Publikationen
Hier finden Sie eine Auswahl an Veröffentlichungen, Whitepaper und wissenschaftlichen Beiträgen mit Bezug zum Green-INNO Projekt.
Die Publikationen bieten fundierte Einblicke in nachhaltige Innovationen und zukunftsweisende Technologien. Erkunden Sie unsere Forschungsergebnisse und bleiben Sie auf dem neuesten Stand der Entwicklungen!
2025
Driving Cooperation in Federated Learning via
Evolutionary Game Theory
Abstract (engl.)
We introduce an enhanced formulation of FedT4T-Pro, a Federated Learning framework designed to systematically assess utility-driven client strategies within resource-constrained environments.
To address key challenges in practical distributed learning systems, such as resource limitations and non-cooperative behaviors, we model client interactions using the Iterated Prisoner’s Dilemma.
Our framework empowers clients to refine their decision rules based on past interactions and available resources, optimizing both individual utility and overall contributions to a global learning objective.
In addition, a novel sampling algorithm for client selection, drawing inspiration from evolutionary biology, is proposed as a natural incentive mechanism to encourage consistent cooperation and resource contributions.
We apply FedT4T-Pro to a Federated Learning benchmark classification task and explore the dynamics of cooperation between clients driven by common strategies from Cooperation theory under the impact of varying resource availability.
Furthermore, we experimentally show that the proposed sampling algorithm fosters collaborative behavior in FL training.
Twin Transition – Sustainable Digital Decision Making in Enterprise Resource Planning
Abstract (short, engl.)
The EU aims for climate neutrality by 2050 through a “twin transition” that combines digitalization and sustainability. Since ERP systems are central to digitizing business processes, integrating sustainability into their functions is key. While research exists on ERP and sustainability, there is little process-focused analysis, particularly on decision-making within ERP workflows. This study addresses that gap by proposing an approach that embeds sustainability considerations into ERP-supported decision processes, demonstrated through the example of creating a purchase requisition.
Sparse optimizations for reservoir computing
Abstract (engl.)
In the field of Recurrent Neural Network, there exists a category of methods that utilize large amounts of randomly connected, fixed artificial neuron layers. These layers generate non-linear dynamic responses through input signals while storing memory within the network for subsequent tasks. Such network layers are referred to as reservoirs, and machine learning approaches employing reservoirs are collectively termed Reservoir Computing. The Echo State Network (ESN), a foundational model within Reservoir Computing, serves as a platform for model development and testing. The aim of this work is to analyze and apply regularization techniques to reservoir computing models in order to achieve more compact model architectures while largely preserving predictive performance. As an approximation of the L1 regularization term, the SmoothL1 function is twice-differentiable, enabling the use of unconstrained optimization methods. We evaluate the ESN with sparse readout on two regression tasks and two classification tasks, comparing it against models without regularization, L2 regularized models, and traditional L1 regularized models. This allows us to examine the parameter variations and performance of the readout layer under SmoothL1 regularization. The effectiveness of the proposed regularization techniques is demonstrated through evaluation on synthetic and real-world multi-dimensional temporal datasets.
Resource-Aware Cooperation in Federated Learning
Abstract (engl.)
We present a novel Federated Learning framework, FedT4T, that systematically evaluates utility-driven client strategies under resource constraints. Recognizing the significant challenges in practical distributed learning environments, such as limited resources and non-cooperative behaviors, we model client interactions using the Iterated Prisoner’s Dilemma. Our framework enables clients to adapt their decision rules based on prior interactions and available resources, optimizing both individual utility and collective contribution to solve a global learning task. We apply FedT4T to a Federated Learning benchmark classification task and explore the dynamics of cooperation between clients driven by common strategies from cooperation theory under the impact of varying resource availability.
The code is publicly available at https://github.com/cairo-thws/FedT4T.
Multiclass Adaptive Subspace Learning
Abstract (engl.)
In modern data analysis, there is an increasing trend towards the integration of information across diverse input formats and perspectives. If the available
data is not given in large quantities deep learning is in general impractical. The recently introduced Adaptive Subspace Kernel Fusion (ASKF) technique provides
an efficient solution for binary classification, facilitating the effective integration of diverse views throughout the learning process. In this paper, we extend ASKF by employing a vector-labeled multi-class model, eliminating the need for multiple individual models typically required in conventional one-vs-rest or one-vs-one approaches. We also evaluated the effect of using GPU-based numerical solvers, optimizing our problem formulation and the generated code for better efficiency. The approach is evaluated on various kernel functions, highlighting our methods ability of robustly dealing with multi-view data.
2024
Optimizing YOLOv5 for Green AI: A Study on Model Pruning and Leightweight Networks
Abstract (engl.)
To achieve state-of-the-art performance, deep learning models are becoming increasingly complex, leading to a significant increase in demand for high-performance computing resources and, in turn, concerns about environmental impact. In this context, the concept of Green AI has been proposed, which advocates optimizing performance by improving model efficiency, rather than relying solely on an increase in computing resources, thereby reducing the impact on the environment. Object detection is a research hotspot in the field of computer vision. This paper focuses on the commonly used YOLOv5 network in object detection, optimizing the YOLOv5 model through pruning and the use of lightweight networks. Implemented on a campus image dataset, a balance between reducing computational load and maintaining accuracy was achieved. The experimental results confirm that strategic model pruning and thoughtful network architecture selection can produce environmentally responsible and computationally efficient deep learning models without significantly reducing performance, aligning with the goals of GreenAI. All related code of the project is available at: https://github.com/xbgthws/Green-AI-project.git.
Sparse Uncertainty-Informed Sampling from Federated Streaming Data
Abstract (engl.)
We present a numerically robust, computationally efficient approach for non-I.I.D. data stream sampling in federated client systems, where resources are limited and labeled data for local model adaptation is sparse and expensive. The proposed method identifies relevant stream observations to optimize the underlying client model, given a local labeling budget, and performs instantaneous labeling decisions without relying on any memory buffering strategies. Our experiments show enhanced training batch diversity and an improved numerical robustness of the proposal
compared to existing strategies over large-scale data streams, making our approach an effective and convenient solution in FL environments.
Deep Transfer Hashing for Adaptive Learning on
Federated Streaming Data
Sample. Hash. Adapt. Repeat.
Abstract (engl.)
This extended abstract explores the integration of federated learning with deep transfer hashing for distributed prediction tasks, emphasizing resource-efficient client training from evolving data streams. Federated learning allows multiple clients to collaboratively train a shared model while maintaining data privacy - by incorporating deep transfer hashing, high-dimensional data can be converted into compact hash codes, reducing data transmission size and network loads. The proposed framework utilizes transfer learning, pre-training deep neural networks on a central server, and fine-tuning on clients to enhance model accuracy and adaptability. A selective hash code sharing mechanism using a privacy-preserving global memory bank further supports client fine-tuning. This approach addresses challenges in previous research by improving computational efficiency and scalability. Practical applications include Car2X event predictions, where a shared model is collectively trained to recognize traffic patterns, aiding in tasks such as traffic density assessment and accident detection. The research aims to develop a robust framework that combines federated learning, deep transfer hashing and transfer learning for efficient and secure downstream task execution.
Domain Borders Are There to Be Crossed With
Federated Few-Shot Adaptation
Abstract (engl.)
Federated Learning has emerged as a leading paradigm for decentralized, privacy-preserving learning, particularly relevant in the era of interconnected edge devices equipped with sensors. However, the practical implementation of Federated Learning faces three primary challenges: the need for human involvement in costly data labelling processes for target adaptation, covariate shift in client device data collection due to environmental factors affecting sensors, leading to discrepancies between source and target samples, and the impracticality of continuous or regular model updates in resource-constrained environments due to limited data transmission capabilities and technical constraints on channel availability and energy efficiency. To tackle these issues, we expand upon an efficient and scalable Federated Learning framework tailored for real-world client adaptation in industrial settings. This framework leverages a pre-trained source model comprising a deep backbone, an adaptation module, and a classifier running on a powerful server. By freezing the backbone and classifier during client adaptation on resource-constrained devices, we allow the domain adaptive linear layer to handle target domain adaptation, thus minimizing overall computational overhead. Furthermore, this setup, designated as FedAcross+, is extended to encompass the processing of streaming data, thereby rendering the solution suit-
able for non-stationary environments. Extensive experimental results demonstrate the effectiveness of FedAcross+ in achieving competitive adaptation on low-end client devices with limited target samples, successfully addressing the challenge of domain shift. Moreover, our framework accommodates sporadic model updates within resource-constrained environments, ensuring practical and seamless deployment.