Building on recent advances in Bayesian statistics and image denoising, we propose Noise2Score3D, a fully unsupervised framework for point cloud denoising. Noise2Score3D learns the score function of the underlying point cloud distribution directly from noisy data, eliminating the need for clean data during training. Using Tweedie's formula, our method performs denoising in a single step, avoiding the iterative processes used in existing unsupervised methods, thus improving both accuracy and efficiency. Additionally, we introduce Total Variation for Point Clouds as a denoising quality metric, which allows for the estimation of unknown noise parameters. Experimental results demonstrate that Noise2Score3D achieves state-of-the-art performance on standard benchmarks among unsupervised learning methods in Chamfer distance and point-to-mesh metrics. Noise2Score3D also demonstrates strong generalization ability beyond training datasets. Our method, by addressing the generalization issue and challenge of the absence of clean data in learning-based methods, paves the way for learning-based point cloud denoising methods in real-world applications.

Distributed Learning (DL) enables the training of machine learning models across multiple devices, yet it faces challenges like non-IID data distributions and device capability disparities, which can impede training efficiency. Communication bottlenecks further complicate traditional Federated Learning (FL) setups. To mitigate these issues, we introduce the Personalized Federated Learning with Decentralized Selection Training (PFedDST) framework. PFedDST enhances model training by allowing devices to strategically evaluate and select peers based on a comprehensive communication score. This score integrates loss, task similarity, and selection frequency, ensuring optimal peer connections. This selection strategy is tailored to increase local personalization and promote beneficial peer collaborations to strengthen the stability and efficiency of the training process. Our experiments demonstrate that PFedDST not only enhances model accuracy but also accelerates convergence. This approach outperforms state-of-the-art methods in handling data heterogeneity, delivering both faster and more effective training in diverse and decentralized systems.

Aiming at learning from a sequence of data instances over time, online learning has attracted increasing attention in the big data era. As two important variants, sparse online learning has been extensively explored by facilitating sparse constraints for online models such as truncated gradient, ℓ1-norm regularization, ℓ1-ball projection, and regularized dual averaging; while online active learning aims to build an online prediction model with a limited number of labeled instances, deploying the so called query strategies to select informative instances over time. However, most existing studies consider sparse online learning or online active learning with fixed feature spaces, whereby in real practice the features may be dynamically evolved over time. To the end, we propose a novel unified one-pass online learning framework named OASF for simultaneously online active learning and sparse online learning tailored for data streams described by open feature spaces, where new features can emerge constantly, and old features may be vanished over various time spans. Specifically, we technically develop an effective online CUR matrix decomposition based on the ℓ1,2mixed norm constraint for simultaneously selecting important up-to-date samples in a sliding window and facilitating stable and meaningful features in open feature spaces over time. If the loss function is simultaneously Lipschitz and convex, a sub-linear regret bound of our proposed algorithm is guaranteed with. Extensive experiments that are conducted with multiple streaming datasets have demonstrated the effectiveness of the proposed OASF compared with state-of-the-art online active learning and sparse online learning methods.

This paper introduces a representative-based approach for distributed learning that transforms multiple raw data points into a virtual representation. Unlike traditional distributed learning methods such as Federated Learning, which do not offer human interpretability, our method makes complex machine learning processes accessible and comprehensible. It achieves this by condensing extensive datasets into digestible formats, thus fostering intuitive human-machine interactions. Additionally, this approach maintains privacy and communication efficiency, and it matches the training performance of models using raw data. Simulation results show that our approach is competitive with or outperforms traditional Federated Learning in accuracy and convergence, especially in scenarios with complex models and a higher number of clients. This framework marks a step forward in integrating human intuition with machine intelligence, which potentially enhances human-machine learning interfaces and collaborative efforts.

Darwinian evolution of the biological brain is documented through multiple lines of evidence, although the modes of evolutionary changes remain unclear. Drawing inspiration from the evolved neural systems (e.g., visual cortex), deep learning models have demonstrated superior performance in visual tasks, among others. While the success of training deep neural networks has been relying on back-propagation (BP) and its variants to learn representations from data, BP does not incorporate the evolutionary processes that govern biological neural systems. This work proposes a neural network optimization framework based on evolutionary theory. Specifically, BP-trained deep neural networks for visual recognition tasks obtained from the ending epochs are considered the primordial ancestors (initial population). Subsequently, the population evolved with differential evolution. Extensive experiments are carried out to examine the relationships between Darwinian evolution and neural network optimization, including the correspondence between datasets, environment, models, and living species. The empirical results show that the proposed framework has positive impacts on the network, with reduced over-fitting and an order of magnitude lower time complexity compared to BP. Moreover, the experiments show that the proposed framework performs well on deep neural networks and big datasets.

To further improve spectral efficiency for current wireless communication systems, we propose a new lazy learning-based cancellation approach to suppress self-interference (SI) sent from a base station and enable in-band full-duplex (IBFD) transmissions in cellular networks. Differ from the existing IBFD systems based on traditional approaches, our proposal consists of two phases: an offline phase for database generation and an online phase for data transmission. In the offline phase, the output before a 0/1 decision is previously measured without the desired signal input and recorded to a database with self-defined feature vectors (FVs). In the online phase, for the same system architecture with the desired signal input, a suitable result is sought from the generated database with the help of a learning method and the use of FV; then, the result is assigned as a value of SI cancellation. Computer simulation results indicate that the proposed cancellation approaches can achieve about 134 dB SI suppression and thus enables the IBFD transmissions in the considered systems.

This paper presents a study on the fading behavior in wideband 60 GHz-Millimeter-wave (MMW) wireless system. The evaluation is carried out based on a two-ray propagation model, with considering the large propagation loss of the multi-reflected waves other than the first reflected wave at 60 GHz-millimeter-wave. The study focuses on the strong fading effect due to the large variation of antenna location compared to the short wavelength (about 5 mm) and the wide frequency range (about 9 GHz) in such MMW wireless system. The influence of the polarization mismatch of antenna is also investigated. To reduce the fading, we employ the technique of space diversity by introducing two or more antennas in receiving side. We perform an optimization of the locations (heights) for these antennas. From the simulation results, we obtain some optimal heights with which the fading effect can be reduced in less than 3 dB. The simulation results also reveal how the polarization mismatch, in two different cases of antenna rotations, influences the system performance, and how space diversity reduce the fading as well. The antenna used in simulation is a planar patch antenna which is considered suitable for portable wireless handset. The radiation pattern is obtained from electromagnetic simulation. This paper demonstrates that by employing multiple antennas with optimized antenna locations can significantly reduce the fading for the 60 GHz-MMW wireless system.