5 papers · 1 filter
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…
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…
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…
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…
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…