1 code implementation • 18 Apr 2024 • Petru Neague, Marcel Gregoriadis, Johan Pouwelse
This study introduces De-DSI, a novel framework that fuses large language models (LLMs) with genuine decentralization for information retrieval, particularly employing the differentiable search index (DSI) concept in a decentralized setting.
no code implementations • 28 Sep 2023 • Konstantinos Andriopoulos, Johan Pouwelse
Large pre-trained language models have demonstrated their proficiency in storing factual knowledge within their parameters and achieving remarkable results when fine-tuned for downstream natural language processing tasks.
no code implementations • 26 Jun 2023 • Thomas Werthenbach, Johan Pouwelse
Numerous studies have been conducted on improving the resilience of federated learning against poisoning and Sybil attacks, whereas the resilience of decentralized learning remains largely unstudied.
1 code implementation • 29 Jan 2023 • Andrew Gold, Johan Pouwelse
Furthermore, we show that such results are obtainable with minimal data preprocessing and computational overhead, and can still return highly relevant results even when a user's device is disconnected from the network.
no code implementations • 21 Oct 2021 • Joost Verbraeken, Martijn de Vos, Johan Pouwelse
We show that when the training classes are non-i. i. d., Bristle significantly outperforms the accuracy of the most Byzantine-resilient baselines by 2. 3x while reducing communication costs by 90%.
no code implementations • 5 Feb 2015 • Olivier Hokke, Alex Kolpa, Joris van den Oever, Alex Walterbos, Johan Pouwelse
Smartphones are becoming more significant in storing and transferring data.
Cryptography and Security