1 citations · 1 across the 14 of their papers we have counts for
9 papers · 1 filter
MoSE: Mixture of Slimmable Experts for Efficient and Adaptive Language Models
Nurbek Tastan, Stefanos Laskaridis, Karthik Nandakumar +1
Mixture-of-Experts (MoE) models scale large language models efficiently by sparsely activating experts, but once an expert is selected, it is executed fully. Hence, the trade-off b…
LoFT: Low-Rank Adaptation That Behaves Like Full Fine-Tuning
Nurbek Tastan, Stefanos Laskaridis, Martin Takac +2
Large pre-trained models are commonly adapted to downstream tasks using parameter-efficient fine-tuning methods such as Low-Rank Adaptation (LoRA), which injects small trainable lo…
Aequa: Fair Model Rewards in Collaborative Learning via Slimmable Networks
Nurbek Tastan, Samuel Horvath, Karthik Nandakumar
Collaborative learning enables multiple participants to learn a single global model by exchanging focused updates instead of sharing data. One of the core challenges in collaborati…
CYCle: Choosing Your Collaborators Wisely to Enhance Collaborative Fairness in Decentralized Learning
Nurbek Tastan, Samuel Horvath, Karthik Nandakumar
Collaborative learning (CL) enables multiple participants to jointly train machine learning (ML) models on decentralized data sources without raw data sharing. While the primary go…
FedPeWS: Personalized Warmup via Subnetworks for Enhanced Heterogeneous Federated Learning
Nurbek Tastan, Samuel Horvath, Martin Takac +1
Statistical data heterogeneity is a significant barrier to convergence in federated learning (FL). While prior work has advanced heterogeneous FL through better optimization object…
Redefining Contributions: Shapley-Driven Federated Learning
Nurbek Tastan, Samar Fares, Toluwani Aremu +2
Federated learning (FL) has emerged as a pivotal approach in machine learning, enabling multiple participants to collaboratively train a global model without sharing raw data. Whil…
Generalized Policy Learning for Smart Grids: FL TRPO Approach
Yunxiang Li, Nicolas Mauricio Cuadrado, Samuel Horváth +1
The smart grid domain requires bolstering the capabilities of existing energy management systems; Federated Learning (FL) aligns with this goal as it demonstrates a remarkable abil…
Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad
Sayantan Choudhury, Nazarii Tupitsa, Nicolas Loizou +3
Adaptive methods are extremely popular in machine learning as they make learning rate tuning less expensive. This paper introduces a novel optimization algorithm named KATE, which…
Vanishing Feature: Diagnosing Model Merging and Beyond
Xingyu Qu, Samuel Horvath
Model merging offers an efficient way to combine pre-trained neural networks but often suffers from inconsistent performance, especially when merging models with different initiali…