Information FusionPub Date : 2025-06-16DOI: 10.1016/j.inffus.2025.103418
Ningke Xu , Shuang Li , Cheng Lu , Yi Zhang
{"title":"Research on multi-channel adaptive coupling prediction system of fusing physical information for spatio-temporal correlation heterogeneity of methane concentration","authors":"Ningke Xu , Shuang Li , Cheng Lu , Yi Zhang","doi":"10.1016/j.inffus.2025.103418","DOIUrl":"10.1016/j.inffus.2025.103418","url":null,"abstract":"<div><div>The dynamic evolution of methane concentration in underground coal mine is the core risk source that induces methane accidents. In order to solve the problem of limited prediction accuracy caused by ignoring the spatio-temporal correlation heterogeneity of methane concentration in existing prediction models and the limitation of interpretability in existing data-driven models, this study proposes a multi-channel adaptive coupling prediction method that fuses physical information. By modeling adaptive fine-grained dependencies across multiple channels, we achieved targeted extraction of dynamic response characteristics of methane concentration from multi-source data in underground coal mines during spatio-temporal evolution processes. For the first time, an error loss term that integrates physical information has been developed for gas concentration prediction, with the final model output obtained by aggregating relevant information through an adaptive graph learning module. The results of the application in different regions of the coal mine show that the proposed method has better versatility and prediction accuracy in the methane concentration prediction task. Through the explainable modeling of dynamic dependencies and the explicit integration of physical constraints, the transparency and credibility of prediction results are significantly improved, which can effectively prevent the occurrence of methane accidents in coal mines and promote the development of the coal mine industry in a sustainable direction.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"124 ","pages":"Article 103418"},"PeriodicalIF":14.7,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144290699","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}
Information FusionPub Date : 2025-06-16DOI: 10.1016/j.inffus.2025.103371
Hui Ma , Sen Lei , Heng-Chao Li , Turgay Celik
{"title":"FER-VMamba: A robust facial expression recognition framework with global compact attention and hierarchical feature interaction","authors":"Hui Ma , Sen Lei , Heng-Chao Li , Turgay Celik","doi":"10.1016/j.inffus.2025.103371","DOIUrl":"10.1016/j.inffus.2025.103371","url":null,"abstract":"<div><div>Facial Expression Recognition (FER) has broad applications in driver safety, human–computer interaction, and cognitive psychology research, where it helps analyze emotional states and enhance social interactions. However, FER in static images faces challenges due to occlusions and pose variations, which hinder the model’s effectiveness in real-world scenarios. To address these issues, we propose FER-VMamba, a robust and efficient architecture designed to improve FER performance in complex scenarios. FER-VMamba comprises two core modules: the Global Compact Attention Module (GCAM) and the Hierarchical Feature Interaction Module (HFIM). GCAM extracts compact global semantic features through Multi-Scale Hybrid Convolutions (MixConv), refining them with a Spatial Channel Attention Mechanism (SCAM) to improve robustness against occlusions and pose variations. HFIM captures local and global dependencies by segmenting feature maps into non-overlapping partitions, which the FER-VSS module processes with Conv-SCAM-Conv for local features and Visual State-Space (VSS) for global dependencies. Additionally, self-attention and relation-attention mechanisms in HFIM refine features by modeling inter-partition relationships, further improving the accuracy of expression recognition. Extensive experiments on the RAF and AffectNet datasets demonstrate that FER-VMamba achieves state-of-the-art performance. Furthermore, we introduce FSL-FER-VMamba, an extension of FER-VSS optimized for cross-domain few-shot FER, providing strong adaptability to domain shifts. <span><span>https://github.com/SwjtuMa/FER-VMamba.git</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"124 ","pages":"Article 103371"},"PeriodicalIF":14.7,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144297056","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":"CLDTracker: A Comprehensive Language Description for visual Tracking","authors":"Mohamad Alansari, Sajid Javed, Iyyakutti Iyappan Ganapathi, Sara Alansari, Muzammal Naseer","doi":"10.1016/j.inffus.2025.103374","DOIUrl":"10.1016/j.inffus.2025.103374","url":null,"abstract":"<div><div>Visual Object Tracking (VOT) remains a fundamental yet challenging task in computer vision due to dynamic appearance changes, occlusions, and background clutter. Traditional trackers, relying primarily on visual cues, often struggle in such complex scenarios. Recent advancements in Vision–Language Models (VLMs) have shown promise in semantic understanding for tasks like open-vocabulary detection and image captioning, suggesting their potential for VOT. However, the direct application of VLMs to VOT is hindered by critical limitations: the absence of a rich and comprehensive textual representation that semantically captures the target object’s nuances, limiting the effective use of language information; inefficient fusion mechanisms that fail to optimally integrate visual and textual features, preventing a holistic understanding of the target; and a lack of temporal modeling of the target’s evolving appearance in the language domain, leading to a disconnect between the initial description and the object’s subsequent visual changes. To bridge these gaps and unlock the full potential of VLMs for VOT, we propose CLDTracker, a novel <strong>C</strong>omprehensive <strong>L</strong>anguage <strong>D</strong>escription framework for robust visual <strong>Track</strong>ing. Our tracker introduces a dual-branch architecture consisting of a textual and a visual branch. In the textual branch, we construct a rich bag of textual descriptions derived by harnessing the powerful VLMs such as CLIP and GPT-4V, enriched with semantic and contextual cues to address the lack of rich textual representation. We further propose a <strong>T</strong>emporal <strong>T</strong>ext <strong>F</strong>eature <strong>U</strong>pdate <strong>M</strong>echanism (TTFUM) to adapt these descriptions across frames, capturing evolving target appearances and tackling the absence of temporal modeling. In parallel, the visual branch extracts features using a Vision Transformer (ViT), and an attention-based cross-modal correlation head fuses both modalities for accurate target prediction, addressing the inefficient fusion mechanisms. Experiments on six standard VOT benchmarks demonstrate that CLDTracker achieves State-of-The-Art (SOTA) performance, validating the effectiveness of leveraging robust and temporally-adaptive vision–language representations for tracking. Code and models are publicly available at: <span><span>https://github.com/HamadYA/CLDTracker</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"124 ","pages":"Article 103374"},"PeriodicalIF":14.7,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144281072","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}
Information FusionPub Date : 2025-06-13DOI: 10.1016/j.inffus.2025.103330
Tsega Weldu Araya , Muhammad Azam , Nizar Bouguila , Jamal Bentahar
{"title":"Multivariate bounded support Kotz mixture model with semi-supervised projected model-based clustering","authors":"Tsega Weldu Araya , Muhammad Azam , Nizar Bouguila , Jamal Bentahar","doi":"10.1016/j.inffus.2025.103330","DOIUrl":"10.1016/j.inffus.2025.103330","url":null,"abstract":"<div><div>Data clustering is a crucial technique in data analysis, aimed at identifying and grouping similar data points to uncover underlying structures within a dataset. We propose a new unsupervised clustering approach using a multivariate bounded Kotz mixture model (BKMM) for data modeling when the data lie within a bounded support region. In many real applications, BKMM effectively handles observed data that fall within these limits, accurately modeling and clustering the observations. In BKMM, parameter estimation is performed by maximizing the log-likelihood using Expectation–Maximization (EM) algorithm and the Newton–Raphson method. Additionally, we explore the enhancements in clustering performance through semi-supervised learning by incorporating a small amount of labeled data to guide the clustering process. Thus, we propose a bounded Kotz mixture model using a semi-supervised projected model-based clustering method (BKMM-SeSProC) to obtain hidden cluster labels. Model selection in mixtures is essential for determining the optimal number of mixture components, and we introduce a minimum message length (MML) model selection criterion to find the best number of clusters in the BKMM-SeSProC approach. A greedy forward search is applied to estimate the optimal number of clusters. We use the same datasets to evaluate our proposed models, BKMM and BKMM-SeSProC, for data clustering. Additionally, we utilize MML model selection with BKMM-SeSProC to determine the number of components. Initially, we validate both proposed models and the model selection process in various medical applications. Furthermore, to assess their broader performance, we test the models on image datasets, including Alzheimer’s disease, lung tissue, and gastrointestinal tract images for disease recognition, and the CIFAR-100 dataset for object categorization. BKMM is compared with the Kotz mixture model (KMM), Student’s t mixture model (SMM), Laplace mixture model (LMM), bounded Gaussian mixture model (BGMM), and Gaussian mixture model (GMM) under similar experimental settings across all datasets. To evaluate the performance of BKMM and BKMM-SeSProC, several performance metrics are employed. To find the best number of clusters for BKMM-SeSProC, we examine the effectiveness of MML model selection against seven different criteria. The experimental results demonstrate that the proposed BKMM outperforms the compared models, KMM, SMM, LMM, BGMM, and GMM, in all applications. Additionally, the semi-supervised projected model-based clustering shows better performance across all evaluation metrics compared to unsupervised BKMM.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"124 ","pages":"Article 103330"},"PeriodicalIF":14.7,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144297053","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":"ISP-free multi-spectrum fused imaging for extremely low-light enhanced photography","authors":"Yilan Nan, Qican Zhang, Tingdong Kou, Tianyue He, Cui Huang, Cuizhen Lu, Junfei Shen","doi":"10.1016/j.inffus.2025.103400","DOIUrl":"10.1016/j.inffus.2025.103400","url":null,"abstract":"<div><div>Achieving high-quality imaging under extremely low-light conditions is crucial for autonomous driving and night surveillance applications. Traditional approaches predominantly focus on the post-processing of degraded RGB data, which struggle to effectively mitigate noise in very low-light situations with limited input information and significant noise interference. In this study, a computational multi-spectral fusion imaging framework is proposed to enhance low-light images by encoding a broader spectrum of optical source information into the imaging pipeline. An end-to-end spectral fusion network (SPFNet), consisting of an encoder for the automatic extraction of scene features and decoder for channel fusion, is designed to integrate spectral fusion with image denoising. Utilizing the novel Multi_Conv module, a diverse range of spectral features are extracted from multi-spectral raw data, providing multi-scale cross-references for noise suppression, thereby facilitating high-quality image fusion. A pilot optical system was built to capture a real-scene multi-spectral-RGB dataset under illuminance conditions below 0.01 lx per spectrum. Experimental results confirm that the proposed method significantly outperforms traditional RGB imaging techniques, demonstrating an average improvement of over 7.87 dB in peak signal-to-noise ratio (PSNR) and 0.25 in structural similarity index (SSIM). Comprehensive ablation and contrast experiments were conducted to verify that the proposed model achieved the best performance in terms of detail reconstruction and color fidelity. Eschewing the need for a cumbersome traditional image signal processing (ISP) pipeline and strict experimental constraints, the proposed framework offers a novel and viable solution for extreme low-light imaging applications, including portable photography, space exploration, remote sensing, and deep-sea exploration.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"124 ","pages":"Article 103400"},"PeriodicalIF":14.7,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144304945","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}
Information FusionPub Date : 2025-06-13DOI: 10.1016/j.inffus.2025.103378
Dongdong Li, Zhenqiang Weng, Zhengji Xuan, Zhe Wang
{"title":"ModiFedCat: A multi-modal distillation based federated catalytic framework","authors":"Dongdong Li, Zhenqiang Weng, Zhengji Xuan, Zhe Wang","doi":"10.1016/j.inffus.2025.103378","DOIUrl":"10.1016/j.inffus.2025.103378","url":null,"abstract":"<div><div>The integration of multi-modal data in federated learning systems faces significant challenges in balancing privacy preservation with effective cross-modal correlation learning under strict client isolation constraints. We propose ModiFedCat, a novel curriculum-guided multi-modal federated distillation framework that combines hierarchical knowledge transfer with adaptive training scheduling to enhance client-side model performance while maintaining rigorous data privacy. Our method computes multi-modal knowledge distillation losses at both the feature extraction and output layers, ensuring that local models are consistently aligned with the global model throughout training. Additionally, we introduce a unique catalyst strategy that dynamically schedules the integration of the distillation loss. By initially training the global model without distillation, we determine the optimal timing for its introduction, thereby maximizing the effectiveness of knowledge transfer once local models have stabilized. Experimental results on three benchmark datasets, AV-MNIST, MM-IMDB, and MIMIC III, demonstrate that ModiFedCat outperforms existing multi-modal federated learning methods. The proposed framework significantly improves the fusion capability of multi-modal models while maintaining client data privacy. This approach balances local adaptation and global knowledge integration, making it a robust solution for multi-modal federated learning scenarios.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"124 ","pages":"Article 103378"},"PeriodicalIF":14.7,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144290600","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}
Information FusionPub Date : 2025-06-13DOI: 10.1016/j.inffus.2025.103379
Xu Liu, Chunlei Wu, Huan Zhang, Leiquan Wang
{"title":"Memory association guided unsupervised anomaly detection with adaptive 3D attention","authors":"Xu Liu, Chunlei Wu, Huan Zhang, Leiquan Wang","doi":"10.1016/j.inffus.2025.103379","DOIUrl":"10.1016/j.inffus.2025.103379","url":null,"abstract":"<div><div>Unsupervised anomaly detection has recently made significant progress in various anomaly detection tasks, including multi-normal class anomaly detection and industrial defect detection. However, existing methods often construct simple feature spaces that struggle to disentangle the abundant anomalous information interwoven with the reconstruction information. To ensure the normalcy of the image feature space, we propose a Memory Association Module-based generator to activate deep interactive memory feature spaces, thereby enhancing the representation of normal feature information. Furthermore, we construct a feature simulation network that utilizes deep feature progressive fusion blocks to capture multi-scale information from the reconstructed image and subsequently corrects the vectors outputted by the memory feature space. Considering the challenges faced by existing methods in identifying edge information and blurry regions within defective images, we propose an adaptive 3D attention module and integrate it into the overall anomaly detection network architecture to enhance the network’s ability to identify hard-to-detect defective areas in images.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"124 ","pages":"Article 103379"},"PeriodicalIF":14.7,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144297054","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}
Information FusionPub Date : 2025-06-13DOI: 10.1016/j.inffus.2025.103372
Fuqun Chen , Guangchang Cai , Ying Li , Le Ou-Yang
{"title":"SpaFusion: A multi-level fusion model for clustering spatial multi-omics data","authors":"Fuqun Chen , Guangchang Cai , Ying Li , Le Ou-Yang","doi":"10.1016/j.inffus.2025.103372","DOIUrl":"10.1016/j.inffus.2025.103372","url":null,"abstract":"<div><div>Cell type identification is crucial for understanding cellular organization and elucidating the mechanisms underlying disease. Recent advances in spatial multi-omics sequencing technologies have enabled the simultaneous profiling of transcriptomics and proteomics data at shared spatial coordinates, providing new opportunities for cell type identification through spatial omics clustering. However, most existing methods primarily focus on clustering spatial transcriptomics data, and effectively integrating multi-omics data for precise cell clustering remains a critical challenge. In this study, we introduce SpaFusion, a novel multi-level fusion model for clustering spatial multi-omics data. We first construct a high-order cell graph to capture more comprehensive relationships between cells. To extract latent features from both local and global perspectives, we propose an architecture that integrates graph autoencoders and transformer modules. Through a multi-level information fusion strategy, SpaFusion captures both omic-specific features and a unified consensus representation across omics. Finally, a consensus clustering strategy is introduced to facilitate information exchange across hierarchical latent representations, thereby enhancing clustering accuracy. Extensive experiments on three real-world spatial transcriptome–proteome datasets demonstrate that SpaFusion consistently outperforms state-of-the-art methods and provides valuable insights into the spatial organization of cell types and their potential roles in disease mechanisms.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"124 ","pages":"Article 103372"},"PeriodicalIF":14.7,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144297055","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}
Information FusionPub Date : 2025-06-12DOI: 10.1016/j.inffus.2025.103376
Man Hu , Yatao Yang , Deng Pan , Zhongliang Guo , Luwei Xiao , Deyu Lin , Shuai Zhao
{"title":"Syntactic paraphrase-based synthetic data generation for backdoor attacks against Chinese language models","authors":"Man Hu , Yatao Yang , Deng Pan , Zhongliang Guo , Luwei Xiao , Deyu Lin , Shuai Zhao","doi":"10.1016/j.inffus.2025.103376","DOIUrl":"10.1016/j.inffus.2025.103376","url":null,"abstract":"<div><div>Language Models (LMs) have shown significant advancements in various Natural Language Processing (NLP) tasks. However, recent studies indicate that LMs are particularly susceptible to malicious backdoor attacks, where attackers manipulate the models to exhibit specific behaviors when they encounter particular triggers. While existing research has focused on backdoor attacks against English LMs, Chinese LMs remain largely unexplored. Moreover, existing backdoor attacks against Chinese LMs exhibit limited stealthiness. In this paper, we investigate the high detectability of current backdoor attacks against Chinese LMs and propose a more stealthy backdoor attack method based on syntactic paraphrasing. Specifically, we leverage large language models (LLMs) to construct a syntactic paraphrasing mechanism that transforms benign inputs into poisoned samples with predefined syntactic structures. Subsequently, we exploit the syntactic structures of these poisoned samples as triggers to create more stealthy and robust backdoor attacks across various attack strategies. Extensive experiments conducted on three major NLP tasks with various Chinese PLMs and LLMs demonstrate that our method can achieve comparable attack performance (almost 100% success rate). Additionally, the poisoned samples generated by our method show lower perplexity and fewer grammatical errors compared to traditional character-level backdoor attacks. Furthermore, our method exhibits strong resistance against two state-of-the-art backdoor defense mechanisms.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"124 ","pages":"Article 103376"},"PeriodicalIF":14.7,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144314632","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}
Information FusionPub Date : 2025-06-12DOI: 10.1016/j.inffus.2025.103373
Xiaohong Cai, Yi Sun, Zhaowen Lin, Ripeng Li, Tianwei Cai
{"title":"Differentially private synthetic data generation for robust information fusion","authors":"Xiaohong Cai, Yi Sun, Zhaowen Lin, Ripeng Li, Tianwei Cai","doi":"10.1016/j.inffus.2025.103373","DOIUrl":"10.1016/j.inffus.2025.103373","url":null,"abstract":"<div><div>Synthetic data is crucial in information fusion in term of enhancing data representation and improving system robustness. Among all synthesis methods, deep generative models exhibit excellent performance. However, recent studies have shown that the generation process faces privacy challenges due to the memorization of training instances by generative models. To maximize the benefits of synthesis data while ensuring data security, we propose a novel framework for the generation and utilization of private synthetic data in information fusion processes. Furthermore, we present differential private adaptive fine-tuning (DP-AdaFit), a method for private parameter efficient fine-tuning that applies differential privacy only to the singular values of the incremental updates. In details, DP-AdaFit adaptively adjusts the rank of the low-rank weight increment matrices according to their importance score, and allows us to achieve an equivalent privacy policy by only injecting noise into gradient of the corresponding singular values. Such a novel approach essentially reduces their parameter budget but avoids too much noise introduced by the singular value decomposition. We decrease the cost on memory and computation nearly half of the SOTA, and achieve the FID of 19.2 on CIFAR10. Our results demonstrate that trading off weights contained in the differential privacy fine-tuning parameters can improve model performance, even achieving generation quality competitive with differential privacy full fine-tuning diffusion model. Our code is available at <span><span>DP-AdaFit</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50367,"journal":{"name":"Information Fusion","volume":"124 ","pages":"Article 103373"},"PeriodicalIF":14.7,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144288925","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}