Federated Learning (FL) is a distributed approach that enables collaborative model training while safeguarding client data privacy. Nevertheless, FL encounters difficulties due to statistical heterogeneity from the varied data distributions across numerous clients, which can affect overall efficiency and performance. Existing state-of-the-art FL methods often concentrate on optimizing interactions between clients, neglecting the potential insights from individual clients during training. Additionally, these approaches generally assume that every period of training has an equal impact on the final model's performance. To address these issues, this paper introduces a novel method, PA3Fed, which conducts period-aware adaptive aggregation for improved federated learning. The key idea is to identify the most critical periods, i.e., those with the highest information content and entropy, where we leverages each client's own performance variations during training for adaptive aggregation. Furthermore, because it operates independently of inter-client optimization approaches, it can be easily incorporated into other baselines for improved performance. Experimental results show that our method improves accuracy by up to 15% and significantly enhances stability.

Sensory training during the early ages is vital for human development. Inspired by this cognitive phenomenon, we observe that the early training stage is also important for the multimodal learning process, where dataset information is rapidly acquired. We refer to this stage as the prime learning window. However, based on our observation, this prime learning window in multimodal learning is often dominated by information-sufficient modalities, which in turn suppresses the information acquisition of informationinsufficient modalities. To address this issue, we propose Information Acquisition Regulation (InfoReg), a method designed to balance information acquisition among modalities. Specifically, InfoReg slows down the information acquisition process of information-sufficient modalities during the prime learning window, which could promote information acquisition of information-insufficient modalities. This regulation enables a more balanced learning process and improves the overall performance of the multimodal network. Experiments show that InfoReg outperforms related multimodal imbalanced methods across various datasets, achieving superior model performance. The code is available at https://github.com/GeWu-Lab/InfoReg_CVPR2025.

Coordinated multi-points (CoMP) transmission has been widely proved to be effective to combat co-channel interference by a number of theoretical literatures. However, a common assumption is made that the optical fiber required by coordination between base stations (BSs) is always ready to be used which is quite impractical in the real world. Therefore, Intra-Site CoMP, which only involves coordination between sector antennas, is much more easily implemented since the sector antennas are located together. In contrast with the previous theoretical researches, a measurement at 2.35 GHz, with a bandwidth of 50 MHz, was carried out to evaluate its spectral efficiency performance. A novel measuring method is put forward to avoid multi-BS synchronization as well as other challenges in the implementation of CoMP. It is found that Intra-Site CoMP can greatly improve the throughput of the system under the measured environment.