Constrained Center Loss for Convolutional Neural Networks

Shi, Zhang-Lei; Wang, Hao; Leung, Chi-Sing

doi:10.1109/tnnls.2021.3104392

Cited by 7 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To assess the effectiveness of HeteroSwitch, we evaluate its impact on both fairness and domain generalization in FL by using the test accuracy of the global model (Shi et al, 2023) on each deployed device type. For fairness, we measure the average variance of accuracy across devicesthe portion of participation of each device type follows the market share summarized in Table . 1.…”

Section: Evaluation Results and Analysismentioning

confidence: 99%

FedGPO: Heterogeneity-Aware Global Parameter optimization for Efficient Federated Learning

Kim¹,

Wu²

2022

2022 IEEE International Symposium on Workload Characterization (IISWC)

View full text Add to dashboard Cite

Federated Learning (FL) is a practical approach to train deep learning models collaboratively across user-end devices, protecting user privacy by retaining raw data on-device. In FL, participating user-end devices are highly fragmented in terms of hardware and software configurations. Such fragmentation introduces a new type of data heterogeneity in FL, namely system-induced data heterogeneity, as each device generates distinct data depending on its hardware and software configurations. In this paper, we first characterize the impact of system-induced data heterogeneity on FL model performance. We collect a dataset using heterogeneous devices with variations across vendors and performance tiers. By using this dataset, we demonstrate that system-induced data heterogeneity negatively impacts accuracy, and deteriorates fairness and domain generalization problems in FL. To address these challenges, we propose HeteroSwitch, which adaptively adopts generalization techniques (i.e., ISP transformation and SWAD) depending on the level of bias caused by varying HW and SW configurations. In our evaluation with a realistic FL dataset (FLAIR), HeteroSwitch reduces the variance of averaged precision by 6.3% across device types.

show abstract

Section: Evaluation Results and Analysismentioning

confidence: 99%

FedGPO: Heterogeneity-Aware Global Parameter optimization for Efficient Federated Learning

Kim¹,

Wu²

2022

2022 IEEE International Symposium on Workload Characterization (IISWC)

View full text Add to dashboard Cite

show abstract

“…Lastly, treesXnets can be extended to evaluate fairness in federated models, i.e. studying the degree of bias in federated models for tabular data [71].…”

Section: Future Directions For Researchmentioning

confidence: 99%

treeXnets: Comparing Federated Tree-BasedModels and Neural Networks on Tabular Data

Lindskog-Münzing,

Prehofer

2024

Preprint

View full text Add to dashboard Cite

Federated Learning (FL) is a privacy-aware machine learning paradigm. It was initially designed to fit parametric models, namely Neural Networks (NNs) and thus, it has excelled on image, audio and text tasks. However, FL for tabular data still receives little attention. Tree-Based Models (TBMs) perform better than NNs on tabular data in a centralized setting, and are starting to see FL integrations. In this paper, we evaluate federated TBMs and NNs for horizontal FL, with varying data partitions, on 31 datasets. We propose treesXnets - a unified benchmarking tool for federated evaluation. treesXnets’ results capture model performance, e.g. accuracy, communication effort, model training duration, and device utilization. A cyclic implementation of federated XGBoost is the best performing model, outperforming the best federated NNs with 5-10% in terms of accuracy and regression error. It is also faster, requires less communication and memory than other federated XGBoost models.

show abstract

“…It is general in the sense that (i) the edge set of G c is empty or non-empty except the complete graph case and (ii) the edge set of G b is non-empty. The presence of competing FL-PTs has been recognized as an important aspect in the FL literature (Kairouz et al 2021;Zhan et al 2022;Shi, Yu, and Leung 2023). In balance theory, a principle, namely "the friend of my enemy is my enemy", can avoid conflict of interest (Leskovec, Huttenlocher, and Kleinberg 2010;Cartwright and Harary 1956).…”

Section: Introductionmentioning

confidence: 99%

FedCompetitors: Harmonious Collaboration in Federated Learning with Competing Participants

Tan,

Cheng,

et al. 2024

AAAI

View full text Add to dashboard Cite

Federated learning (FL) provides a privacy-preserving approach for collaborative training of machine learning models. Given the potential data heterogeneity, it is crucial to select appropriate collaborators for each FL participant (FL-PT) based on data complementarity. Recent studies have addressed this challenge. Similarly, it is imperative to consider the inter-individual relationships among FL-PTs where some FL-PTs engage in competition. Although FL literature has acknowledged the significance of this scenario, practical methods for establishing FL ecosystems remain largely unexplored. In this paper, we extend a principle from the balance theory, namely “the friend of my enemy is my enemy”, to ensure the absence of conflicting interests within an FL ecosystem. The extended principle and the resulting problem are formulated via graph theory and integer linear programming. A polynomial-time algorithm is proposed to determine the collaborators of each FL-PT. The solution guarantees high scalability, allowing even competing FL-PTs to smoothly join the ecosystem without conflict of interest. The proposed framework jointly considers competition and data heterogeneity. Extensive experiments on real-world and synthetic data demonstrate its efficacy compared to five alternative approaches, and its ability to establish efficient collaboration networks among FL-PTs.

show abstract

Constrained Center Loss for Convolutional Neural Networks

Cited by 7 publications

References 37 publications

FedGPO: Heterogeneity-Aware Global Parameter optimization for Efficient Federated Learning

FedGPO: Heterogeneity-Aware Global Parameter optimization for Efficient Federated Learning

treeXnets: Comparing Federated Tree-BasedModels and Neural Networks on Tabular Data

FedCompetitors: Harmonious Collaboration in Federated Learning with Competing Participants

Contact Info

Product

Resources

About