Federated learning (FL) demonstrates its advantages in integrating distributed infrastructure, communication, computing and learning in a privacy-preserving manner. However, the robustness and capabilities of existing FL methods are challenged by limited and dynamic data and conditions, complexities including heterogeneities and uncertainties, and analytical explainability. Bayesian federated learning (BFL) has emerged as a promising approach to address these issues. This survey presents a critical overview of BFL, including its basic concepts, its relations to Bayesian learning in the context of FL, and a taxonomy of BFL from both Bayesian and federated perspectives. We categorize and discuss client- and server-side and FL-based BFL methods and their pros and cons. The limitations of the existing BFL methods and the future directions of BFL research further address the intricate requirements of real-life FL applications.
Reconfigurable intelligent surface (RIS)-assisted localization has attracted extensive attention as it can enable and enhance localization services in extreme scenarios. However, most existing works treat RISs as anchors with known positions and orientations, which is not realistic in the applications for mobile RISs or uncalibrated RISs. This work considers the joint RIS calibration and user positioning (JrCUP) problem in an uplink system with an active RIS. We propose a novel two-stage method to solve the considered JrCUP problem. The first stage comprises a tensor-ESPRIT estimator, followed by channel parameters refinement using least-squares. In the second stage, we propose a 2D search-based algorithm to estimate the 3D user position, 3D RIS position, 1D RIS orientation, and clock bias from the estimated channel parameters. The Cram\'er- Rao lower bounds (CRLBs) of the channel parameters and localization parameters are derived, which verify the effectiveness of the proposed algorithms. In addition, simulation studies reveal that the active RIS can significantly improve the localization performance compared to the passive case even with a small power supply. Moreover, we find that blind areas may occur where JrCUP localization performance is limited, which can be mitigated by either providing extra prior information or deploying more base stations.
Multi-label recognition (MLR) with incomplete labels is very challenging. Recent works strive to explore the image-to-label correspondence in the vision-language model, \ie, CLIP, to compensate for insufficient annotations. In spite of promising performance, they generally overlook the valuable prior about the label-to-label correspondence. In this paper, we advocate remedying the deficiency of label supervision for the MLR with incomplete labels by deriving a structured semantic prior about the label-to-label correspondence via a semantic prior prompter. We then present a novel Semantic Correspondence Prompt Network (SCPNet), which can thoroughly explore the structured semantic prior. A Prior-Enhanced Self-Supervised Learning method is further introduced to enhance the use of the prior. Comprehensive experiments and analyses on several widely used benchmark datasets show that our method significantly outperforms existing methods on all datasets, well demonstrating the effectiveness and the superiority of our method. Our code will be available at https://github.com/jameslahm/SCPNet.
Active learning selects informative samples for annotation within budget, which has proven efficient recently on object detection. However, the widely used active detection benchmarks conduct image-level evaluation, which is unrealistic in human workload estimation and biased towards crowded images. Furthermore, existing methods still perform image-level annotation, but equally scoring all targets within the same image incurs waste of budget and redundant labels. Having revealed above problems and limitations, we introduce a box-level active detection framework that controls a box-based budget per cycle, prioritizes informative targets and avoids redundancy for fair comparison and efficient application. Under the proposed box-level setting, we devise a novel pipeline, namely Complementary Pseudo Active Strategy (ComPAS). It exploits both human annotations and the model intelligence in a complementary fashion: an efficient input-end committee queries labels for informative objects only; meantime well-learned targets are identified by the model and compensated with pseudo-labels. ComPAS consistently outperforms 10 competitors under 4 settings in a unified codebase. With supervision from labeled data only, it achieves 100% supervised performance of VOC0712 with merely 19% box annotations. On the COCO dataset, it yields up to 4.3% mAP improvement over the second-best method. ComPAS also supports training with the unlabeled pool, where it surpasses 90% COCO supervised performance with 85% label reduction. Our source code is publicly available at https://github.com/lyumengyao/blad.
Positioning with 5G signals generally requires connection to several base stations (BSs), which makes positioning more demanding in terms of infrastructure than communications. To address this issue, there have been several theoretical studies on single BS positioning, leveraging high-resolution angle and delay estimation and multipath exploitation possibilities at mmWave frequencies. This paper presents the first realistic experimental validation of such studies, involving a commercial 5G mmWave BS and a user equipment (UE) development kit mounted on a test vehicle. We present the relevant signal models, signal processing methods (including channel parameter estimation and position estimation), and validate these based on real data collected in an outdoor science park environment. Our results indicate that positioning is possible, but the performance with a single BS is limited by the knowledge of the position and orientation of the infrastructure and the multipath visibility and diversity.
Convolutional neural networks (CNNs) have gained remarkable success in recent years. However, their performance highly relies on the architecture hyperparameters, and finding proper hyperparameters for a deep CNN is a challenging optimization problem owing to its high-dimensional and computationally expensive characteristics. Given these difficulties, this study proposes a surrogate-assisted highly cooperative hyperparameter optimization (SHCHO) algorithm for chain-styled CNNs. To narrow the large search space, SHCHO first decomposes the whole CNN into several overlapping sub-CNNs in accordance with the overlapping hyperparameter interaction structure and then cooperatively optimizes these hyperparameter subsets. Two cooperation mechanisms are designed during this process. One coordinates all the sub-CNNs to reproduce the information flow in the whole CNN and achieve macro cooperation among them, and the other tackles the overlapping components by simultaneously considering the involved two sub-CNNs and facilitates micro cooperation between them. As a result, a proper hyperparameter configuration can be effectively located for the whole CNN. Besides, SHCHO also employs the well-performing surrogate technique to assist in the hyperparameter optimization of each sub-CNN, thereby greatly reducing the expensive computational cost. Extensive experimental results on two widely-used image classification datasets indicate that SHCHO can significantly improve the performance of CNNs.
Positioning is expected to be a core function in intelligent transportation systems (ITSs) to support communication and location-based services, such as autonomous driving, traffic control, etc. With the advent of low-cost reflective reconfigurable intelligent surfaces (RISs) to be deployed in beyond 5G/6G networks, extra anchors with high angular resolutions can boost signal quality and makes high-precision positioning with extended coverage possible in ITS scenarios. However, the passive nature of the RIS requires a signal source such as a base station (BS), which limits the positioning service in extreme situations, such as tunnels or dense urban areas, where 5G/6G BSs are not accessible. In this work, we show that with the assistance of (at least) two RISs and sidelink communication between two user equipments (UEs), these UEs can be localized even without any BSs involvement. A two-stage 3D sidelink positioning algorithm is proposed, benchmarked by the derived Cram\'er-Rao bounds. The effects of multipath and RIS profile designs on positioning performance are evaluated, and several scenarios with different RIS and UE locations are discussed for localizability analysis. Simulation results demonstrate the promising positioning accuracy of the proposed BS-free sidelink communication system in challenging ITS scenarios. Additionally, we propose and evaluate several solutions to eliminate potential blind areas where positioning performance is poor, such as removing clock offset via round-trip communication, adding geometrical prior or constraints, as well as introducing more RISs.
The widespread emergence of smart devices for ECG has sparked demand for intelligent single-lead ECG-based diagnostic systems. However, it is challenging to develop a single-lead-based ECG interpretation model for multiple diseases diagnosis due to the lack of some key disease information. In this work, we propose inter-lead Multi-View Knowledge Transferring of ECG (MVKT-ECG) to boost single-lead ECG's ability for multi-label disease diagnosis. This training strategy can transfer superior disease knowledge from multiple different views of ECG (e.g. 12-lead ECG) to single-lead-based ECG interpretation model to mine details in single-lead ECG signals that are easily overlooked by neural networks. MVKT-ECG allows this lead variety as a supervision signal within a teacher-student paradigm, where the teacher observes multi-lead ECG educates a student who observes only single-lead ECG. Since the mutual disease information between the single-lead ECG and muli-lead ECG plays a key role in knowledge transferring, we present a new disease-aware Contrastive Lead-information Transferring(CLT) to improve the mutual disease information between the single-lead ECG and muli-lead ECG. Moreover, We modify traditional Knowledge Distillation to multi-label disease Knowledge Distillation (MKD) to make it applicable for multi-label disease diagnosis. The comprehensive experiments verify that MVKT-ECG has an excellent performance in improving the diagnostic effect of single-lead ECG.
A smart city involves, among other elements, intelligent transportation, crowd monitoring, and digital twins, each of which requires information exchange via wireless communication links and localization of connected devices and passive objects (including people). Although localization and sensing (L&S) are envisioned as core functions of future communication systems, they have inherently different demands in terms of infrastructure compared to communications. Wireless communications generally requires a connection to only a single access point (AP), while L&S demand simultaneous line-of-sight propagation paths to several APs, which serve as location and orientation anchors. Hence, a smart city deployment optimized for communication will be insufficient to meet stringent L&S requirements. In this article, we argue that the emerging technologies of reconfigurable intelligent surfaces (RISs) and sidelink communications constitute the key to providing ubiquitous coverage for L&S in smart cities with low-cost and energy-efficient technical solutions. To this end, we propose and evaluate AP-coordinated and self-coordinated RIS-enabled L&S architectures and detail three groups of application scenarios, relying on low-complexity beacons, cooperative localization, and full-duplex transceivers. A list of practical issues and consequent open research challenges of the proposed L&S systems is also provided.
Localization (position and orientation estimation) is envisioned as a key enabler to satisfy the requirements of communication and context-aware services in the sixth generation (6G) communication systems. User localization can be achieved based on delay and angle estimation using uplink or downlink pilot signals. However, hardware impairments (HWIs) distort the signals at both the transmitter and receiver sides and thus affect the localization performance. While this impact can be ignored at lower frequencies where HWIs are less severe, and the localization requirements are not stringent, modeling and analysis efforts are needed for high-frequency 6G bands (e.g., sub-THz) to assess degradation in localization accuracy due to HWIs. In this work, we model various types of impairments for a sub-THz multiple-input-multiple-output communication system and conduct a misspecified Cram\'er-Rao bound analysis to evaluate HWI-induced performance losses in terms of angle/delay estimation and the resulting 3D position/orientation estimation error. Complementary to the localization analysis, we also investigate the effect of individual and overall HWIs on communication in terms of symbol error rate (SER). Our extensive simulation results demonstrate that each type of HWI leads to a different level of degradation in angle and delay estimation performance. The prominent factors on delay estimation (e.g., phase noise and carrier frequency offset) will have a dominant negative effect on SER, while the impairments affecting only the angle estimation (e.g., mutual coupling and antenna displacement) induce slight degradation in SER performance.