Search Results for author: Christopher Brinton

Found 10 papers, 3 papers with code

Differential Privacy in Hierarchical Federated Learning: A Formal Analysis and Evaluation

no code implementations21 Jan 2024 Frank Po-Chen Lin, Christopher Brinton

While federated learning (FL) eliminates the transmission of raw data over a network, it is still vulnerable to privacy breaches from the communicated model parameters.

Federated Learning

Exploring the Efficacy of ChatGPT in Analyzing Student Teamwork Feedback with an Existing Taxonomy

no code implementations9 May 2023 Andrew Katz, Siqing Wei, Gaurav Nanda, Christopher Brinton, Matthew Ohland

This study contributes to the growing body of research on the use of AI models in educational contexts and highlights the potential of ChatGPT for facilitating analysis of student comments.

Robust Non-Linear Feedback Coding via Power-Constrained Deep Learning

no code implementations25 Apr 2023 JungHoon Kim, Taejoon Kim, David Love, Christopher Brinton

The design of codes for feedback-enabled communications has been a long-standing open problem.

Delay-Aware Hierarchical Federated Learning

no code implementations22 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.

Federated Learning

Multi-Layer Personalized Federated Learning for Mitigating Biases in Student Predictive Analytics

no code implementations5 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.

Knowledge Tracing Personalized Federated Learning

Mitigating Biases in Student Performance Prediction via Attention-Based Personalized Federated Learning

no code implementations2 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.

Personalized Federated Learning

Process-BERT: A Framework for Representation Learning on Educational Process Data

1 code implementation28 Apr 2022 Alexander Scarlatos, Christopher Brinton, Andrew Lan

One can use process data for many downstream tasks such as learning outcome prediction and automatically delivering personalized intervention.

Representation Learning

Stabilized Likelihood-based Imitation Learning via Denoising Continuous Normalizing Flow

no code implementations29 Sep 2021 Xin Zhang, Yanhua Li, Ziming Zhang, Christopher Brinton, Zhenming Liu, Zhi-Li Zhang, Hui Lu, Zhihong Tian

State-of-the-art imitation learning (IL) approaches, e. g, GAIL, apply adversarial training to minimize the discrepancy between expert and learner behaviors, which is prone to unstable training and mode collapse.

Denoising Imitation Learning

Can we Generalize and Distribute Private Representation Learning?

1 code implementation5 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.

Federated Learning Generative Adversarial Network +2

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