Xuetao Wei

We propose DHetGAN, a decentralized federated generative adversarial network (GAN) learning framework for multi-source heterogeneous data. Unlike standard decentralized federated learning for non-GAN models, DHetGAN requires each node to solve a local minimax GAN game via adversarial training of its discriminator and generator, which are then averaged in a decentralized manner to reach consensus. To address data heterogeneity across nodes, we develop a GAN-intrinsic aggregation strategy that assigns averaging weights using a privacy-preserving divergence proxy quantifying inter-node distributional divergence. The proxy is estimated locally by each node – without revealing sensitive data – from coupled discriminator-genera tor values calibrated by the neighborhood-level maximal discrimina tor confidence, specific to the minimax GAN game. To reduce communication overhead, we present a compression method tailored to DHet GAN. We theoretically analyze convergence guarantees of our frame work, demonstrating strong inter-node coupling, contracting gradient magnitudes, and uniformly bounded consensus dynamics for both discriminators and generators. We also establish a sufficient condition for full mode coverage in DHetGAN and identify practical training set tings under which this condition holds. Extensive experiments and comparisons with benchmarks show that DHetGAN achieves superior generative performance, strong stability, diversity of mode coverage, and fast convergence, while substantially reducing communication overhead, even under extreme non-i.i.d. data heterogeneity.

Tensor network structure search (TN-SS) aims to automatically discover optimal network topologies and rank configurations for efficient tensor decomposition in high-dimensional data representation. Despite recent advances, existing TN-SS methods face significant limitations in computational tractability, structure adaptivity, and optimization robustness across diverse tensor characteristics. They struggle with three key challenges: single-scale optimization missing multi-scale structures, discrete search spaces hindering smooth structure evolution, and separated structure-parameter optimization causing computational inefficiency. We propose RGTN (Renormalization Group guided Tensor Network search), a physics-inspired framework transforming TN-SS via multi-scale renormalization group flows. Unlike fixed-scale discrete search methods, RGTN uses dynamic scale-transformation for continuous structure evolution across resolutions. Its core innovation includes learnable edge gates for optimization-stage topology modification and intelligent proposals based on physical quantities like node tension measuring local stress and edge information flow quantifying connectivity importance. Starting from low-complexity coarse scales and refining to finer ones, RGTN finds compact structures while escaping local minima via scale-induced perturbations. Extensive experiments on light field data, high-order synthetic tensors, and video completion tasks show RGTN achieves state-of-the-art compression ratios and runs 4-600$\times$ faster than existing methods, validating the effectiveness of our physics-inspired approach.

Fine-grained urban flow inference is crucial for urban planning and intelligent transportation systems, enabling precise traffic management and resource allocation. However, the practical deployment of existing methods is hindered by two key challenges: the prohibitive computational cost of over-parameterized models and the suboptimal performance of conventional loss functions on the highly skewed distribution of urban flows. To address these challenges, we propose a unified solution that synergizes architectural efficiency with adaptive optimization. Specifically, we first introduce PLGF, a lightweight yet powerful architecture that employs a Progressive Local-Global Fusion strategy to effectively capture both fine-grained details and global contextual dependencies. Second, we propose DualFocal Loss, a novel function that integrates dual-space supervision with a difficulty-aware focusing mechanism, enabling the model to adaptively concentrate on hard-to-predict regions. Extensive experiments on 4 real-world scenarios validate the effectiveness and scalability of our method. Notably, while achieving state-of-the-art performance, PLGF reduces the model size by up to 97% compared to current high-performing methods. Furthermore, under comparable parameter budgets, our model yields an accuracy improvement of over 10% against strong baselines. The implementation is included in the https://github.com/Yasoz/PLGF.

In sharded blockchains, peers are divided into smaller groups (shards) that generate and verify blocks in parallel, offering enhanced throughput and reduced delays. These properties make sharded blockchains a promising solution for secure data management in Internet of Things (IoT) systems. Particularly, geolocation-based sharded blockchain assign geographically proximate peers to the same shard, enabling faster IoT transaction processing. Yet, peers in each shard can easily collude to falsely accept/reject blocks. To resolve this issue, in this article, we propose a robust reputation-based shard inspection framework. The framework adopts the shard inspection mechanism where a group of inspectors selected from the most reputable peers randomly verify blocks in each shard. This enables avoiding collusion attacks and enhancing the security of each shard. However, additional block verifications during the inspection process can incur significant block delays and energy overheads. To reduce these overheads, we formulate an optimization problem that jointly determines the number of inspectors and the inspection interval to maximize the system utility, which is proportional to the blockchain throughput and energy consumption. We then develop a distributed algorithm that enables dividing the optimization problem into subproblems solvable independently by each shard. Experimental results show that our framework can maximize the system utility, while maintaining high levels of security in each shard.