99 citations · 260 across the 15 of their papers we have counts for
16 papers
Embracing Federated Learning: Enabling Weak Client Participation via Partial Model Training
Sunwoo Lee, Tuo Zhang, Saurav Prakash +2
In Federated Learning (FL), clients may have weak devices that cannot train the full model or even hold it in their memory space. To implement large-scale FL applications, thus, it…
ATP: Enabling Fast LLM Serving via Attention on Top Principal Keys
Yue Niu, Saurav Prakash, Salman Avestimehr
We propose a new attention mechanism with linear complexity, ATP, that fixates \textbf{A}ttention on \textbf{T}op \textbf{P}rincipal keys, rather than on each individual token. Par…
All Rivers Run to the Sea: Private Learning with Asymmetric Flows
Yue Niu, Ramy E. Ali, Saurav Prakash +1
Data privacy is of great concern in cloud machine-learning service platforms, when sensitive data are exposed to service providers. While private computing environments (e.g., secu…
Federated Classification in Hyperbolic Spaces via Secure Aggregation of Convex Hulls
Saurav Prakash, Jin Sima, Chao Pan +2
Hierarchical and tree-like data sets arise in many applications, including language processing, graph data mining, phylogeny and genomics. It is known that tree-like data cannot be…
Machine Unlearning of Federated Clusters
Chao Pan, Jin Sima, Saurav Prakash +2
Federated clustering (FC) is an unsupervised learning problem that arises in a number of practical applications, including personalized recommender and healthcare systems. With the…
Federated Learning of Large Models at the Edge via Principal Sub-Model Training
Yue Niu, Saurav Prakash, Souvik Kundu +2
Federated Learning (FL) is emerging as a popular, promising decentralized learning framework that enables collaborative training among clients, with no need to share private data b…
Lottery Aware Sparsity Hunting: Enabling Federated Learning on Resource-Limited Edge
Sara Babakniya, Souvik Kundu, Saurav Prakash +2
Edge devices can benefit remarkably from federated learning due to their distributed nature; however, their limited resource and computing power poses limitations in deployment. A…
Basil: A Fast and Byzantine-Resilient Approach for Decentralized Training
Ahmed Roushdy Elkordy, Saurav Prakash, A. Salman Avestimehr
Detection and mitigation of Byzantine behaviors in a decentralized learning setting is a daunting task, especially when the data distribution at the users is heterogeneous. As our…
Coded Computing for Low-Latency Federated Learning over Wireless Edge Networks
Saurav Prakash, Sagar Dhakal, Mustafa Akdeniz +4
Federated learning enables training a global model from data located at the client nodes, without data sharing and moving client data to a centralized server. Performance of federa…
Secure and Fault Tolerant Decentralized Learning
Saurav Prakash, Hanieh Hashemi, Yongqin Wang +2
Federated learning (FL) is a promising paradigm for training a global model over data distributed across multiple data owners without centralizing clients' raw data. However, shari…
Coded Computing for Federated Learning at the Edge
Saurav Prakash, Sagar Dhakal, Mustafa Akdeniz +2
Federated Learning (FL) is an exciting new paradigm that enables training a global model from data generated locally at the client nodes, without moving client data to a centralize…
Coded Federated Learning
Sagar Dhakal, Saurav Prakash, Yair Yona +2
Federated learning is a method of training a global model from decentralized data distributed across client devices. Here, model parameters are computed locally by each client devi…
A Pre-defined Sparse Kernel Based Convolution for Deep CNNs
Souvik Kundu, Saurav Prakash, Haleh Akrami +2
The high demand for computational and storage resources severely impede the deployment of deep convolutional neural networks (CNNs) in limited-resource devices. Recent CNN architec…
CodedReduce: A Fast and Robust Framework for Gradient Aggregation in Distributed Learning
Amirhossein Reisizadeh, Saurav Prakash, Ramtin Pedarsani +1
We focus on the commonly used synchronous Gradient Descent paradigm for large-scale distributed learning, for which there has been a growing interest to develop efficient and robus…
Coded Computing for Distributed Graph Analytics
Saurav Prakash, Amirhossein Reisizadeh, Ramtin Pedarsani +1
Performance of distributed graph processing systems significantly suffers from 'communication bottleneck' as a large number of messages are exchanged among servers at each step of…
Coded Computation over Heterogeneous Clusters
Amirhossein Reisizadeh, Saurav Prakash, Ramtin Pedarsani +1
In large-scale distributed computing clusters, such as Amazon EC2, there are several types of "system noise" that can result in major degradation of performance: bottlenecks due to…