More Like this

1. PluralLLM: Pluralistic Alignment in LLMs via Federated Learning

   https://doi.org/10.1145/3722570.3726898  

   Srewa, Mahmoud; Zhao, Tianyu; Elmalaki, Salma (May 2025, ACM)

   Ensuring Large Language Models (LLM) align with diverse human preferences while preserving privacy and fairness remains a challenge. Existing methods, such as Reinforcement Learning with Human Feedback (RLHF), rely on centralized data collection, making them computationally expensive and privacy-invasive. We introduce PluralLLM a federated learning-based approach that enables multiple user groups to collaboratively train a transformer-based preference predictor without sharing sensitive data, which can also serve as a reward model for aligning LLMs. Our method leverages Federated Averaging (FedAvg) to aggregate preference updates efficiently, achieving 46% faster convergence, a 4% improvement in alignment scores, and nearly the same group fairness measure as in centralized training. Evaluated on a Q/A preference alignment task, PluralLLM demonstrates that federated preference learning offers a scalable and privacy-preserving alternative for aligning LLMs with diverse human values. 

   more » « less
2. Federated Learning Robustness on Real World Data in Intelligent Transportation Systems

   Korobeinikov, Dmitrii; Chuprov, Sergei; Zatsarenko, Raman; Reznik, Leon (June 2024, 19th Annual Symposium on Information Assurance (ASIA’ 24) , June 4-5, 2024, Albany, NY)

   Goal, S (Ed.)

   Machine Learning models are widely utilized in a variety of applications, including Intelligent Transportation Systems (ITS). As these systems are operating in highly dynamic environments, they are exposed to numerous security threats that cause Data Quality (DQ) variations. Among such threats are network attacks that may cause data losses. We evaluate the influence of these factors on the image DQ and consequently on the image ML model performance. We propose and investigate Federated Learning (FL) as the way to enhance the overall level of privacy and security in ITS, as well as to improve ML model robustness to possible DQ variations in real-world applications. Our empirical study conducted with traffic sign images and YOLO, VGG16 and ResNet models proved the greater robustness of FL-based architecture over a centralized one. 

   more » « less
3. Collaborative inference for treatment effect with distributed data‐sharing management in multicenter studies

   https://doi.org/10.1002/sim.10068  

   Hu, Mengtong; Shi, Xu; Song, Peter X‐K (May 2024, Statistics in Medicine)

   Data sharing barriers present paramount challenges arising from multicenter clinical studies where multiple data sources are stored and managed in a distributed fashion at different local study sites. Merging such data sources into a common data storage for a centralized statistical analysis requires a data use agreement, which is often time‐consuming. Data merging may become more burdensome when propensity score modeling is involved in the analysis because combining many confounding variables, and systematic incorporation of this additional modeling in a meta‐analysis has not been thoroughly investigated in the literature. Motivated from a multicenter clinical trial of basal insulin treatment for reducing the risk of post‐transplantation diabetes mellitus, we propose a new inference framework that avoids the merging of subject‐level raw data from multiple sites at a centralized facility but needs only the sharing of summary statistics. Unlike the architecture of federated learning, the proposed collaborative inference does not need a center site to combine local results and thus enjoys maximal protection of data privacy and minimal sensitivity to unbalanced data distributions across data sources. We show theoretically and numerically that the new distributed inference approach has little loss of statistical power compared to the centralized method that requires merging the entire data. We present large‐sample properties and algorithms for the proposed method. We illustrate its performance by simulation experiments and the motivating example on the differential average treatment effect of basal insulin to lower risk of diabetes among kidney‐transplant patients compared to the standard‐of‐care. 

   more » « less
4. Data heterogeneity in federated learning with Electronic Health Records: Case studies of risk prediction for acute kidney injury and sepsis diseases in critical care

   https://doi.org/10.1371/journal.pdig.0000117  

   Rajendran, Suraj; Xu, Zhenxing; Pan, Weishen; Ghosh, Arnab; Wang, Fei (March 2023, PLOS Digital Health)

   Frasch, Martin G. (Ed.)

   With the wider availability of healthcare data such as Electronic Health Records (EHR), more and more data-driven based approaches have been proposed to improve the quality-of-care delivery. Predictive modeling, which aims at building computational models for predicting clinical risk, is a popular research topic in healthcare analytics. However, concerns about privacy of healthcare data may hinder the development of effective predictive models that are generalizable because this often requires rich diverse data from multiple clinical institutions. Recently, federated learning (FL) has demonstrated promise in addressing this concern. However, data heterogeneity from different local participating sites may affect prediction performance of federated models. Due to acute kidney injury (AKI) and sepsis’ high prevalence among patients admitted to intensive care units (ICU), the early prediction of these conditions based on AI is an important topic in critical care medicine. In this study, we take AKI and sepsis onset risk prediction in ICU as two examples to explore the impact of data heterogeneity in the FL framework as well as compare performances across frameworks. We built predictive models based on local, pooled, and FL frameworks using EHR data across multiple hospitals. The local framework only used data from each site itself. The pooled framework combined data from all sites. In the FL framework, each local site did not have access to other sites’ data. A model was updated locally, and its parameters were shared to a central aggregator, which was used to update the federated model’s parameters and then subsequently, shared with each site. We found models built within a FL framework outperformed local counterparts. Then, we analyzed variable importance discrepancies across sites and frameworks. Finally, we explored potential sources of the heterogeneity within the EHR data. The different distributions of demographic profiles, medication use, and site information contributed to data heterogeneity. 

   more » « less
5. FedDNA: Federated learning using dynamic node alignment

   https://doi.org/10.1371/journal.pone.0288157  

   Wang, Shuwen; Zhu, Xingquan (July 2023, PLOS ONE)

   Donta, Praveen Kumar (Ed.)

   Federated Learning (FL), as a new computing framework, has received significant attentions recently due to its advantageous in preserving data privacy in training models with superb performance. During FL learning, distributed sites first learn respective parameters. A central site will consolidate learned parameters, using average or other approaches, and disseminate new weights across all sites to carryout next round of learning. The distributed parameter learning and consolidation repeat in an iterative fashion until the algorithm converges or terminates. Many FL methods exist to aggregate weights from distributed sites, but most approaches use a static node alignment approach, where nodes of distributed networks are statically assigned, in advance, to match nodes and aggregate their weights. In reality, neural networks, especially dense networks, have nontransparent roles with respect to individual nodes. Combined with random nature of the networks, static node matching often does not result in best matching between nodes across sites. In this paper, we propose, FedDNA, adynamic node alignmentfederated learning algorithm. Our theme is to find best matching nodes between different sites, and then aggregate weights of matching nodes for federated learning. For each node in a neural network, we represent its weight values as a vector, and use a distance function to find most similar nodes,i.e., nodes with the smallest distance from other sides. Because finding best matching across all sites are computationally expensive, we further design a minimum spanning tree based approach to ensure that a node from each site will have matched peers from other sites, such that the total pairwise distances across all sites are minimized. Experiments and comparisons demonstrate that FedDNA outperforms commonly used baseline, such as FedAvg, for federated learning. 

   more » « less