The joint clustering of multimodal remote sensing (RS) data represents a multi-objective optimization challenge involving conflicting modality-specific objectives and diverse regularization objectives. Current approaches to multi-view subspace clustering (MVSC) often oversimplify this task by transforming it into a weighted single-objective optimization problem, neglecting the intricate interactions between objectives and leading to suboptimal subspace representations. The presence of quadratic decision variables in MVSC renders direct application on large-scale RS data impracticable using multi-objective evolutionary algorithms (MOEAs). To overcome this challenge, we propose a novel MVSC method termed Multi-objective Multi-view Attributed Learning (MMAGL). Instead of optimizing every self-representation coefficient individually, our method transforms MVSC into a link prediction task over a sparse attributed graph that fuses different modalities. We incorporate superpixel-based sample reduction and proximity-based population coding, leveraging spatial and structural priors, respectively. This results in a significantly compressed decision space, enabling optimization with MOEAs. To fully exploit node attributes and the graph structure, we redefine self-representation using contrastive learning and introduce an efficient graph filtering through a generalized spectral graph convolution, enhancing clustering discriminability. The proposed MMAGL constitutes a hybrid and versatile framework, adaptable to any MOEA. Extensive experimental evaluations demonstrate that our MMAGL method surpasses the current state-of-the-art on multimodal RS benchmarks (e.g., with nearly 2% gain on Trento and 3% on Houston) on overall accuracy.

As one of the representative models in the field of image generation, generative adversarial networks (GANs) face a significant challenge: how to make the best trade-off between the quality of generated images and training stability. The U-Net based GAN (U-Net GAN), a recently developed approach, can generate high-quality synthetic images by using a U-Net architecture for the discriminator. However, this model may suffer from severe mode collapse. In this study, a stable U-Net GAN (SUGAN) is proposed to mainly solve this problem. First, a gradient normalization module is introduced to the discriminator of U-Net GAN. This module effectively reduces gradient magnitudes, thereby greatly alleviating the problems of gradient instability and overfitting. As a result, the training stability of the GAN model is improved. Additionally, in order to solve the problem of blurred edges of the generated images, a modified residual network is used in the generator. This modification enhances its ability to capture image details, leading to higher-definition generated images. Extensive experiments conducted on several datasets show that the proposed SUGAN significantly improves over the Inception Score (IS) and Fréchet Inception Distance (FID) metrics compared with several state-of-the-art and classic GANs. The training process of our SUGAN is stable, and the quality and diversity of the generated samples are higher. This clearly demonstrates the effectiveness of our approach for image generation tasks. The source code and trained model of our SUGAN have been publicly released.

Hyperspectral band selection, aimed at identifying key spectral bands from the original image, is crucial for reducing dimensionality and enhancing computational efficiency in hyperspectral image (HSI) analysis. Graph learning-based methods have attracted considerable attention due to their efficiency in representing structural correlations between bands and their powerful capability to extract features. However, existing methods have limitations in utilizing spatial relationships among bands and learning their discriminative characteristics. To address these limitations, we propose a Diversity Learning Guided Dual Graph Autoencoder (DLG-DGAE) for unsupervised hyperspectral band selection. In our framework, we integrate a Dual Graph Autoencoder (DGAE) module designed to extract information from both the spatial and spectral relationships among bands, thus fully capturing the structural similarity of the bands. Additionally, we introduce a Spectral Diversity Learning (SDL) strategy to reduce redundant information in the latent representation and enhance the discriminative properties of each band. In the final step, we proceed to cluster the fused latent embeddings. Within each cluster, we select the band exhibiting the highest information entropy as the representative band. Through extensive experimentation on three publicly available datasets, our results consistently indicate that the proposed method surpasses other state-of-the-art techniques. The code is available at https://github.com/fengwe1/DLG-DGAE.

In the digital era, escalating concerns over personal privacy and social security have led to the advocacy for the “right to be forgotten”, a principle that empowers individuals to request the deletion of their personal data from online platforms. Consequently, machine unlearning (MU) has been proposed as a method for targeted data deletion within machine learning models. However, MU encounters difficulties in distributed learning environments, such as federated learning (FL), where direct access to data is restricted. Federated unlearning (FU) has been developed in response, aiming to facilitate the process of data deletion requests from clients within FL frameworks. Despite advancements, FU methods based on approximate unlearning present a risk of potential data breaches, while methods reliant on retraining necessitate either complete or repeated retraining of clients, which is inefficient. Addressing these challenges, we introduce the federated cluster slicing algorithm (FedCSA), a novel FU strategy that achieves precision and efficiency in data unlearning. FedCSA organizes clients into distinct slices based on model deviation values, facilitating targeted retraining of local models upon unlearning requests. This method not only ensures consistency in the independent and identically distributed degree across slices but also improves unlearning efficiency and maintains global model accuracy. Moreover, FedCSA features an adaptive clustering mechanism that autonomously determines the optimal number of slices, optimizing the unlearning process. Our empirical analysis, conducted across the MNIST, Fashion-MNIST, and CIFAR-10 datasets, underscores FedCSA's superior performance. FedCSA exhibits a fourfold increase in unlearning efficiency compared to traditional retraining methods. Furthermore, when juxtaposed with the sharded, isolated, sliced, and aggregated technique, FedCSA demonstrates a 4%–5% enhancement in global model accuracy. These findings corroborate the efficacy of FedCSA.

Text classification aims to classify text according to pre-defined categories. Despite the success of existing methods based on the fine-tuning paradigm, there is a significant gap between fine-tuning and pre-training. Currently, prompt learning methods can bring state of the art (SOTA) performance to pre-trained language models (PLMs) in text classification and transform a classification problem into a masked language modeling problem. The crucial step of prompt learning is to construct a map between original labels and the label extension words. However, most mapping construction methods consider only labels themselves; relying solely on a label is not sufficient to achieve accurate prediction of mask tokens, especially in classification tasks where semantic features and label words are highly interrelated. Therefore, the accurate prediction of mask tokens requires one to consider additional factors beyond just label words. To this end, we propose a contrastive sample method based on knowledge-guided prompt learning framework (ConKgPrompt) for text classification. Specifically, this framework utilizes external knowledge bases (KBs) to expand the label vocabulary of verbalizers at multiple granularities. In the contrastive sample module, we incorporate supervised contrastive learning to make representations more expressive. Our approach was validated on four benchmark datasets, and extensive experimental results and analysis demonstrated the effectiveness of each module of the ConKgPrompt method.