrotic cells. We demonstrate that relational topological features can extract biological insight, including the dominant immune cell phenotype (an important predictor of patient prognosis) and the parameter regimes of a data-generating model. The methods provide a quantitative perspective on the relational analysis of multispecies spatial data, overcome the limits of traditional PH, and are readily computable.

MLP-AIR: An effective MLP-based module for actor interaction relation learning in group activity recognition

Modeling actor interaction relations is crucial for group activity recognition. Previous approaches often adopt a fixed paradigm that involves calculating an affinity matrix to model these interaction relations, yielding significant performance. On the one hand, the affinity matrix introduces an inductive bias that actor interaction relations should be dynamically computed based on the input actor features. On the other hand, MLPs with static parameterization, in which parameters are fixed after training, can represent arbitrary functions. Therefore, it is an open question whether inductive bias is necessary for modeling actor interaction relations. To explore the impact of this inductive bias, we propose an affinity matrix-free paradigm that directly uses the MLP with static parameterization to model actor interaction relations. We term this approach MLP-AIR. This paradigm overcomes the limitations of the inductive bias and enhances the capture of implicit actor interaction relations. Specifically, MLP-AIR consists of two sub-modules: the MLP-based Interaction relation modeling module (MLP-I) and the MLP-based Relation refining module (MLP-R). MLP-I is used to model the spatial–temporal interaction relations by emphasizing cross-actor and cross-frame feature learning. Meanwhile, MLP-R is used to refine the relation between different channels of each relation feature, thereby enhancing the expression ability of the features. MLP-AIR is a plug-and-play module. To evaluate our module, we applied MLP-AIR to replicate three representative methods. We conducted extensive experiments on two widely used benchmarks—the Volleyball and Collective Activity datasets. The experiments demonstrate that MLP-AIR achieves favorable results. The code is available at https://github.com/Xuguoliang12/MLP-AIR.

Enhancing molecular property prediction with auxiliary learning and task-specific adaptation

Pretrained Graph Neural Networks have been widely adopted for various molecular property prediction tasks. Despite their ability to encode structural and relational features of molecules, traditional fine-tuning of such pretrained GNNs on the target task can lead to poor generalization. To address this, we explore the adaptation of pretrained GNNs to the target task by jointly training them with multiple auxiliary tasks. This could enable the GNNs to learn both general and task-specific features, which may benefit the target task. However, a major challenge is to determine the relatedness of auxiliary tasks with the target task. To address this, we investigate multiple strategies to measure the relevance of auxiliary tasks and integrate such tasks by adaptively combining task gradients or by learning task weights via bi-level optimization. Additionally, we propose a novel gradient surgery-based approach, Rotation of Conflicting Gradients (RCGrad\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mathop {\ exttt{RCGrad}}\\limits$$\\end{document}), that learns to align conflicting auxiliary task gradients through rotation. Our experiments with state-of-the-art pretrained GNNs demonstrate the efficacy of our proposed methods, with improvements of up to 7.7% over fine-tuning. This suggests that incorporating auxiliary tasks along with target task fine-tuning can be an effective way to improve the generalizability of pretrained GNNs for molecular property prediction.Scientific contributionWe introduce a novel framework for adapting pretrained GNNs to molecular tasks using auxiliary learning to address the critical issue of negative transfer. Leveraging novel gradient surgery techniques such as RCGrad\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mathop {\ exttt{RCGrad}}\\limits$$\\end{document}, the proposed adaptation framework represents a significant departure from the dominant pretraining fine-tuning approach for molecular GNNs. Our contributions are significant for drug discovery research, especially for tasks with limited data, filling a notable gap in the efficient adaptation of pretrained models for molecular GNNs.

Attentive multi-granularity perception network for person search

Person search is an extremely challenging task that seeks to identify individuals through joint person detection and person re-identification from uncropped real scene images. Previous studies primarily focus on learning rich features to enhance identification. However, arbitrary feature enhancement strategies may introduce unwanted background noise. Moreover, different scenarios usually exhibit varying pedestrian appearances or even intricate occlusions, leading to inconsistent/incomplete pedestrian features in different images. In this paper, we introduce a novel Attentive Multi-granularity Perception (AMP) module seamlessly integrated into our AMPN network. This module specifically addresses appearance variations and occlusions within a person's Region of Interest (RoI). The AMP module harnesses discriminative relationship features from various local regions, significantly enhancing identification accuracy. It comprises two principal components: the Pedestrian Perception Enhancement (PPE) block and the Background Interference Suppressor (BIS). The PPE block introduces a Spatial-wise Feature Mixer and a Channel-wise Feature Mixer, which effectively capture and refine discriminative relation features. Simultaneously, the BIS operates in parallel with the PPE block, enriching the discriminative relation features and enhancing the distinctiveness between the foreground and background. Our AMP module is plug-and-play and can integrate with other person search models. Extensive experiments validate our model's merits, achieving state-of-the-art performance on CUHK-SYSU and a 4.8% mAP gain over SeqNet on PRW at a desirable speed. Our code is accessible at https://github.com/zqx951102/AMPN.

Integration Policy Networks and the Potential for Local Integration Policy Diffusion in European Small- and Medium-Sized Towns and Rural Areas: A Comparative Analysis

This article aims to open a debate about the diffusion of local integration policies in European small- and medium-sized towns and rural areas (SMsTRAs), shedding light on local policymakers’ relational environment and key features of policy networks that influence policy diffusion. Elaborating on data collected through 343 interviews across 34 SMsTRAs, analysed through social network analysis and qualitative content analysis, it concludes that the relational environment in SMsTRAs is unfavourable for integration policy diffusion due to specific characteristics of integration policy networks and the growing politicisation of local integration policymaking. Nonetheless, relevant variation is identified across different types of SMsTRAs.

Early identification of high attention content for online mental health community users based on multi-level fusion model

PurposeThe overload of user-generated content in online mental health community makes the focus and resonance tendencies of the participating groups less clear. Thus, the purpose of this paper is to build an early identification mechanism for users' high attention content to promote early intervention and effective dissemination of professional medical guidance.Design/methodology/approachWe decouple the identification mechanism from two processes: early feature combing and algorithmic model construction. Firstly, based on the differentiated needs and concerns of the participant groups, the multiple features of “information content + source users” are refined. Secondly, a multi-level fusion model is constructed for features processing. Specifically, Bidirectional Encoder Representation from Transformers (BERT)-Bi-directional Long-Short Term Memory (BiLSTM)-Linear are used to refine the semantic features, while Graph Attention Networks (GAT) is used to capture the entity attributes and relation features. Finally, the Convolutional Neural Network (CNN) is used to optimize the multi-level fusion features.FindingsThe results show that the ACC of the multi-level fusion model is 84.42%, F1 is 79.43% and R is 76.71%. Compared with other baseline models and single feature elements, the ACC and F1 values are improved to different degrees.Originality/valueThe originality of this paper lies in analyzing multiple features based on early stages and constructing a new multi-level fusion model for processing. Further, the study is valuable for the orientation of psychological patients' needs and early guidance of professional medical care.

Interaction-and-Response Network for Distantly Supervised Relation Extraction.

Distantly supervised relation extraction (DSRE) aims to identify semantic relations from massive plain texts. A broad range of the prior research has leveraged a series of selective attention mechanisms over sentences in a bag to extract relation features without considering dependencies among the relation features. As a result, potential discriminative information existed in the dependencies is ignored, causing a decline in the performance of extracting entity relations. In this article, we focus on going beyond the selective attention mechanisms and propose a new framework termed interaction-and-response network (IR-Net) that adaptively recalibrates the features of sentence, bag, and group levels by explicitly modeling interdependencies among the features on each level. The IR-Net consists of a series of interactive and responsive modules throughout feature hierarchy, seeking to strengthen its power of learning salient discriminative features for distinguishing entity relations. We conduct extensive experiments on three benchmark DSRE datasets, including NYT-10, NYT-16, and Wiki-20m. The experimental results demonstrate that the IR-Net brings obvious improvements in performance when comparing ten state-of-the-art DSRE methods for entity relation extraction.

Various Approaches for Software vulnerability Assessment and Risk Identification using soft computing Techniques

The detection of software flaws is a viable technique for enhancing the quality of technology and testing management by providing rapid detection of deficiency simulation models until the actual testing phase starts. These prediction outcomes help designers of technology effectively devote their available resources to components that are more vulnerable to deficiencies. In this research investigation, a software bug prediction model is proposed using Deep Learning (DL) approach. The Recurrent Neural Network (RNN) is used for classification of source code including numerous soft computing techniques. Numerous preprocessing and data filtration techniques have been carried out for data balancing and normalization. The Term Frequency and Inverse Document Frequency (TF-IDF) and relation features extraction techniques is used to generate Vector Space Model (VSM). The classification has been done using RNN on both training and validation dataset. The evaluation of performance of proposed work is performed using various real-time and synthetic accessible databases. It is observed from the experimental results that the proposed framework performs better when different evaluated with different datasets

Meta-path structured graph pre-training for improving knowledge tracing in intelligent tutoring

Knowledge tracing (KT) aims to predict students’ future performance by tracking their learning behaviors in intelligent tutoring systems (ITS). In KT, three main types of entities are involved: students, exercises, and knowledge concepts. Graph structures provide an effective framework for establishing relationships between different entities. However, existing KT methods have neglected complex connections and implicit relational features, thus facing challenges in capturing high-order information in educational data. To this end, this paper proposes MPSG, a Meta-Path Structured Graph method designed to harness high-order information between entities to pre-train informative exercise embeddings for improving KT. Technically, structured by different meta-paths, four relation graphs are derived to establish implicit cross-entity relationships. On each graph, the surrounding neighbors of each node are then obtained through an intimacy-based sampling strategy. Subsequently, during the representation learning stage, node features under different meta-path views are generated and then aggregated to obtain the final exercise embeddings. The learned embeddings are optimized through three auxiliary tasks, anchored within a self-supervised learning paradigm. Extensive experiments across four public datasets demonstrate that our method can significantly enhance the predictive performance of downstream KT models.

Exploring the Role of Self-Adaptive Feature Words in Relation Quintuple Extraction for Scientific Literature

Extracting relation quintuple and feature words from unstructured text is a prelude to the construction of the scientific knowledge base. At present, the prior works use explicit clues between entities to study this task but ignore the use and the association of the feature words. In this work, we propose a new method to generate self-adaptive feature words from the original text for every single sample. These words can add additional correlation information to the knowledge graph. We allow the model to generate a new word representation and apply it to the original sentence to judge the relation type and locate the head and tail of the relation quintuple. Compared with the previous works, the feature words increase the flexibility of relying on information and improve the explanatory ability. Extensive experiments on scientific field datasets illustrate that the self-adaptive feature words method (SAFW) is good at ferreting out the unique feature words and obtaining the core part for the quintuple. It achieves good performance on four public datasets and obtains a markable performance improvement compared with other baselines.