Mining potential associations among entities in ethnic culture knowledge graphs is valuable for revealing evolutionary relationships among cultural elements and provides new technical paths for systematic modeling and intelligent reasoning of ethnic culture. However， because such graphs have characteristics of many-to-one attribute affiliations， highly homogeneous structures， and numerous noisy edges， the existing link prediction models are limited in capturing fine-grained feature associations among cultural entities simultaneously and resisting noisy edge interference in the graphs effectively， which restricts prediction performance and model robustness. To address these problems， a Graph Neural Network （GNN） model with similarity-aware features， SRGCN （Similarity-aware Relational Graph Convolutional Network） was proposed. In SRGCN， a dynamic aggregation mechanism was constructed on the basis of node feature similarity， so as to capture feature associations among entities more accurately. At the same time， a dual-level contrastive learning framework was introduced to suppress noise interference effectively， and a linearly weighted multi-objective loss function was designed， where the weights of primary and auxiliary tasks were adjusted dynamically to further enhance the model robustness. Experimental results on the HeritEdge ethnic culture knowledge graph dataset show that SRGCN outperforms the optimal baseline model， LTRGN （Linear self-attention with multi-Relational Graph Network）， achieving improvements of 28.4% and 32.5% on Mean Reciprocal Rank （MRR） and Hits@10， respectively， demonstrating better performance.

Malicious traffic detection is one of the key technologies to deal with network security challenges. Aiming at the problems of insufficient local labeled data and degradation of co-trained model performance due to non-Independent and Identical Distribution （non-IID） when using federated learning for malicious traffic detection， a semi-supervised federated learning-based malicious traffic detection model was constructed. The proposed model was trained effectively by information extracted from unlabeled data with the help of semi-supervised learning techniques of pseudo-labeling and consistency regularization terms. At the same time， a nonlinear function was designed to dynamically adjust the weights of the client's local supervised and unsupervised losses during aggregation to make full use of unlabeled data and improve accuracy of the model. To reduce the impact of non-IID problems on performance of the global model， a federated aggregation algorithm FedLD （Federated-Loss-Data） was proposed， which adaptively adjusted the weights of different client models in the global model aggregation process through a weight calculation method that combined training loss and data volume. Experimental results show that on NSL-KDD dataset， the proposed model can achieve higher detection accuracy when labeled data is limited. Compared with the baseline model FedSem （Federated Semi-supervised）， the proposed model has the detection accuracy increased by 4.11 percentage points， and the recall in Normal， Denial-of-Service （DoS）， Probe and other categories also increased by 1.65 to 7.66 percentage points， verifying that the proposed model is more suitable for applications in the field of malicious traffic detection.

With the continuous development of network applications， network resources are growing exponentially and information overload is becoming increasingly serious， so how to efficiently obtain the resources that meet the user needs has become one of the problems that bothering people. Recommendation system can effectively filter mass information and recommend the resources that meet the users needs. The research status of the recommendation system was introduced in detail， including three traditional recommendation methods of content-based recommendation， collaborative filtering recommendation and hybrid recommendation， and the research progress of four common deep learning recommendation models based on Convolutional Neural Network （CNN）， Deep Neural Network （DNN）， Recurrent Neural Network （RNN） and Graph Neural Network （GNN） were analyzed in focus. The commonly used datasets in recommendation field were summarized， and the differences between the traditional recommendation algorithms and the deep learning-based recommendation algorithms were analyzed and compared. Finally， the representative recommendation models in practical applications were summarized， and the challenges and the future research directions of recommendation system were discussed.

Aiming at the problem that the nearest neighbor parameters need to be set manually in density peak clustering algorithm based on shared nearest neighbor， a density peak clustering algorithm based on adaptive nearest neighbor parameters was proposed. Firstly， the proposed nearest neighbor parameter search algorithm was used to automatically obtain the nearest neighbor parameters. Then， the clustering centers were selected through the decision diagram. Finally， according to the proposed allocation strategy of representative points， all sample points were clustered through allocating the representative points and the non-representative points sequentially. The clustering results of the proposed algorithm was compared with those of the six algorithms such as Shared-Nearest-Neighbor-based Clustering by fast search and find of Density Peaks （SNN?DPC）， Clustering by fast search and find of Density Peaks （DPC）， Affinity Propagation （AP）， Ordering Points To Identify the Clustering Structure （OPTICS）， Density-Based Spatial Clustering of Applications with Noise （DBSCAN）， and K-means on the synthetic datasets and UCI datasets. Experimental results show that， the proposed algorithm is better than the other six algorithms on the evaluation indicators such as Adjusted Mutual Information （AMI）， Adjusted Rand Index （ARI） and Fowlkes and Mallows Index （FMI）. The proposed algorithm can automatically obtain the effective nearest neighbor parameters， and can better allocate the sample points in the edge region of the cluster.

Aiming at the problem of big clustering error of the Sparse Subspace Clustering （SSC） methods， an SSC method based on random blocking was proposed. First， the original problem dataset was divided into several subsets randomly to construct several sub-problems. Then， after obtaining the coefficient matrices of several sub-problems by the sparse subspace Alternating Direction Method of Multipliers （ADMM） respectively， these coefficient matrices were expanded into coefficient matrices of the same size as the original problem and integrated into a coefficient matrix. Finally， a similarity matrix was calculated according to the coefficient matrix obtained by the integration， and the clustering result of the original problem was obtained by using the Spectral Clustering （SC） algorithm. The SSC method based on random blocking has the subspace clustering error reduced by 3.12 percentage points on average compared with the optional algorithm among SSC， Stochastic Sparse Subspace Clustering via Orthogonal Matching Pursuit with Consensus （S³COMP-C）， scalable Sparse Subspace Clustering by Orthogonal Matching Pursuit （SSCOMP）， SC and K-Means algorithms， and has all the mutual information， Rand index and entropy significantly better than comparison algorithms. Experimental results show that the SSC method based on random blocking can significantly reduce subspace clustering error， and improve the clustering performance.

Concerning the premature convergence of invasive weed optimization algorithm, a new invasive weed optimization with multi-population based on chaotic sequence (CMIWO) was proposed. Firstly, chaotic sequence was adopted to initialize population at the initialization of algorithm, which improved the quality of the initial solution. Secondly, threshold was used to estimate the cluster degree of individuals in iterations and if cluster degree was less than threshold, initializing population with chaotic sequence was implemented again, thus the algorithm could effectively jump out of local minima. Thirdly, the weed population was divided into five groups to collaborate so as to discourage premature convergence, thus improving the algorithm's precision and increasing the convergence speed. In the end, the test results on eight test functions show that the proposed algorithm improves the accuracy by 25% to 300% than basic algorithm in terms of optimal value and 50% to 100% for standard deviation.