78 citations · 293 across the 56 of their papers we have counts for
22 papers · 1 filter
AgentWeave: Efficient Distributed Agent Serving via Flow Decomposition
Kaibin Guo, Pengtu Li, Zicong Hong +4
Agent applications are evolving into workflows composed of large language model (LLM) calls and tool invocations, termed modules. Existing distributed agent systems typically adopt…
Efficient and Robust Online Learning to Rank in Decentralized Systems
Marcel Gregoriadis, Martijn de Vos, Sayan Biswas +2
In Online Learning to Rank (OLTR), ranking models are trained directly from live user interactions, but existing systems rely on a trusted central server to collect and process the…
Efficient Pyramidal Analysis of Gigapixel Images on a Decentralized Modest Computer Cluster
Marie Reinbigler, Rishi Sharma, Rafael Pires +3
Analyzing gigapixel images is recognized as computationally demanding. In this paper, we introduce PyramidAI, a technique for analyzing gigapixel images with reduced computational…
HarMoEny: Efficient Multi-GPU Inference of MoE Models
Zachary Doucet, Rishi Sharma, Martijn de Vos +3
Mixture-of-Experts (MoE) models offer computational efficiency during inference by activating only a subset of specialized experts for a given input. This enables efficient model s…
Practical Federated Learning without a Server
Akash Dhasade, Anne-Marie Kermarrec, Erick Lavoie +3
Federated Learning (FL) enables end-user devices to collaboratively train ML models without sharing raw data, thereby preserving data privacy. In FL, a central parameter server coo…
Boosting Asynchronous Decentralized Learning with Model Fragmentation
Sayan Biswas, Anne-Marie Kermarrec, Alexis Marouani +3
Decentralized learning (DL) is an emerging technique that allows nodes on the web to collaboratively train machine learning models without sharing raw data. Dealing with stragglers…
PeerSwap: A Peer-Sampler with Randomness Guarantees
Rachid Guerraoui, Anne-Marie Kermarrec, Anastasiia Kucherenko +2
The ability of a peer-to-peer (P2P) system to effectively host decentralized applications often relies on the availability of a peer-sampling service, which provides each participa…
Noiseless Privacy-Preserving Decentralized Learning
Sayan Biswas, Mathieu Even, Anne-Marie Kermarrec +4
Decentralized learning (DL) enables collaborative learning without a server and without training data leaving the users' devices. However, the models shared in DL can still be used…
On the Inherent Anonymity of Gossiping
Rachid Guerraoui, Anne-Marie Kermarrec, Anastasiia Kucherenko +2
Detecting the source of a gossip is a critical issue, related to identifying patient zero in an epidemic, or the origin of a rumor in a social network. Although it is widely acknow…
Get More for Less in Decentralized Learning Systems
Akash Dhasade, Anne-Marie Kermarrec, Rafael Pires +3
Decentralized learning (DL) systems have been gaining popularity because they avoid raw data sharing by communicating only model parameters, hence preserving data confidentiality.…
Decentralized Learning Made Easy with DecentralizePy
Akash Dhasade, Anne-Marie Kermarrec, Rafael Pires +2
Decentralized learning (DL) has gained prominence for its potential benefits in terms of scalability, privacy, and fault tolerance. It consists of many nodes that coordinate withou…
Decentralized Learning Made Practical with Client Sampling
Martijn de Vos, Akash Dhasade, Anne-Marie Kermarrec +3
Decentralized learning (DL) leverages edge devices for collaborative model training while avoiding coordination by a central server. Due to privacy concerns, DL has become an attra…
TEE-based decentralized recommender systems: The raw data sharing redemption
Akash Dhasade, Nevena Dresevic, Anne-Marie Kermarrec +1
Recommenders are central in many applications today. The most effective recommendation schemes, such as those based on collaborative filtering (CF), exploit similarities between us…
Beyond One Third Byzantine Failures
Cheng Wang, Carole Delporte-Gallet, Hugues Fauconnier +2
The Byzantine agreement problem requires a set of processes to agree on a value sent by a transmitter, despite a subset of processes behaving in an arbitrary, i.e. Byzantin…
Clustered Network Coding for Maintenance in Practical Storage Systems
Anne-Marie Kermarrec, Erwan Le Merrer, Gilles Straub +1
Classical erasure codes, e.g. Reed-Solomon codes, have been acknowledged as an efficient alternative to plain replication to reduce the storage overhead in reliable distributed sto…
Regenerating Codes: A System Perspective
Steve Jiekak, Anne-Marie Kermarrec, Nicolas Le Scouarnec +2
The explosion of the amount of data stored in cloud systems calls for more efficient paradigms for redundancy. While replication is widely used to ensure data availability, erasure…
On Dynamic Distributed Computing
Rachid Guerraoui, Florian Huc, Anne-Marie Kermarrec
This paper shows for the first time that distributed computing can be both reliable and efficient in an environment that is both highly dynamic and hostile. More specifically, we s…
Scalable and Secure Aggregation in Distributed Networks
Sebastien Gambs, Rachid Guerraoui, Hamza Harkous +2
We consider the problem of computing an aggregation function in a \emph{secure} and \emph{scalable} way. Whereas previous distributed solutions with similar security guarantees hav…
Energy Aware Self-Organizing Density Management in Wireless Sensor Networks
Erwan Le Merrer, Vincent Gramoli, Anne-Marie Kermarrec +2
Energy consumption is the most important factor that determines sensor node lifetime. The optimization of wireless sensor network lifetime targets not only the reduction of energy…
Core Persistence in Peer-to-Peer Systems: Relating Size to Lifetime
Vincent Gramoli, Anne-Marie Kermarrec, Achour Mostefaoui +2
Distributed systems are now both very large and highly dynamic. Peer to peer overlay networks have been proved efficient to cope with this new deal that traditional approaches can…
Distributed Slicing in Dynamic Systems
Antonio Fernandez, Vincent Gramoli, Ernesto Jimenez +2
Peer to peer (P2P) systems are moving from application specific architectures to a generic service oriented design philosophy. This raises interesting problems in connection with p…
Distributed Slicing in Dynamic Systems
Antonio Fernandez, Vincent Gramoli, Ernesto Jimenez +2
Peer to peer (P2P) systems are moving from application specific architectures to a generic service oriented design philosophy. This raises interesting problems in connection with p…