Google enhances federated learning privacy with TEEs; new arXiv papers explore model merging and efficiency

COVERAGE [16]

1. Google AI / Research TIER_1 English(EN) · 2026-10-02 14:57

   Toward provably private learning from federated data

   Mobile Systems

2. arXiv cs.LG TIER_1 English(EN) · Dun Zeng, Xiangjing Hu, Shiyu Liu, Yue Yu, Qifan Wang, Zenglin Xu · 2026-10-03 04:00

   StoCFL: A Stochastically Clustered Federated Learning Framework for Non-IID Data with Dynamic Client Participation

   arXiv:2303.00897v2 Announce Type: replace Abstract: Federated learning is a distributed learning framework that takes full advantage of private data samples kept on edge devices. In real-world federated learning systems, these data samples are often decentralized and Non-Independ…

3. arXiv cs.LG TIER_1 English(EN) · Seyed Mohammad Azimi-Abarghouyi · 2026-10-03 04:00

   Progressive-Resolution Secure Aggregation for Federated Learning

   arXiv:2610.00695v1 Announce Type: cross Abstract: Secure aggregation lets a server recover an aggregate of client updates without observing any individual update, but conventional protocols fix the aggregate precision when clients upload. We introduce and formulate a new progress…

4. arXiv cs.LG TIER_1 English(EN) · Seungjun Lee, Ensieh Khazaei, Dimitrios Hatzinakos, Baturalp Buyukates, Sunwoo Lee · 2026-10-03 04:00

   Latent Information Sharing for Accelerating Federated Learning

   arXiv:2610.01126v1 Announce Type: new Abstract: Federated learning (FL) is a communication-efficient distributed learning paradigm. However, client drift remains one of the most critical challenges, hindering the efficient training of a global model. In this study, we propose a n…

5. arXiv cs.LG TIER_1 English(EN) · Minghui Chen, Meirui Jiang, Xin Zhang, Qi Dou, Zehua Wang, Xiaoxiao Li · 2026-10-03 04:00

   Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning

   arXiv:2410.23660v2 Announce Type: replace Abstract: Federated learning (FL) is a learning paradigm that enables collaborative training of models using decentralized data. Recently, the utilization of pre-trained weight initialization in FL has been demonstrated to effectively imp…

6. arXiv cs.LG TIER_1 English(EN) · Sachi Shome, William Eiers · 2026-10-02 04:00

   Compression Footprints as Security Signals for Model-Poisoning Defense in Federated Learning

   arXiv:2609.40312v1 Announce Type: new Abstract: Lossy compression is widely used in Federated Learning (FL) but is generally treated as an error source, while conventional poisoning defenses inspect update geometry. In this work, we instead treat the compressor's response as a se…

7. arXiv cs.AI TIER_1 English(EN) · Junkang Liu · 2026-10-02 04:00

   FedLore: Communication and Memory Efficient Federated Learning via Shared Gradient Low-Rank Projection

   arXiv:2610.01620v1 Announce Type: new Abstract: Federated training of foundation models is constrained by client memory and communication costs. LoRA-based methods reduce these costs through low-rank adapters, but their fixed rank budget can limit adaptation. Gradient low-rank op…

8. arXiv cs.LG TIER_1 English(EN) · Muzaffer Citir, Hiroki Nishikawa, Sangyoung Park · 2026-10-02 04:00

   Client and Training Data Selection for Computationally Efficient Synchronized Federated Learning

   arXiv:2609.39250v1 Announce Type: new Abstract: Federated learning (FL) is a promising paradigm of machine learning, which preserves user privacy by enabling learning without sharing raw data with a cloud server. Straggling clients have been a problem for FL as they introduce del…

9. arXiv cs.LG TIER_1 English(EN) · Pengfei Li, Mohammad Khalil · 2026-10-02 04:00

   Beyond Uniform Compression: Budgeted Transmission Allocation for Extreme Federated Learning

   arXiv:2609.39646v1 Announce Type: new Abstract: Federated learning faces severe communication bottlenecks when clients upload high-dimensional model updates. Existing methods often compress these updates uniformly across all layers. This uniform approach ignores the heterogeneous…

10. Hugging Face Daily Papers TIER_1 English(EN) · 2026-09-30 08:14

    Client and Training Data Selection for Computationally Efficient Synchronized Federated Learning

    Federated learning (FL) is a promising paradigm of machine learning, which preserves user privacy by enabling learning without sharing raw data with a cloud server. Straggling clients have been a problem for FL as they introduce delays in aggregating the local models and hence, t…

11. arXiv cs.LG TIER_1 English(EN) · Haomin Bai, Junyan Sun, Sifan Yang, Bo Xue, Lijun Zhang · 2026-09-30 04:00

    Communication-Efficient Agnostic Federated Learning via Faster Convergence and Compression

    arXiv:2609.36610v1 Announce Type: new Abstract: Agnostic federated learning (AFL) seeks a model that performs reliably across $m$ heterogeneous workers, but communication remains a bottleneck. We improve communication efficiency by reducing the number of synchronization rounds vi…

12. arXiv cs.LG TIER_1 English(EN) · Prasanjit Dubey, Aritra Guha, Xiaoming Huo · 2026-09-30 04:00

    Byzantine-Robust Federated RAG via Aligned Calibration and Fixed-Membership Conformal Prediction

    arXiv:2609.33037v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) lets language models answer questions more accurately by consulting relevant documents. Many valuable collections, such as medical records, cannot be pooled because of privacy rules. Fe…

13. arXiv cs.LG TIER_1 English(EN) · Leonardo F. Toso, James Anderson, Rafael Pinot, Nirupam Gupta · 2026-09-30 04:00

    Byzantine-Robust Federated Representation Learning

    arXiv:2609.36660v1 Announce Type: new Abstract: We study federated learning (FL) with adversarial clients, where the goal is to minimize the average loss of the honest (non-adversarial) clients without knowing their identity. Under heterogeneity, a single shared model parameter i…

14. Hugging Face Daily Papers TIER_1 English(EN) · 2026-09-29 03:26

    Communication-Efficient Agnostic Federated Learning via Faster Convergence and Compression

    Agnostic federated learning (AFL) seeks a model that performs reliably across $m$ heterogeneous workers, but communication remains a bottleneck. We improve communication efficiency by reducing the number of synchronization rounds via faster convergence and the communication cost …

15. arXiv cs.CV TIER_1 English(EN) · Bar{\i}\c{s} B\"uy\"ukta\c{s}, Beg\"um Demir · 2026-10-02 04:00

    FedMAD: Modulation-Aware Directional Aggregation for Federated Learning in Remote Sensing Image Classification

    arXiv:2610.00693v1 Announce Type: new Abstract: Federated learning (FL) has recently attracted increasing attention in remote sensing (RS) since it enables collaborative model training across decentralized RS image archives without requiring direct access to local data. However, …

16. MarkTechPost TIER_1 English(EN) · Michal Sutter · 2026-10-04 07:29

    Google Research Moves Federated Learning Into TEEs: Gboard Now Trains With Externally Verifiable Differential Privacy

    <p>Google Research has unveiled a federated learning system that moves gradient computation from phones into attested server-side TEEs. Access policies are published to Sigstore's Rekor log and the binaries are reproducibly buildable, so central differential privacy can be checke…