Low-dimensional Vector Research Articles

Research on a Link Prediction Algorithm Based on Hypergraph Representation Learning

Link prediction is a crucial area of study within complex networks research. Mapping nodes to low-dimensional vectors through network embeddings is a vital technique for link prediction. Most of the existing methods employ “node–edge”-structured networks to model the data and learn node embeddings. In this paper, we initially introduce the Clique structure to enhance the existing model and investigate the impact of introducing two Clique structures (LECON: Learning Embedding based on Clique Of the Network) and nine motifs (LEMON: Learning Embedding based on Motif Of the Network), respectively, on experimental performance. Subsequently, we introduce a hypergraph to model the network and reconfigure the network by mapping hypermotifs to two structures: open hypermotif and closed hypermotif, respectively. Then, we introduce hypermotifs as supernodes to capture the structural similarity between nodes in the network (HMRLH: HyperMotif Representation Learning on Hypergraph). After that, taking into account the connectivity and structural similarity of the involved nodes, we propose the Depth and Breadth Motif Random Walk method to acquire node sequences. We then apply this method to the LEMON (LEMON-DB: LEMON-Depth and Breadth Motif Random Walk) and HMRLH (HMRLH-DB: HMRLH-Depth and Breadth Motif Random Walk) algorithms. The experimental results on four different datasets indicate that, compared with the LEMON method, the LECON method improves experimental performance while reducing time complexity. The HMRLH method, utilizing hypernetwork modeling, proves more effective in extracting node features. The LEMON-DB and HMRLH-DB methods, incorporating new random walk approaches, outperform the original methods in the field of link prediction. Compared with state-of-the-art baselines, the proposed approach in this paper effectively enhances link prediction accuracy, demonstrating a certain level of superiority.

An intelligent online fault diagnosis system for gas turbine sensors based on unsupervised learning method LOF and KELM

The performance of gas turbine inevitably grades slowly in service. In order to obtain high-precision state assessment, an intelligent online real-time sensor fault diagnosis algorithm was proposed in this paper. This method can automatically establish an accurate diagnosis model in a short time, realize the rapid diagnosis of sensor faults, and can effectively solve the problem of operation data imbalance. Firstly, wavelet analysis quickly converts the high-dimensional time-series sensor signal into a low-dimensional feature vector. Then, the unsupervised method LOF was used to screen the abnormal sensor signals. Finally, the KELM is used to achieve fast online identify the fault modes of the sensors. This fault diagnosis system achieves a faster diagnosis speed while ensuring the accuracy. The effectiveness of the method proposed in this paper was verified on the operational data of a gas turbine, the diagnosis time is about 0.233 s, which greatly increases the diagnosis speed compared with other methods, at the same time, the proposed method can guarantee more than 95 % of diagnosis accuracy.

APTM: Structurally Informative Network Representation Learning

Network representation learning algorithms provide a method to map complex network data into low-dimensional real vectors, aiming to capture and preserve structural information within the network. In recent years, these algorithms have found widespread applications in tasks such as link prediction and node classification in graph data mining. In this work, we propose a novel algorithm based on an adaptive transfer probability matrix. We use a deep neural network, comprising an autoencoder, to encode and reduce the dimensionality of the generated matrix, thereby encoding the intricate structural information of the network into low-dimensional real vectors. We evaluate the algorithm's performance through node classification, and in comparison with mainstream network representation learning algorithms, our proposed algorithm demonstrates favorable results. It outperforms baseline models in terms of micro-F1 scores on three datasets: PPI, Citeseer, and Wiki.

Deep autoencoder architecture with outliers for temporal attributed network embedding

Temporal attributed network embedding aspires to learn a low-dimensional vector representation for each node in each snapshot of a temporal network, which can be capable of various network analysis tasks such as link prediction and node classification. In temporal attributed networks, attribute similarities or link structures of certain nodes may deviate from the regular nodes of the community they belong to, which are called community outlier nodes. However, many existing embedding methods consider only the link structures and their attributes of the nodes adhere to the community structure of the network while ignoring outlier nodes, this can affect the embedding performance of the regular nodes. In this paper, we propose a temporal attributed network embedding framework with outliers, based on autoencoders, to solve the problem. In particular, we propose an outlier-aware autoencoder to model the node information, which combines the current snapshot and previous snapshots to jointly learn embedded vectors of nodes in the current snapshot of a temporal network. In feature preprocessing, we propose a simplified higher graph convolutional mechanism to incorporate attribute information into link structure information, which can leverage attribute features into link structure. Experimental results on node classification and link prediction reveal that our model is competitive against various baseline models.

Learning to compensate for lack of information: Extracting latent knowledge for effective temporal knowledge graph completion

The goal of temporal knowledge graph embedding (TKGE) is to represent the entities and relations in a given temporal knowledge graph (TKG) as low-dimensional vectors (i.e., embeddings), which preserve both semantic information and temporal dynamics of the factual information. In this paper, we posit that the intrinsic difficulty of existing TKGE methods lies in the lack of information in KG snapshots with timestamps, each of which contains the facts that co-occur at a specific timestamp. To address this challenge, we propose a novel self-supervised TKGE approach, THOR (Three-tower grapH cOnvolution netwoRks (GCNs)), which extracts latent knowledge from TKGs by jointly leveraging both temporal and atemporal dependencies between entities and the structural dependency between relations. THOR learns the embeddings of entities and relations, obtained from three-tower GCNs by (1) maximizing the likelihood of the facts in a TKG and (2) addressing the lack of information in a TKG based on the auxiliary supervision signals of each entity. Our experiments on three real-world datasets demonstrate that THOR significantly outperforms 17 competitors in terms of TKG completion tasks. THOR yields up to 9.37% higher accuracy than the best competitor.

Attributed network embedding based on self-attention mechanism for recommendation method

Network embedding is a technique used to learn a low-dimensional vector representation for each node in a network. This method has been proven effective in network mining tasks, especially in the area of recommendation systems. The real-world scenarios often contain rich attribute information that can be leveraged to enhance the performance of representation learning methods. Therefore, this article proposes an attribute network embedding recommendation method based on self-attention mechanism (AESR) that caters to the recommendation needs of users with little or no explicit feedback data. The proposed AESR method first models the attribute combination representation of items and then uses a self-attention mechanism to compactly embed the combination representation. By representing users as different anchor vectors, the method can efficiently learn their preferences and reconstruct them with few learning samples. This achieves accurate and fast recommendations and avoids data sparsity problems. Experimental results show that AESR can provide personalized recommendations even for users with little explicit feedback information. Moreover, the attribute extraction of documents can effectively improve recommendation accuracy on different datasets. Overall, the proposed AESR method provides a promising approach to recommendation systems that can leverage attribute information for better performance.

Pumping the brakes on RNA velocity by understanding and interpreting RNA velocity estimates.

RNA velocity analysis of single cells offers the potential to predict temporal dynamics from gene expression. In many systems, RNA velocity has been observed to produce a vector field that qualitatively reflects known features of the system. However, the limitations of RNA velocity estimates are still not well understood. We analyze the impact of different steps in the RNA velocity workflow on direction and speed. We consider both high-dimensional velocity estimates and low-dimensional velocity vector fields mapped onto an embedding. We conclude the transition probability method for mapping velocity estimates onto an embedding is effectively interpolating in the embedding space. Our findings reveal a significant dependence of the RNA velocity workflow on smoothing via the k-nearest-neighbors (k-NN) graph of the observed data. This reliance results in considerable estimation errors for both direction and speed in both high- and low-dimensional settings when the k-NN graph fails to accurately represent the true data structure; this is an unknown feature of real data. RNA velocity performs poorly at estimating speed in both low- and high-dimensional spaces, except in very low noise settings. We introduce a novel quality measure that can identify when RNA velocity should not be used. Our findings emphasize the importance of choices in the RNA velocity workflow and highlight critical limitations of data analysis. We advise against over-interpreting expression dynamics using RNA velocity, particularly in terms of speed. Finally, we emphasize that the use of RNA velocity in assessing the correctness of a low-dimensional embedding is circular.

Nonlinear characterization of enhanced and generalized Hjorth’s feature space for bearing condition monitoring

The degradation assessment of rolling bearings provides a reasonable maintenance plan for the safe operation of mechanical equipment. The general strategy for bearing condition monitoring is to construct a health indicator (HI) to characterize different degradation stages. A preferable HI that can sensitively detect initial faults and track machine degradation is crucial to developing timely maintenance strategies for mechanical equipment to avoid catastrophic accidents. However, many developed and reported HIs are still insensitive to early faults, resulting in delayed maintenance schedules. To identify the incipient defects as early as possible, a novel HI constructed by nonlinear characterization of enhanced and generalized Hjorth’s feature space based on extended probability entropy is proposed in this paper. Firstly, the time-frequency spectral amplitude modulation helps to enhance the characteristics of the original signal with the amplitude editing in the time-frequency domain. Then, three new features of generalized Hjorth’s parameter combinations are designed and combined with other similar feature combinations to construct a high-dimensional enhanced and generalized Hjorth’s feature space. On this basis, a set of low-dimensional sensitive features is obtained by nonlinearly characterizing high-dimensional features through extended probability entropy after these features are standardized. Finally, a novel HI is developed by calculating the distance between the minimum volume ellipse (MVE) center of the low-dimensional feature subspace based on nonlinear characterization and the low-dimensional feature vector of the real-time monitoring signal. The performance of the proposed approach is verified in three cases, whose experimental results indicate that the proposed HI is more sensitive and significant in detecting early faults compared to some current HIs.

GcForest-based compound-protein interaction prediction model and its application in discovering small-molecule drugs targeting CD47.

Identifying compound-protein interaction plays a vital role in drug discovery. Artificial intelligence (AI), especially machine learning (ML) and deep learning (DL) algorithms, are playing increasingly important roles in compound-protein interaction (CPI) prediction. However, ML relies on learning from large sample data. And the CPI for specific target often has a small amount of data available. To overcome the dilemma, we propose a virtual screening model, in which word2vec is used as an embedding tool to generate low-dimensional vectors of SMILES of compounds and amino acid sequences of proteins, and the modified multi-grained cascade forest based gcForest is used as the classifier. This proposed method is capable of constructing a model from raw data, adjusting model complexity according to the scale of datasets, especially for small scale datasets, and is robust with few hyper-parameters and without over-fitting. We found that the proposed model is superior to other CPI prediction models and performs well on the constructed challenging dataset. We finally predicted 2 new inhibitors for clusters of differentiation 47(CD47) which has few known inhibitors. The IC50s of enzyme activities of these 2 new small molecular inhibitors targeting CD47-SIRPα interaction are 3.57 and 4.79μM respectively. These results fully demonstrate the competence of this concise but efficient tool for CPI prediction.

Disambiguation of company names via deep recurrent networks

Name Entity Disambiguation is the Natural Language Processing task of identifying textual records corresponding to the same Named Entity, i.e., real-world entities represented as a list of attributes (names, places, organisations, etc.). In this work, we face the task of disambiguating companies on the basis of their written names. We propose a Siamese LSTM Network approach to extract – via supervised learning – an embedding of company name strings in a (relatively) low dimensional vector space and use this representation to identify pairs of company names that actually represent the same company (i.e., the same Entity).Given that the manual labelling of string pairs is a rather onerous task, we analyse how an Active Learning approach to prioritise the samples to be labelled leads to a more efficient overall learning pipeline.The contributions of this work are: with empirical investigations on real-world industrial data, we show that our proposed Siamese Network outperforms several benchmark approaches based on standard string matching algorithms when enough labelled data are available; moreover, we show that Active Learning prioritisation is indeed helpful when labelling resources are limited, and let the learning models reach the out-of-sample performance saturation with less labelled data with respect to standard (random) data labelling approaches.

Entity Embeddings in Remote Sensing: Application to Deformation Monitoring for Infrastructure

There is a critical need for a global monitoring capability for Tailings Storage Facilities (TSFs), to help protect the surrounding communities and the environment. Satellite Synthetic Aperture Radar Interferometry (InSAR) shows much promise towards this ambition. However, extracting meaningful information and interpreting the deformation patterns from InSAR data can be a challenging task. One approach to address this challenge is through the use of data science techniques. In this study, the representation of InSAR metadata as Entity Embeddings within a Deep Learning framework (EE-DL) is investigated for modelling the spatio-temporal deformation response. Entity embeddings are commonly used in natural-language-processing tasks. They represent discrete objects, such as words, as continuous, low-dimensional vectors that can be manipulated mathematically. We demonstrate that EE-DL can be used to predict anomalous patterns in the InSAR time series. To evaluate the performance of the EE-DL approach in SAR interferometry, we conducted experiments over a mining test site (Cadia, Australia), which has been subject to a TSF failure. This study demonstrated that EE-DL can detect and predict the fine spatial movement patterns that eventually resulted in the failure. We also compared the results with deformation predictions from common baseline models, the Random Forest model and Gaussian Process Regression (GPR). Both EE-DL and GPR greatly outperform Random Forest. While GPR is also able to predict displacement patterns with millimetric accuracy, it detects a significantly lower number of anomalies compared to EE-DL. Overall, our study showed that EE-DL is a promising approach for building early-warning systems for critical infrastructures that use InSAR to predict ground deformations.

End-to-end metric learning from corrupted images using triplet dimensionality reduction loss

In this paper, we present a novel dimensionality reduction term (i.e. TripletPCA and ContrastivePCA) designed to enhance the robustness of pair-based loss functions in metric learning against image corruptions. Notably, our approach achieves this without the need for any data preprocessing steps. Our method can be seamlessly integrated into existing models, such as a block with Plug & Play framework. To the best of our knowledge, our TripletPCA and ContrastivePCA represent the first attempts to incorporate dimensionality reduction directly into pair-based metric learning losses for end-to-end metric learning. By projecting image features into low-dimensional vectors, our proposed loss functions effectively retain the essential components of images while mitigating the impact of corrupted features. Consequently, our metric learning loss function accurately computes feature distances through the projection. Experimental results demonstrate that our dimensionality reduction term can be easily incorporated into various types of existing deep neural networks. This integration leads to a substantial improvement in performance on standard benchmark datasets for corrupted image classification tasks. On several corruption datasets, we achieve an average performance improvement of 10.55% compared to existing baseline methods. Our code is available at https://github.com/Juryun/TDRL.

KSFinder-a knowledge graph model for link prediction of novel phosphorylated substrates of kinases.

Aberrant protein kinase regulation leading to abnormal substrate phosphorylation is associated with several human diseases. Despite the promise of therapies targeting kinases, many human kinases remain understudied. Most existing computational tools predicting phosphorylation cover less than 50% of known human kinases. They utilize local feature selection based on protein sequences, motifs, domains, structures, and/or functions, and do not consider the heterogeneous relationships of the proteins. In this work, we present KSFinder, a tool that predicts kinase-substrate links by capturing the inherent association of proteins in a network comprising 85% of the known human kinases. We also postulate the potential role of two understudied kinases based on their substrate predictions from KSFinder. KSFinder learns the semantic relationships in a phosphoproteome knowledge graph using a knowledge graph embedding algorithm and represents the nodes in low-dimensional vectors. A multilayer perceptron (MLP) classifier is trained to discern kinase-substrate links using the embedded vectors. KSFinder uses a strategic negative generation approach that eliminates biases in entity representation and combines data from experimentally validated non-interacting protein pairs, proteins from different subcellular locations, and random sampling. We assess KSFinder's generalization capability on four different datasets and compare its performance with other state-of-the-art prediction models. We employ KSFinder to predict substrates of 68 "dark" kinases considered understudied by the Illuminating the Druggable Genome program and use our text-mining tool, RLIMS-P along with manual curation, to search for literature evidence for the predictions. In a case study, we performed functional enrichment analysis for two dark kinases - HIPK3 and CAMKK1 using their predicted substrates. KSFinder shows improved performance over other kinase-substrate prediction models and generalized prediction ability on different datasets. We identified literature evidence for 17 novel predictions involving an understudied kinase. All of these 17 predictions had a probability score ≥0.7 (nine at >0.9, six at 0.8-0.9, and two at 0.7-0.8). The evaluation of 93,593 negative predictions (probability ≤0.3) identified four false negatives. The top enriched biological processes of HIPK3 substrates relate to the regulation of extracellular matrix and epigenetic gene expression, while CAMKK1 substrates include lipid storage regulation and glucose homeostasis. KSFinder outperforms the current kinase-substrate prediction tools with higher kinase coverage. The strategically developed negatives provide a superior generalization ability for KSFinder. We predicted substrates of 432 kinases, 68 of which are understudied, and hypothesized the potential functions of two dark kinases using their predicted substrates.

HPRE: Leveraging hierarchy-aware paired relation vectors for knowledge graph embedding

Knowledge graphs exhibit a typical hierarchical structure and find extensive applications in various artificial intelligence domains. However, large-scale knowledge graphs need to be completed, which limits the performance of knowledge graphs in downstream tasks. Knowledge graph embedding methods have emerged as a primary solution to enhance knowledge graph completeness. These methods aim to represent entities and relations as low-dimensional vectors, focusing on handling relation patterns and multi-relation types. Researchers need to pay more attention to the crucial feature of hierarchical relationships in real-world knowledge graphs. We propose a novel knowledge graph embedding model called Hierarchy-Aware Paired Relation Vectors Knowledge Graph Embedding (HPRE) to bridge this gap. By leveraging the power of 2D coordinates, HPRE adeptly model relation patterns, multi-relation types, and hierarchical features in the knowledge graph. Specifically, HPRE employs paired relation vectors to capture the distinct characteristics of head and tail entities, facilitating a better fit for relational patterns and multi-relation scenarios. Additionally, HPRE employs angular coordinates to differentiate entities at various levels of the hierarchy, effectively representing the hierarchical nature of the knowledge graph. The experimental results show that the HPRE model can effectively learn the hierarchical features of the knowledge graph and achieve state-of-the-art experimental results on multiple real-world datasets for the link prediction task.

Voxel2vec: A Natural Language Processing Approach to Learning Distributed Representations for Scientific Data.

Relationships in scientific data, such as the numerical and spatial distribution relations of features in univariate data, the scalar-value combinations' relations in multivariate data, and the association of volumes in time-varying and ensemble data, are intricate and complex. This paper presents voxel2vec, a novel unsupervised representation learning model, which is used to learn distributed representations of scalar values/scalar-value combinations in a low-dimensional vector space. Its basic assumption is that if two scalar values/scalar-value combinations have similar contexts, they usually have high similarity in terms of features. By representing scalar values/scalar-value combinations as symbols, voxel2vec learns the similarity between them in the context of spatial distribution and then allows us to explore the overall association between volumes by transfer prediction. We demonstrate the usefulness and effectiveness of voxel2vec by comparing it with the isosurface similarity map of univariate data and applying the learned distributed representations to feature classification for multivariate data and to association analysis for time-varying and ensemble data.

Billion-Scale Bipartite Graph Embedding: A Global-Local Induced Approach

Bipartite graph embedding (BGE), as the fundamental task in bipartite network analysis, is to map each node to compact low-dimensional vectors that preserve intrinsic properties. The existing solutions towards BGE fall into two groups: metric-based methods and graph neural network-based (GNN-based) methods. The latter typically generates higher-quality embeddings than the former due to the strong representation ability of deep learning. Nevertheless, none of the existing GNN-based methods can handle billion-scale bipartite graphs due to the expensive message passing or complex modelling choices. Hence, existing solutions face a challenge in achieving both embedding quality and model scalability. Motivated by this, we propose a novel graph neural network named AnchorGNN based on global-local learning framework, which can generate high-quality BGE and scale to billion-scale bipartite graphs. Concretely, AnchorGNN leverages a novel anchor-based message passing schema for global learning, which enables global knowledge to be incorporated to generate node embeddings. Meanwhile, AnchorGNN offers an efficient one-hop local structure modelling using maximum likelihood estimation for bipartite graphs with rational analysis, avoiding large adjacency matrix construction. Both global information and local structure are integrated to generate distinguishable node embeddings. Extensive experiments demonstrate that AnchorGNN outperforms the best competitor by up to 36% in accuracy and achieves up to 28 times speed-up against the only metric-based baseline on billion-scale bipartite graphs.

Transformer based contextual text representation framework for intelligent information retrieval

With the advent of transformer-based architectures, the contextual representation of text data has leveraged the query and the document to be represented in low-dimensional dense vector space. These vectors are learned embeddings of fixed sizes, resulting in deeper text understanding. In this study, we designed a pipeline for effectively retrieving documents from a large search space by combining the deeper text understanding capabilities of the transformer-based BERT model and a phrase embedding-based query expansion model. To learn the contextual representations, we fine-tuned a deep semantic matching model by separately encoding the document and the query. The encoder model is based on the Sentence BERT (SBERT) architecture, which separately generates dense vector representations of documents and queries. The study has also addressed the maximum token length limitation of transformer-based models through the summarization of lengthy documents. In addition, to improve the clarity and completeness of short queries and reduce the semantic gap, a phrase embedding-based query expansion model is employed. The documents and their dense vectors are indexed using the Elasticsearch engine, and matched them with query vectors for retrieving query-specific documents. Finally, the BERT-based cross-encoder model is used to re-rank the relevant records for each query. It performs full self-attention over the inputs, and yields richer text interactions to produce the final results. To assess performance, experiments are conducted on two well-known datasets, TREC-CDS-2014 and OHSUMED. A comparative analysis is carried out, which clearly demonstrates that the proposed framework produced competitive retrieval results.

Maximum Likelihood Estimation of Hierarchical Linear Models from Incomplete Data: Random Coefficients, Statistical Interactions, and Measurement Error

We consider two-level models where a continuous response R and continuous covariates C are assumed missing at random. Inferences based on maximum likelihood or Bayes are routinely made by estimating their joint normal distribution from observed data and . However, if the model for R given C includes random coefficients, interactions, or polynomial terms, their joint distribution will be nonstandard. We propose a family of unique factorizations involving selected “provisionally known random effects” u such that is normally distributed and u is a low-dimensional normal random vector; we approximate via adaptive Gauss-Hermite quadrature. For polynomial models, the approximation is exact but, in any case, can be made as accurate as required given sufficient computation time. The model incorporates random effects as explanatory variables, reducing bias due to measurement error. By construction, our factorizations solve problems of compatibility among fully conditional distributions that have arisen in Bayesian imputation based on the Gibbs Sampler. We spell out general rules for selecting u, and show that our factorizations can support fully compatible Bayesian methods of imputation using the Gibbs Sampler. Supplementary materials for this article are available online.

Estimating the relative importance of nodes in complex networks based on network embedding and gravity model

Identifying nodes that hold relative importance in complex networks is a burgeoning research area. Previous studies have demonstrated the effectiveness of the gravity model in capturing interactions among nodes in high-dimensional network space. Traditional algorithms predominantly concentrate on structural characteristics and node random walks in high-dimensional network space, overlooking substantial computational overhead and intricacies within the high-dimensional space. Simultaneously, the rapid evolution of the Internet has given rise to a series of emerging technologies, such as embedding models that can map high-dimensional network nodes to low-dimensional vector space. To address this issue, we introduce a novel algorithm for quantifying node relative importance, denoted as the Network Embedding and Gravity Model (NEGM). First, the network embedding method transforms nodes into low-dimensional, real-valued, dense vectors in Euclidean space. Then, drawing inspiration from Newton's law of universal gravitation, it proposes a novel gravity model. Finally, utilizing the novel gravity model, it calculates the aggregate attractive force of all nodes within the target node set. Experimental results show that NEGM excels in measuring the relative importance of nodes in various types of networks, demonstrating its significant potential for mining deep-seated information within authentic networks like protein networks and criminal networks.

Mineral prospectivity mapping integrated with geological map knowledge graph and geochemical data: A case study of gold deposits at Raofeng area, Shaanxi Province

The knowledge graph in geological applications is highly regarded, and its usefulness requires the support of geological survey data. Therefore, this paper proposes a mineral prospectivity mapping (MPM) method that integrates geological map knowledge graphs with geochemical data. The geological map knowledge graph is used in the vectorized form as knowledge features in the training of the mineral prediction model. It is also used for knowledge-based ore-forming interpretation of prospective areas, achieving bidirectional application of knowledge in prediction and interpretation of prediction results. Unlike most knowledge graphs, the geological map knowledge graph represents spatial correlations and geological features in the form of “entity-relation-entity” triplets, with geological map units as entities and assigned geological attributes. Based on this, an MPM process driven by knowledge graph and data is proposed: (1) Convert the geological map knowledge graph into low-dimensional vectors using node2VEC. (2) Align geological knowledge with geochemical data spatially through knowledge embedding gridization, achieving a forward fusion of knowledge and data. (3) Collect the integrated data using window sampling as the training dataset for DenseNet to train the mineral prospection model. A case study was conducted to demonstrate the advantages of the method for producing a potential map linked to gold mineralization in the Rao Feng area, Shaanxi Province, China. The results show that the prospective areas with knowledge graph embedding and geochemical data are better and delineate six unmineralized prospective areas. Ore-forming interpretations based on knowledge graph information were conducted on the prospective areas, demonstrating strong consistency between the ore-forming geological features of the prediction areas and known mineral deposits.