no code implementations • 15 Apr 2024 • Satyavrat Wagle, Seyyedali Hosseinalipour, Naji Khosravan, Christopher G. Brinton
Specifically, we introduce a \textit{smart information push-pull} methodology for data/embedding exchange tailored to FL settings with either soft or strict data privacy restrictions.
no code implementations • 9 Apr 2024 • Payam Abdisarabshali, Kwang Taik Kim, Michael Langberg, Weifeng Su, Seyyedali Hosseinalipour
In this paper, we incorporate multi-granular system dynamics (MSDs) into FL, including (M1) dynamic wireless channel capacity, captured by a set of discrete-time events, called $\mathscr{D}$-Events, and (M2) dynamic datasets of users.
1 code implementation • 5 Feb 2024 • Shahryar Zehtabi, Dong-Jun Han, Rohit Parasnis, Seyyedali Hosseinalipour, Christopher G. Brinton
Decentralized Federated Learning (DFL) has received significant recent research attention, capturing settings where both model updates and model aggregations -- the two key FL processes -- are conducted by the clients.
no code implementations • 3 Feb 2024 • Yun-Wei Chu, Dong-Jun Han, Seyyedali Hosseinalipour, Christopher G. Brinton
Most existing federated learning (FL) methodologies have assumed training begins from a randomly initialized model.
no code implementations • 7 Jan 2024 • Kasra Borazjani, Naji Khosravan, Leslie Ying, Seyyedali Hosseinalipour
Given the frequent presence of diverse data modalities within patient records, leveraging FL in a multi-modal learning framework holds considerable promise for cancer staging.
no code implementations • 31 Dec 2023 • JungHoon Kim, Taejoon Kim, Anindya Bijoy Das, Seyyedali Hosseinalipour, David J. Love, Christopher G. Brinton
In this work, we aim to enhance and balance the communication reliability in GTWCs by minimizing the sum of error probabilities via joint design of encoders and decoders at the users.
no code implementations • 23 Dec 2023 • Dong-Jun Han, Seyyedali Hosseinalipour, David J. Love, Mung Chiang, Christopher G. Brinton
While network coverage maps continue to expand, many devices located in remote areas remain unconnected to terrestrial communication infrastructures, preventing them from getting access to the associated data-driven services.
no code implementations • 7 Nov 2023 • Su Wang, Roberto Morabito, Seyyedali Hosseinalipour, Mung Chiang, Christopher G. Brinton
Our optimization methodology aims to select the best combination of sampled nodes and data offloading configuration to maximize FedL training accuracy while minimizing data processing and D2D communication resource consumption subject to realistic constraints on the network topology and device capabilities.
no code implementations • 3 Jul 2023 • Zhang Liu, Lianfen Huang, Zhibin Gao, Manman Luo, Seyyedali Hosseinalipour, Huaiyu Dai
In this paper, we propose a graph neural network-augmented deep reinforcement learning scheme (GA-DRL) for scheduling DAG tasks over dynamic VCs.
no code implementations • 22 May 2023 • Zhan-Lun Chang, Seyyedali Hosseinalipour, Mung Chiang, Christopher G. Brinton
Our analysis sheds light on the joint impact of device training variables (e. g., number of local gradient descent steps), asynchronous scheduling decisions (i. e., when a device trains a task), and dynamic data drifts on the performance of ML training for different tasks.
no code implementations • 30 Apr 2023 • Myeung Suk Oh, Seyyedali Hosseinalipour, Taejoon Kim, David J. Love, James V. Krogmeier, Christopher G. Brinton
For dynamic sensor selection, two greedy selection strategies are proposed, each of which exploits properties revealed in the derived CRLB expressions.
no code implementations • 24 Apr 2023 • Su Wang, Seyyedali Hosseinalipour, Christopher G. Brinton
Our methodology, Source-Target Determination and Link Formation (ST-LF), optimizes both (i) classification of devices into sources and targets and (ii) source-target link formation, in a manner that considers the trade-off between ML model accuracy and communication energy efficiency.
no code implementations • 14 Apr 2023 • Payam Abdisarabshali, Nicholas Accurso, Filippo Malandra, Weifeng Su, Seyyedali Hosseinalipour
Motivated by these challenges, we introduce a generic FL paradigm over NextG networks, called dynamic multi-service FL (DMS-FL).
no code implementations • 22 Mar 2023 • Frank Po-Chen Lin, Seyyedali Hosseinalipour, Nicolò Michelusi, Christopher Brinton
The paper introduces delay-aware hierarchical federated learning (DFL) to improve the efficiency of distributed machine learning (ML) model training by accounting for communication delays between edge and cloud.
no code implementations • 15 Mar 2023 • Su Wang, Seyyedali Hosseinalipour, Vaneet Aggarwal, Christopher G. Brinton, David J. Love, Weifeng Su, Mung Chiang
Federated learning (FL) has been promoted as a popular technique for training machine learning (ML) models over edge/fog networks.
no code implementations • 12 Jan 2023 • Myeung Suk Oh, Anindya Bijoy Das, Seyyedali Hosseinalipour, Taejoon Kim, David J. Love, Christopher G. Brinton
Radio access networks (RANs) in monolithic architectures have limited adaptability to supporting different network scenarios.
no code implementations • 5 Dec 2022 • Yun-Wei Chu, Seyyedali Hosseinalipour, Elizabeth Tenorio, Laura Cruz, Kerrie Douglas, Andrew Lan, Christopher Brinton
Traditional learning-based approaches to student modeling (e. g., predicting grades based on measured activities) generalize poorly to underrepresented/minority student groups due to biases in data availability.
no code implementations • 23 Nov 2022 • Shahryar Zehtabi, Seyyedali Hosseinalipour, Christopher G. Brinton
We theoretically demonstrate that our methodology converges to the globally optimal learning model at a $O{(\frac{\ln{k}}{\sqrt{k}})}$ rate under standard assumptions in distributed learning and consensus literature.
no code implementations • 4 Aug 2022 • Satyavrat Wagle, Seyyedali Hosseinalipour, Naji Khosravan, Mung Chiang, Christopher G. Brinton
In most of the current literature, FL has been studied for supervised ML tasks, in which edge devices collect labeled data.
no code implementations • 2 Aug 2022 • Yun-Wei Chu, Seyyedali Hosseinalipour, Elizabeth Tenorio, Laura Cruz, Kerrie Douglas, Andrew Lan, Christopher Brinton
To learn better representations of student activity, we augment our approach with a self-supervised behavioral pretraining methodology that leverages multiple modalities of student behavior (e. g., visits to lecture videos and participation on forums), and include a neural network attention mechanism in the model aggregation stage.
no code implementations • 7 May 2022 • JungHoon Kim, Seyyedali Hosseinalipour, Andrew C. Marcum, Taejoon Kim, David J. Love, Christopher G. Brinton
Intelligent reflecting surfaces (IRS) consist of configurable meta-atoms, which can alter the wireless propagation environment through design of their reflection coefficients.
1 code implementation • 7 Apr 2022 • Shahryar Zehtabi, Seyyedali Hosseinalipour, Christopher G. Brinton
Through theoretical analysis, we demonstrate that our methodology achieves asymptotic convergence to the globally optimal learning model under standard assumptions in distributed learning and graph consensus literature, and without restrictive connectivity requirements on the underlying topology.
no code implementations • 26 Mar 2022 • Bhargav Ganguly, Seyyedali Hosseinalipour, Kwang Taik Kim, Christopher G. Brinton, Vaneet Aggarwal, David J. Love, Mung Chiang
CE-FL also introduces floating aggregation point, where the local models generated at the devices and the servers are aggregated at an edge server, which varies from one model training round to another to cope with the network evolution in terms of data distribution and users' mobility.
no code implementations • 18 Mar 2022 • Dinh C. Nguyen, Seyyedali Hosseinalipour, David J. Love, Pubudu N. Pathirana, Christopher G. Brinton
To assist the ML model training for resource-constrained MDs, we develop an offloading strategy that enables MDs to transmit their data to one of the associated ESs.
no code implementations • 7 Feb 2022 • Seyyedali Hosseinalipour, Su Wang, Nicolo Michelusi, Vaneet Aggarwal, Christopher G. Brinton, David J. Love, Mung Chiang
PSL considers the realistic scenario where global aggregations are conducted with idle times in-between them for resource efficiency improvements, and incorporates data dispersion and model dispersion with local model condensation into FedL.
1 code implementation • ICLR 2022 • Sheikh Shams Azam, Seyyedali Hosseinalipour, Qiang Qiu, Christopher Brinton
In this paper, we question the rationale behind propagating large numbers of parameters through a distributed system during federated learning.
no code implementations • 27 Dec 2021 • David Nickel, Frank Po-Chen Lin, Seyyedali Hosseinalipour, Nicolo Michelusi, Christopher G. Brinton
Federated learning (FL) has emerged as a popular technique for distributing machine learning across wireless edge devices.
no code implementations • 3 Dec 2021 • JungHoon Kim, Seyyedali Hosseinalipour, Andrew C. Marcum, Taejoon Kim, David J. Love, Christopher G. Brinton
We consider a practical setting where (i) the IRS reflection coefficients are achieved by adjusting tunable elements embedded in the meta-atoms, (ii) the IRS reflection coefficients are affected by the incident angles of the incoming signals, (iii) the IRS is deployed in multi-path, time-varying channels, and (iv) the feedback link from the base station to the IRS has a low data rate.
1 code implementation • 7 Sep 2021 • Frank Po-Chen Lin, Seyyedali Hosseinalipour, Sheikh Shams Azam, Christopher G. Brinton, Nicolò Michelusi
Federated learning has emerged as a popular technique for distributing model training across the network edge.
no code implementations • 29 Jun 2021 • Su Wang, Seyyedali Hosseinalipour, Maria Gorlatova, Christopher G. Brinton, Mung Chiang
The presence of time-varying data heterogeneity and computational resource inadequacy among device clusters motivate four key parts of our methodology: (i) stratified UAV swarms of leader, worker, and coordinator UAVs, (ii) hierarchical nested personalized federated learning (HN-PFL), a distributed ML framework for personalized model training across the worker-leader-core network hierarchy, (iii) cooperative UAV resource pooling to address computational inadequacy of devices by conducting model training among the UAV swarms, and (iv) model/concept drift to model time-varying data distributions.
1 code implementation • 18 Mar 2021 • Frank Po-Chen Lin, Seyyedali Hosseinalipour, Sheikh Shams Azam, Christopher G. Brinton, Nicolo Michelusi
Federated learning has emerged as a popular technique for distributing machine learning (ML) model training across the wireless edge.
no code implementations • 25 Jan 2021 • Myeung Suk Oh, Seyyedali Hosseinalipour, Taejoon Kim, Christopher G. Brinton, David J. Love
Our methodology includes a new successive channel denoising process based on channel curvature computation, for which we obtain a channel curvature magnitude threshold to identify unreliable channel estimates.
no code implementations • 4 Jan 2021 • Su Wang, Mengyuan Lee, Seyyedali Hosseinalipour, Roberto Morabito, Mung Chiang, Christopher G. Brinton
The conventional federated learning (FedL) architecture distributes machine learning (ML) across worker devices by having them train local models that are periodically aggregated by a server.
no code implementations • 2 Nov 2020 • JungHoon Kim, Seyyedali Hosseinalipour, Taejoon Kim, David J. Love, Christopher G. Brinton
Applications of intelligent reflecting surfaces (IRSs) in wireless networks have attracted significant attention recently.
1 code implementation • 5 Oct 2020 • Sheikh Shams Azam, Taejin Kim, Seyyedali Hosseinalipour, Carlee Joe-Wong, Saurabh Bagchi, Christopher Brinton
We study the problem of learning representations that are private yet informative, i. e., provide information about intended "ally" targets while hiding sensitive "adversary" attributes.
no code implementations • 29 Sep 2020 • Mengyuan Lee, Seyyedali Hosseinalipour, Christopher G. Brinton, Guanding Yu, Huaiyu Dai
However, the problem of allocating items among the bidders to maximize the auctioneers" revenue, i. e., the winner determination problem (WDP), is NP-complete to solve and inapproximable.
no code implementations • 26 Jul 2020 • Hung T. Nguyen, Vikash Sehwag, Seyyedali Hosseinalipour, Christopher G. Brinton, Mung Chiang, H. Vincent Poor
In this paper, we propose a fast-convergent federated learning algorithm, called FOLB, which performs intelligent sampling of devices in each round of model training to optimize the expected convergence speed.
1 code implementation • 18 Jul 2020 • Seyyedali Hosseinalipour, Sheikh Shams Azam, Christopher G. Brinton, Nicolo Michelusi, Vaneet Aggarwal, David J. Love, Huaiyu Dai
We derive the upper bound of convergence for MH-FL with respect to parameters of the network topology (e. g., the spectral radius) and the learning algorithm (e. g., the number of D2D rounds in different clusters).
no code implementations • 7 Jun 2020 • Seyyedali Hosseinalipour, Christopher G. Brinton, Vaneet Aggarwal, Huaiyu Dai, Mung Chiang
There are several challenges with employing conventional federated learning in contemporary networks, due to the significant heterogeneity in compute and communication capabilities that exist across devices.
no code implementations • 10 May 2020 • Ali Rahmati, Seyyedali Hosseinalipour, Ismail Guvenc, Huaiyu Dai, Arupjyoti Bhuyan
Deployment of unmanned aerial vehicles (UAVs) is recently getting significant attention due to a variety of practical use cases, such as surveillance, data gathering, and commodity delivery.