Cross-Domain Decentralized Graph Learning (CD-DGL) is a promising paradigm that enables efficient, privacy-preserving collaboration among multiple parties to unlock the value of cross-domain graph data. However, it faces two fundamental challenges. First, inconsistent label spaces across domains drive local models to learn domain-specific biases, which means domain-invariant topological knowledge extraction beyond label constraints is difficult. Second, existing domain topology shift and heterogeneous model architectures make direct model aggregation infeasible. To address these issues, we first use Extended Persistent Homology (EPH) to reveal and quantify the problem of domain topology shift induced by the cross-domain setting. Building on this insight, we present Decentralized Graph Learning with Topology-Aware Knowledge Fusion (DGTF), a novel framework designed to facilitate positive topological knowledge transfer in CD-DGL. Our framework achieves this by integrating two core strategies: first, a contrastive learning-based approach to extract task-agnostic topological knowledge, and second, a topology-aware, model-independent knowledge fusion method to effectively integrate this topological information. Extensive experiments conducted under various cross-domain and model-heterogeneous settings validate the superiority and effectiveness of our proposed framework.

In this work, we study to release the potential of massive heterogeneous weak computing power to collaboratively train large-scale models on dispersed datasets. In order to improve both efficiency and accuracy in resource-adaptive collaborative learning, we take the first step to consider the unstructured pruning, varying submodel architectures, knowledge loss, and straggler challenges simultaneously. We propose a novel semiasynchronous collaborative training framework, namely Co-S2P, with data distribution-aware structured pruning and cross-block knowledge transfer mechanism to address the above concerns. Furthermore, we provide theoretical proof that Co-S2P can achieve asymptotic optimal convergence rate of O(1/√ N∗EQ). Finally, we conduct extensive experiments on two types of tasks with a real-world hardware testbed including diverse IoT devices. The experimental results demonstrate that Co-S2P improves accuracy by up to 8.8% and resource utilization by up to 1.2× compared to state-of-the-art methods, while reducing memory consumption by approximately 22% and training time by about 24% on all resource-limited devices.

The growing resource demands of large-scale transformer models pose significant challenges for resource-constrained users, particularly in distributed environments. To address this issue, we propose a federated learning framework called Fed-Grow, which enables multiple participants to collaboratively learn a lightweight scaling operation that transfers knowledge from pretrained small models to a large transformer model. In Fed-Grow, we introduce the Dual-LiGO (Dual Linear Growth Operator) architecture, consisting of Local-LiGO and Global-LiGO components. Local-LiGO addresses model heterogeneity by adapting each participant's pre-trained model to a common intermediate form, while Global-LiGO facilitates knowledge sharing across participants without sharing local models or raw data, ensuring privacy preservation. This federated approach offers a scalable solution for growing large transformers in a distributed manner, where only the Global-LiGO is shared, significantly reducing communication overhead while maintaining comparable model performance under the same communication constraints. Experimental results demonstrate that Fed-Grow outperforms state-of-the-art methods in terms of accuracy and precision, while reducing the number of trainable parameters by 59.25% and communication costs by 73.01%. These improvements allow for higher efficiency in training large models in distributed environments, without sacrificing performance. To the best of our knowledge, Fed-Grow is the first method that enables cooperative transformer scaling in a distributed setting, making it a practical solution for resource-constrained users.

This paper examines the theoretical performance of distributed diffusion models in environments where computational resources and data availability vary significantly among workers. Traditional models centered on single-worker scenarios fall short in such distributed settings, particularly when some workers are resource-constrained. This discrepancy in resources and data diversity challenges the assumption of accurate score function estimation foundational to single-worker models. We establish the inaugural generation error bound for distributed diffusion models in resource-limited settings, establishing a linear relationship with the data dimension $d$ and consistency with established single-worker results. Our analysis highlights the critical role of hyperparameter selection in influencing the training dynamics, which are key to the performance of model generation. This study provides a streamlined theoretical approach to optimizing distributed diffusion models, paving the way for future research in this area.

Meta computing, as an innovative computing paradigm, aims to transform the Internet into a vast and distributed computing resource pool. This paradigm holds significant promise for the Industrial Internet of Things (IIoT), offering efficient, fault-tolerant, and personalized services while ensuring strong security and privacy. Nowadays, content delivery networks (CDNs) are integral to this vision, providing critical network support by reducing latency, alleviating network congestion, and enhancing service quality. Accurate prediction of CDN cache group performance, which involves heterogeneous edge servers handling diverse workloads, is essential for optimal resource utilization, dynamic load balancing, and efficient traffic management in IIoT. This article addresses the challenge of performance prediction in CDNs using machine learning techniques. By leveraging business request data, load information, and other relevant features, our approach aims to predict key performance indicators, such as CPU utilization, bandwidth usage, and I/O operations. We propose a comprehensive feature engineering method that aggregates input metrics across devices, categorizes business requests using clustering, and incorporates time series modeling to capture traffic patterns. Extensive experiments demonstrate the effectiveness of our approach, highlighting its potential to enhance resource management and service quality in CDNs, thereby supporting the deployment of meta computing in IIoT.

Implementing large language models (LLMs)-driven root cause analysis (RCA) in cloud-native systems has become a key topic of modern software operations and maintenance. However, existing LLM-based approaches face three key challenges: multi-modality input constraint, context window limitation, and dynamic dependence graph. To address these issues, we propose a tool-assisted LLM agent with multi-modality observation data for fine-grained RCA, namely TAMO, including multi-modality alignment tool, root cause localization tool, and fault types classification tool. In detail, TAMO unifies multi-modal observation data into time-aligned representations for cross-modal feature consistency. Based on the unified representations, TAMO then invokes its specialized root cause localization tool and fault types classification tool for further identifying root cause and fault type underlying system context. This approach overcomes the limitations of LLMs in processing real-time raw observational data and dynamic service dependencies, guiding the model to generate repair strategies that align with system context through structured prompt design. Experiments on two benchmark datasets demonstrate that TAMO outperforms state-of-the-art (SOTA) approaches with comparable performance.