Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJuly 2024
MiniPFL: Mini federations for hierarchical personalized federated learning
Future Generation Computer Systems (FGCS), Volume 157, Issue CPages 41–50https://doi.org/10.1016/j.future.2024.03.026AbstractPersonalized federated learning trains personalized models tailored to meet individual client’s specific data distributions. However, global models often introduce irrelevant information into personalized models, reducing communication efficiency ...
Graphical abstractDisplay Omitted
Highlights- Propose a bi-component framework for client aggregation and clustering.
- Combines global and mini-federations for enhanced personalization.
- MiniPFL cuts communication rounds by 30%, excelling in performance.
- research-articleJuly 2024
Meta Generative Flow Networks with personalization for task-specific adaptation
Information Sciences: an International Journal (ISCI), Volume 672, Issue Chttps://doi.org/10.1016/j.ins.2024.120569AbstractMulti-task reinforcement learning and meta-reinforcement learning have been developed to enhance the learning capabilities on new tasks, but they tend to focus on maximizing rewards, leading to poor performance in exploration. To address this ...
Graphical abstract Highlights- A method is proposed to boost the exploration performance of reinforcement learning on new tasks.
- A personalized method is proposed to boost reinforcement learning on distinct tasks.
- The convergence analysis is established for the ...
- research-articleMay 2024
Enabling Multi-Frequency and Wider-Band RFID Sensing Using COTS Device
IEEE/ACM Transactions on Networking (TON), Volume 32, Issue 4Pages 3591–3605https://doi.org/10.1109/TNET.2024.3394974RFID shows great potentials to build useful sensing applications. However, current RFID sensing can obtain mainly a single-dimensional sensing measurement from each reader-to-tag query, such as phase, RSS, etc. This is sufficient to fulfill the designs ...
- research-articleMay 2024
Genre Classification Empowered by Knowledge-Embedded Music Representation
IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP), Volume 32Pages 2764–2776https://doi.org/10.1109/TASLP.2024.3402115This paper introduces a pioneering framework for music representation learning, which harnesses knowledge graph embeddings to enrich genre classification. Leveraging metadata from publicly available datasets like FMA and OpenMIC-2018, the constructed ...
- research-articleJanuary 2024
RoseAgg: Robust Defense Against Targeted Collusion Attacks in Federated Learning
IEEE Transactions on Information Forensics and Security (TIFS), Volume 19Pages 2951–2966https://doi.org/10.1109/TIFS.2024.3352415Recent defense approaches against targeted model poisoning attacks aim to prevent specific prediction failures in federated learning (FL). However, these defenses remain susceptible to targeted collusion attacks, particularly under conditions of high ...
-
- research-articleFebruary 2024
TL-MSE2-Net: Transfer learning based nested model for cerebrovascular segmentation with aneurysms
Computers in Biology and Medicine (CBIM), Volume 167, Issue Chttps://doi.org/10.1016/j.compbiomed.2023.107609AbstractCerebrovascular (i.e., cerebral vessel) segmentation is essential for diagnosing and treating brain diseases. Convolutional neural network models, such as U-Net, are commonly used for this purpose. Unfortunately, such models may not be entirely ...
Highlights- A transferability framework is designed to address the small amount of private clinical cerebrovascular datasets.
- Exploration of adaptive strategies for different modalities of cerebrovascular datasets (MRI-CT).
- Extracting ...
- research-articleNovember 2023
Towards Hierarchical Clustered Federated Learning With Model Stability on Mobile Devices
IEEE Transactions on Mobile Computing (ITMV), Volume 23, Issue 6Pages 7148–7164https://doi.org/10.1109/TMC.2023.3332637Clustered federated learning (CFL) has proved to be an effective way to alleviate the non-IID (not independently and identically distributed) data challenge, which severely restricts the wider application of federated learning. However, existing ...
- research-articleOctober 2023
FedRich: Towards efficient federated learning for heterogeneous clients using heuristic scheduling
Information Sciences: an International Journal (ISCI), Volume 645, Issue Chttps://doi.org/10.1016/j.ins.2023.119360AbstractFederated Learning (FL) always involves a large number of heterogeneous clients (both in statistic and resource heterogeneity) when collaboratively training a model, leading to a compromise in the model performance. Recent research has ...
Graphical abstract - research-articleSeptember 2023
Cross-technology Communication between Visible Light and Battery-free RFIDs
- Ge Wang,
- Lubing Han,
- Yuance Chang,
- Yuting Shi,
- Chen Qian,
- Cong Zhao,
- Han Ding,
- Wei Xi,
- Cui Zhao,
- Jizhong Zhao
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT), Volume 7, Issue 3Article No.: 129, Pages 1–20https://doi.org/10.1145/3610883The ubiquity of illumination facilities enables the versatile development of Visible Light Communication (VLC). VLC-based research achieved high-speed wireless access and decimeter-level indoor localization with complex equipment. However, it is still ...
- research-articleJune 2023
Heartbeating With LTE Networks for Ambient Backscatter
IEEE Transactions on Mobile Computing (ITMV), Volume 23, Issue 5Pages 4246–4258https://doi.org/10.1109/TMC.2023.3290298Different from intermittent ISM signals like Bluetooth and WiFi, LTE signals are continuous in time and more pervasive in space, which makes them suitable carriers for ambient backscatter systems. However, due to the continuous LTE traffic and complex ...
- research-articleMay 2023
Co-MDA: Federated Multisource Domain Adaptation on Black-Box Models
IEEE Transactions on Circuits and Systems for Video Technology (IEEETCSVT), Volume 33, Issue 12Pages 7658–7670https://doi.org/10.1109/TCSVT.2023.3277135Federated domain adaptation (FDA) is an effective method for performing learning tasks over distributed networks, which well improves data privacy and portability in unsupervised multi-source domain adaptation (UMDA) tasks. Despite the impressive gains ...
- research-articleMarch 2023
MI-Mesh: 3D Human Mesh Construction by Fusing Image and Millimeter Wave
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT), Volume 7, Issue 1Article No.: 10, Pages 1–24https://doi.org/10.1145/3580861Estimating 3D human mesh is appealing for various application scenarios. Current mainstream solution predicts the meshes either from the image or the human reflected RF-signals. In this paper, instead of investigating which approach is better, we propose ...
- research-articleJanuary 2023
RF-Chain: Decentralized, Credible, and Counterfeit-proof Supply Chain Management with Commodity RFIDs
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT), Volume 6, Issue 4Article No.: 184, Pages 1–28https://doi.org/10.1145/3569493Blockchain-based supply chains provide a new solution to decentralized multi-party product management. However, existing methods, including ID-based and cryptographic-based solutions, cannot achieve both counterfeit resistance and decentralization in ...
- research-articleDecember 2022
High-efficient hierarchical federated learning on non-IID data with progressive collaboration
Future Generation Computer Systems (FGCS), Volume 137, Issue CPages 111–128https://doi.org/10.1016/j.future.2022.07.010AbstractHierarchical federated learning (HFL) allows multiple edge aggregations at edge devices before one global aggregation to address both issues of non-independent and identically distributed (non-IID) data and communication bottleneck in ...
Highlights- FedPEC breaks the assumption that clients can be assigned to any edge device.
- ...
- research-articleSeptember 2022
ScreenInformer: Whispering Secret Information via an LCD Screen
2022 19th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON)Pages 181–189https://doi.org/10.1109/SECON55815.2022.9918570In this paper, we observe an acoustic covert channel by modulating capacitor squeal on the monitor's power supply unit, and then present ScreenInformer to build a covert communication within a physically isolated network system. Unlike traditional ...
- research-articleSeptember 2022
UltraSpeech: Speech Enhancement by Interaction between Ultrasound and Speech
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT), Volume 6, Issue 3Article No.: 111, Pages 1–25https://doi.org/10.1145/3550303Speech enhancement can benefit lots of practical voice-based interaction applications, where the goal is to generate clean speech from noisy ambient conditions. This paper presents a practical design, namely UltraSpeech, to enhance speech by exploring ...
- ArticleAugust 2022
Multi-objective RL with Preference Exploration
AbstractTraditional multi-objective reinforcement learning problems pay attention to the expected return of each objective under different preferences. However, the difference in strategy in practice is also important. This paper proposes an algorithm ...
- research-articleJuly 2022
A Generalized Method to Combat Multipaths for RFID Sensing
IEEE/ACM Transactions on Networking (TON), Volume 31, Issue 1Pages 336–351https://doi.org/10.1109/TNET.2022.3190862There have been increasing interests in exploring the sensing capabilities of RFID to enable numerous IoT applications, including object localization, trajectory tracking, and human behavior sensing. However, most existing methods rely on the signal ...
- research-articleMay 2022
M2N: Mutual constraint network for multi-level unsupervised domain adaptation
Neurocomputing (NEUROC), Volume 487, Issue CPages 269–279https://doi.org/10.1016/j.neucom.2021.11.011Graphical abstractDisplay Omitted
Highlights- This work is inspired by recent studies on deep learning with noisy label.
- The ...
Unsupervised domain adaptation (UDA) algorithms aim to transfer the knowledge learned from the labeled source domain to the unlabeled target domain. To tackle this issue, domain-alignment models based on different representation space ...
- research-articleMay 2022
RF-Wise: Pushing the Limit of RFID-based Sensing
IEEE INFOCOM 2022 - IEEE Conference on Computer CommunicationsPages 1779–1788https://doi.org/10.1109/INFOCOM48880.2022.9796909RFID shows great potentials to build useful sensing applications. However, current RFID sensing can obtain mainly a single-dimensional sensing measurement from each reader-to-tag query, such as phase, RSS, etc. This is sufficient to fulfill the designs ...