SPStacy Patterson

Stacy Patterson

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Stacy Patterson has a total of 61 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Measuring Privacy Risks and Tradeoffs in Financial Synthetic Data Generation

    by Michael Zuo, Inwon Kang, Stacy Patterson, Oshani Seneviratne

    We explore the privacy-utility tradeoff of synthetic data generation schemes on tabular financial datasets, a domain characterized by high regulatory risk and severe class imbalance. We consider representative tabular data generators, including autoencoders, generative adversarial networks, diffusion, and copula synthesizers. To address the challenges of the financial domain, we provide novel privacy-preserving implementations of GAN and autoencoder synthesizers. We evaluate whether and how well the generators simultaneously achieve data quality, downstream utility, and privacy, with comparison across balanced and imbalanced input datasets. Our results offer insight into the distinct challenges of generating synthetic data from datasets that exhibit severe class imbalance and mixed-type attributes.


  • Open Access

    Multi-task Code LLMs: Data Mix or Model Merge?

    by Mingzhi Zhu, Michele Merler, Boris Sobolev, Rahul Krishna, Raju Pavuluri, Stacy Patterson

  • Open Access

    Multi-task Code LLMs: Data Mix or Model Merge?

    by Mingzhi Zhu, Boris Sobolev, Rahul Krishna, Raju Pavuluri, Stacy Patterson, Michele Merler

    Recent research advocates deploying smaller, specialized code LLMs in agentic frameworks alongside frontier models, sparking interest in efficient strategies for multi-task learning that balance performance, constraints, and costs. We compare two approaches for creating small, multi-task code LLMs: data mixing versus model merging. We conduct extensive experiments across two model families (Qwen Coder and DeepSeek Coder) at two scales (2B and 7B parameters), fine-tuning them for code generation and code summarization tasks. Our evaluation on HumanEval, MBPP, and CodeXGlue benchmarks reveals that model merging achieves the best overall performance at larger scale across model families, retaining 96% of specialized model performance on code generation tasks while maintaining summarization capabilities. Notably, merged models can even surpass individually fine-tuned models, with our best configuration of Qwen Coder 2.5 7B model achieving 92.7% Pass@1 on HumanEval compared to 90.9% for its task-specific fine-tuned equivalent. At a smaller scale we find instead data mixing to be a preferred strategy. We further introduce a weight analysis technique to understand how different tasks affect model parameters and their implications for merging strategies. The results suggest that careful merging and mixing strategies can effectively combine task-specific capabilities without significant performance degradation, making them ideal for resource-constrained deployment scenarios.

  • Optimal Assignment and Motion Control in Two-Class Continuum Swarms

    by Max Emerick, Stacy Patterson, Bassam Bamieh

    We consider optimal swarm control problems where two different classes of agents are present. Continuum idealizations of large-scale swarms are used where the dynamics describe the evolution of the spatially-distributed densities of each agent class. The problem formulation we adopt is motivated by applications where agents of one class are assigned to agents of the other class, which we refer to as demand and resource agents respectively. Assignments have costs related to the distances between mutually assigned agents, and the overall cost of an assignment is quantified by a Wasserstein distance between the densities of the two agent classes. When agents can move, the assignment cost can decrease at the expense of a physical motion cost, and this tradeoff sets up a nonlinear infinite-dimensional optimal control problem. We show that in one spatial dimension, this problem can be converted to an infinite-dimensional, but decoupled, linear- quadratic (LQ) tracking problem when expressed in terms of the quantile functions of the respective agent densities. Solutions are given in the general one-dimensional case, as well as in the special cases of constant and periodically time-varying demands.

  • Open Access

    Fed-RD: Privacy-Preserving Federated Learning for Financial Crime Detection

    by Saikat Islam Khan, Aparna Gupta, Oshani Seneviratne, Stacy Patterson

    We introduce Federated Learning for Relational Data (Fed-RD), a novel privacy-preserving federated learning algorithm specifically developed for financial transaction datasets partitioned vertically and horizontally across parties. Fed-RD strategically employs differential privacy and secure multiparty computation to guarantee the privacy of training data. We provide theoretical analysis of the end-to-end privacy of the training algorithm and present experimental results on realistic synthetic datasets. Our results demonstrate that Fed-RD achieves high model accuracy with minimal degradation as privacy increases, while consistently surpassing benchmark results.

  • Open Access

    A Differentially Private Blockchain-Based Approach for Vertical Federated Learning

    by Linh Tran, Sanjay Chari, Saikat Islam Khan, Aaron Zachariah, Stacy Patterson, Oshani Seneviratne

    We present the Differentially Private Blockchain-Based Vertical Federal Learning (DP-BBVFL) algorithm that provides verifiability and privacy guarantees for decentralized applications. DP-BBVFL uses a smart contract to aggregate the feature representations, i.e., the embeddings, from clients transparently. We apply local differential privacy to provide privacy for embeddings stored on a blockchain, hence protecting the original data. We provide the first prototype application of differential privacy with blockchain for vertical federated learning. Our experiments with medical data show that DP-BBVFL achieves high accuracy with a tradeoff in training time due to on-chain aggregation. This innovative fusion of differential privacy and blockchain technology in DP-BBVFL could herald a new era of collaborative and trustworthy machine learning applications across several decentralized application domains.

  • Flexible Vertical Federated Learning With Heterogeneous Parties

    by Timothy Castiglia, Shiqiang Wang, Stacy Patterson

    We propose flexible vertical federated learning (Flex-VFL), a distributed machine algorithm that trains a smooth, nonconvex function in a distributed system with vertically partitioned data. We consider a system with several parties that wish to collaboratively learn a global function. Each party holds a local dataset; the datasets have different features but share the same sample ID space. The parties are heterogeneous in nature: the parties’ operating speeds, local model architectures, and optimizers may be different from one another and, further, they may change over time. To train a global model in such a system, Flex-VFL utilizes a form of parallel block coordinate descent (P-BCD), where parties train a partition of the global model via stochastic coordinate descent. We provide theoretical convergence analysis for Flex-VFL and show that the convergence rate is constrained by the party speeds and local optimizer parameters. We apply this analysis and extend our algorithm to adapt party learning rates in response to changing speeds and local optimizer parameters. Finally, we compare the convergence time of Flex-VFL against synchronous and asynchronous VFL algorithms, as well as illustrate the effectiveness of our adaptive extension.


  • Open Access

    Flexible Vertical Federated Learning with Heterogeneous Parties

    by Timothy Castiglia, Shiqiang Wang, Stacy Patterson

    We propose Flexible Vertical Federated Learning (Flex-VFL), a distributed machine algorithm that trains a smooth, non-convex function in a distributed system with vertically partitioned data. We consider a system with several parties that wish to collaboratively learn a global function. Each party holds a local dataset; the datasets have different features but share the same sample ID space. The parties are heterogeneous in nature: the parties' operating speeds, local model architectures, and optimizers may be different from one another and, further, they may change over time. To train a global model in such a system, Flex-VFL utilizes a form of parallel block coordinate descent, where parties train a partition of the global model via stochastic coordinate descent. We provide theoretical convergence analysis for Flex-VFL and show that the convergence rate is constrained by the party speeds and local optimizer parameters. We apply this analysis and extend our algorithm to adapt party learning rates in response to changing speeds and local optimizer parameters. Finally, we compare the convergence time of Flex-VFL against synchronous and asynchronous VFL algorithms, as well as illustrate the effectiveness of our adaptive extension.


  • Formal Verification of Safety-Critical Aerospace Systems

    by Saswata Paul, Elkin Cruz, Airin Dutta, Ankita Bhaumik, Erik Blasch, Gul Agha, Stacy Patterson, Fotis Kopsaftopoulos, Carlos Varela

    Developments in autonomous aircraft, such as electrical vertical take-off and landing (eVTOL) vehicles and multicopter drones, raise safety-critical concerns in populated areas. This article presents the ASSURE ( A nalysis of S afety-Critical S ystems U sing Formal Methods-Based R untime E valuation ) framework, which is a collection of techniques for aiding in the formal verification of safety-critical aerospace systems. ASSURE supports the rigorous verification of deterministic and non-deterministic properties of both distributed and centralized aerospace applications by using formal theorem proving tools. We present verifiable algorithms and software, formal reasoning models, formal proof libraries , and a data-driven runtime verification approach for aerospace systems towards a provably safe Internet of Planes (IoP) infrastructure.


  • Open Access

    Cross-Silo Federated Learning for Multi-Tier Networks with Vertical and Horizontal Data Partitioning

    by Anirban Das, Timothy Castiglia, Shiqiang Wang, Stacy Patterson

    We consider federated learning in tiered communication networks. Our network model consists of a set of silos, each holding a vertical partition of the data. Each silo contains a hub and a set of clients, with the silo’s vertical data shard partitioned horizontally across its clients. We propose Tiered Decentralized Coordinate Descent (TDCD), a communication-efficient decentralized training algorithm for such two-tiered networks. The clients in each silo perform multiple local gradient steps before sharing updates with their hub to reduce communication overhead. Each hub adjusts its coordinates by averaging its workers’ updates, and then hubs exchange intermediate updates with one another. We present a theoretical analysis of our algorithm and show the dependence of the convergence rate on the number of vertical partitions and the number of local updates. We further validate our approach empirically via simulation-based experiments using a variety of datasets and objectives.