Qiyang Zhang

Alaa Saleh, Praveen Kumar Donta, Roberto Morabito et al.

Human biological systems sustain life through extraordinary resilience, continually detecting damage, orchestrating targeted responses, and restoring function through self-healing. Inspired by these capabilities, this paper introduces ReCiSt, a bio-inspired agentic self-healing framework designed to achieve resilience in Distributed Computing Continuum Systems (DCCS). Modern DCCS integrate heterogeneous computing resources, ranging from resource-constrained IoT devices to high-performance cloud infrastructures, and their inherent complexity, mobility, and dynamic operating conditions expose them to frequent faults that disrupt service continuity. These challenges underscore the need for scalable, adaptive, and self-regulated resilience strategies. ReCiSt reconstructs the biological phases of Hemostasis, Inflammation, Proliferation, and Remodeling into the computational layers Containment, Diagnosis, Meta-Cognitive, and Knowledge for DCCS. These four layers perform autonomous fault isolation, causal diagnosis, adaptive recovery, and long-term knowledge consolidation through Language Model (LM)-powered agents. These agents interpret heterogeneous logs, infer root causes, refine reasoning pathways, and reconfigure resources with minimal human intervention. The proposed ReCiSt framework is evaluated on public fault datasets using multiple LMs, and no baseline comparison is included due to the scarcity of similar approaches. Nevertheless, our results, evaluated under different LMs, confirm ReCiSt's self-healing capabilities within tens of seconds with minimum of 10% of agent CPU usage. Our results also demonstrated depth of analysis to over come uncertainties and amount of micro-agents invoked to achieve resilience.

Praveen Kumar Donta, Alaa Saleh, Ying Li et al.

Agentic Artificial Intelligence (AI) represents a fundamental shift in the design of intelligent systems, characterized by interconnected components that collectively enable autonomous perception, reasoning, planning, action, and learning. Recent research on agentic AI has largely focused on technical foundations, including system architectures, reasoning and planning mechanisms, coordination strategies, and application-level performance across domains. However, the societal, ethical, economic, environmental, and governance implications of agentic AI remain weakly integrated into these technical treatments. This paper addresses this gap by presenting a socio-technical analysis of agentic AI that explicitly connects core technical components with societal context. We examine how architectural choices in perception, cognition, planning, execution, and memory introduce dependencies related to data governance, accountability, transparency, safety, and sustainability. To structure this analysis, we adopt the MAD-BAD-SAD construct as an analytical lens, capturing motivations, applications, and moral dilemmas (MAD); biases, accountability, and dangers (BAD); and societal impact, adoption, and design considerations (SAD). Using this lens, we analyze ethical considerations, implications, and challenges arising from contemporary agentic AI systems and assess their manifestation across emerging applications, including healthcare, education, industry, smart and sustainable cities, social services, communications and networking, and earth observation and satellite communications. The paper further identifies open challenges and suggests future research directions, framing agentic AI as an integrated socio-technical system whose behavior and impact are co-produced by algorithms, data, organizational practices, regulatory frameworks, and social norms.

Peihan Ye, Alfreds Lapkovskis, Alaa Saleh et al.

The computational demands of modern AI services are increasingly shifting execution beyond centralized clouds toward a computing continuum spanning edge and end devices. However, the scale, heterogeneity, and cross-layer dependencies of these environments make resilience difficult to maintain. Existing fault-management methods are often too static, fragmented, or heavy to support timely self-healing, especially under noisy logs and edge resource constraints. To address these limitations, this paper presents NeSy-Edge, a neuro-symbolic framework for trustworthy self-healing in the computing continuum. The framework follows an edge-first design, where a resource-constrained edge node performs local perception and reasoning, while a cloud model is invoked only at the final diagnosis stage. Specifically, NeSy-Edge converts raw runtime logs into structured event representations, builds a prior-constrained sparse symbolic causal graph, and integrates causal evidence with historical troubleshooting knowledge for root-cause analysis and recovery recommendation. We evaluate our work on representative Loghub datasets under multiple levels of semantic noise, considering parsing quality, causal reasoning, end-to-end diagnosis, and edge-side resource usage. The results show that NeSy-Edge remains robust even at the highest noise level, achieving up to 75% root-cause analysis accuracy and 65% end-to-end accuracy while operating within about 1500 MB of local memory.

Yakun Wang, Daixin Wang, Hongrui Liu et al.

Link prediction, as a fundamental task for graph neural networks (GNNs), has boasted significant progress in varied domains. Its success is typically influenced by the expressive power of node representation, but recent developments reveal the inferior performance of low-degree nodes owing to their sparse neighbor connections, known as the degree-based long-tailed problem. Will the degree-based long-tailed distribution similarly constrain the efficacy of GNNs on link prediction? Unexpectedly, our study reveals that only a mild correlation exists between node degree and predictive accuracy, and more importantly, the number of common neighbors between node pairs exhibits a strong correlation with accuracy. Considering node pairs with less common neighbors, i.e., tail node pairs, make up a substantial fraction of the dataset but achieve worse performance, we propose that link prediction also faces the long-tailed problem. Therefore, link prediction of GNNs is greatly hindered by the tail node pairs. After knowing the weakness of link prediction, a natural question is how can we eliminate the negative effects of the skewed long-tailed distribution on common neighbors so as to improve the performance of link prediction? Towards this end, we introduce our long-tailed framework (LTLP), which is designed to enhance the performance of tail node pairs on link prediction by increasing common neighbors. Two key modules in LTLP respectively supplement high-quality edges for tail node pairs and enforce representational alignment between head and tail node pairs within the same category, thereby improving the performance of tail node pairs.

Chinmaya Kumar Dehury, Siddharth Singh Kushwaha, Qiyang Zhang et al.

Edge intelligence delivers low-latency inference, yet most edge analytics remain hard-coded and must be redeployed as conditions change. When data patterns shift or new questions arise, engineers often need to write new scripts and push updates to devices, which slows iteration and raises operating costs. This limited adaptability reduces scalability and autonomy in large, heterogeneous, and resource-constrained edge deployments, and it increases reliance on human oversight. Meanwhile, large language models (LLMs) can interpret instructions and generate code, but their compute and memory requirements typically prevent direct deployment on edge devices. We address this gap with the LLM-assisted Edge Intelligence (LEI) framework, which removes the need for manually specified business logic. In LEI, a cloud-hosted LLM coordinates the creation and update of device-side logic as requirements evolve. The system generates candidate lightweight programs, checks them against available data and constraints, and then deploys the selected version to each device. This lets each device receive a tailored program based on sample data, metadata, context, and current resource limits. We evaluate LEI on four heterogeneous datasets, including air quality, temperature \& humidity, wind, and soil datasets using multiple LLM backends. The experimental results show that the framework maintains low average CPU and memory utilization during the execution. These results indicate that the framework adapts efficiently to changing conditions while maintaining resource efficiency.

Akash Pallath, Qiyang Zhang

Handsearch is an important technique that contributes to thorough literature search in systematic reviews. Traditional handsearch requires reviewers to systematically browse through each issue of a curated list of field-specific journals and conference proceedings to find articles relevant to their review. This manual process is not only time-consuming, laborious, costly, and error-prone, but it also lacks replicability and cross-checking mechanisms. In an attempt to solve these problems, this paper presents a free and open-source Python package and an accompanying web-app, Paperfetcher, to automate handsearch for systematic reviews. With Paperfetcher's assistance, researchers can retrieve articles from designated journals within a specified time frame with just a few clicks. In addition to handsearch, this tool also incorporates snowballing in both directions. Paperfetcher allows researchers to download retrieved studies as a list of DOIs or as an RIS database to facilitate seamless import into citation management and systematic review screening software. To our knowledge, Paperfetcher is the first tool that automates handsearch with high usability and a multi-disciplinary focus.

Zhibin Zhao, Qiyang Zhang, Xiaolei Yu et al.

Recent progress on intelligent fault diagnosis (IFD) has greatly depended on deep representation learning and plenty of labeled data. However, machines often operate with various working conditions or the target task has different distributions with the collected data used for training (the domain shift problem). Besides, the newly collected test data in the target domain are usually unlabeled, leading to unsupervised deep transfer learning based (UDTL-based) IFD problem. Although it has achieved huge development, a standard and open source code framework as well as a comparative study for UDTL-based IFD are not yet established. In this paper, we construct a new taxonomy and perform a comprehensive review of UDTL-based IFD according to different tasks. Comparative analysis of some typical methods and datasets reveals some open and essential issues in UDTL-based IFD which are rarely studied, including transferability of features, influence of backbones, negative transfer, physical priors, etc. To emphasize the importance and reproducibility of UDTL-based IFD, the whole test framework will be released to the research community to facilitate future research. In summary, the released framework and comparative study can serve as an extended interface and basic results to carry out new studies on UDTL-based IFD. The code framework is available at \url{https://github.com/ZhaoZhibin/UDTL}.

Alireza Furutanpey, Qiyang Zhang, Philipp Raith et al.

Nanosatellite constellations equipped with sensors capturing large geographic regions provide unprecedented opportunities for Earth observation. As constellation sizes increase, network contention poses a downlink bottleneck. Orbital Edge Computing (OEC) leverages limited onboard compute resources to reduce transfer costs by processing the raw captures at the source. However, current solutions have limited practicability due to reliance on crude filtering methods or over-prioritizing particular downstream tasks. This work presents FOOL, an OEC-native and task-agnostic feature compression method that preserves prediction performance. FOOL partitions high-resolution satellite imagery to maximize throughput. Further, it embeds context and leverages inter-tile dependencies to lower transfer costs with negligible overhead. While FOOL is a feature compressor, it can recover images with competitive scores on quality measures at lower bitrates. We extensively evaluate transfer cost reduction by including the peculiarity of intermittently available network connections in low earth orbit. Lastly, we test the feasibility of our system for standardized nanosatellite form factors. We demonstrate that FOOL permits downlinking over 100x the data volume without relying on prior information on the downstream tasks.

Praveen Kumar Donta, Qiyang Zhang, Schahram Dustdar

Over the Eight decades, computing paradigms have shifted from large, centralized systems to compact, distributed architectures, leading to the rise of the Distributed Computing Continuum (DCC). In this model, multiple layers such as cloud, edge, Internet of Things (IoT), and mobile platforms work together to support a wide range of applications. Recently, the emergence of Generative AI and large language models has further intensified the demand for computational resources across this continuum. Although traditional performance metrics have provided a solid foundation, they need to be revisited and expanded to keep pace with changing computational demands and application requirements. Accurate performance measurements benefit both system designers and users by supporting improvements in efficiency and promoting alignment with system goals. In this context, we review commonly used metrics in DCC and IoT environments. We also discuss emerging performance dimensions that address evolving computing needs, such as sustainability, energy efficiency, and system observability. We also outline criteria and considerations for selecting appropriate metrics, aiming to inspire future research and development in this critical area.

Yakun Wang, Binbin Hu, Shuo Yang et al.

The rapid development of graph neural networks (GNNs) encourages the rising of link prediction, achieving promising performance with various applications. Unfortunately, through a comprehensive analysis, we surprisingly find that current link predictors with dynamic negative samplers (DNSs) suffer from the migration phenomenon between "easy" and "hard" samples, which goes against the preference of DNS of choosing "hard" negatives, thus severely hindering capability. Towards this end, we propose the MeBNS framework, serving as a general plugin that can potentially improve current negative sampling based link predictors. In particular, we elaborately devise a Meta-learning Supported Teacher-student GNN (MST-GNN) that is not only built upon teacher-student architecture for alleviating the migration between "easy" and "hard" samples but also equipped with a meta learning based sample re-weighting module for helping the student GNN distinguish "hard" samples in a fine-grained manner. To effectively guide the learning of MST-GNN, we prepare a Structure enhanced Training Data Generator (STD-Generator) and an Uncertainty based Meta Data Collector (UMD-Collector) for supporting the teacher and student GNN, respectively. Extensive experiments show that the MeBNS achieves remarkable performance across six link prediction benchmark datasets.

Yunquan Gao, Zhiguo Zhang, Praveen Kumar Donta et al.

Deep Neural Networks (DNNs) are increasingly deployed across diverse industries, driving demand for mobile device support. However, existing mobile inference frameworks often rely on a single processor per model, limiting hardware utilization and causing suboptimal performance and energy efficiency. Expanding DNN accessibility on mobile platforms requires adaptive, resource-efficient solutions to meet rising computational needs without compromising functionality. Parallel inference of multiple DNNs on heterogeneous processors remains challenging. Some works partition DNN operations into subgraphs for parallel execution across processors, but these often create excessive subgraphs based only on hardware compatibility, increasing scheduling complexity and memory overhead. To address this, we propose an Advanced Multi-DNN Model Scheduling (ADMS) strategy for optimizing multi-DNN inference on mobile heterogeneous processors. ADMS constructs an optimal subgraph partitioning strategy offline, balancing hardware operation support and scheduling granularity, and uses a processor-state-aware algorithm to dynamically adjust workloads based on real-time conditions. This ensures efficient workload distribution and maximizes processor utilization. Experiments show ADMS reduces multi-DNN inference latency by 4.04 times compared to vanilla frameworks.

Mengwei Xu, Wangsong Yin, Dongqi Cai et al.

Large foundation models, including large language models (LLMs), vision transformers (ViTs), diffusion, and LLM-based multimodal models, are revolutionizing the entire machine learning lifecycle, from training to deployment. However, the substantial advancements in versatility and performance these models offer come at a significant cost in terms of hardware resources. To support the growth of these large models in a scalable and environmentally sustainable way, there has been a considerable focus on developing resource-efficient strategies. This survey delves into the critical importance of such research, examining both algorithmic and systemic aspects. It offers a comprehensive analysis and valuable insights gleaned from existing literature, encompassing a broad array of topics from cutting-edge model architectures and training/serving algorithms to practical system designs and implementations. The goal of this survey is to provide an overarching understanding of how current approaches are tackling the resource challenges posed by large foundation models and to potentially inspire future breakthroughs in this field.

Qiyang Zhang, Xiang Li, Xiangying Che et al.

Deploying deep learning (DL) on mobile devices has been a notable trend in recent years. To support fast inference of on-device DL, DL libraries play a critical role as algorithms and hardware do. Unfortunately, no prior work ever dives deep into the ecosystem of modern DL libs and provides quantitative results on their performance. In this paper, we first build a comprehensive benchmark that includes 6 representative DL libs and 15 diversified DL models. We then perform extensive experiments on 10 mobile devices, which help reveal a complete landscape of the current mobile DL libs ecosystem. For example, we find that the best-performing DL lib is severely fragmented across different models and hardware, and the gap between those DL libs can be rather huge. In fact, the impacts of DL libs can overwhelm the optimizations from algorithms or hardware, e.g., model quantization and GPU/DSP-based heterogeneous computing. Finally, atop the observations, we summarize practical implications to different roles in the DL lib ecosystem.

Jing Cheng, Haifeng Wang, Yanjie Zhu et al.

Medical imaging is playing a more and more important role in clinics. However, there are several issues in different imaging modalities such as slow imaging speed in MRI, radiation injury in CT and PET. Therefore, accelerating MRI, reducing radiation dose in CT and PET have been ongoing research topics since their invention. Usually, acquiring less data is a direct but important strategy to address these issues. However, less acquisition usually results in aliasing artifacts in reconstructions. Recently, deep learning (DL) has been introduced in medical image reconstruction and shown potential on significantly speeding up MR reconstruction and reducing radiation dose. In this paper, we propose a general framework on combining the reconstruction model with deep learning to maximize the potential of deep learning and model-based reconstruction, and give the examples to demonstrate the performance and requirements of unrolling different algorithms using deep learning.