Kuan-Ching Li

Segment-Account Migration: Efficient Account Migration Based on Lock-Free Mechanism

Blockchain represents a critical technical solution for achieving reliable and trustworthy distributed storage in JointCloud computing. Sharding technology can enhance the scalability of blockchain. However, while improving throughput, the massive cross-shard transactions introduced by sharding have become a new performance bottleneck. To mitigate this problem, state-of-the-art studies have adopted account migration strategies to reduce the amount of cross-shard transactions, nevertheless, prevailing methodologies depend on lock mechanisms that result in significant latency overhead for locked transactions. This work proposes Segment-Account Migration (SAM), an efficient lock-free account migration protocol by segmenting the account balance, retaining a portion on the source shard to support payer transactions while transferring the remainder and the account state to the target shard, thereby eliminating transaction locks during migration. Furthermore, the SAM protocol introduces a time window-based rollback mechanism to handle migration failures and defend against replay attacks. Experiments on the Ethereum dataset demonstrate that SAM reduces the average completion time of related-party transactions by 24.85% and decreases the average amount of state synchronization data by 34.65%. This significant improvement enhances migration efficiency while maintaining security, offering a reliable and effective solution for the scalability of sharded blockchains.

Communication-Efficient Federated Learning Based on a Two-Stage Adaptive Basis Matrix for Gradient Compression

Federated learning (FL) faces significant communication overhead due to the repeated exchange of large gradient tensors between clients and the server. While existing compression techniques, such as sparsification and quantization, help reduce this cost, they often result in information loss, which can negatively impact model accuracy. In this work, we propose TDGC-FL, a communication-efficient federated learning framework based on a two-stage adaptive basis matrix for gradient compression, which simultaneously minimizes transmission volume and preserves model accuracy. compression to simultaneously minimize transmission volume and maintain accuracy. TDGC-FL decomposes aggregated gradients on the server, extracts compact basis matrices, and transmits them to clients, which then approximate their gradients and return only low-dimensional coefficient matrices. An adaptive update mechanism, driven by a multi-factor mixed error metric, ensures that the basis matrices remain accurate throughout the training process. Extensive experiments on MNIST, FMNIST, CIFAR10, and SVHN show that TDGC-FL reduces communication overhead by up to 82.83% compared to FedAvg, and by 37.70%–73.53% relative to FedPAQ, QSGD, Topk, and Mask, while consistently achieving higher model accuracy, demonstrating that TDGC-FL effectively addresses the accuracy–efficiency trade-off, thus enabling federated learning to achieve scalability and high performance in bandwidth-constrained environments.

Lightweight and robust audio-visual emotion recognition via multi-scale mamba temporal modeling and quality-aware expert fusion

Multimodal emotion recognition for real-time human–computer interaction requires both high recognition accuracy and low computational cost. However, existing audio-visual methods often rely on heavy Transformer-based fusion or high-capacity visual backbones, making them difficult to deploy on edge devices. Moreover, their robustness to degraded audio-visual inputs and their class-wise behavior for ambiguous emotions remain insufficiently analyzed. To address these issues, we propose a lightweight audio-visual emotion recognition framework. The visual stream uses ShuffleNet for efficient facial feature extraction, while the audio stream uses multiscale MFCCs and efficient sequence modeling to capture emotional prosody. A cross-modal auxiliary fusion module is further introduced to align audio and visual representations, and lightweight channel attention is used to emphasize emotion-relevant features. Experiments on CREMA-D and IEMO-CAP demonstrate that the proposed method achieves competitive recognition accuracy with significantly fewer parameters and lower computational cost. Additional analyses on edge-device inference, audio-visual degradation, class-wise confusion, and batch-size sensitivity further validate the efficiency and robustness of the proposed framework.

MultiSecDFL: Multi-Metric Filtering-Based Secure Aggregation Method for Decentralized Federated Learning