The spiking federated learning (FL) is an emerging distributed learning paradigm that allows resource-constrained devices to train collaboratively at low power consumption without exchanging local data. It takes advantage of both the privacy computation property in FL and the energy efficiency in spiking neural networks (SNNs). However, existing spiking FL methods employ a random selection approach for client aggregation, assuming unbiased client participation. This neglect of statistical heterogeneity significantly affects the convergence and precision of the global model. In this work, we propose a credit assignment-based active client selection strategy for spiking federated learning, the SFedCA, to aggregate clients contributing to the global sample distribution balance judiciously. Specifically, the client credits are assigned by the firing intensity state before and after local model training, which reflects the difference in local data distribution from the global model. The comprehensive experiments are conducted on various non-identical and independent distribution (non-IID) scenarios. The experimental results demonstrate that the SFedCA outperforms the existing state-of-the-art spiking FL methods and requires fewer communication rounds.
{"title":"SFedCA: Credit Assignment-Based Active Client Selection Strategy for Spiking Federated Learning.","authors":"Qiugang Zhan, Jinbo Cao, Xiurui Xie, Huajin Tang, Malu Zhang, Shantian Yang, Guisong Liu","doi":"10.1109/TNNLS.2025.3639578","DOIUrl":"https://doi.org/10.1109/TNNLS.2025.3639578","url":null,"abstract":"<p><p>The spiking federated learning (FL) is an emerging distributed learning paradigm that allows resource-constrained devices to train collaboratively at low power consumption without exchanging local data. It takes advantage of both the privacy computation property in FL and the energy efficiency in spiking neural networks (SNNs). However, existing spiking FL methods employ a random selection approach for client aggregation, assuming unbiased client participation. This neglect of statistical heterogeneity significantly affects the convergence and precision of the global model. In this work, we propose a credit assignment-based active client selection strategy for spiking federated learning, the SFedCA, to aggregate clients contributing to the global sample distribution balance judiciously. Specifically, the client credits are assigned by the firing intensity state before and after local model training, which reflects the difference in local data distribution from the global model. The comprehensive experiments are conducted on various non-identical and independent distribution (non-IID) scenarios. The experimental results demonstrate that the SFedCA outperforms the existing state-of-the-art spiking FL methods and requires fewer communication rounds.</p>","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":8.9,"publicationDate":"2025-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145714236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-09DOI: 10.1109/TNNLS.2025.3639562
Bowen Zheng, Ran Cheng
In the history of knowledge distillation (KD), the focus has once shifted over time from logit-based to feature-based approaches. However, this transition has been revisited with the advent of decoupled KD (DKD), which reemphasizes the importance of logit knowledge through advanced decoupling and weighting strategies. While DKD marks a significant advancement, its underlying mechanisms merit deeper exploration. As a response, we rethink DKD from a predictive distribution perspective. First, we introduce an enhanced version, the generalized DKD (GDKD) loss, which offers a more versatile method for decoupling logits. Then, we pay particular attention to the teacher model's predictive distribution and its impact on the gradients of GDKD loss, uncovering two critical insights often overlooked: 1) the partitioning by the top logit considerably improves the interrelationship of nontop logits and 2) amplifying the focus on the distillation loss of nontop logits enhances the knowledge extraction among them. Utilizing these insights, we further propose a streamlined GDKD algorithm with an efficient partition strategy to handle the multimodality of teacher models' predictive distribution. Our comprehensive experiments conducted on a variety of benchmarks, including CIFAR-100, ImageNet, Tiny-ImageNet, CUB-200-2011, and Cityscapes, demonstrate GDKD's superior performance over both the original DKD and other leading KD methods. The code is available at https://github.com/ZaberKo/GDKD.
{"title":"Rethinking Decoupled Knowledge Distillation: A Predictive Distribution Perspective.","authors":"Bowen Zheng, Ran Cheng","doi":"10.1109/TNNLS.2025.3639562","DOIUrl":"https://doi.org/10.1109/TNNLS.2025.3639562","url":null,"abstract":"<p><p>In the history of knowledge distillation (KD), the focus has once shifted over time from logit-based to feature-based approaches. However, this transition has been revisited with the advent of decoupled KD (DKD), which reemphasizes the importance of logit knowledge through advanced decoupling and weighting strategies. While DKD marks a significant advancement, its underlying mechanisms merit deeper exploration. As a response, we rethink DKD from a predictive distribution perspective. First, we introduce an enhanced version, the generalized DKD (GDKD) loss, which offers a more versatile method for decoupling logits. Then, we pay particular attention to the teacher model's predictive distribution and its impact on the gradients of GDKD loss, uncovering two critical insights often overlooked: 1) the partitioning by the top logit considerably improves the interrelationship of nontop logits and 2) amplifying the focus on the distillation loss of nontop logits enhances the knowledge extraction among them. Utilizing these insights, we further propose a streamlined GDKD algorithm with an efficient partition strategy to handle the multimodality of teacher models' predictive distribution. Our comprehensive experiments conducted on a variety of benchmarks, including CIFAR-100, ImageNet, Tiny-ImageNet, CUB-200-2011, and Cityscapes, demonstrate GDKD's superior performance over both the original DKD and other leading KD methods. The code is available at https://github.com/ZaberKo/GDKD.</p>","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":8.9,"publicationDate":"2025-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145714213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-09DOI: 10.1109/tnnls.2025.3638635
Yhonatan Kvich,Pagoti Reshma,Pradyumna Pradhan,Ramunaidu Randhi,Yonina C Eldar
In this article, we introduce a deep unfolding framework for Tail-iterative soft thresholding algorithm (ISTA) and Tail-fast ISTA (FISTA), extending classical sparse recovery algorithms into learned architectures and improving upon existing unfolding techniques. By combining the interpretability of iterative solvers with the adaptability of model-based networks, our approach achieves efficient and robust recovery of sparse signals. Tail-based methods incorporate an iterative support estimation step, where the support and target estimations are refined alternately, providing a key advantage over traditional approaches. We integrate this into our architecture, enhancing both recovery performance and noise robustness. We compare the proposed methods against classical solvers, including FISTA and Tail-FISTA, as well as deep unfolding techniques, LISTA and DU-FISTA, across various sparsity levels, dynamic ranges (DRs), and both noiseless and noisy conditions. In noiseless cases, our methods achieve slightly lower performance than classical solvers but with significantly reduced computational costs. Under heavy noise and a high number of nonzero elements, where classical methods struggle, our learned approaches remain resilient and achieve improved recovery rates. To evaluate generalization, we also tested our methods on data generated with a perturbed sensing matrix. In this case, under noisy scenarios, our proposed methods outperform classical sparse recovery algorithms. The proposed framework is general and applies to any linear sparse recovery task in compressed sensing (CS), offering computational efficiency, robustness to noise, and adaptability to real-world data, showcasing the advantages of deep unfolding techniques with iterative support estimation.
{"title":"Deep Unfolding of Tail-Based Methods for Robust Sparse Recovery Under Noise and Model Mismatch.","authors":"Yhonatan Kvich,Pagoti Reshma,Pradyumna Pradhan,Ramunaidu Randhi,Yonina C Eldar","doi":"10.1109/tnnls.2025.3638635","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3638635","url":null,"abstract":"In this article, we introduce a deep unfolding framework for Tail-iterative soft thresholding algorithm (ISTA) and Tail-fast ISTA (FISTA), extending classical sparse recovery algorithms into learned architectures and improving upon existing unfolding techniques. By combining the interpretability of iterative solvers with the adaptability of model-based networks, our approach achieves efficient and robust recovery of sparse signals. Tail-based methods incorporate an iterative support estimation step, where the support and target estimations are refined alternately, providing a key advantage over traditional approaches. We integrate this into our architecture, enhancing both recovery performance and noise robustness. We compare the proposed methods against classical solvers, including FISTA and Tail-FISTA, as well as deep unfolding techniques, LISTA and DU-FISTA, across various sparsity levels, dynamic ranges (DRs), and both noiseless and noisy conditions. In noiseless cases, our methods achieve slightly lower performance than classical solvers but with significantly reduced computational costs. Under heavy noise and a high number of nonzero elements, where classical methods struggle, our learned approaches remain resilient and achieve improved recovery rates. To evaluate generalization, we also tested our methods on data generated with a perturbed sensing matrix. In this case, under noisy scenarios, our proposed methods outperform classical sparse recovery algorithms. The proposed framework is general and applies to any linear sparse recovery task in compressed sensing (CS), offering computational efficiency, robustness to noise, and adaptability to real-world data, showcasing the advantages of deep unfolding techniques with iterative support estimation.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"133 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145710805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-09DOI: 10.1109/TNNLS.2025.3642587
{"title":"2025 Index IEEE Transactions on Neural Networks and Learning Systems","authors":"","doi":"10.1109/TNNLS.2025.3642587","DOIUrl":"10.1109/TNNLS.2025.3642587","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"36 12","pages":"20470-20767"},"PeriodicalIF":8.9,"publicationDate":"2025-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11289848","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145717967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-08DOI: 10.1109/tnnls.2025.3634765
Xiaoyi Wang, Peng Wang, Juan Cheng, Daiyin Zhu, Henry Leung, Paolo Gamba
{"title":"Hyperspectral Anomaly Detection via Hybrid Convolutional and Transformer-Based U-Net With Error Attention Mechanism","authors":"Xiaoyi Wang, Peng Wang, Juan Cheng, Daiyin Zhu, Henry Leung, Paolo Gamba","doi":"10.1109/tnnls.2025.3634765","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3634765","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"3 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145704009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号