Federated Hierarchical Reinforcement Learning for Adaptive Traffic Signal Control

Multi-agent reinforcement learning (MARL) has shown promise for adaptive traffic signal control (ATSC), enabling multiple intersections to coordinate signal timings in real time. However, in large-scale settings, MARL faces constraints due to extensive data sharing and communication requirements. Federated learning (FL) mitigates these challenges by training shared models without directly exchanging raw data, yet traditional FL methods such as FedAvg struggle with highly heterogeneous intersections. Different intersections exhibit varying traffic patterns, demands, and road structures, so performing FedAvg across all agents is inefficient. To address this gap, we propose Hierarchical Federated Reinforcement Learning (HFRL) for ATSC. HFRL employs clustering-based or optimization-based techniques to dynamically group intersections and perform FedAvg independently within groups of intersections with similar characteristics, enabling more effective coordination and scalability than standard FedAvg. Our experiments on synthetic and real-world traffic networks demonstrate that HFRL not only outperforms both decentralized and standard federated RL approaches but also identifies suitable grouping patterns based on network structure or traffic demand, resulting in a more robust framework for distributed, heterogeneous systems.

Confronting Discrimination in Classification: Smote Based on Marginalized Minorities in the Kernel Space for Imbalanced Data

Financial fraud detection poses a typical challenge characterized by class imbalance, where instances of fraud are extremely rare but can lead to unpredictable economic losses if misidentified. Precisely classifying these critical minority samples represents a challenging task within the classification. The primary difficulty arises from mainstream classifiers, which often exhibit "implicit discrimination" against minority samples in evaluation metrics, which results in frequent misclassifications, and the key to the problem lies in the overlap of feature spaces between majority and minority samples. To address these challenges, oversampling is a feasible solution, yet current classical oversampling methods often lack the necessary caution in sample selection, exacerbating feature space overlap. In response, we propose a novel classification oversampling approach based on the decision boundary and sample proximity relationships. This method carefully considers the distance between critical samples and the decision hyperplane, as well as the density of surrounding samples, resulting in an adaptive oversampling strategy in the kernel space. Finally, we test the proposed method on a classic financial fraud dataset, and the results show that our proposed method provides an effective and robust solution that can improve the classification accuracy of minorities.