Junwei Cheng,Ke Liang,Pengxing Feng,Weixiong Liu,Yong Tang,Chaobo He
{"title":"Clustering Diffusion Model with Frequency-Signal Modulation for Variational Graph Autoencoders.","authors":"Junwei Cheng,Ke Liang,Pengxing Feng,Weixiong Liu,Yong Tang,Chaobo He","doi":"10.1109/tpami.2025.3614385","DOIUrl":"https://doi.org/10.1109/tpami.2025.3614385","url":null,"abstract":"Variational autoencoders (VAEs) have been widely used for node clustering, with existing methods mainly focusing on enhancing the expressiveness of their latent space. Recently, the integration of diffusion models with VAEs has provided new opportunities to achieve this objective. However, the mechanism by which the diffusion model improves performance remains unclear. To bridge this gap, we conduct an empirical analysis from the perspective of graph spectral theory, revealing that the signal modulation induced by diffusion models closely aligns with the low-frequency spectral characteristics of VAEs, which in turn explains their effectiveness. Nevertheless, further experiments highlight that diffusion models exhibit limitations in modulating high-frequency signals, which diverge from the spectral characteristics of VAEs. Moreover, existing diffusion methods fail to enable the latent space to adequately capture and reflect cluster-specific characteristics. To address these challenges, we propose a novel plug-and-play method, FVD, to improve the performance of VAE-based methods in node clustering tasks. Specifically, we incorporate the graph wavelet transform as a secondary signal modulator, enabling independent adjustments of specific frequency bands to better align with the spectral characteristics of VAEs. Additionally, we introduce the Student's t-distribution as a conditional constraint in the reverse process of FVD, deriving a more compact variational lower bound. This enhancement preserves fine-grained node information while focusing on clustering details, effectively mitigating the cluster collapse phenomenon. Comprehensive experimental results demonstrate that integrating FVD with existing methods achieves competitive performance improvements in most cases.","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"1 1","pages":""},"PeriodicalIF":23.6,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145140289","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}
{"title":"Ape Optimizer: A p-Power Adaptive Filter-Based Approach for Deep Learning Optimization.","authors":"Yufei Jin,Han Yang,Xinrui Wang,Yingche Xu,Zhuoran Zhang","doi":"10.1109/tnnls.2025.3610665","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3610665","url":null,"abstract":"Deep learning has been widely applied in various domains. Current widely-used optimizers, such as SGD, Adam, and their variants, are designed based on the assumption that the gradient noise generated during model training follows a Gaussian distribution. However, recent empirical studies have found that the gradient noise often does not follow a Gaussian distribution. Instead, the noise exhibits heavy-tailed characteristics consistent with an $alpha $ -stable distribution, casting doubt on the performance and robustness of optimizers designed under the assumption of Gaussian noise. Inspired by the least mean p-power (LMP) algorithm from the field of adaptive filtering, we propose a novel optimizer called Ape for deep learning. Ape integrates a p-power adjustment mechanism to compress large gradients and amplify small ones, mitigating the impact of heavy-tailed gradient distributions. It also employs an approach for estimating second moments tailored to $alpha $ -stable distributions. Extensive experiments on benchmark datasets demonstrate Ape's effectiveness in improving both accuracy and training speed compared to existing optimizers. The Ape optimizer showcases the potential of cross-disciplinary approaches in advancing deep learning optimization techniques and lays the groundwork for future innovations in this domain.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"19 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145140293","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}
{"title":"Multi-Agent Transformer-Based Workload Allocation and Worker Selection in Distributed Coded Machine Learning","authors":"Yitong Zhou, Qiang Ye, Hui Huang","doi":"10.1109/tccn.2025.3614383","DOIUrl":"https://doi.org/10.1109/tccn.2025.3614383","url":null,"abstract":"","PeriodicalId":13069,"journal":{"name":"IEEE Transactions on Cognitive Communications and Networking","volume":"17 1","pages":""},"PeriodicalIF":8.6,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145141309","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}
{"title":"Optimal Energy Management of Microgrid Based on Quantum Annealing Algorithm","authors":"Baonan Wang, Hui Wang, Dan Zhang","doi":"10.1109/tii.2025.3606931","DOIUrl":"https://doi.org/10.1109/tii.2025.3606931","url":null,"abstract":"","PeriodicalId":13301,"journal":{"name":"IEEE Transactions on Industrial Informatics","volume":"10 1","pages":""},"PeriodicalIF":12.3,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145141330","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}
{"title":"MOJO: MOtion Pattern Learning and JOint-based Fine-grained Mining for Person Re-identification Based on 4D LiDAR Point Clouds","authors":"Zhiyang Lu, Chenglu Wen, Ming Cheng, Cheng Wang","doi":"10.1109/tifs.2025.3614500","DOIUrl":"https://doi.org/10.1109/tifs.2025.3614500","url":null,"abstract":"","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"18 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145141360","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}
Kewei Xia, Jiahan Peng, Wei Wang, Yao Zou, Zongyu Zuo
{"title":"Distributed Robustness-and-Safety-Critical Formation Control of Unmanned Aerial Vehicles","authors":"Kewei Xia, Jiahan Peng, Wei Wang, Yao Zou, Zongyu Zuo","doi":"10.1109/taes.2025.3614205","DOIUrl":"https://doi.org/10.1109/taes.2025.3614205","url":null,"abstract":"","PeriodicalId":13157,"journal":{"name":"IEEE Transactions on Aerospace and Electronic Systems","volume":"92 1","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145141552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}