With the development of smart devices, the computing capabilities of portable end devices such as mobile phones have been greatly enhanced. Meanwhile, traditional cloud computing faces great challenges caused by privacy-leakage and time-delay problems, there is a trend to push models down to edges and end devices. However, due to the limitation of computing resource, it is difficult for end devices to complete complex computing tasks alone. Therefore, this article divides the model into two parts and deploys them on multiple end devices and edges, respectively. Meanwhile, an early exit is set to reduce computing resource overhead, forming a hierarchical distributed architecture. In order to enable the distributed model to continuously evolve by using new data generated by end devices, we comprehensively consider various data distributions on end devices and edges, proposing a hierarchical federated learning framework FLEE , which can realize dynamical updates of models without redeploying them. Through image and sentence classification experiments, we verify that it can improve model performances under all kinds of data distributions, and prove that compared with other frameworks, the models trained by FLEE consume less global computing resource in the inference stage.

In the vanilla federated learning (FL) framework, the central server distributes a globally unified model to each client and uses labeled samples for training. However, in most cases, clients are equipped with different devices and are exposed to a variety of situations. There are great differences between clients in storage, computing, communication, and other resources, which makes unified deep models used in traditional FL cannot fit clients’ personalized resource conditions. Furthermore, a great deal of labeled data is needed in traditional FL, whereas data labeling requires a great investment of time and resources, which is hard to do for individual clients. As a result, clients only have a vast amount of unlabeled data, which goes against the federated learning needs. To address the aforementioned two issues, we propose Semi-HFL, a semi-supervised federated learning approach for heterogeneous devices, which divides a deep model into a series of small submodels by inserting early exit branches to meet the resource requirements of different devices. Furthermore, considering the availability of labeled data, Semi-HFL introduces semi-supervised techniques for training in the above heterogeneous learning process. Specifically, two training phases are included in the semi-supervised learning process, unsupervised learning on clients and supervised learning on the server, which makes full use of clients’ unlabeled data. Through image classification, text classification, next-word prediction, and multi-task FL experiments based on five kinds of datasets, it is verified that compared with the traditional homogeneous learning method, Semi-HFL not only achieves higher accuracies but also significantly reduces the global resource overhead.

The proliferation of end devices has led to a distributed computing paradigm, wherein on-device machine learning models continuously process diverse data generated by these devices. The dynamic nature of this data, characterized by continuous changes or data drift, poses significant challenges for on-device models. To address this issue, continual learning (CL) is proposed, enabling machine learning models to incrementally update their knowledge and mitigate catastrophic forgetting. However, the traditional centralized approach to CL is unsuitable for end devices due to privacy and data volume concerns. In this context, federated CL (FCL) emerges as a promising solution, preserving user data locally while enhancing models through collaborative updates. Aiming at the challenges of limited storage resources for CL, poor autonomy in task shift detection, and difficulty in coping with new adversarial tasks in the FCL scenario, we propose a novel FCL framework named self-adaptive federated CL (SacFL). $\rm {SacFL}$ employs an encoder–decoder architecture to separate task-robust and task-sensitive components, significantly reducing storage demands by retaining lightweight task-sensitive components for resource-constrained end devices. Moreover, $\rm {SacFL}$ leverages contrastive learning to introduce an autonomous data shift detection mechanism, enabling it to discern whether a new task has emerged and whether it is a benign task. This capability ultimately allows the device to autonomously trigger CL or attack defense strategy without additional information, which is more practical for end devices. Comprehensive experiments conducted on multiple text and image datasets, such as Cifar100 and THUCNews, have validated the effectiveness of $\rm {SacFL}$ in both class-incremental and domain-incremental scenarios. Furthermore, a demo system has been developed to verify its practicality.

In the era of information, data plays a crucial role, especially in the assessment of competitive works. However, large-scale innovative competitions encounter challenges including broad and repetitive indices, incomplete coverage, and ambiguous evaluation standards. To tackle these issues, this paper puts forward a three-fold evaluation program framework: work distribution, evaluation score adjustment, and innovative work selection. At the work distribution stage, a multi-constraint optimization model is formulated to minimize cross-degree variance. The distribution method is optimized using an enhanced particle swarm algorithm. For the scoring stage, three methods are employed: two-stage standard value adjustment for in-group + out-group, standard value adjustment based on judging experience, and standard value adjustment based on distribution distance. These methods ensure a reasonable, fair, and accurate scoring process. In the innovative work selection stage, the standardized extreme deviation model with integral improvement and the integral extreme deviation threshold model are introduced to enhance the judging process’s recognition ability for highly innovative works. Through the implementation of this evaluation program framework, we aim to address the current challenges in evaluating works in large-scale innovation competitions. It is anticipated that the framework will improve the accuracy and comprehensiveness of evaluation indices, thereby fostering scientific research and innovation development.

With the rapid development of the Internet of Things and edge computing, federated learning (FL) has become an important technique for collaborative intelligent modeling across distributed nodes. However, in real-world open environments, federated systems must continuously cope with dynamically joining devices, evolving service requirements, and privacy-driven data deletion, making traditional federated training paradigms built on static assumptions increasingly inadequate. To address this challenge, this paper provides a systematic survey of key research progress on federated learning from the perspective of continuous model evolution in open environments. Specifically, we analyze three core problems faced by federated systems in open environments: how to efficiently adapt to newly arrived nodes or data distributions, how to preserve performance on historical tasks during continual training, and how to effectively remove the contribution of specific data or nodes under privacy and compliance requirements. We then organize the literature around three major technical routes, namely federated domain adaptation, federated continual learning, and federated unlearning. On this basis, we further summarize commonly used evaluation metrics and mainstream experimental benchmarks in this area. Finally, we discuss the major challenges and future research directions of federated model evolution in open environments, with the goal of providing a systematic reference for building adaptive and sustainably evolving distributed intelligent systems.