In federated recommendation systems, model poisoning attacks aim to manipulate the gradient information of multiple target items sent back from local clients to the central server, with the goal of abnormally increasing their exposure across the system. Existing multi-target attack approaches directly manipulate multiple target items and apply a uniform attack strategy to all target items, which may lead to suboptimal promotion effectiveness. To address this issue, we introduce ProitMTA, a novel multi-target model poisoning attack framework that introduces proxy items and provides tailored attack strategies for target items. ProitMTA employs a three-stage process that balances the promotion of multiple target items while preserving recommendation quality. First,proxy item generationuses a Gaussian Mixture Model to create proxy items that represent diverse attack strategies. Second,proxy attack constructiondesigns customized gradient manipulation strategies for each proxy item. Finally,proxy-based target item attacktransfers these strategies to actual target items, enhancing their promotion while minimizing the negative impact on system performance. Through comprehensive experiments on multiple base federated recommendation frameworks and diverse real-world datasets, we demonstrate that ProitMTA outperforms existing attack methods, achieving higher success rates in target item promotion with minimal system-wide performance degradation. Our research highlights the vulnerability of federated recommendation systems when facing multi-target poisoning attacks and underscores the importance of researching effective defense mechanisms We have released our code athttps://github.com/zdy769243418/ProitMTA.

Cross-domain sequential recommendation (CSR) has garnered significant attention. Current federated frameworks for CSR leverage information across multiple domains but often rely on user alignment, which increases communication costs and privacy risks. In this work, we propose FedCSR, a novel federated cross-domain sequential recommendation framework that eliminates the need for user alignment between platforms. FedCSR fully utilizes cross-domain knowledge to address the key challenges related to data heterogeneity both inter- and intra-platform. To tackle the heterogeneity of data patterns between platforms, we introduce Model Contrastive Learning (MCL) to reduce the gap between local and global models. Additionally, we design Sequence Contrastive Learning (SCL) to address the heterogeneity of user preferences across different domains within a platform by employing tailored sequence augmentation techniques. Extensive experiments conducted on multiple real-world datasets demonstrate that FedCSR achieves superior performance compared to existing baseline methods.

Domain heterogeneity in federated learning presents significant challenges, particularly in complex tasks like semantic segmentation, where pixel-level accuracy is crucial. Existing approaches primarily focus on extracting domain-specific features, but they often overlook the importance of class-level feature invariance. In this paper, we propose FedSS, a novel federated semantic segmentation framework designed to address domain heterogeneity. FedSS introduces a Fine-grained Domain-agnostic Feature Extraction (DFE) module that standardizes feature maps using category-level statistics to ensure domain-agnostic feature extraction. Additionally, the Adaptive Ordering Based Feature Decorrelation (AFD) module enhances the model’s ability to distinguish between different semantic categories by decorrelating feature channels. To further tackle domain discrepancies, we present a Domain Fairness-aware Aggregation Strategy (DFA) that dynamically adjusts aggregation weights based on local domain variations. Our approach improves the robustness and generalization of the semantic segmentation model across diverse domains, ensuring more accurate and reliable pixel-level predictions. Experimental results demonstrate the effectiveness of FedSS in addressing domain heterogeneity and enhancing segmentation performance in federated learning settings. The source code is released at https://github.com/vibratingwings/FedSemanSeg

Federated Class Incremental Learning (FCIL) has emerged as a new paradigm due to its applicability in real-world scenarios. In FCIL, clients continuously generate new data with unseen class labels and do not share local data due to privacy restrictions, and each client’s class distribution evolves dynamically and independently. However, existing work still faces two significant challenges. Firstly, current methods lack a better balance between maintaining sound anti-forgetting effects over old data (stability) and ensuring good adaptability for new tasks (plasticity). Secondly, some FCIL methods overlook that the incremental data will also have a non-identical label distribution, leading to poor performance. This paper proposes CGoFed, which includes relax-constrained gradient update and cross-task gradient regularization modules. The relax-constrained gradient update prevents forgetting the knowledge about old data while quickly adapting to the new data by constraining the gradient update direction to a gradient space that minimizes interference with historical tasks. The cross-task gradient regularization also finds applicable historical models from other clients and trains a personalized global model to address the non-identical label distribution problem. The results demonstrate that the CGoFed performs well in alleviating catastrophic forgetting and improves model performance by 8% -23% compared with the SOTA comparison method.

Federated Graph Learning (FGL) enables multiple clients to collaboratively learn node representations from private subgraph data, such as user transactions or social networks. Local models are trained on clients and then aggregated by a central server, supporting large-scale graph learning without sharing raw data. However, most existing FGL methods assume that the number of nodes in the graph remains constant, while real-world scenarios often evolve, with new nodes and edges continually added and older ones removed due to limited device memory. We define this setting as Federated Continual Graph Learning (FCGL). In FCGL, global model aggregation may cause interference occur inter-task and inter-client, therefore, FCGL suffers from the global catastrophic forgetting: as the global model adapts to newly added nodes, it loses knowledge acquired from earlier graph data of clients. To address this, we propose GRE-FL, a generative replay framework, which can mitigate global catastrophic forgetting by generating a global summary graph at the server to preserve critical information from historical nodes. It also improves performance by equipping local models with a gating graph attention network for better feature extraction. Experiments show that GRE-FL achieves strong performance across multiple datasets.

Personalized federated learning (PFL) has become a hot research topic that can learn a personalized learning model for each client. Existing PFL models prefer to aggregate similar clients with similar data distribution to improve the performance of learning models. However, similarity-based PFL methods may exacerbate the class imbalance problem. In this article, we propose a novel dynamic affinity-based PFL (DA-PFL) model to alleviate the class imbalanced problem during federated learning. Specifically, we build an affinity metric from a complementary perspective to guide which clients should be aggregated. We then design a dynamic aggregation strategy that adjusts client aggregation based on the affinity metric in each round, thereby reducing the risk of class imbalance. Extensive experiments demonstrate that the proposed DA-PFL model can significantly improve the accuracy of each client in four real-world datasets with state-of-the-art comparison methods.

Cross-domain Sequential Recommendation (CSR) which leverages user sequence data from multiple domains has received extensive attention in recent years. However, the existing CSR methods require sharing origin user data across domains, which violates the General Data Protection Regulation (GDPR). Thus, it is necessary to combine federated learning (FL) and CSR to fully utilize knowledge from different domains while preserving data privacy. Nonetheless, the sequence feature heterogeneity across different domains significantly impacts the overall performance of FL. In this paper, we propose FedDCSR, a novel federated cross-domain sequential recommendation framework via disentangled representation learning. Specifically, to address the sequence feature heterogeneity across domains, we introduce an approach called inter-intra domain sequence representation disentanglement (SRD) to disentangle the user sequence features into domain-shared and domain-exclusive features. In addition, we design an intra domain contrastive infomax (CIM) strategy to learn richer domain-exclusive features of users by performing data augmentation on user sequences. Extensive experiments on three real-world scenarios demonstrate that FedDCSR achieves significant improvements over existing baselines1.