Mingyang Zhou

Class imbalance is a significant challenge in many practical classification tasks, particularly in federated learning (FL), where both global data imbalance and local data heterogeneity across clients worsen the problem. Addressing the class imbalance problem effectively while adhering to privacy constraints remains a formidable challenge. A common solution is to rebalance (or reweight) the samples of different classes; however, the rebalancing ratio largely depends on empirical results. In this study, we propose an analytical class rebalancing method to compute the optimal rebalancing ratios for imbalanced datasets. We first theoretically derive the relationship between evaluation metrics--such as macro-precision, macro-recall, and macro-F1--and the rebalancing ratio. Based on these findings, we devise an efficient algorithm to determine the optimal rebalancing ratio that maximizes the corresponding metrics. Our method is parameter-free and doesn't increase the complexity of existing neural models. We demonstrate that our method achieves the optimum ratio for maximizing the concerned metrics while maintaining low computational complexity, scaling linearly with both the number of clients and samples. Experimental results on different datasets validate the effectiveness of our algorithms. To the best of our knowledge, we are the first to provide an analytical and parameter-free solution to the problem.

Since the collection of labeled gaze data is laborious and time-consuming, methods which can learn generalizable features by leveraging large-scale available unlabeled data are desirable. In recent years, we have witnessed the tremendous capabilities of diffusion models in generating images as well as their potential in feature representation learning. In this paper, we investigate whether they can acquire discriminative representations for gaze estimation via generative pre-training. To achieve this goal, we propose a self-supervised learning framework with diffusion models for gaze estimation, called GazeDiff. Specifically, we utilize a conditional diffusion model to generate target image with gaze direction specified by the reference image as the pre-training task. To facilitate the diffusion model to learn gaze related features as condition, we propose a disentangling feature learning strategy, which first learns appearance feature, head pose feature, and eye direction feature respectively, and then combines them as the conditional features. Extensive experiments demonstrate denoising diffusion models are also good general gaze feature learners.

Social media platforms, as complex socio-technical ecosystems, have reshaped the way individuals access, share, and interpret information. The interplay of diverse users, rapid content flow, and intricate network structures exemplifies the complexity science domain, where dynamic interactions give rise to emergent patterns of influence and opinion formation. In this perspective, we review three key areas of intelligent information dissemination on social media: 1) rumor and fake news detection, 2) competitive dissemination, and 3) the identification of influential nodes. We highlight recent advancements that leverage complexity-aware models, graph-based algorithms, and deep learning techniques to manage content credibility and guide the spread of verified information. Finally, we propose future research directions that bridge theory and practice, ultimately contributing to a more informed, reliable, and adaptive digital information ecosystem.