搜索结果：Forget

Adherence research has historically focused on medication-taking behaviors. While evidence suggests that males are generally more adherent to medication regimens than females, the influence of sex on overall adherence behaviors remains unclear. We explored how sex influences a multidimensional profile of adherence beyond medication using the Generic French Adherence in Chronic Diseases Profile (GACID-P). We conducted a cross-sectional study using data from the validation of the GACID-P. Participants were adults (>18 years) with chronic conditions attending specialist care across the Grand-Est region of France. The 25-item self-report GACID-P assesses four domains of adherence - Intention to comply with treatment, Forgetting to take medication, Healthy lifestyle, and Limitation of risk-related consumer habits - with scores ranging from 0 (worst) to 10 (best), except for forgetting, which is reverse scored. Analyses included sex-stratified comparisons, multivariable linear regression models, and multivariate analysis of variance to examine sex-based adherence patterns within and across domains. Among 397 participants (53% male; mean age: males 57.1 ± 10.7, females 59.3 ± 11.7), domain scores indicated generally good adherence. Within domains, males had higher scores than females for Intention to comply (9.18 ± 1.15 vs 8.96 ± 1.51), less Forgetting to take medication (1.35 ± 2.42 vs 1.82 ± 2.85), more Healthy lifestyle (6.92 ± 1.95 vs 6.61 ± 2.00), while females scored higher for Limitation of risk-related consumer habits (6.15 ± 2.14 vs 5.24 ± 2.14); however, none of these differences reached statistical significance. Across domains, a multivariate analysis suggested a sex effect (Wilks' Lambda = 0.84, F(4,73) = 3.58, p=0.010), driven primarily by differences in Forgetting to take medication where males reported less forgetting than females, when adherence patterns are considered jointly across domains (F(1,76) = 10.39, p = 0.0019). Despite the absence of statistically significant sex-based differences within individual GACID-P domains, a multivariate analysis suggested potential differences when adherence behaviors were considered jointly. While these findings should be interpreted cautiously, they support consideration of a sex-based lens to better understand adherence. We did this study to better understand whether males and females differ in how they follow their treatment plans for long-term health conditions. Most previous research has focused only on how well people take their medications. These earlier studies suggest that males may take their medicines more regularly than females. However, following a treatment plan involves more than medication alone, and much less is known about whether males and females differ in other important parts of following treatment plans. We wanted to look at the bigger picture. We used a survey that examines several different areas of treatment behavior. These include taking medications as prescribed, remembering to take medications on time, making healthy lifestyle choices, and avoiding risky habits. By looking across all of these areas, we hoped to get a fuller understanding of how people follow treatment plans. When we compared males and females, we did not find clear differences in any single area on its own. There was a general pattern where males tended to report slightly better behaviours in some areas (such as taking medications as directed, remembering doses and having healthier lifestyle habits), while females tended to report slightly higher avoidance of risky habits, but these differences were small and not strong enough to draw firm conclusions.However, when we looked at all of the treatment behaviors together, one finding stood out: males were less likely to forget their medications compared to females. This may suggest that any influence of sex on treatment habits is complex and may not be apparent within individual areas alone.

Some images are consistently more likely to be remembered or forgotten, but there is debate over the mechanisms that underlie these effects. Here we attempted to narrow the theoretical space by examining forgetting functions for high- and low-memorable images (faces and scenes). Experiments 1 and 2 used a continuous recognition procedure-a modified recognition memory task in which study events are interleaved with test trials-and Experiment 3 evaluated forgetting over longer retention intervals using a traditional study-test procedure. Forgetting functions were estimated using a hierarchical Bayesian model that accounted for subject and item effects, in addition to retention interval. The results from all three experiments revealed a consistent pattern: high-memorable images enjoyed both a higher initial degree of learning and a lower rate of forgetting than low-memorable images. This combination of results indicates that high-memorable images benefit both from enhanced encoding and from retarded forgetting. We discuss the implications of these findings for theories of image memorability. (PsycInfo Database Record (c) 2026 APA, all rights reserved).

Personalized Federated Continual Learning (PFCL) requires that the server not only effectively integrate temporal knowledge accumulated across past tasks and spatial knowledge distributed among heterogeneous clients, but also ensure strong personalized performance of the global model for each client. Existing methods, whether in Personalized Federated Learning (PFL) or Federated Continual Learning (FCL), have overlooked the multi-granularity representation of knowledge, which can be utilized to overcome Spatial-Temporal Catastrophic Forgetting (STCF) and enable coarse-to-fine personalization. Furthermore, most approaches rely on local client-side personalization, increasing computational load and failing to address the risks posed by malicious or low-quality clients. To this end, we propose FedMGP+, which utilizes multi-granularity prompts to address these challenges, namely coarse-grained global prompt and fine-grained local prompt. The former focuses on efficiently transferring shared global knowledge without spatial forgetting, and the latter emphasizes specific learning of personalized local knowledge to overcome temporal forgetting. Visualization results and theoretical analyses further reveal that coarse-grained prompts primarily guide regional attention, whereas fine-grained prompts enrich object-level representations within those regions. Building upon this, Personalized Selective Prompt Fusion is designed to exclusively fuse coarse-grained knowledge on the server to generate client-specific global prompts, reducing local overhead and resisting poisoning attacks from malicious clients. Extensive experiments demonstrate that the proposed FedMGP+ effectively mitigates forgetting, significantly enhances personalized performance, and provides robust defense against poisoning and gradient leakage attacks.

Federated learning (FL) is a widely adopted paradigm that enables collaborative model training while preserving data privacy. As concerns around data poisoning and the "right to be forgotten" continue to grow, federated unlearning, which is the ability to remove the influence of specific training data from a trained FL model, has become increasingly critical. However, existing unlearning methods often require expensive retraining or fail to achieve good forgetting effects, limiting their practicality in real-world FL systems. In this work, we propose FuGuard, a dual-strategy federated unlearning framework, designed for efficient and ideal client-level data removal. FuGuard combines the generative surrogate, which approximates the contribution of the target client, with optimal transport regularization that softly constrains model parameter drift during unlearning. This approach effectively removes the influence of the target client while preserving the stability and performance of the global model. To evaluate the forgetting capability, we conduct testing using backdoor attacks and member inference attacks (MIAs) for residual data influence. Empirical results on different benchmarks demonstrate that FuGuard significantly reduces the impact of the target client's data while maintaining the performance of nontarget clients, consistently outperforming state-of-the-art baselines in both forgetting effectiveness and accuracy retention. Our code is accessible at: https://anonymous.4open.science/r/FuGuard-0263.

Current few-shot learning (FSL) methods struggle with fine-grained texture loss, inefficient cross-modal knowledge integration, and catastrophic forgetting. To resolve these bottlenecks, we propose the Adaptive cognitive driven cross modal network (ACD-Net) for few-shot fine-grained recognition. Inspired by human cognition, ACD-Net introduces three systematic innovations. First, the Adaptive Dual-Domain Cognitive Attention (ADCA) module employs Two-Dimensional Discrete Wavelet Transform and Gated Recurrent Units to decouple high-frequency textures from noise and dynamically localize discriminative regions. Second, the Graph-Guided Semantic-to-Visual Distillation (GSD) strategy utilizes Graph Convolutional Networks and a bilinear attention mechanism to seamlessly embed structured semantic priors into the visual space, generating exceptionally robust category prototypes. Finally, the Dynamic Balanced Anti-forgetting (DBAF) loss function mitigates catastrophic forgetting during fine-tuning by adaptively adjusting regularization weights based on gradient orthogonality between old and novel tasks. Extensive evaluations on the miniImageNet, CUB-200-2011, and Medical-44 datasets demonstrate that ACD-Net achieves state-of-the-art results, elevating average accuracy by 1.75% and 1.36% in 1-shot and 5-shot scenarios, respectively. Ultimately, ACD-Net establishes an innovative paradigm for FSL, offering pragmatic solutions for complex real-world deployments including industrial defect inspection and intelligent clinical diagnosis.

Vibration-based sensing systems for deployed industrial fault diagnosis often face incremental fault classes, changing degradation stages, and limited permission to retain historical sensor streams. Static fault classifiers are therefore insufficient for online maintenance settings in which a model must learn new sensor-observed states while preserving previous diagnostic knowledge under a bounded memory budget. This paper proposes ASBR-CL, an adaptive stage-aware balanced replay framework for continual fault diagnosis under a fixed exemplar-memory budget. ASBR-CL combines dataset-adaptive exemplar memory, balanced replay between current data and retained exemplars, and a conditional validation checkpoint module that is enabled only when it improves balanced stage recognition. Experiments on SEU-enhanced92, the 92-dimensional feature construction for SEU, and XJTU-bearing23, the 23-dimensional feature construction for XJTU-SY, compare ASBR-CL with DGGN/MFF same-backbone continual-learning baselines and XJTU imbalance-aware variants under five random seeds and K=100 training exemplars. On SEU, the selected ASBR-CL setting reports 97.49±1.18 Average Accuracy, 90.37±4.53 Final Accuracy, 90.37±4.53 Macro Recall, and 11.50±5.25 Average Forgetting. On XJTU, the conservative ASBR-CL-BoundedVal-K100 setting is not a universal Final Accuracy winner: DGGN-ER reaches a slightly higher Final Accuracy (89.52±2.68 versus 89.05±2.48). The ASBR-CL evidence instead lies in balanced recognition and retention, with Macro Recall 75.00±2.00, Macro-F1 67.66±3.83, and Average Forgetting 20.39±4.89, compared with DGGN-ER at 63.94±7.50, 55.48±12.82, and 41.11±13.61. Additional validation-resource, RMS-derived stage-definition, and imbalance-aware baseline analyses show that the revised XJTU claim should be framed as more stable Macro Recall, Macro-F1, and forgetting control under memory-limited continual diagnosis, not as superiority on every accuracy metric.

Removing the influence of specific training samples from a trained classifier on demand, without retraining from scratch, is central to compliance with data-deletion requests. We study this problem under a trigger-based framing in which a visible pattern inserted into an input activates a forgetting behavior at inference time, so that the clean form of the input is classified normally while the triggered form yields a maximally uncertain response. We develop a three-stage training pipeline consisting of a Pretraining Stage on clean retain data, a Conditioning Stage that binds the trigger to a uniform-posterior response under a bounded Kullback-Leibler objective with joint batches, and an Unlearning Stage that applies the same uniform target to triggered forget samples while an Elastic Weight Consolidation penalty protects retention-critical parameters. We evaluate the method on CIFAR-10 and SVHN with a six-condition protocol that covers every combination of data split and trigger state and we report multi-seed results. On held-out test data the proposed model attains a conditional gap of 23.04 pp on CIFAR-10 and 71.54 pp on SVHN, while a baseline trained without trigger conditioning exhibits gaps of only 1.16 pp and 0.35 pp, confirming that the effect is a learned input-conditioned behavior rather than a property of the trigger pattern itself. Membership inference AUC is 0.502 on CIFAR-10 and 0.511 on SVHN, closer to chance than for the baseline. Selectivity in this framework is carried by the trigger state at inference rather than by a sample-level discrimination between forget and retain subsets, a structural property of any method whose input-side signal does not depend on sample identity. A residual clean-input capacity loss of roughly 17 pp on CIFAR-10 and 9 pp on SVHN remains the principal limitation, and the six-condition protocol is provided as a reusable tool for evaluating trigger-conditional unlearning methods.

Understanding the forgetting mechanisms in working memory is a considerable challenge for cognitive psychologists. Traditional views attribute forgetting in working memory to interference and decay, but whether verbal working memory undergoes spontaneous decay is still debated. In the present study, we examined this issue by asking participants to simultaneously memorize visual and verbal items, but requiring them to prioritize the visual materials. If spontaneous decay occurs in verbal working memory, and if the potential antiforgetting mechanisms (e.g., attentional refreshing) are primarily engaged in slowing the decay of visual information, then we should see a gradual decline in performance on verbal memory tasks over the retention interval, even in the absence of any new interfering stimuli during the retention interval (note, interference alone would not predict performance change over time). In Experiment 1, participants prioritized memorizing handwriting styles while retaining two Chinese names. Results showed a time-based decline in name recall accuracy. Experiment 2 replaced names with alphanumeric strings and manipulated the visual memory load. A spontaneous decline in verbal memory performance was found again. In addition, by isolating the influence of item errors and binding errors on task performance, the results of Experiment 2 additionally reveal an attentional mechanism capable of specifically counteracting the decay of binding strength. Experiment 3 further ruled out insufficient consolidation time as the cause of the declines. These results provide evidence for spontaneous decay in verbal working memory, modulated by attentional resource allocation, supporting the dynamic balance view between decay and active antidecay mechanisms. (PsycInfo Database Record (c) 2026 APA, all rights reserved).

Current multi-view clustering methods are developed under the assumption that all views are simultaneously accessible to the model. However, this assumption can break down in real-world scenarios where views are incrementally acquired over time, necessitating the development of continual multi-view clustering (CMVC) approaches. Existing CMVC methods typically adopt late-fusion strategies, training a separate model for each incoming view to extract view-specific information-such as partition matrices, similarity matrices, or latent representations-which are then used to update a shared consensus representation via a moving average mechanism. However, these methods are sensitive to view-specific noise and struggle to handle large discrepancies across views. To address these limitations, we revisit CMVC from a domain adaptation perspective and propose AdaptCMVC++, which continuously integrates information from newly available views while mitigating catastrophic forgetting. Specifically, a self-training framework is introduced to extend the model to new views, specifically designed to be robust to view-specific noise. To combat catastrophic forgetting, a structure-alignment mechanism is proposed to enable the model to explore the global group structure across multiple views. Furthermore, a dimensionality adaptation module is incorporated to accommodate multi-view data with diverse image dimensionalities. Extensive experiments on several multi-view benchmarks and a newly constructed dataset demonstrate the effectiveness and generalization capability of our proposed method for the CMVC task. The implementation is publicly available at: https://github.com/Wjing-bjtu/AdaptCMVC AdaptCMVC++.

Class Incremental Learning (CIL) aims to learn new concepts consistently from a data stream without forgetting. Unlike typical CIL methods which need to learn a model from scratch, pre-trained model (PTM) can easily adapt to a new task with fine-tuning. However, existing PTM-based CIL methods fail to achieve a trade-off between performance and computational expenditure, i.e., they either adopt the same parameter space so that leading catastrophic forgetting, or expand a new branch for each task but adding more computational cost. To this end, we propose MetrIc Learning with Expandable Subspace (Miles) to harness the prior information within pre-trained knowledge, thereby orchestrating an efficient expansion of the parameter space through guided optimization. Specifically, it decouples the learnable modules with the pre-trained model, exploiting prior information from intermediate features of the backbone network to enable more flexible parameter expansion. Then, a central loss is adopted to guide the new category to cluster towards the corresponding prototype in the new task subspace while incorporating an auxiliary distance regularization term to maintain metric equilibrium across tasks. Extensive experiments on six benchmark datasets demonstrate that Miles achieves state-of-the-art performance in various CIL settings.

Machine learning models built from national health surveys enable population-scale risk stratification, yet the GDPR's "right to be forgotten" mandates that participants' data and their downstream impacts be fully erasable upon request. Existing privacy-preserving and unlearning approaches remain limited because they can be computationally prohibitive, provide only approximate protection by obscuring individual influence, rely on parameter-level approximation, or depend on localized retraining whose effectiveness is sensitive to data partitioning. In health survey settings, cohort heterogeneity across sociodemographic, behavioral, and clinical dimensions can further induce imbalanced shard distributions, thereby compromising the stability and effectiveness of unlearning. To overcome these challenges, we propose a subgroup-aware exact unlearning framework for heterogeneous health survey data, in which GRC uses a multi-stage refinement process to discover epidemiologically coherent subgroups and construct proportion-preserving shards for localized unlearning. These subgroup labels facilitate proportional shard partitioning, effectively preserving cohort ratios and ensuring balanced representation within each shard. Each shard undergoes incremental training with intermediate model snapshots periodically recorded; upon receiving a deletion request, only affected shards roll back to their nearest clean snapshot and undergo localized retraining, followed by aggregation via a soft-voting ensemble to restore global consistency. This design provides a structured exact unlearning workflow with bounded retraining scope and empirically strong forgetting performance while maintaining predictive performance. Evaluations on depression-risk prediction tasks derived from the NHANES and CHARLS datasets demonstrate that our approach consistently improves Zero-Retrain-Forgetting performance while preserving predictive utility, supporting an effective and practical exact unlearning strategy for prediction models driven by health survey data.

Atopic dermatitis (AD) is a chronic inflammatory dermatosis requiring multifaceted treatment. Poor adherence to topical therapy hinders symptom management, highlighting the need to identify barriers influencing adherence among adults with AD. Identify factors influencing adherence to topical therapy among adults with AD and outline strategies to improve adherence. We conducted a systematic review following PRISMA guidelines and with PROSPERO registration (CRD42023488557). PubMed and EMBASE were searched in December 2023 for articles with relevant terms published from 2000 to 2023, and the search was updated in April 2025. Eligible studies reported original data on adherence to topical therapy in adults with AD and findings were categorized using the World Health Organization's adherence dimensions. A total of 50 studies involving 17,124 adults across 17 countries were analyzed. Patient-related barriers included patient forgetfulness, knowledge about AD and treatment options, as well as topical corticosteroid phobia. Therapy-related factors included regimen complexity, vehicle preparation, and symptom perception. Cost and advice from family, friends, and the internet were frequent socioeconomic concerns. Healthcare system factors included clinician communication, time constraints, and inconsistent guidance. Condition-related factors including disease severity and chronicity also shaped adherence. Topical therapy adherence among adults with AD is influenced by several modifiable barriers including patient forgetfulness, education, treatment duration, and vehicle preparation. Future work should standardize adherence measurement tools and definitions. Proposed strategies may integrate patient-centered education, simplified regimens, reminder tools, cost reduction, and strong therapeutic relationships to support sustained adherence and improve long-term outcomes.