Here is our new webiste “Distributed Learning System Lab"

We are the Distributed Learning Systems Lab at the Distributed Systems Section, EWI faculty, TU Delft. We working on a wide variety of research problems in distributed machine learning systems, and developing cutting edge AI technology for industry.

Our lab is supported by TU Delft, Aegon, ABB Research, Swiss National Science Foundation (SNSF), and Dutch National Science Foundation (NWO).

News

[04/23] Our paper, “LeadFL: Client Self-Defense against Model Poisoning in Federated Learning" , is accpted in ICML 23

[03/23] Our paper, “Fabricated Flips: Poisoning Federated Learning without Data" , is accpted in DSN 23

[02/23] Our paper, “Maverick Matters: Client Contribution and Selection in Federated Learning" , is accpted in PAKDD 23

[01/23] Our paper, “Defending Against Free-Riders Attacks in Distributed Generative Adversarial Networks" , is accpted in Financial Crypto 23

[12/22] Our paper, “Robust Learning via Golden Symmetric Loss of (un)Trusted Labels " , is accpted in SIAM SDM 23

[10/22] Our paper, “FedKNow:Federated Continual Learning with Signature Task Knowledge Integration at Edge" , is accpted in IEEE ICDE 23

[10/22] Our paper, “Permutation-Invariant Tabular Data Synthesis " , is accpted in IEEE Bigdata 22

[09/22] Our paper, “Trusted Loss Correction for Noisy Multi-Label Learning" , is accpted in ACML 22

[09/22] Our paper, “Multi Label Loss Correction against Missing and Corrupted Labels" , is accpted in ACML 22

[08/22] Our paper, “FreezOff: A Middleware for Heterogeneous Federated Learning Systems” , is accpted in Middleware 22

[08/22] Our paper, “Community-based Approach to Gender-Constrained Influence Maximization" , is accpted in CIKM 22

[06/22] Our paper, “AGIC: Approximate Gradient Inversion Attack on Federated Learning" , is accpted in SRDS22

[06/22] Our paper, “Performance Modeling for Short-Term Cache Allocation" , is accepted at ACM ICPP 2022

[05/22] Lydia receives a NWO Preserpectief grant, a large scaled multi-disciplinary project.