Multi-modal fusion indoor localization enabled by significant information gain is a crucial approach to ensure both accuracy and robustness. However, pronounced feature heterogeneity across modalities originating from distinct sources, and even intra-modality heterogeneity arising from multi-scale issues, can lead to severe ambiguity in location semantics, thereby severely constraining the localization accuracy of existing fusion methods. To address these challenges, we propose an accurate multi-modal fusion localization framework (FDLoc) that leverages frequency feature decomposition and dual-grained feature fusion to reduce intra- and inter-modality heterogeneity between magnetic and Wi-Fi modalities. First, we invoke Wavelet Packet Transforms to decompose the raw bimodal features in the frequency domain for explicitly representing their scale differences, and design a temporal-frequency attention to guide finegrained modeling of multi-scale features within each modality; by using nonlinear feature transformations, we further align the features of two modalities and adaptively fuse them across modalities, resulting in fused features with consistent semantic representation. Second, we incorporate contextual information from the localization process by employing a pretrained region prediction network to learn grid-level probability distribution, and use these coarse-grained region features to constrain the localization model for consistent positional convergence. Finally, we fuse the coarse- and fine-grained location semantic features using a gated network to achieve accurate location prediction. Experimental evaluations in typical indoor scenarios show that FDLoc consistently outperforms existing methods, with an average accuracy improvement of approximately 51 %.

Federated Learning (FL) is typically deployed in a client-server architecture, which makes the Edge-Cloud architecture an ideal backbone for FL. A significant challenge in this setup arises from the diverse data feature distributions across different edge locations (i.e., non-IID data). In response, Personalized Federated Learning (PFL) approaches have been developed. Network segmentation-based PFL is an important approach to achieving PFL, in which the training network is divided into a global segment for server aggregation and a local segment maintained client-side. Existing methods determine the segmentation before the training, and the segmentation remains fixed throughout the PFL training. However, our investigation reveals that model representations vary as PFL progresses and the fixed segmentation may not deliver best performance across various training settings. To address this, we propose PFed-NS, a PFL framework based on adaptive network segmentation. This adaptive segmentation technique is composed of two elements: a mechanism for assessing divergence of clients’ probability density functions constructed from network layers’ outputs, and a model for dynamically establishing divergence thresholds, beyond which server aggregation is deemed detrimental. Further optimization strategies are proposed to reduce the computation and communication costs incurred by divergence modeling. Moreover, we propose a divergence-based BN strategy to optimize BN performance for network segmentation-based PFL. Extensive experiments have been conducted to compare PFed-NS against recent PFL models. The results demonstrate its superiority in enhancing model accuracy and accelerating convergence.

Abstract Social recommendation often incorporates trusted social links with user-item interactions to enhance rating prediction. Although methods that aggregate explicit social links have shown promising prospects, they are often constrained by the absence of explicit social data and the assumption of homogeneity, thus overlooking variations in social influence and consistency. These limitations hinder semantic expression and recommendation performance. Therefore, we propose a novel framework for social recommendation. First, we design a bipartite network embedding scheme, which learns vertex representations in the embedding space by modeling 1st-order explicit relations and higher-order implicit relations between vertices. Then, the similarity of the embedding vectors is used to extract top-k semantically consistent friends for each user. Next, we design an algorithm to assign a specific influence value to each user. Finally, we combine the top-k friends of the user and their influence values into an ensemble and add it as a regularization term to the rating prediction process of the user to correct the bias. Experiments on three real benchmark datasets show significant improvements in EISF over state-of-the-art methods.