Most existing Personalized Federated Learning (PFL) approaches rely on frequent client-to-cloud communication to ensure convergence, making them vulnerable to bandwidth constraints and network latency. To address this deficiency, we propose Hier-pFedMe, a novel client-edge-cloud tri-level PFL framework formulated as hierarchical optimization with Moreau envelopes. Unlike traditional client-cloud bi-level architectures, Hier-pFedMe introduces an additional intermediate edge-server level to coordinate client training, alleviating the communication burden on the central cloud server and improving efficiency through parallel edge server operations. Moreover, the hierarchical design enhances privacy by restricting client updates to small groups via edge servers, limiting direct access to client updates by the central server. Experiments on CIFAR-10, CIFAR-100 and Tiny-ImageNet datasets demonstrate that Hier-pFedMe improves personalized learning performance while reducing communication overhead on heterogeneous data.

The deep precipitation nowcasting using radar echo map prediction can mitigate the socio-economic impact of extreme precipitation events. Existing methods employ long short-term memory (LSTM) to extract rich precipitation features. However, existing methods often combine the learning and modeling of rain and nonrain regions in a single module, without clearly distinguishing their different features and motion patterns, which impairs the spatial distribution and precipitation intensity prediction of rainfall. Moreover, these LSTMs only capture local spatiotemporal features, while ignoring the global spatiotemporal features, resulting in prediction results lacking structural and strength consistency. Therefore, we propose a dual regions center displacement (DRCD) module, which separately learns and models the spatial information of rainfall and nonrainfall regions and employs this module to estimate the locations and intensity residuals of the future regions. Moreover, we also introduce a novel Global LSTM module (GLSTM) that learns the global spatiotemporal features from the sequences, which can estimate the structure and intensity of dual regions. Extensive experiments demonstrate that our method has superior or competitive performance over the state-of-the-art precipitation nowcasting methods and has the potential to be implemented as an alternative product globally.

This work addresses the problem of cross-domain few-shot classification which aims at recognizing novel categories in unseen domains with only a few labeled data samples. We think that the pre-trained model contains the redundant elements which are useless or even harmful for the downstream tasks. To remedy the drawback, we introduce an$L^{2}$-SP regularized dense-sparse-dense (DSD) fine-tuning flow for regularizing the capacity of pre-trained networks and achieving efficient few-shot domain adaptation. Given a pre-trained model from the source domain, we start by carrying out a conventional dense fine-tuning step using the target data. Then we execute a sparse pruning step that prunes the unimportant connections and fine-tunes the weights of sub-network. Finally, initialized with the fine-tuned sub-network, we retrain the original dense network as the output model for the target domain. The whole fine-tuning procedure is regularized by an$L^{2}$-SP term. In contrast to the existing methods that either tune the weights or prune the network structure for domain adaptation, our regularized DSD fine-tuning flow simultaneously exploits the benefits of sparsity regularity and dense network capacity to gain the best of both worlds. Our method can be applied in a plug-and-play manner to improve the existing fine-tuning methods. Extensive experimental results on benchmark datasets demonstrate that our method in many cases outperforms the existing cross-domain few-shot classification methods in significant margins. Our code will be released soon.

Cross-domain few-shot learning (CDFSL) has received great interest for its effectiveness in solving the problem of the shift between source and target domains in few-shot scenarios. To extract more representative features, recent CDFSL works have exploited small-scale unlabeled samples from the target domain during the feature extraction phase. Existing self-supervised CDFSL methods, however, typically fine-tune the weights of the pre-trained model without taking into account the mismatch between source and target domains. To address this shortcoming, we introduce a self-supervised soft weight pruning strategy for cross-domain few-shot classification tasks with unlabeled target data. Starting from a pre-trained network from the source domain, our approach iterates between pruning out the relatively unimportant connections of the network and reactivating the pruned connections in a joint contrastive and$L^{2}$-SPregularized training framework. By combining the soft weight pruning strategy and regularization, our method effectively restricts redundant weights while simultaneously learning crucial features for both source and target tasks. Our approach, in comparison to other methods, does not involve any additional modules in the models; however, it can still achieve remarkable performance. Our approach can be efficiently incorporated into a variety of contrastive learning methods in a plug-and-play fashion. Extensive experimental results on several benchmark datasets demonstrate that our proposed method outperforms existing representative cross-domain few-shot methods by a large margin. The code for our work can be found athttps://github.com/nuistji/swp-cdfsl.