Aug 2026· Advanced Electromagnetics· Vol 15, pp. 5151-5163· 0 citations
TL;DR
A personalized learning path recommendation model based on federated learning that effectively balances global generalization and local adaptation while maintaining privacy protection is constructed, providing a feasible solution for secure and intelligent recommendation in distributed learning environments and offering technical insights for collaborative intelligence in privacy-sensitive electromagnetic information systems.
Abstract
To address the conflict between model generalization and personalized recommendation in distributed educational environments, this paper constructs a personalized learning path recommendation model based on federated learning. Such privacy-preserving collaborative learning frameworks are also valuable for intelligent information processing and distributed decision-making in modern electromagnetic communication and edge computing systems, where data sharing is often restricted. The proposed model employs a Graph Neural Network (GNN)-Transformer hybrid encoder that combines knowledge graphs with learning behavior sequences to accurately capture knowledge transfer relationships. A dynamic knowledge distillation aggregation strategy is introduced to generate soft labels from the global model for guiding local optimization, thereby preserving personalized characteristics while improving semantic consistency. Furthermore, an adaptive aggregation mechanism based on Kullback-Leibler (KL) divergence dynamically adjusts client weights to enhance robustness under heterogeneous data distributions. Experimental results demonstrate that the proposed method achieves excellent recommendation accuracy (average Hit@5 of 0.676 ± 0.009), sequence consistency (average NDCG@10 of 0.712 ± 0.008), and personalized responsiveness (average personalized score difference rate of 0. 38). The framework effectively balances global generalization and local adaptation while maintaining privacy protection, providing a feasible solution for secure and intelligent recommendation in distributed learning environments and offering technical insights for collaborative intelligence in privacy-sensitive electromagnetic information systems.
Federated learning (FL) is a practical framework that can train models on distributed user data while guaranteeing data privacy; however, due to heterogeneity in which each user has a different data distribution, problems frequently arise where both global and personalization performance deteriorate simultaneously. This dissertation presents methodologies for building efficient personalized models by identifying which strategies are effective in the global training stage and by showing how to preserve global knowledge while securing user-specific performance during local adaptation. First, we show that as data heterogeneity increases, the collapse of feature vectors is a more fundamental bottleneck than classifier weights, and propose a method that directly mitigates the discrepancy in representation magnitude between local and global models. Second, we analyze that a training approach that strengthens local alignment can induce forgetting of global knowledge (e.g., categories not observed locally), and propose a method that achieves both local alignment and global knowledge preservation by combining feature distillation based on the global model's feature vectors. Third, in federated personalized reward model learning with preference heterogeneity, we empirically verify the conventional belief that"increasing the number of global models yields better initialization,"and we show that when sufficient local fine-tuning is allowed, a single global initialization can instead provide stronger personalization performance. This study redefines the role of global initialization under data and preference heterogeneity and provides practical training strategies that simultaneously satisfy global knowledge preservation and personalization.
In online art education, the learning path has strong non-linear dependence and significant individual differences. Traditional sequential recommendation methods are inefficient because they struggle to dynamically model the skill topological constraints. This paper proposes a personalized art learning path recommendation algorithm named Art-DQN, which integrates graph attention networks and improved deep Q networks. Firstly, an art skill directed topological graph is constructed, and the graph attention network is used to extract high-order neighborhood features of the learner's skill state; Secondly, a dual-channel feature fusion module is designed, combining the skill graph features with the behavior sequence features encoded by LSTM and inputting them into the Q network; Finally, an ε-greedy exploration strategy based on skill topological constraints and a prioritized experience replay mechanism are proposed. Experiments on a dataset containing 500 real learners' logs and 1000 simulation trajectories show that the average skill mastery time of Art-DQN is 32.4 steps, which is 22.3% lower than that of the standard DQN, the target skill achievement rate reaches 92%, the number of prerequisite violations is 0, the path redundancy is as low as 0.09, and the convergence speed is increased by 41%. Ablation experiments verify the independent contributions of the dual-channel fusion and dynamic reward weights, and parameter sensitivity analysis and robustness tests further prove the stability of the algorithm. This algorithm provides an effective solution that combines structural constraints and personalized adaptation for intelligent recommendation in art education.
Sinuo Sun, Yansong Li· Journal of Discovery Core· 0 citations
Smart education platforms accumulate large volumes of learning resources and interaction logs. However, fixed recommendation sequences are often unable to adapt to differences in knowledge foundations, learning behaviors, and cognitive progress among learners. Existing learning path recommendation methods primarily focus on static matching and single-step ranking, while providing limited support for modeling learning state evolution and long-term path benefits. To improve learning resource recommendation accuracy, path continuity, and learning completion outcomes, a personalized learning path (PLP) optimization model integrating Transformer and Reinforcement Learning is developed. The model aims to generate learning resource sequences that align with individual cognitive processes through dynamic state awareness, sequential policy decision-making, and the incorporation of educational constraints. First, learning behavior sequences, knowledge point information, answer feedback, resource access records, and time intervals are encoded within a unified framework. A Transformer is employed to capture long-range dependencies and dynamic state features. Second, PLP generation is formulated as a continuous decision-making process, in which RL performs policy search within the candidate resource space. Finally, knowledge prerequisite relationships, difficulty progression rules, learning load boundaries, and a multi-objective reward function are incorporated into a unified optimization framework. Offline simulation experiments are conducted on three public datasets, namely EdNet, ASSISTments, and Junyi. Performance is compared with Self-Attentive Knowledge Tracing, Separable Self-Attentive Neural Knowledge Tracing Plus, Unified Knowledge Tracing (UniKT), and Time-Aware Reinforcement Learning. Experimental results indicate that Transformer and Reinforcement Learning for Learning Path (TFRL-Path) achieves a hit ratio of 0.846 on EdNet, exceeding UniKT by 0.025. On ASSISTments, the mean average precision reaches 0.737 and the completion rate reaches 0.801. On Junyi, precision reaches 0.736 and convergence epochs decrease to 38. The cross-dataset average composite score reaches 0.798 with a standard deviation of 0.028. The prerequisite satisfaction rate reaches 0.872, while the resource repetition rate decreases to 0.121. These findings suggest that closed-loop coordination among state representation, policy optimization, and educational constraints contributes to improvements in personalized learning path recommendation quality.
Local Inference Guided Aggregation for Heterogeneous Training Environments to Yield Enhancement Through Agreement and Regularization (LIGHTYEAR), a federated learning framework that performs update selection in function space using an NTK-based agreement score to characterize predictive behavior and determine a personalized aggregation set for each client.
Mirko Konstantin, S. Zachow, Anirban Mukhopadhyay· 0 citations
Federated Recommendation (FedRec) enables privacy-preserving recommendation by training models across user devices without sharing raw interaction data. However, personalized FedRec still faces a trade-off between personalization and resource efficiency. In this paper, we revisit personalization from the perspective of the local optimization horizon. We find that sufficiently long local optimization can form user-specific item structures, but frequent synchronization or full replacement can disrupt them. Based on this observation, we propose
FedRKG
, a model-agnostic framework that forms personalized item embeddings through
Long-Horizon Local Optimization
and injects common global knowledge through intermittent
Regularized Knowledge Guidance
. This design incorporates shared collaborative signals without replacing local embeddings or maintaining dual representations. We further introduce
Adaptive Guidance
to control the influence of global knowledge at the user–item interaction level. Extensive experiments show that FedRKG consistently outperforms state-of-the-art FedRec baselines while reducing storage and communication costs. Our code is available at
https://github.com/Jaehyung-Lim/FedRKG_JIIS26_SCIE
.
Jaehyung Lim, Wonbin Kweon, Woojoo Kim et al.· Journal of Intelligence and...· 0 citations
This study offers a novel method for attaining hyper-personalization in e-commerce by combining business intelligence (BI) and machine learning technologies with collaborative filtering driven by artificial intelligence (AI). The main goal is to improve recommendation systems so that they can provide highly relevant and personalized product recommendations that suit the tastes and habits of specific users. The suggested method enhances recommendation accuracy and diversity by utilizing sophisticated deep learning architectures like convolutional and recurrent neural networks to record intricate user-item interaction patterns. Hybrid models are used to overcome issues like data sparsity and cold-start issues. These models combine content-based and collaborative filtering, and they make use of auxiliary data sources like social networks. Real-time data analysis, user segmentation, and performance monitoring are further made possible by the integration of BI tools, which promotes operational enhancements and strategic decision-making. According to experimental data, this all inclusive methodology performs noticeably better than conventional techniques, attaining greater precision, recall, and user engagement metrics. In the end, a strong, scalable solution that can offer a smooth, customized shopping experience, boost customer satisfaction, cultivate loyalty, and propel revenue growth in cutthroat e-commerce environments is produced by the synergistic use of AI, machine learning, and BI.
Najhan Muhamad Ibrahim, Abiduzzaman S. M.· International Journal of Inn...· 0 citations