Rate-splitting multiple access (RSMA) has emerged as a potential non-orthogonal transmission strategy and powerful interference management scheme for 6G. Most of the existing works on RSMA beamforming design assume instantaneous or statistical channel state information (CSI) is available at the transmitter. Such an assumption however is impractical especially in massive multiple-input multiple-output (MIMO) due to the dynamic wireless environments and the challenges in channel estimation. In this work, we propose a novel beamforming design framework based on online learning and online control to adaptively learn the best precoding action for a RSMA-aided downlink massive MIMO without explicit CSI feedback. In particular, we first formulate the precoder selection problem that maximizes the ergodic sum-rate subject to a long-term transmit power constraint as a constrained combinatorial multi-armed bandit (CMAB) problem. Then we propose a precoder selection with bandit learning algorithm for RSMA (PBR). Our theoretical analysis shows that PBR achieves a sublinear regret bound with a long-term power constraint guarantee. Through experimental results, we not only verify our theoretical analysis but also demonstrate the outperformance of PBR in terms of sum-rate and power consumption compared with the conventional transmission schemes without using RSMA.

In satellite-terrestrial integrated networks, it is a common practice to schedule real-time tasks from low Earth orbit (LEO) satellites to ground stations (GSs) for data processing. However, the joint task scheduling and resource allocation under unknown environment dynamics (e.g., transmission latency) remains to be a challenging problem. First, the tradeoff between task latencies and energy consumption should be carefully considered when making decisions to minimize task latencies under time-averaged energy consumption constraints. Second, to learn the environment uncertainties and minimize the system performance loss (i.e., regret) in terms of task latencies, both online feedback and offline history should be leveraged efficiently, and the accompanying exploration-exploitation tradeoff should be dealt with in a proper way. In this article, we formulate the joint task scheduling and resource allocation problem as a constrained combinatorial multi-armed bandit (CMAB) problem. To solve the problem, by integrating online learning, online control, and offline historical information, we propose aTask scheduling and Resource allocation scheme with Data-driven Bandit LearningcalledTRDBL. Our theoretical and numerical results show that TRDBL achieves a sublinear time-averaged regret while satisfying the time-averaged energy consumption constraints.

Adaptation to out-of-distribution data is a meta-challenge for all statistical learning algorithms that strongly rely on the i.i.d. assumption. It leads to unavoidable labor costs and confidence crises in realistic applications. For that, domain generalization aims at mining domain-irrelevant knowledge from multiple source domains that can generalize to unseen target domains. In this paper, by leveraging the frequency domain of an image, we uniquely work with two key observations: (i) the high-frequency information of an image depicts object edge structure, which preserves high-level semantic information of the object is naturally consistent across different domains, and (ii) the low-frequency component retains object smooth structure, while this information is susceptible to domain shifts. Motivated by the above observations, we introduce (i) an encoder-decoder structure to disentangle high- and low-frequency features of an image, (ii) an information interaction mechanism to ensure the helpful knowledge from both two parts can cooperate effectively, and (iii) a novel data augmentation technique that works on the frequency domain to encourage the robustness of frequency-wise feature disentangling. The proposed method obtains state-of-the-art performance on three widely used domain generalization benchmarks (Digit-DG, Office-Home, and PACS).

In satellite-terrestrial integrated networks, it is a common practice to distribute real-time tasks from low Earth orbit (LEO) satellites to ground stations (GSs) for data processing. However, it remains an open problem how to match tasks with proper GSs in an online fashion with unknown dynamics, e.g., transmission latency. Moreover, such a problem is further complicated by the non-trivial interaction between the decision-making procedure and long-term constraints on time-averaged energy consumptions. In this paper, by formulating the energy-constrained online matching problem with unknown transmission latency as a constrained Combinatorial Multi-Armed Bandit (CMAB) problem, we adopt bandit learning methods and virtual queue techniques to deal with the exploration-exploitation tradeoff and long-term constraints, respectively. With an effective integration of online learning and online control, we propose a Task-matching and Resource-allocation with Data-driven Bandit Learning (TRDBL) scheme. Our theoretical analysis shows that TRDBL achieves a sublinear regret bound with a time-averaged energy constraints guarantee in the long run. Through simulation results we not only verify our theoretical analysis but also demonstrate the outperformance of TRDBL in terms of both task latency reduction and energy efficiency.

This paper presents an effective video cut-out approach, which can be utilized to segment the moving object in video shots. We first introduce the Octagon-Sensitive-Filtering (OSF) and its illumination invariant feature (IIF), which is computed on each pixel of the image via adding contributions from neighboring pixels. We integrate our IIF into the variational model and obtain the seeds during preprocessing to help address large displacement and illumination changes. An effective seed update method based on tracking-then-refinement based on IIF is presented to compensate for location ambiguities, and the strategy is effective to deal with illumination variances and objects deformation. Furthermore, we apply the IIF-based graph-cut to deal with fuzzy boundaries. Multiple experiments on quantitative challenging datasets have shown the robustness, high-quality video cut-out and efficiency of our approach to acute variances of illumination and complex motion.

Video composition aims at cloning a patch from the source video into the target scene to create a seamless and harmonious blending frame sequence. Previous work in video composition usually suffer from artifacts around the blending region and spatial-temporal consistency when illumination intensity varies in the input source and target video. We propose an illumination-guided video composition method via a unified spatial and temporal optimization framework. Our method can produce globally consistent composition results and maintain the temporal coherency. We first compute a spatial-temporal blending boundary iteratively. For each frame, the gradient field of the target and source frames are mixed adaptively based on gradients and inter-frame color difference. The temporal consistency is further obtained by optimizing luminance gradients throughout all the composition frames. Moreover, we extend the mean-value cloning by smoothing discrepancies between the source and target frames, then eliminate the color distribution overflow exponentially to reduce falsely blending pixels. Various experiments have shown the effectiveness and high-quality performance of our illumination-guided composition.

Left-censored missing values commonly exist in targeted metabolomics datasets and can be considered as missing not at random (MNAR). Improper data processing procedures for missing values will cause adverse impacts on subsequent statistical analyses. However, few imputation methods have been developed and applied to the situation of MNAR in the field of metabolomics. Thus, a practical left-censored missing value imputation method is urgently needed. We developed an iterative Gibbs sampler based left-censored missing value imputation approach (GSimp). We compared GSimp with other three imputation methods on two real-world targeted metabolomics datasets and one simulation dataset using our imputation evaluation pipeline. The results show that GSimp outperforms other imputation methods in terms of imputation accuracy, observation distribution, univariate and multivariate analyses, and statistical sensitivity. Additionally, a parallel version of GSimp was developed for dealing with large scale metabolomics datasets. The R code for GSimp, evaluation pipeline, tutorial, real-world and simulated targeted metabolomics datasets are available at: https://github.com/WandeRum/GSimp.