Knowledge Science, Engineering and Management: 18th International Conference, KSEM 2025, Macao, China, August 4–7, 2025, Proceedings, Part II(15920 Lecture Notes in Computer Science)

About the Book

The six-volume proceedings set LNAI 15919, 15920, 15921, 15922, 15923 and 15924 constitutes the refereed proceedings of the 18th International Conference on Knowledge Science, Engineering and Management, KSEM 2025, held in Macao, China during August 4-7, 2025.

The 106 papers and 66 short papers are included in these proceedings were carefully reviewed and selected from 354 submissions. They focus on all aspects of the exchange of research in artificial intelligence, data science, knowledge engineering, AI safety, large language models, and related frontier areas.

Table of Contents:
 .- Noise-Resistant Federated Open Set Recognition. .- Graph Representation-aware Online Aggregations over Knowledge Graph. .- LWMUNet: Enhancing Semantic Segmentation with Learnable Linked Sliding-Window Serialization. .- A Trusted Federated Learning Scheme for Distributed GAN Model Training. .- Multimodal Sentiment Analysis with Modality-Robust and -Biased Representations and Distance-aware Contrastive Learning. .- DeNoiseFood dataset with ECAMixDNet: an efficient denoising framework for complex textured food images. .- Leveraging Language Model and Knowledge Tracing for Personalized Question Generation. .- MFTP: Multi-round Feedback for Dynamic Travel Itinerary Optimization. .- GraphRAG-KM: An Automated Framework for Transforming Industrial Documents into Ontology and Conceptual Models. .- MPN: Leveraging Multilingual Patch Neuron for Cross-lingual Model Editing. .- AD^2-pFed: Personalized Federated Learning Based on Adaptive Bilateral Distillation with Diffusion Models. .- FATDyG: A Dynamic Network Link Prediction Framework for Time, Space, and Frequency Awareness. .- Resource Optimization for FPGA-based SM9 Digital Signature Algorithm. .- Enhancing Pruning Efficiency via Maximum Prunable Channel Selection in Tiny Object Detection. .- A Multimodal Fusion Framework employing Full-stage Attention for Survival Prediction. .- Differentially Private Graph Data Publishing via Feature-based Community Detection. .- Solving the Problem of Task Offloading in Heterogeneous Edge Computing Environments Using Deep Q-Networks and Attention Mechanisms. .- Ant Colony Sampling with Mixture of Experts for Combinatorial Optimization. .- MSCAN: Multi-Scale Context-Aware Network for Multivariate Long-Term Forecasting. .- PAformer: Transformer with Learnable Period Detection and Periodic Attention for Multivariate Time Series. .- ELS-GDR: Efficient Extraction of Long-Term Sequential Signals for Guiding Diffusion-Based Recommendation. .- EntiFA: Entity-based Fine-grained Adaptation for Knowledge Enhancement in Large Language Models. .- StressSentry-FHE: A Transformer-based Privacy-Preserving Framework for Stress Detection Using Quantized Attention. .- Dual Attention Transformer with Multi-scale Perception for Multivariate Time Series Forecasting. .- Uncertainty-Aware Prototype Semantic Decoupling for Text-Based Person Search in Full Images. .- Scale Margin Loss for Object Detection. .- Enhancing Fundus Image-based Glaucoma Screening via Dynamic Global-Local Feature Integration. .- BackdoorHunter: Poisoned Training Data Removal via Contrastive Responses under Pruned Models. .- Can LLMs Assist Computer Education? an Empirical Case Study of DeepSeek. .- Privacy-Preserving Federated Learning via Homomorphic Adversarial Networks. .- SoMORE: Social Context-aware MLLM for Video Character Search. .- A Multimodal Feature Fusion Method for Analyzing Children's Interests. .- Seaformer: An Adaptive forecasting Framework for Multi-source Heterogeneous Ocean Observation Data. .- Hybrid Kolmogorov-Arnold and Graph Attention Networks for Gold Price Forecasting under Uncertainty.