activity
20242026
collaborators
Showing 2024Show all

5 papers · 1 filter

cs.DC2024

Priority-Aware Model-Distributed Inference at Edge Networks

Teng Li, Hulya Seferoglu

Distributed inference techniques can be broadly classified into data-distributed and model-distributed schemes. In data-distributed inference (DDI), each worker carries the entire…

cs.CR2024

Privacy-Preserving Hierarchical Model-Distributed Inference

Fatemeh Jafarian Dehkordi, Yasaman Keshtkarjahromi, Hulya Seferoglu

This paper focuses on designing a privacy-preserving Machine Learning (ML) inference protocol for a hierarchical setup, where clients own/generate data, model owners (cloud servers…

cs.DC2024

Early-Exit meets Model-Distributed Inference at Edge Networks

Marco Colocrese, Erdem Koyuncu, Hulya Seferoglu

Distributed inference techniques can be broadly classified into data-distributed and model-distributed schemes. In data-distributed inference (DDI), each worker carries the entire…

cs.LG2024

Differentiated Aggregation to Improve Generalization in Federated Learning

Peyman Gholami, Hulya Seferoglu

This paper focuses on reducing the communication cost of federated learning by exploring generalization bounds and representation learning. We first characterize a tighter generali…

cs.LG2024

DIGEST: Fast and Communication Efficient Decentralized Learning with Local Updates

Peyman Gholami, Hulya Seferoglu

Two widely considered decentralized learning algorithms are Gossip and random walk-based learning. Gossip algorithms (both synchronous and asynchronous versions) suffer from high c…