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.
Jia-Hong Xiao, Yuxiang Chen, Chao-Yi Yang et al.· IEEE Transactions on Mobile...· 0 citations
In blockchain-based medical data sharing systems, sensitive medical data such as electronic health records and diagnostic reports require secure sharing with fine-grained access control and accountable usage. Existing attribute-based encryption (ABE) schemes lack mechanisms for auditing data usage after decryption, leaving data misuse undetectable and unaccountable. To address this limitation, this paper proposes Commit-HABE, a commitment-based auditable ABE scheme. Users submit their attribute sets along with signed usage commitments prior to data access, which are immutably recorded on a consortium blockchain. In addition, a traceable watermark cryptographically linked to each commitment can be embedded into the decrypted data, enabling post-hoc leakage detection and attribution. Security analysis indicates that Commit-HABE achieves data confidentiality, commitment non-repudiation, and traceability. We implement Commit-HABE alongside three representative CP-ABE schemes and conduct a performance evaluation. Experimental results demonstrate that Commit-HABE reduces encryption time by up to 29.5% compared to existing schemes and maintains comparable decryption performance. The commitment overhead is negligible $(\approx 0.0016 \text{ms})$, watermark embedding scales linearly from 0.28 ms to 6.10 ms, and the blockchain system sustains 100% success under up to 100 queries per second.
Ke-Fei Li, Xiangwei Meng, Cangming Liang et al.· Fall Joint Computer Conferen...· 0 citations
This work proposes HFL-Lite, a hierarchical federated learning framework that achieves practical privacy without cryptographic primitives, and shows that HFL-Lite reduces per-round communication to 0.5 KB and sensor-side latency to 9 ms while delivering competitive accuracy.
Cangming Liang, Kuan Ching Li, Zulong Diao et al.· Tsinghua Science and Technol...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
