Search Results for author: Saber Malekmohammadi

Found 9 papers, 2 papers with code

On the Implicit Relation Between Low-Rank Adaptation and Differential Privacy

no code implementations26 Sep 2024 Saber Malekmohammadi, Golnoosh Farnadi

We show theoretically that the low-rank adaptation used in LoRA and FLoRA is equivalent to injecting some random noise into the batch gradients w. r. t the adapter parameters, and we quantify the variance of the injected noise.

LEMMA Relation

Semi-Variance Reduction for Fair Federated Learning

no code implementations23 Jun 2024 Saber Malekmohammadi

VRed encourages equality between clients' loss functions by penalizing their variance.

Fairness Federated Learning

Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning

1 code implementation5 Jun 2024 Saber Malekmohammadi, YaoLiang Yu, Yang Cao

Furthermore, there is often heterogeneity in batch and/or dataset size of clients, which as shown, results in extra variation in the DP noise level across clients model updates.

Federated Learning

Differentially Private Clustered Federated Learning

no code implementations29 May 2024 Saber Malekmohammadi, Afaf Taik, Golnoosh Farnadi

To address this gap, we propose an algorithm for differentially private clustered FL, which is robust to the DP noise in the system and identifies the underlying clients' clusters correctly.

Clustering Fairness +1

Proportional Fairness in Federated Learning

1 code implementation3 Feb 2022 Guojun Zhang, Saber Malekmohammadi, Xi Chen, YaoLiang Yu

With the increasingly broad deployment of federated learning (FL) systems in the real world, it is critical but challenging to ensure fairness in FL, i. e. reasonably satisfactory performances for each of the numerous diverse clients.

Fairness Federated Learning

An Operator Splitting View of Federated Learning

no code implementations12 Aug 2021 Saber Malekmohammadi, Kiarash Shaloudegi, Zeou Hu, YaoLiang Yu

Over the past few years, the federated learning ($\texttt{FL}$) community has witnessed a proliferation of new $\texttt{FL}$ algorithms.

Federated Learning

PePScenes: A Novel Dataset and Baseline for Pedestrian Action Prediction in 3D

no code implementations14 Dec 2020 Amir Rasouli, Tiffany Yau, Peter Lakner, Saber Malekmohammadi, Mohsen Rohani, Jun Luo

To this end, we propose a new pedestrian action prediction dataset created by adding per-frame 2D/3D bounding box and behavioral annotations to the popular autonomous driving dataset, nuScenes.

Autonomous Driving Motion Planning +2

Graph-SIM: A Graph-based Spatiotemporal Interaction Modelling for Pedestrian Action Prediction

no code implementations3 Dec 2020 Tiffany Yau, Saber Malekmohammadi, Amir Rasouli, Peter Lakner, Mohsen Rohani, Jun Luo

2) We introduce a new dataset that provides 3D bounding box and pedestrian behavioural annotations for the existing nuScenes dataset.

Autonomous Vehicles Clustering

Non-Parametric Graph Learning for Bayesian Graph Neural Networks

no code implementations23 Jun 2020 Soumyasundar Pal, Saber Malekmohammadi, Florence Regol, Yingxue Zhang, Yishi Xu, Mark Coates

A Bayesian framework which targets posterior inference of the graph by considering it as a random quantity can be beneficial.

Graph Learning Link Prediction +1

Cannot find the paper you are looking for? You can Submit a new open access paper.