8 papers
ERIS: Enhancing Privacy and Scalability in Federated Learning via Federated Shard Aggregation
Dario Fenoglio, Pasquale Polverino, Jacopo Quizi +3
Scaling Federated Learning (FL) to billion-parameter models forces a challenging trade-off between privacy, scalability, and model utility. Existing solutions often tackle these ch…
Robust Federated Inference
Akash Dhasade, Sadegh Farhadkhani, Rachid Guerraoui +4
Federated inference, in the form of one-shot federated learning, edge ensembles, or federated ensembles, has emerged as an attractive solution to combine predictions from multiple…
Navigating the Accuracy-Size Trade-Off with Flexible Model Merging
Akash Dhasade, Divyansh Jhunjhunwala, Milos Vujasinovic +2
Model merging has emerged as an efficient method to combine multiple single-task fine-tuned models. The merged model can enjoy multi-task capabilities without expensive training. W…
Efficient Federated Search for Retrieval-Augmented Generation using Lightweight Routing
Akash Dhasade, Rachid Guerraoui, Anne-Marie Kermarrec +4
Large language models (LLMs) achieve remarkable performance across domains but remain prone to hallucinations and inconsistencies. Retrieval-augmented generation (RAG) mitigates th…
Effective LoRA Adapter Routing using Task Representations
Akash Dhasade, Anne-Marie Kermarrec, Igor Pavlovic +4
Low-rank adaptation (LoRA) enables parameter efficient specialization of large language models (LLMs) through modular adapters, resulting in rapidly growing public adapter pools sp…
Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption
Sayan Biswas, Philippe Chartier, Akash Dhasade +7
In contemporary cloud-based services, protecting users' sensitive data and ensuring the confidentiality of the server's model are critical. Fully homomorphic encryption (FHE) enabl…