activity
20172022
most citedEfficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspaces

5 citations · 10 across the 6 of their papers we have counts for

collaborators

10 papers

cs.LG2022

Neural Routing in Meta Learning

Jicang Cai, Saeed Vahidian, Weijia Wang +2

Meta-learning often referred to as learning-to-learn is a promising notion raised to mimic human learning by exploiting the knowledge of prior tasks but being able to adapt quickly…

cs.LG20222 cited

Rethinking Data Heterogeneity in Federated Learning: Introducing a New Notion and Standard Benchmarks

Mahdi Morafah, Saeed Vahidian, Chen Chen +2

Though successful, federated learning presents new challenges for machine learning, especially when the issue of data heterogeneity, also known as Non-IID data, arises. To cope wit…

cs.LG20225 cited

Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspaces

Saeed Vahidian, Mahdi Morafah, Weijia Wang +4

Clustered federated learning (FL) has been shown to produce promising results by grouping clients into clusters. This is especially effective in scenarios where separate groups of…

cs.LG2021

Personalized Federated Learning by Structured and Unstructured Pruning under Data Heterogeneity

Saeed Vahidian, Mahdi Morafah, Bill Lin

The traditional approach in FL tries to learn a single global model collaboratively with the help of many clients under the orchestration of a central server. However, learning a s…

cs.LG20203 cited

Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models

Siavash Khodadadeh, Sharare Zehtabian, Saeed Vahidian +3

Unsupervised meta-learning approaches rely on synthetic meta-tasks that are created using techniques such as random selection, clustering and/or augmentation. Unfortunately, cluste…

cs.LG2019

Coresets for Estimating Means and Mean Square Error with Limited Greedy Samples

Saeed Vahidian, Baharan Mirzasoleiman, Alexander Cloninger

In a number of situations, collecting a function value for every data point may be prohibitively expensive, and random sampling ignores any structure in the underlying data. We int…