Enhancing Federated Semi-Supervised Learning with Out-of-Distribution Filtering Amidst Class Mismatches

Jiajun Jin; Fanghao Ni; Shuying Dai; Keqin Li; Bo Hong

doi:10.5281/zenodo.11068390

Authors

Jiajun Jin University of Maine at Presque Isle
Fanghao Ni Northern Arizona University
Shuying Dai Indian Institute of Technology Guwahati
Keqin Li AMA University
Bo Hong Northern Arizona University

DOI:

https://doi.org/10.5281/zenodo.11068390

References:

78

Keywords:

Federated Learning, Semi-Supervised Learning, Class Mismatch

Abstract

Federated Learning (FL) has gained prominence as a method for training models on edge computing devices, enabling the preservation of data privacy by eliminating the need to share sensitive informa- tion. While the majority of FL approaches have been developed with a focus on supervised learning, a limited number of studies have explored the incorporation of unlabeled data. These studies typically operate under the assumption that labeled and unlabeled data share identical class distributions. However, in practical scenarios, where unlabeled data may include classes absent from the labeled dataset, the performance of existing methodologies can significantly decline. This paper delves into federated semi-supervised learning amidst discrepancies between the classes of labeled and unlabeled data. We introduce an innovative FL framework designed to alleviate the adverse effects of class mismatches. Our framework features a pioneering historic global ensemble consistency loss and a server-based adjustment mechanism for out-of-distribution (OOD) filtering, effectively enhancing model performance in the presence of class mismatches.

Author Biographies

Jiajun Jin, University of Maine at Presque Isle

Independent researcher.

Fanghao Ni, Northern Arizona University

Independent researcher.

Shuying Dai, Indian Institute of Technology Guwahati

Independent researcher.

Keqin Li, AMA University

Independent researcher.

Bo Hong, Northern Arizona University

Independent researcher.

References

McMahan, B., Moore, E., Ramage, D., Hampson, S. Arcas, B.A.y.. (2017). Communication-Efficient Learning of Deep Networks from Decentralized Data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, in PMLR 54:1273-1282

Jeong W, Yoon J, Yang E, Hwang SJ. FEDERATED SEMI-SUPERVISED LEARNING WITH INTER-CLIENT CONSISTENCY DISJOINT LEARNING.

Li T, Sahu AK, Zaheer M, Sanjabi M, Talwalkar A, Smith V. Federated optimization in heterogeneous networks. arXiv preprint arXiv:1812.06127. 2018 Dec 14

Zhao Y, Li M, Lai L, Suda N, Civin D, Chandra V. Federated learning with non-iid data. arXiv preprint arXiv:1806.00582. 2018 Jun 2.

Bian, Jieming, Cong Shen, and Jie Xu. ”Federated learning via indirect server-client communications.” 2023 57th Annual Conference on Information Sciences and Systems (CISS). IEEE, 2023.

Zhao Y, Liu H, Li H, Barnaghi P, Haddadi H. Semi-supervised Federated Learning for Activity Recognition. arXiv preprint arXiv:2011.00851. 2020 Nov 2.

Jin Y, Wei X, Liu Y, Yang Q. Towards utilizing unlabeled data in federated learning: A survey and prospective. arXiv e-prints. 2020 Feb:arXiv-2002.

Chen Y, Zhu X, Li W, Gong S. Semi-supervised learning under class distribution mismatch. InProceedings of the AAAI Conference on Artificial Intelligence 2020 Apr 3 (Vol. 34, No. 04, pp. 3569-3576).

Guo LZ, Zhang ZY, Jiang Y, Li YF, Zhou ZH. Safe deep semi-supervised learning for unseen-class unlabeled data. InInternational Conference on Machine Learning 2020 Nov 21 (pp. 3897-3906). PMLR.

Sohn K, Berthelot D, Li CL, Zhang Z, Carlini N, Cubuk ED, Kurakin A, Zhang H, Raffel C. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. arXiv preprint arXiv:2001.07685. 2020 Jan 21.

Xie Q, Dai Z, Hovy E, Luong MT, Le QV. Unsupervised data augmentation for consistency training. arXiv preprint arXiv:1904.12848. 2019 Apr 29.

Berthelot D, Carlini N, Goodfellow I, Papernot N, Oliver A, Raffel C. Mixmatch: A holistic approach to semi-supervised learning. arXiv preprint arXiv:1905.02249. 2019 May 6.

Berthelot D, Carlini N, Cubuk ED, Kurakin A, Sohn K, Zhang H, Raffel C. Remixmatch: Semi-supervised learning with distribution alignment and augmentation anchoring. arXiv preprint arXiv:1911.09785. 2019 Nov 21.

Liang S, Li Y, Srikant R. Enhancing the reliability of out-of-distribution image detection in neural networks. arXiv preprint arXiv:1706.02690. 2017 Jun 8.

Hendrycks D, Gimpel K. A baseline for detecting misclassified and out-of-distribution examples in neural networks. arXiv preprint arXiv:1610.02136. 2016 Oct 7.

Bian, J., Fu, Z., Xu, J. (2021). FedSEAL: semi-supervised federated learning with self-ensemble learning and negative learning. arXiv preprint arXiv:2110.07829.

Peng, Yuanzhe. ”A survey on modern recommendation system based on big data.” arXiv preprint arXiv:2206.02631 (2022).

Sun, Anchen, et al. ”Who Said What? An Automated Approach to Analyzing Speech in Preschool Classrooms.” arXiv preprint arXiv:2401.07342 (2024).

Sun, Anchen, et al. ”Multimodal Data Integration and User Interaction for Avatar Simulation in Augmented Reality.” IJMDEM vol.13, no.1 2022: pp.1-19. http://doi.org/10.4018/IJMDEM.304391

Tan, Z., Beigi, A., Wang, S., Guo, R., Bhattacharjee, A., Jiang, B., Karami, M., Li, J., Cheng, L., & Liu, H. (2024). Large Language Models for Data Annotation: A Survey. ArXiv Preprint ArXiv:2402.13446.

Tan, Z., Cheng, L., Wang, S., Bo, Y., Li, J., & Liu, H. (2023). Interpreting pretrained language models via concept bottlenecks. ArXiv Preprint ArXiv:2311.05014.

Zhao, S., Gan, L., Tuan, L. A., Fu, J., Lyu, L., Jia, M., & Wen, J. (2024). Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning. ArXiv Preprint ArXiv:2402.12168.

Zhao, S., Jia, M., Tuan, L. A., Pan, F., & Wen, J. (2024). Universal vulnerabilities in large language models: Backdoor attacks for in-context learning. ArXiv Preprint ArXiv:2401.05949.

Xin, Y., Luo, S., Jin, P., Du, Y., & Wang, C. (2023). Self-Training with Label-Feature-Consistency for Domain Adaptation. International Conference on Database Systems for Advanced Applications, 84–99.

Wang, Q., Wang, C., Lai, Z., & Zhou, Y. (2024). InsectMamba: Insect Pest Classification with State Space Model. ArXiv Preprint ArXiv:2404.03611.

Nian, Y., Jin, W., & Lin, L. (2023). In-process global interpretation for graph learning via distribution matching. ArXiv Preprint ArXiv:2306.10447.

Su, J., Nair, S., & Popokh, L. (2023). EdgeGYM: a reinforcement learning environment for constraint-aware NFV resource allocation. 2023 IEEE 2nd International Conference on AI in Cybersecurity (ICAIC), 1–7.

Ning, Q., Zheng, W., Xu, H., Zhu, A., Li, T., Cheng, Y., Feng, S., Wang, L., Cui, D., & Wang, K. (2022). Rapid segmentation and sensitive analysis of CRP with paper-based microfluidic device using machine learning. Analytical and Bioanalytical Chemistry, 414(13), 3959–3970.

Yang, W., Jiang, Y., Chi, Y., Xu, Z., & Wei, W. (2024). Long-Term Network Structure Evolution Investigation for Sustainability Improvement: An Empirical Analysis on Global Top Full-Service Carriers. Aerospace, 11(2), 128.

Chen, S., Kann, B. H., Foote, M. B., Aerts, H. J., Savova, G. K., Mak, R. H., & Bitterman, D. S. (2023). Use of artificial intelligence chatbots for cancer treatment information. JAMA Oncology, 9(10), 1459–1462.

Derton, A., Guevara, M., Chen, S., Moningi, S., Kozono, D. E., Liu, D., Miller, T. A., Savova, G. K., Mak, R. H., & Bitterman, D. S. (2023). Natural language processing methods to empirically explore social contexts and needs in cancer patient notes. JCO Clinical Cancer Informatics, 7, e2200196.

Guevara, M., Chen, S., Thomas, S., Chaunzwa, T. L., Franco, I., Kann, B. H., Moningi, S., Qian, J. M., Goldstein, M., Harper, S., & others. (2024). Large language models to identify social determinants of health in electronic health records. NPJ Digital Medicine, 7(1), 6.

Wang, C., Chen, F., Zhang, Y., Wang, S., Yu, B., & Cheng, J. (2022). Temporal stability of factors affecting injury severity in rear-end and non-rear-end crashes: A random parameter approach with heterogeneity in means and variances. Analytic Methods in Accident Research, 35, 100219.

Deng, T., Xie, H., Wang, J., & Chen, W. (2023). Long-Term Visual Simultaneous Localization and Mapping: Using a Bayesian Persistence Filter-Based Global Map Prediction. IEEE Robotics & Automation Magazine, 30(1), 36–49.

Ning, Q., Zheng, W., Xu, H., Zhu, A., Li, T., Cheng, Y., ... & Wang, K. (2022). Rapid segmentation and sensitive analysis of CRP with paper-based microfluidic device using machine learning. Analytical and Bioanalytical Chemistry, 414(13), 3959-3970.

Ru, J., Yu, H., Liu, H., Liu, J., Zhang, X., & Xu, H. (2022). A Bounded Near-Bottom Cruise Trajectory Planning Algorithm for Underwater Vehicles. Journal of Marine Science and Engineering, 11(1), 7.

Yao, J., Wu, T., & Zhang, X. (2023). Improving depth gradientcontinuity in transformers: A comparative study on monocular depth estimation with cnn. ArXiv Preprint ArXiv:2308.08333.

Wang, X., Qiao, Y., Xiong, J., Zhao, Z., Zhang, N., Feng, M., & Jiang, C. (2024). Advanced Network Intrusion Detection with TabTransformer. Journal of Theory and Practice of Engineering Science, 4(03), 191-198.

Liu, T., Cai, Q., Xu, C., Hong, B., Ni, F., Qiao, Y., & Yang, T. (2024). Rumor Detection with A Novel Graph Neural Network Approach. Academic Journal of Science and Technology, 10(1), 305–310.

Wang, R., Chen, X., Khalilian-Gourtani, A., Chen, Z., Yu, L., Flinker, A., & Wang, Y. (2020). Stimulus speech decoding from human cortex with generative adversarial network transfer learning. 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), 390–394.

Chen, X., Wang, R., Khalilian-Gourtani, A., Yu, L., Dugan, P., Friedman, D., Doyle, W., Devinsky, O., Wang, Y., & Flinker, A. (2023). A Neural Speech Decoding Framework Leveraging Deep Learning and Speech Synthesis. BioRxiv, 2023–09.

Su, J., Nair, S., & Popokh, L. (2022, November). Optimal resource allocation in sdn/nfv-enabled networks via deep reinforcement learning. In 2022 IEEE Ninth International Conference on Communications and Networking (ComNet) (pp. 1-7). IEEE.

Tang, Z., Wang, Y., & Chang, T.-H. (2024). z-SignFedAvg: A Unified Stochastic Sign-Based Compression for Federated Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 38(14), 15301–15309.

Liu, T., Cai, Q., Xu, C., Hong, B., Xiong, J., Qiao, Y., & Yang, T. (2024). Image Captioning in News Report Scenario. Academic Journal of Science and Technology, 10(1), 284–289.

Liu, H., Shen, Y., Yu, S., Gao, Z., & Wu, T. (2024). Deep Reinforcement Learning for Mobile Robot Path Planning. ArXiv Preprint ArXiv:2404.06974.

Tang, Z., Chang, T.-H., Ye, X., & Zha, H. (2023). Low-rank matrix recovery with unknown correspondence. Uncertainty in Artificial Intelligence, 2111–2122.

Su, J., Jiang, C., Jin, X., Qiao, Y., Xiao, T., Ma, H., Wei, R., Jing, Z., Xu, J., & Lin, J. (2024). Large Language Models for Forecasting and Anomaly Detection: A Systematic Literature Review. ArXiv Preprint ArXiv:2402.10350.

Yi, X., & Qiao, Y. (2024). GPU-Based Parallel Computing Methods for Medical Photoacoustic Image Reconstruction. arXiv preprint arXiv:2404.10928.

Xin, Y., Du, J., Wang, Q., Lin, Z., & Yan, K. (2024, March). VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understanding. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 38, No. 14, pp. 16085-16093).

Zhu, A., Li, J., & Lu, C. (2021). Pseudo view representation learning for monocular RGB-D human pose and shape estimation. IEEE Signal Processing Letters, 29, 712-716.

Xin, Y., Du, J., Wang, Q., Yan, K., & Ding, S. (2024, March). Mmap: Multi-modal alignment prompt for cross-domain multi-task learning. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 38, No. 14, pp. 16076-16084).

Zhu, Armando, Keqin, Li, Tong, Wu, Peng, Zhao, Wenjing, Zhou, Bo, Hong. "Cross-Task Multi-Branch Vision Transformer for Facial Expression and Mask Wearing Classification". arXiv preprint arXiv:2404.14606. (2024).

Delezenne, Q., Petrunin, I., Xu, Z., Neptune, J., & Bleakley, T. (2024). Autonomous Navigation with Taxiway Crossings Identification using Camera Vision and Airport Map. AIAA SCITECH 2024 Forum, 1300.

Zhao, S., Jia, M., Tuan, L. A., Pan, F., & Wen, J. (2024). Universal vulnerabilities in large language models: Backdoor attacks for in-context learning. ArXiv Preprint ArXiv:2401.05949.

Read, A. J., Zhou, W., Saini, S. D., Zhu, J., & Waljee, A. K. (2023). Prediction of Gastrointestinal Tract Cancers Using Longitudinal Electronic Health Record Data. Cancers, 15(5), 1399.

Chen, J., Chen, X., Wang, R., Le, C., Khalilian-Gourtani, A., Jensen, E., Dugan, P., Doyle, W., Devinsky, O., Friedman, D., & others. (2024). Subject-Agnostic Transformer-Based Neural Speech Decoding from Surface and Depth Electrode Signals. BioRxiv, 2024–03.

Deng, T., Chen, Y., Zhang, L., Yang, J., Yuan, S., Wang, D., & Chen, W. (2024). Compact 3D Gaussian Splatting For Dense Visual SLAM. ArXiv Preprint ArXiv:2403.11247.

Yan, C., Qiu, Y., & Zhu, Y. (2021). Predict Oil Production with LSTM Neural Network. Proceedings of the 9th International Conference on Computer Engineering and Networks, 357–364.

Zhu, A., Li, J., & Lu, C. (2021). Pseudo view representation learning for monocular RGB-D human pose and shape estimation. IEEE Signal Processing Letters, 29, 712–716.

Yao, J., Pan, X., Wu, T., & Zhang, X. (2024). Building lane-level maps from aerial images. ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and SignalProcessing (ICASSP), 3890–3894.

Peng, Q., Zheng, C., & Chen, C. (2023). Source-free domain adaptive human pose estimation. Proceedings of the IEEE/CVF International Conference on Computer Vision, 4826–4836.

Peng, Q., Ding, Z., Lyu, L., Sun, L., & Chen, C. (2023). RAIN: regularization on input and network for black-box domain adaptation. Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 4118–4126.

Tian, Y., Han, Y., Chen, X., Wang, W., & Chawla, N. V. (2024). TinyLLM: Learning a Small Student from Multiple Large Language Models. ArXiv Preprint ArXiv:2402.04616.

Wu, J., Lai, Z., Chen, S., Tao, R., Zhao, P., & Hovakimyan, N. (2024). The new agronomists: Language models are experts in crop management. ArXiv Preprint ArXiv:2403.19839.

Jing, Z., Su, Y., Han, Y., Yuan, B., Liu, C., Xu, H., & Chen, K. (2024). When Large Language Models Meet Vector Databases: A Survey. ArXiv Preprint ArXiv:2402.01763.

Liu, T., Xu, C., Qiao, Y., Jiang, C., & Yu, J. (2024). Particle Filter SLAM for Vehicle Localization. Journal of Industrial Engineering and Applied Science, 2(1), 27-31.

Zhu, A., Li, K., Wu, T., Zhao, P., Zhou, W., & Hong, B. (2024). Cross-Task Multi-Branch Vision Transformer for Facial Expression and Mask Wearing Classification. ArXiv Preprint ArXiv:2404.14606.

Weng, Y., & Wu, J. (2024). Fortifying the global data fortress: a multidimensional examination of cyber security indexes and data protection measures across 193 nations. International Journal of Frontiers in Engineering Technology, 6(2).

Wang, C., Abdel-Aty, M., & Han, L. (2024). Effects of speed difference on injury severity of freeway rear-end crashes: Insights from correlated joint random parameters bivariate probit models and temporal instability. Analytic Methods in Accident Research, 100320.

Li, Z., Huang, Y., Zhu, M., Zhang, J., Chang, J., & Liu, H. (2024). Feature manipulation for ddpm based change detection. ArXiv Preprint ArXiv:2403.15943.

Yao, J., Li, C., Sun, K., Cai, Y., Li, H., Ouyang, W., & Li, H. (2023). Ndc-scene: Boost monocular 3d semantic scene completion in normalized devicecoordinates space. 2023 IEEE/CVF International Conference on Computer Vision (ICCV), 9421–9431.

Wang, C., Easa, S. M., Chen, F., & Cheng, J. (2023). Difference in perception-reaction time of plain and plateau drivers at expressway exit ramps. Transportation Research Part F: Traffic Psychology and Behaviour, 98, 318–336.

Peng, Q., Zheng, C., & Chen, C. (2024). A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose Estimation. ArXiv Preprint ArXiv:2403.11310.

Deng, T., Wang, Y., Xie, H., Wang, H., Wang, J., Wang, D., & Chen, W. (2024). NeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and Denoising. ArXiv Preprint ArXiv:2403.20034.

Popokh, L., Su, J., Nair, S., & Olinick, E. (2021). IllumiCore: Optimization Modeling and Implementation for Efficient VNF Placement. 2021 International Conference on Software, Telecommunications and Computer Networks (SoftCOM), 1–7.

Xiong, S., Payani, A., Kompella, R., & Fekri, F. (2024). Large language models can learn temporal reasoning. ArXiv Preprint ArXiv:2401.06853.

Guo, F., Wu, J. Z., & Pan, L. (2023, July). An Empirical Study of AI Model’s Performance for Electricity Load Forecasting with Extreme Weather Conditions. In International Conference on Science of Cyber Security (pp. 193-204). Cham: Springer Nature Switzerland.

Guo, F. (2023, July). A Study of Smart Grid Program Optimization Based on K-Mean Algorithm. In 2023 3rd International Conference on Electrical Engineering and Mechatronics Technology (ICEEMT) (pp. 711-714). IEEE.