ERIS: Enhancing Privacy and Scalability in Federated Learning via Federated Shard Aggregation

TL;DR

ERIS introduces a federated learning framework with federated shard aggregation that enhances privacy and scalability, reduces communication costs, and maintains model utility across diverse tasks.

Contribution

ERIS proposes a novel federated shard aggregation mechanism that removes central bottlenecks, improves privacy, and integrates compression for scalable, secure federated learning.

Findings

ERIS achieves FedAvg-level utility in experiments.

ERIS reduces communication bottlenecks significantly.

ERIS enhances robustness against inference and reconstruction attacks.

Abstract

Scaling Federated Learning (FL) to billion-parameter models forces a challenging trade-off between privacy, scalability, and model utility. Existing solutions often tackle these challenges in isolation, sacrificing accuracy, relying on costly cryptographic tools, or introducing communication and optimization inefficiencies that affect convergence. We introduce ERIS, an FL framework centered on Federated Shard Aggregation (FSA), a novel mechanism that partitions each client update into non-overlapping shards whose aggregation is distributed across multiple client-side aggregators. FSA removes the central aggregation bottleneck, limits the information visible to any single observer, and preserves the centralized FL update after reassembly. ERIS can further readily integrate Distributed Shifted Compression (DSC) to reduce transmitted payloads and exposed coordinates. We prove that ERIS preserves convergence under standard assumptions and bounds mutual information leakage by the observable fraction of each update, decreasing with the number of client-side aggregators, and with the compression level when DSC is enabled. Experiments across image and text tasks, including large language models, show that ERIS achieves FedAvg-level utility while substantially reducing communication bottlenecks and improving robustness to membership inference and reconstruction attacks, without relying on heavy cryptography or utility-degrading perturbations.